diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,1801 @@ +{"current_steps": 5, "total_steps": 179570, "loss": 1.1606, "lr": 1.113771788160606e-08, "epoch": 0.0002784429470401515, "percentage": 0.0, "elapsed_time": "0:00:04", "remaining_time": "1 day, 18:26:02", "throughput": 571.73, "total_tokens": 2432} +{"current_steps": 10, "total_steps": 179570, "loss": 1.3714, "lr": 2.5059865233613633e-08, "epoch": 0.000556885894080303, "percentage": 0.01, "elapsed_time": "0:00:08", "remaining_time": "1 day, 16:35:30", "throughput": 623.23, "total_tokens": 5072} +{"current_steps": 15, "total_steps": 179570, "loss": 1.1292, "lr": 3.8982012585621204e-08, "epoch": 0.0008353288411204544, "percentage": 0.01, "elapsed_time": "0:00:12", "remaining_time": "1 day, 16:36:38", "throughput": 647.16, "total_tokens": 7904} +{"current_steps": 20, "total_steps": 179570, "loss": 1.0661, "lr": 5.290415993762878e-08, "epoch": 0.001113771788160606, "percentage": 0.01, "elapsed_time": "0:00:16", "remaining_time": "1 day, 16:06:27", "throughput": 651.6, "total_tokens": 10480} +{"current_steps": 25, "total_steps": 179570, "loss": 1.2808, "lr": 6.682630728963636e-08, "epoch": 0.0013922147352007574, "percentage": 0.01, "elapsed_time": "0:00:19", "remaining_time": "1 day, 14:52:11", "throughput": 651.19, "total_tokens": 12688} +{"current_steps": 30, "total_steps": 179570, "loss": 1.0217, "lr": 8.074845464164393e-08, "epoch": 0.0016706576822409088, "percentage": 0.02, "elapsed_time": "0:00:23", "remaining_time": "1 day, 14:31:14", "throughput": 655.97, "total_tokens": 15200} +{"current_steps": 35, "total_steps": 179570, "loss": 1.5048, "lr": 9.46706019936515e-08, "epoch": 0.0019491006292810603, "percentage": 0.02, "elapsed_time": "0:00:26", "remaining_time": "1 day, 14:17:36", "throughput": 661.44, "total_tokens": 17776} +{"current_steps": 40, "total_steps": 179570, "loss": 0.7688, "lr": 1.0859274934565907e-07, "epoch": 0.002227543576321212, "percentage": 0.02, "elapsed_time": "0:00:30", "remaining_time": "1 day, 14:13:12", "throughput": 666.49, "total_tokens": 20432} +{"current_steps": 45, "total_steps": 179570, "loss": 1.0285, "lr": 1.2251489669766666e-07, "epoch": 0.0025059865233613633, "percentage": 0.03, "elapsed_time": "0:00:34", "remaining_time": "1 day, 14:29:56", "throughput": 671.02, "total_tokens": 23312} +{"current_steps": 50, "total_steps": 179570, "loss": 1.0239, "lr": 1.3643704404967421e-07, "epoch": 0.0027844294704015148, "percentage": 0.03, "elapsed_time": "0:00:38", "remaining_time": "1 day, 14:21:26", "throughput": 674.78, "total_tokens": 25952} +{"current_steps": 55, "total_steps": 179570, "loss": 0.8002, "lr": 1.5035919140168183e-07, "epoch": 0.003062872417441666, "percentage": 0.03, "elapsed_time": "0:00:41", "remaining_time": "1 day, 14:00:00", "throughput": 677.21, "total_tokens": 28384} +{"current_steps": 60, "total_steps": 179570, "loss": 1.3517, "lr": 1.6428133875368938e-07, "epoch": 0.0033413153644818176, "percentage": 0.03, "elapsed_time": "0:00:45", "remaining_time": "1 day, 13:55:25", "throughput": 679.51, "total_tokens": 31008} +{"current_steps": 65, "total_steps": 179570, "loss": 1.6452, "lr": 1.7820348610569697e-07, "epoch": 0.003619758311521969, "percentage": 0.04, "elapsed_time": "0:00:49", "remaining_time": "1 day, 13:48:08", "throughput": 679.24, "total_tokens": 33472} +{"current_steps": 70, "total_steps": 179570, "loss": 1.5396, "lr": 1.9212563345770452e-07, "epoch": 0.0038982012585621205, "percentage": 0.04, "elapsed_time": "0:00:52", "remaining_time": "1 day, 13:37:58", "throughput": 676.85, "total_tokens": 35760} +{"current_steps": 75, "total_steps": 179570, "loss": 1.2987, "lr": 2.0604778080971208e-07, "epoch": 0.004176644205602272, "percentage": 0.04, "elapsed_time": "0:00:55", "remaining_time": "1 day, 13:13:13", "throughput": 675.86, "total_tokens": 37840} +{"current_steps": 80, "total_steps": 179570, "loss": 1.4261, "lr": 2.199699281617197e-07, "epoch": 0.004455087152642424, "percentage": 0.04, "elapsed_time": "0:00:59", "remaining_time": "1 day, 13:05:12", "throughput": 677.29, "total_tokens": 40304} +{"current_steps": 85, "total_steps": 179570, "loss": 0.819, "lr": 2.3389207551372728e-07, "epoch": 0.004733530099682575, "percentage": 0.05, "elapsed_time": "0:01:03", "remaining_time": "1 day, 13:04:26", "throughput": 677.4, "total_tokens": 42816} +{"current_steps": 90, "total_steps": 179570, "loss": 1.3968, "lr": 2.4781422286573486e-07, "epoch": 0.005011973046722727, "percentage": 0.05, "elapsed_time": "0:01:07", "remaining_time": "1 day, 13:13:07", "throughput": 678.93, "total_tokens": 45616} +{"current_steps": 95, "total_steps": 179570, "loss": 1.0586, "lr": 2.617363702177424e-07, "epoch": 0.005290415993762878, "percentage": 0.05, "elapsed_time": "0:01:11", "remaining_time": "1 day, 13:23:55", "throughput": 682.29, "total_tokens": 48624} +{"current_steps": 100, "total_steps": 179570, "loss": 0.814, "lr": 2.7565851756975e-07, "epoch": 0.0055688589408030295, "percentage": 0.06, "elapsed_time": "0:01:14", "remaining_time": "1 day, 13:15:57", "throughput": 682.15, "total_tokens": 50992} +{"current_steps": 105, "total_steps": 179570, "loss": 1.3604, "lr": 2.8958066492175756e-07, "epoch": 0.005847301887843181, "percentage": 0.06, "elapsed_time": "0:01:18", "remaining_time": "1 day, 13:15:08", "throughput": 683.33, "total_tokens": 53616} +{"current_steps": 110, "total_steps": 179570, "loss": 1.3025, "lr": 3.0350281227376515e-07, "epoch": 0.006125744834883332, "percentage": 0.06, "elapsed_time": "0:01:22", "remaining_time": "1 day, 13:23:30", "throughput": 684.72, "total_tokens": 56496} +{"current_steps": 115, "total_steps": 179570, "loss": 1.1738, "lr": 3.174249596257727e-07, "epoch": 0.006404187781923484, "percentage": 0.06, "elapsed_time": "0:01:26", "remaining_time": "1 day, 13:33:37", "throughput": 686.15, "total_tokens": 59456} +{"current_steps": 120, "total_steps": 179570, "loss": 0.8376, "lr": 3.3134710697778026e-07, "epoch": 0.006682630728963635, "percentage": 0.07, "elapsed_time": "0:01:30", "remaining_time": "1 day, 13:34:13", "throughput": 687.62, "total_tokens": 62192} +{"current_steps": 125, "total_steps": 179570, "loss": 0.9078, "lr": 3.4526925432978785e-07, "epoch": 0.006961073676003787, "percentage": 0.07, "elapsed_time": "0:01:34", "remaining_time": "1 day, 13:39:29", "throughput": 689.06, "total_tokens": 65072} +{"current_steps": 130, "total_steps": 179570, "loss": 1.1432, "lr": 3.5919140168179543e-07, "epoch": 0.007239516623043938, "percentage": 0.07, "elapsed_time": "0:01:38", "remaining_time": "1 day, 13:46:34", "throughput": 689.69, "total_tokens": 67952} +{"current_steps": 135, "total_steps": 179570, "loss": 1.0255, "lr": 3.73113549033803e-07, "epoch": 0.00751795957008409, "percentage": 0.08, "elapsed_time": "0:01:42", "remaining_time": "1 day, 13:52:14", "throughput": 690.4, "total_tokens": 70816} +{"current_steps": 140, "total_steps": 179570, "loss": 1.1087, "lr": 3.8703569638581055e-07, "epoch": 0.007796402517124241, "percentage": 0.08, "elapsed_time": "0:01:47", "remaining_time": "1 day, 14:07:15", "throughput": 691.09, "total_tokens": 74000} +{"current_steps": 145, "total_steps": 179570, "loss": 1.2571, "lr": 4.0095784373781813e-07, "epoch": 0.008074845464164393, "percentage": 0.08, "elapsed_time": "0:01:51", "remaining_time": "1 day, 14:12:07", "throughput": 692.17, "total_tokens": 76928} +{"current_steps": 150, "total_steps": 179570, "loss": 1.0229, "lr": 4.148799910898257e-07, "epoch": 0.008353288411204545, "percentage": 0.08, "elapsed_time": "0:01:55", "remaining_time": "1 day, 14:19:42", "throughput": 693.36, "total_tokens": 79984} +{"current_steps": 155, "total_steps": 179570, "loss": 0.8433, "lr": 4.288021384418333e-07, "epoch": 0.008631731358244696, "percentage": 0.09, "elapsed_time": "0:01:59", "remaining_time": "1 day, 14:24:04", "throughput": 694.49, "total_tokens": 82944} +{"current_steps": 160, "total_steps": 179570, "loss": 0.9072, "lr": 4.4272428579384083e-07, "epoch": 0.008910174305284848, "percentage": 0.09, "elapsed_time": "0:02:03", "remaining_time": "1 day, 14:30:44", "throughput": 695.28, "total_tokens": 85968} +{"current_steps": 165, "total_steps": 179570, "loss": 0.9444, "lr": 4.566464331458484e-07, "epoch": 0.009188617252324999, "percentage": 0.09, "elapsed_time": "0:02:07", "remaining_time": "1 day, 14:34:06", "throughput": 696.02, "total_tokens": 88880} +{"current_steps": 170, "total_steps": 179570, "loss": 1.1879, "lr": 4.70568580497856e-07, "epoch": 0.00946706019936515, "percentage": 0.09, "elapsed_time": "0:02:11", "remaining_time": "1 day, 14:38:52", "throughput": 696.47, "total_tokens": 91824} +{"current_steps": 175, "total_steps": 179570, "loss": 1.0967, "lr": 4.844907278498635e-07, "epoch": 0.009745503146405302, "percentage": 0.1, "elapsed_time": "0:02:15", "remaining_time": "1 day, 14:34:59", "throughput": 696.7, "total_tokens": 94400} +{"current_steps": 180, "total_steps": 179570, "loss": 1.2914, "lr": 4.984128752018711e-07, "epoch": 0.010023946093445453, "percentage": 0.1, "elapsed_time": "0:02:19", "remaining_time": "1 day, 14:33:23", "throughput": 696.86, "total_tokens": 97056} +{"current_steps": 185, "total_steps": 179570, "loss": 0.9584, "lr": 5.123350225538787e-07, "epoch": 0.010302389040485605, "percentage": 0.1, "elapsed_time": "0:02:23", "remaining_time": "1 day, 14:33:49", "throughput": 696.77, "total_tokens": 99760} +{"current_steps": 190, "total_steps": 179570, "loss": 1.1604, "lr": 5.262571699058863e-07, "epoch": 0.010580831987525756, "percentage": 0.11, "elapsed_time": "0:02:27", "remaining_time": "1 day, 14:39:09", "throughput": 697.26, "total_tokens": 102768} +{"current_steps": 195, "total_steps": 179570, "loss": 0.8385, "lr": 5.401793172578939e-07, "epoch": 0.010859274934565908, "percentage": 0.11, "elapsed_time": "0:02:31", "remaining_time": "1 day, 14:40:50", "throughput": 697.69, "total_tokens": 105616} +{"current_steps": 200, "total_steps": 179570, "loss": 0.9168, "lr": 5.541014646099015e-07, "epoch": 0.011137717881606059, "percentage": 0.11, "elapsed_time": "0:02:35", "remaining_time": "1 day, 14:46:04", "throughput": 698.64, "total_tokens": 108720} +{"current_steps": 205, "total_steps": 179570, "loss": 1.3144, "lr": 5.68023611961909e-07, "epoch": 0.01141616082864621, "percentage": 0.11, "elapsed_time": "0:02:39", "remaining_time": "1 day, 14:53:02", "throughput": 699.25, "total_tokens": 111872} +{"current_steps": 210, "total_steps": 179570, "loss": 1.1688, "lr": 5.819457593139166e-07, "epoch": 0.011694603775686362, "percentage": 0.12, "elapsed_time": "0:02:43", "remaining_time": "1 day, 14:46:21", "throughput": 699.13, "total_tokens": 114256} +{"current_steps": 215, "total_steps": 179570, "loss": 1.483, "lr": 5.958679066659241e-07, "epoch": 0.011973046722726513, "percentage": 0.12, "elapsed_time": "0:02:47", "remaining_time": "1 day, 14:46:06", "throughput": 699.56, "total_tokens": 117040} +{"current_steps": 220, "total_steps": 179570, "loss": 0.8078, "lr": 6.097900540179317e-07, "epoch": 0.012251489669766665, "percentage": 0.12, "elapsed_time": "0:02:50", "remaining_time": "1 day, 14:43:14", "throughput": 700.12, "total_tokens": 119712} +{"current_steps": 225, "total_steps": 179570, "loss": 1.0887, "lr": 6.237122013699393e-07, "epoch": 0.012529932616806816, "percentage": 0.13, "elapsed_time": "0:02:55", "remaining_time": "1 day, 14:45:26", "throughput": 700.62, "total_tokens": 122640} +{"current_steps": 230, "total_steps": 179570, "loss": 1.5127, "lr": 6.376343487219468e-07, "epoch": 0.012808375563846968, "percentage": 0.13, "elapsed_time": "0:02:58", "remaining_time": "1 day, 14:39:03", "throughput": 699.72, "total_tokens": 124864} +{"current_steps": 235, "total_steps": 179570, "loss": 0.7586, "lr": 6.515564960739544e-07, "epoch": 0.013086818510887119, "percentage": 0.13, "elapsed_time": "0:03:02", "remaining_time": "1 day, 14:36:50", "throughput": 699.96, "total_tokens": 127504} +{"current_steps": 240, "total_steps": 179570, "loss": 1.4413, "lr": 6.65478643425962e-07, "epoch": 0.01336526145792727, "percentage": 0.13, "elapsed_time": "0:03:05", "remaining_time": "1 day, 14:34:29", "throughput": 699.74, "total_tokens": 130048} +{"current_steps": 245, "total_steps": 179570, "loss": 0.7355, "lr": 6.794007907779696e-07, "epoch": 0.013643704404967422, "percentage": 0.14, "elapsed_time": "0:03:09", "remaining_time": "1 day, 14:33:41", "throughput": 700.61, "total_tokens": 132880} +{"current_steps": 250, "total_steps": 179570, "loss": 1.1142, "lr": 6.933229381299773e-07, "epoch": 0.013922147352007573, "percentage": 0.14, "elapsed_time": "0:03:13", "remaining_time": "1 day, 14:32:03", "throughput": 701.3, "total_tokens": 135632} +{"current_steps": 255, "total_steps": 179570, "loss": 0.8715, "lr": 7.072450854819848e-07, "epoch": 0.014200590299047725, "percentage": 0.14, "elapsed_time": "0:03:16", "remaining_time": "1 day, 14:23:29", "throughput": 700.66, "total_tokens": 137712} +{"current_steps": 260, "total_steps": 179570, "loss": 1.2473, "lr": 7.211672328339924e-07, "epoch": 0.014479033246087876, "percentage": 0.14, "elapsed_time": "0:03:20", "remaining_time": "1 day, 14:21:48", "throughput": 700.78, "total_tokens": 140336} +{"current_steps": 265, "total_steps": 179570, "loss": 0.86, "lr": 7.350893801859999e-07, "epoch": 0.014757476193128028, "percentage": 0.15, "elapsed_time": "0:03:23", "remaining_time": "1 day, 14:20:01", "throughput": 700.62, "total_tokens": 142896} +{"current_steps": 270, "total_steps": 179570, "loss": 0.6749, "lr": 7.490115275380075e-07, "epoch": 0.01503591914016818, "percentage": 0.15, "elapsed_time": "0:03:27", "remaining_time": "1 day, 14:21:33", "throughput": 700.94, "total_tokens": 145760} +{"current_steps": 275, "total_steps": 179570, "loss": 1.2604, "lr": 7.629336748900151e-07, "epoch": 0.01531436208720833, "percentage": 0.15, "elapsed_time": "0:03:31", "remaining_time": "1 day, 14:22:51", "throughput": 701.0, "total_tokens": 148560} +{"current_steps": 280, "total_steps": 179570, "loss": 1.3121, "lr": 7.768558222420227e-07, "epoch": 0.015592805034248482, "percentage": 0.16, "elapsed_time": "0:03:35", "remaining_time": "1 day, 14:23:01", "throughput": 701.16, "total_tokens": 151312} +{"current_steps": 285, "total_steps": 179570, "loss": 0.9475, "lr": 7.907779695940303e-07, "epoch": 0.015871247981288635, "percentage": 0.16, "elapsed_time": "0:03:39", "remaining_time": "1 day, 14:24:16", "throughput": 701.87, "total_tokens": 154256} +{"current_steps": 290, "total_steps": 179570, "loss": 0.7494, "lr": 8.047001169460379e-07, "epoch": 0.016149690928328787, "percentage": 0.16, "elapsed_time": "0:03:43", "remaining_time": "1 day, 14:21:47", "throughput": 701.02, "total_tokens": 156608} +{"current_steps": 295, "total_steps": 179570, "loss": 0.9838, "lr": 8.186222642980454e-07, "epoch": 0.016428133875368938, "percentage": 0.16, "elapsed_time": "0:03:47", "remaining_time": "1 day, 14:22:21", "throughput": 700.7, "total_tokens": 159280} +{"current_steps": 300, "total_steps": 179570, "loss": 0.8668, "lr": 8.325444116500529e-07, "epoch": 0.01670657682240909, "percentage": 0.17, "elapsed_time": "0:03:51", "remaining_time": "1 day, 14:23:04", "throughput": 700.69, "total_tokens": 162032} +{"current_steps": 305, "total_steps": 179570, "loss": 1.5454, "lr": 8.464665590020605e-07, "epoch": 0.01698501976944924, "percentage": 0.17, "elapsed_time": "0:03:55", "remaining_time": "1 day, 14:26:37", "throughput": 701.1, "total_tokens": 165088} +{"current_steps": 310, "total_steps": 179570, "loss": 0.881, "lr": 8.603887063540681e-07, "epoch": 0.017263462716489392, "percentage": 0.17, "elapsed_time": "0:03:59", "remaining_time": "1 day, 14:27:11", "throughput": 700.9, "total_tokens": 167792} +{"current_steps": 315, "total_steps": 179570, "loss": 0.6944, "lr": 8.743108537060757e-07, "epoch": 0.017541905663529544, "percentage": 0.18, "elapsed_time": "0:04:02", "remaining_time": "1 day, 14:23:46", "throughput": 700.79, "total_tokens": 170224} +{"current_steps": 320, "total_steps": 179570, "loss": 0.85, "lr": 8.882330010580833e-07, "epoch": 0.017820348610569695, "percentage": 0.18, "elapsed_time": "0:04:06", "remaining_time": "1 day, 14:25:48", "throughput": 701.27, "total_tokens": 173200} +{"current_steps": 325, "total_steps": 179570, "loss": 0.6016, "lr": 9.021551484100908e-07, "epoch": 0.018098791557609847, "percentage": 0.18, "elapsed_time": "0:04:11", "remaining_time": "1 day, 14:27:26", "throughput": 701.38, "total_tokens": 176064} +{"current_steps": 330, "total_steps": 179570, "loss": 0.6547, "lr": 9.160772957620984e-07, "epoch": 0.018377234504649998, "percentage": 0.18, "elapsed_time": "0:04:14", "remaining_time": "1 day, 14:27:38", "throughput": 701.22, "total_tokens": 178752} +{"current_steps": 335, "total_steps": 179570, "loss": 0.9922, "lr": 9.29999443114106e-07, "epoch": 0.01865567745169015, "percentage": 0.19, "elapsed_time": "0:04:18", "remaining_time": "1 day, 14:24:02", "throughput": 701.04, "total_tokens": 181136} +{"current_steps": 340, "total_steps": 179570, "loss": 0.4951, "lr": 9.439215904661136e-07, "epoch": 0.0189341203987303, "percentage": 0.19, "elapsed_time": "0:04:22", "remaining_time": "1 day, 14:23:47", "throughput": 700.67, "total_tokens": 183728} +{"current_steps": 345, "total_steps": 179570, "loss": 1.079, "lr": 9.57843737818121e-07, "epoch": 0.019212563345770452, "percentage": 0.19, "elapsed_time": "0:04:26", "remaining_time": "1 day, 14:25:34", "throughput": 700.89, "total_tokens": 186640} +{"current_steps": 350, "total_steps": 179570, "loss": 0.5845, "lr": 9.717658851701287e-07, "epoch": 0.019491006292810604, "percentage": 0.19, "elapsed_time": "0:04:30", "remaining_time": "1 day, 14:29:44", "throughput": 701.03, "total_tokens": 189728} +{"current_steps": 355, "total_steps": 179570, "loss": 0.7466, "lr": 9.856880325221362e-07, "epoch": 0.019769449239850755, "percentage": 0.2, "elapsed_time": "0:04:34", "remaining_time": "1 day, 14:29:20", "throughput": 700.58, "total_tokens": 192288} +{"current_steps": 360, "total_steps": 179570, "loss": 0.6946, "lr": 9.996101798741438e-07, "epoch": 0.020047892186890907, "percentage": 0.2, "elapsed_time": "0:04:38", "remaining_time": "1 day, 14:32:15", "throughput": 701.1, "total_tokens": 195392} +{"current_steps": 365, "total_steps": 179570, "loss": 0.5769, "lr": 1.0135323272261514e-06, "epoch": 0.020326335133931058, "percentage": 0.2, "elapsed_time": "0:04:42", "remaining_time": "1 day, 14:29:02", "throughput": 700.83, "total_tokens": 197760} +{"current_steps": 370, "total_steps": 179570, "loss": 1.0085, "lr": 1.027454474578159e-06, "epoch": 0.02060477808097121, "percentage": 0.21, "elapsed_time": "0:04:46", "remaining_time": "1 day, 14:30:25", "throughput": 700.99, "total_tokens": 200640} +{"current_steps": 375, "total_steps": 179570, "loss": 0.7809, "lr": 1.0413766219301666e-06, "epoch": 0.02088322102801136, "percentage": 0.21, "elapsed_time": "0:04:50", "remaining_time": "1 day, 14:31:21", "throughput": 701.32, "total_tokens": 203536} +{"current_steps": 380, "total_steps": 179570, "loss": 1.1245, "lr": 1.0552987692821742e-06, "epoch": 0.021161663975051512, "percentage": 0.21, "elapsed_time": "0:04:54", "remaining_time": "1 day, 14:34:34", "throughput": 701.43, "total_tokens": 206576} +{"current_steps": 385, "total_steps": 179570, "loss": 0.6628, "lr": 1.0692209166341817e-06, "epoch": 0.021440106922091664, "percentage": 0.21, "elapsed_time": "0:04:58", "remaining_time": "1 day, 14:37:43", "throughput": 701.49, "total_tokens": 209600} +{"current_steps": 390, "total_steps": 179570, "loss": 0.7843, "lr": 1.0831430639861893e-06, "epoch": 0.021718549869131815, "percentage": 0.22, "elapsed_time": "0:05:02", "remaining_time": "1 day, 14:38:09", "throughput": 701.75, "total_tokens": 212448} +{"current_steps": 395, "total_steps": 179570, "loss": 0.4944, "lr": 1.097065211338197e-06, "epoch": 0.021996992816171967, "percentage": 0.22, "elapsed_time": "0:05:06", "remaining_time": "1 day, 14:39:23", "throughput": 701.97, "total_tokens": 215360} +{"current_steps": 400, "total_steps": 179570, "loss": 0.9736, "lr": 1.1109873586902045e-06, "epoch": 0.022275435763212118, "percentage": 0.22, "elapsed_time": "0:05:10", "remaining_time": "1 day, 14:40:41", "throughput": 702.31, "total_tokens": 218320} +{"current_steps": 405, "total_steps": 179570, "loss": 1.0249, "lr": 1.124909506042212e-06, "epoch": 0.02255387871025227, "percentage": 0.23, "elapsed_time": "0:05:14", "remaining_time": "1 day, 14:40:50", "throughput": 702.12, "total_tokens": 221008} +{"current_steps": 410, "total_steps": 179570, "loss": 0.7584, "lr": 1.1388316533942195e-06, "epoch": 0.02283232165729242, "percentage": 0.23, "elapsed_time": "0:05:18", "remaining_time": "1 day, 14:38:56", "throughput": 701.69, "total_tokens": 223424} +{"current_steps": 415, "total_steps": 179570, "loss": 0.6075, "lr": 1.152753800746227e-06, "epoch": 0.023110764604332572, "percentage": 0.23, "elapsed_time": "0:05:22", "remaining_time": "1 day, 14:42:24", "throughput": 701.9, "total_tokens": 226560} +{"current_steps": 420, "total_steps": 179570, "loss": 0.4651, "lr": 1.1666759480982346e-06, "epoch": 0.023389207551372724, "percentage": 0.23, "elapsed_time": "0:05:26", "remaining_time": "1 day, 14:44:37", "throughput": 702.01, "total_tokens": 229552} +{"current_steps": 425, "total_steps": 179570, "loss": 0.9168, "lr": 1.1805980954502422e-06, "epoch": 0.023667650498412875, "percentage": 0.24, "elapsed_time": "0:05:31", "remaining_time": "1 day, 14:46:14", "throughput": 702.0, "total_tokens": 232448} +{"current_steps": 430, "total_steps": 179570, "loss": 0.9522, "lr": 1.1945202428022498e-06, "epoch": 0.023946093445453027, "percentage": 0.24, "elapsed_time": "0:05:34", "remaining_time": "1 day, 14:45:24", "throughput": 702.04, "total_tokens": 235120} +{"current_steps": 435, "total_steps": 179570, "loss": 0.9983, "lr": 1.2084423901542574e-06, "epoch": 0.024224536392493178, "percentage": 0.24, "elapsed_time": "0:05:39", "remaining_time": "1 day, 14:50:34", "throughput": 701.88, "total_tokens": 238336} +{"current_steps": 440, "total_steps": 179570, "loss": 0.5044, "lr": 1.222364537506265e-06, "epoch": 0.02450297933953333, "percentage": 0.25, "elapsed_time": "0:05:43", "remaining_time": "1 day, 14:52:45", "throughput": 702.27, "total_tokens": 241440} +{"current_steps": 445, "total_steps": 179570, "loss": 0.8925, "lr": 1.2362866848582725e-06, "epoch": 0.02478142228657348, "percentage": 0.25, "elapsed_time": "0:05:47", "remaining_time": "1 day, 14:53:44", "throughput": 702.58, "total_tokens": 244400} +{"current_steps": 450, "total_steps": 179570, "loss": 0.8346, "lr": 1.2502088322102801e-06, "epoch": 0.025059865233613633, "percentage": 0.25, "elapsed_time": "0:05:51", "remaining_time": "1 day, 14:50:38", "throughput": 701.96, "total_tokens": 246608} +{"current_steps": 455, "total_steps": 179570, "loss": 0.909, "lr": 1.2641309795622877e-06, "epoch": 0.025338308180653784, "percentage": 0.25, "elapsed_time": "0:05:55", "remaining_time": "1 day, 14:51:59", "throughput": 701.97, "total_tokens": 249504} +{"current_steps": 460, "total_steps": 179570, "loss": 1.0266, "lr": 1.2780531269142953e-06, "epoch": 0.025616751127693935, "percentage": 0.26, "elapsed_time": "0:05:59", "remaining_time": "1 day, 14:52:10", "throughput": 702.11, "total_tokens": 252320} +{"current_steps": 465, "total_steps": 179570, "loss": 0.7911, "lr": 1.2919752742663029e-06, "epoch": 0.025895194074734087, "percentage": 0.26, "elapsed_time": "0:06:03", "remaining_time": "1 day, 14:50:29", "throughput": 702.04, "total_tokens": 254864} +{"current_steps": 470, "total_steps": 179570, "loss": 0.5067, "lr": 1.3058974216183105e-06, "epoch": 0.026173637021774238, "percentage": 0.26, "elapsed_time": "0:06:07", "remaining_time": "1 day, 14:53:20", "throughput": 702.24, "total_tokens": 258000} +{"current_steps": 475, "total_steps": 179570, "loss": 1.1996, "lr": 1.319819568970318e-06, "epoch": 0.02645207996881439, "percentage": 0.26, "elapsed_time": "0:06:10", "remaining_time": "1 day, 14:50:49", "throughput": 702.4, "total_tokens": 260528} +{"current_steps": 480, "total_steps": 179570, "loss": 0.7372, "lr": 1.3337417163223256e-06, "epoch": 0.02673052291585454, "percentage": 0.27, "elapsed_time": "0:06:14", "remaining_time": "1 day, 14:51:53", "throughput": 702.89, "total_tokens": 263584} +{"current_steps": 485, "total_steps": 179570, "loss": 0.445, "lr": 1.3476638636743332e-06, "epoch": 0.027008965862894693, "percentage": 0.27, "elapsed_time": "0:06:18", "remaining_time": "1 day, 14:51:01", "throughput": 702.98, "total_tokens": 266272} +{"current_steps": 490, "total_steps": 179570, "loss": 0.3943, "lr": 1.3615860110263408e-06, "epoch": 0.027287408809934844, "percentage": 0.27, "elapsed_time": "0:06:22", "remaining_time": "1 day, 14:51:56", "throughput": 703.29, "total_tokens": 269248} +{"current_steps": 495, "total_steps": 179570, "loss": 0.198, "lr": 1.3755081583783484e-06, "epoch": 0.027565851756974995, "percentage": 0.28, "elapsed_time": "0:06:26", "remaining_time": "1 day, 14:52:34", "throughput": 703.13, "total_tokens": 272016} +{"current_steps": 500, "total_steps": 179570, "loss": 1.2813, "lr": 1.3894303057303558e-06, "epoch": 0.027844294704015147, "percentage": 0.28, "elapsed_time": "0:06:30", "remaining_time": "1 day, 14:50:00", "throughput": 702.75, "total_tokens": 274320} +{"current_steps": 505, "total_steps": 179570, "loss": 0.3979, "lr": 1.4033524530823633e-06, "epoch": 0.0281227376510553, "percentage": 0.28, "elapsed_time": "0:06:34", "remaining_time": "1 day, 14:48:55", "throughput": 702.96, "total_tokens": 277024} +{"current_steps": 510, "total_steps": 179570, "loss": 1.0497, "lr": 1.417274600434371e-06, "epoch": 0.02840118059809545, "percentage": 0.28, "elapsed_time": "0:06:38", "remaining_time": "1 day, 14:49:19", "throughput": 703.04, "total_tokens": 279856} +{"current_steps": 515, "total_steps": 179570, "loss": 0.5223, "lr": 1.4311967477863785e-06, "epoch": 0.0286796235451356, "percentage": 0.29, "elapsed_time": "0:06:41", "remaining_time": "1 day, 14:46:35", "throughput": 702.95, "total_tokens": 282240} +{"current_steps": 520, "total_steps": 179570, "loss": 0.2944, "lr": 1.445118895138386e-06, "epoch": 0.028958066492175753, "percentage": 0.29, "elapsed_time": "0:06:45", "remaining_time": "1 day, 14:47:26", "throughput": 703.06, "total_tokens": 285136} +{"current_steps": 525, "total_steps": 179570, "loss": 0.7013, "lr": 1.4590410424903937e-06, "epoch": 0.029236509439215904, "percentage": 0.29, "elapsed_time": "0:06:49", "remaining_time": "1 day, 14:47:35", "throughput": 703.1, "total_tokens": 287920} +{"current_steps": 530, "total_steps": 179570, "loss": 0.6451, "lr": 1.4729631898424013e-06, "epoch": 0.029514952386256055, "percentage": 0.3, "elapsed_time": "0:06:53", "remaining_time": "1 day, 14:48:32", "throughput": 703.39, "total_tokens": 290912} +{"current_steps": 535, "total_steps": 179570, "loss": 0.5118, "lr": 1.4868853371944089e-06, "epoch": 0.029793395333296207, "percentage": 0.3, "elapsed_time": "0:06:57", "remaining_time": "1 day, 14:49:23", "throughput": 703.37, "total_tokens": 293760} +{"current_steps": 540, "total_steps": 179570, "loss": 0.5021, "lr": 1.5008074845464164e-06, "epoch": 0.03007183828033636, "percentage": 0.3, "elapsed_time": "0:07:02", "remaining_time": "1 day, 14:51:52", "throughput": 703.41, "total_tokens": 296848} +{"current_steps": 545, "total_steps": 179570, "loss": 0.4185, "lr": 1.514729631898424e-06, "epoch": 0.03035028122737651, "percentage": 0.3, "elapsed_time": "0:07:06", "remaining_time": "1 day, 14:52:40", "throughput": 703.54, "total_tokens": 299760} +{"current_steps": 550, "total_steps": 179570, "loss": 0.8383, "lr": 1.5286517792504316e-06, "epoch": 0.03062872417441666, "percentage": 0.31, "elapsed_time": "0:07:09", "remaining_time": "1 day, 14:51:37", "throughput": 703.65, "total_tokens": 302432} +{"current_steps": 555, "total_steps": 179570, "loss": 0.8052, "lr": 1.5425739266024392e-06, "epoch": 0.030907167121456813, "percentage": 0.31, "elapsed_time": "0:07:13", "remaining_time": "1 day, 14:52:16", "throughput": 703.7, "total_tokens": 305296} +{"current_steps": 560, "total_steps": 179570, "loss": 0.6892, "lr": 1.5564960739544468e-06, "epoch": 0.031185610068496964, "percentage": 0.31, "elapsed_time": "0:07:17", "remaining_time": "1 day, 14:52:26", "throughput": 703.49, "total_tokens": 307984} +{"current_steps": 565, "total_steps": 179570, "loss": 0.8356, "lr": 1.5704182213064544e-06, "epoch": 0.03146405301553712, "percentage": 0.31, "elapsed_time": "0:07:21", "remaining_time": "1 day, 14:51:41", "throughput": 703.55, "total_tokens": 310672} +{"current_steps": 570, "total_steps": 179570, "loss": 0.3406, "lr": 1.584340368658462e-06, "epoch": 0.03174249596257727, "percentage": 0.32, "elapsed_time": "0:07:25", "remaining_time": "1 day, 14:52:33", "throughput": 703.96, "total_tokens": 313728} +{"current_steps": 575, "total_steps": 179570, "loss": 0.3754, "lr": 1.5982625160104695e-06, "epoch": 0.03202093890961742, "percentage": 0.32, "elapsed_time": "0:07:29", "remaining_time": "1 day, 14:54:25", "throughput": 703.95, "total_tokens": 316736} +{"current_steps": 580, "total_steps": 179570, "loss": 0.4562, "lr": 1.6121846633624771e-06, "epoch": 0.03229938185665757, "percentage": 0.32, "elapsed_time": "0:07:33", "remaining_time": "1 day, 14:51:27", "throughput": 703.72, "total_tokens": 318992} +{"current_steps": 585, "total_steps": 179570, "loss": 0.862, "lr": 1.6261068107144847e-06, "epoch": 0.032577824803697725, "percentage": 0.33, "elapsed_time": "0:07:37", "remaining_time": "1 day, 14:50:43", "throughput": 703.41, "total_tokens": 321504} +{"current_steps": 590, "total_steps": 179570, "loss": 0.25, "lr": 1.640028958066492e-06, "epoch": 0.032856267750737876, "percentage": 0.33, "elapsed_time": "0:07:41", "remaining_time": "1 day, 14:51:51", "throughput": 703.57, "total_tokens": 324496} +{"current_steps": 595, "total_steps": 179570, "loss": 0.3209, "lr": 1.6539511054184997e-06, "epoch": 0.03313471069777803, "percentage": 0.33, "elapsed_time": "0:07:45", "remaining_time": "1 day, 14:52:39", "throughput": 703.9, "total_tokens": 327520} +{"current_steps": 600, "total_steps": 179570, "loss": 0.1763, "lr": 1.6678732527705072e-06, "epoch": 0.03341315364481818, "percentage": 0.33, "elapsed_time": "0:07:49", "remaining_time": "1 day, 14:54:03", "throughput": 704.03, "total_tokens": 330544} +{"current_steps": 605, "total_steps": 179570, "loss": 0.4138, "lr": 1.6817954001225148e-06, "epoch": 0.03369159659185833, "percentage": 0.34, "elapsed_time": "0:07:53", "remaining_time": "1 day, 14:54:41", "throughput": 704.16, "total_tokens": 333456} +{"current_steps": 610, "total_steps": 179570, "loss": 0.4268, "lr": 1.6957175474745224e-06, "epoch": 0.03397003953889848, "percentage": 0.34, "elapsed_time": "0:07:57", "remaining_time": "1 day, 14:56:46", "throughput": 704.24, "total_tokens": 336560} +{"current_steps": 615, "total_steps": 179570, "loss": 1.9085, "lr": 1.70963969482653e-06, "epoch": 0.03424848248593863, "percentage": 0.34, "elapsed_time": "0:08:01", "remaining_time": "1 day, 14:53:30", "throughput": 703.6, "total_tokens": 338544} +{"current_steps": 620, "total_steps": 179570, "loss": 0.3286, "lr": 1.7235618421785376e-06, "epoch": 0.034526925432978785, "percentage": 0.35, "elapsed_time": "0:08:05", "remaining_time": "1 day, 14:53:52", "throughput": 703.76, "total_tokens": 341440} +{"current_steps": 625, "total_steps": 179570, "loss": 0.428, "lr": 1.7374839895305452e-06, "epoch": 0.034805368380018936, "percentage": 0.35, "elapsed_time": "0:08:09", "remaining_time": "1 day, 14:53:32", "throughput": 703.71, "total_tokens": 344128} +{"current_steps": 630, "total_steps": 179570, "loss": 0.6135, "lr": 1.7514061368825527e-06, "epoch": 0.03508381132705909, "percentage": 0.35, "elapsed_time": "0:08:12", "remaining_time": "1 day, 14:53:18", "throughput": 703.43, "total_tokens": 346720} +{"current_steps": 635, "total_steps": 179570, "loss": 0.4574, "lr": 1.7653282842345603e-06, "epoch": 0.03536225427409924, "percentage": 0.35, "elapsed_time": "0:08:17", "remaining_time": "1 day, 14:55:25", "throughput": 703.58, "total_tokens": 349872} +{"current_steps": 640, "total_steps": 179570, "loss": 0.383, "lr": 1.779250431586568e-06, "epoch": 0.03564069722113939, "percentage": 0.36, "elapsed_time": "0:08:21", "remaining_time": "1 day, 14:54:43", "throughput": 703.6, "total_tokens": 352544} +{"current_steps": 645, "total_steps": 179570, "loss": 0.5215, "lr": 1.7931725789385755e-06, "epoch": 0.03591914016817954, "percentage": 0.36, "elapsed_time": "0:08:25", "remaining_time": "1 day, 14:55:16", "throughput": 703.61, "total_tokens": 355392} +{"current_steps": 650, "total_steps": 179570, "loss": 0.9503, "lr": 1.807094726290583e-06, "epoch": 0.03619758311521969, "percentage": 0.36, "elapsed_time": "0:08:28", "remaining_time": "1 day, 14:54:38", "throughput": 703.71, "total_tokens": 358112} +{"current_steps": 655, "total_steps": 179570, "loss": 0.6048, "lr": 1.8210168736425907e-06, "epoch": 0.036476026062259845, "percentage": 0.36, "elapsed_time": "0:08:33", "remaining_time": "1 day, 14:56:06", "throughput": 704.05, "total_tokens": 361280} +{"current_steps": 660, "total_steps": 179570, "loss": 0.4819, "lr": 1.8349390209945982e-06, "epoch": 0.036754469009299996, "percentage": 0.37, "elapsed_time": "0:08:37", "remaining_time": "1 day, 14:56:37", "throughput": 704.27, "total_tokens": 364240} +{"current_steps": 665, "total_steps": 179570, "loss": 0.5532, "lr": 1.8488611683466058e-06, "epoch": 0.03703291195634015, "percentage": 0.37, "elapsed_time": "0:08:41", "remaining_time": "1 day, 14:57:29", "throughput": 704.25, "total_tokens": 367136} +{"current_steps": 670, "total_steps": 179570, "loss": 0.6727, "lr": 1.8627833156986134e-06, "epoch": 0.0373113549033803, "percentage": 0.37, "elapsed_time": "0:08:45", "remaining_time": "1 day, 14:57:58", "throughput": 704.25, "total_tokens": 369984} +{"current_steps": 675, "total_steps": 179570, "loss": 0.2362, "lr": 1.8767054630506208e-06, "epoch": 0.03758979785042045, "percentage": 0.38, "elapsed_time": "0:08:49", "remaining_time": "1 day, 14:57:16", "throughput": 704.3, "total_tokens": 372672} +{"current_steps": 680, "total_steps": 179570, "loss": 0.7317, "lr": 1.8906276104026284e-06, "epoch": 0.0378682407974606, "percentage": 0.38, "elapsed_time": "0:08:53", "remaining_time": "1 day, 14:58:29", "throughput": 704.44, "total_tokens": 375712} +{"current_steps": 685, "total_steps": 179570, "loss": 0.5484, "lr": 1.904549757754636e-06, "epoch": 0.03814668374450075, "percentage": 0.38, "elapsed_time": "0:08:57", "remaining_time": "1 day, 14:59:18", "throughput": 704.43, "total_tokens": 378608} +{"current_steps": 690, "total_steps": 179570, "loss": 0.3058, "lr": 1.9184719051066435e-06, "epoch": 0.038425126691540905, "percentage": 0.38, "elapsed_time": "0:09:01", "remaining_time": "1 day, 14:58:26", "throughput": 704.2, "total_tokens": 381120} +{"current_steps": 695, "total_steps": 179570, "loss": 0.4615, "lr": 1.9323940524586513e-06, "epoch": 0.038703569638581056, "percentage": 0.39, "elapsed_time": "0:09:04", "remaining_time": "1 day, 14:55:52", "throughput": 703.94, "total_tokens": 383328} +{"current_steps": 700, "total_steps": 179570, "loss": 0.3774, "lr": 1.9463161998106587e-06, "epoch": 0.03898201258562121, "percentage": 0.39, "elapsed_time": "0:09:08", "remaining_time": "1 day, 14:55:07", "throughput": 703.87, "total_tokens": 385936} +{"current_steps": 705, "total_steps": 179570, "loss": 0.7145, "lr": 1.9602383471626665e-06, "epoch": 0.03926045553266136, "percentage": 0.39, "elapsed_time": "0:09:12", "remaining_time": "1 day, 14:56:15", "throughput": 703.94, "total_tokens": 388928} +{"current_steps": 710, "total_steps": 179570, "loss": 0.5191, "lr": 1.974160494514674e-06, "epoch": 0.03953889847970151, "percentage": 0.4, "elapsed_time": "0:09:16", "remaining_time": "1 day, 14:57:08", "throughput": 704.07, "total_tokens": 391920} +{"current_steps": 715, "total_steps": 179570, "loss": 0.7229, "lr": 1.9880826418666817e-06, "epoch": 0.03981734142674166, "percentage": 0.4, "elapsed_time": "0:09:20", "remaining_time": "1 day, 14:56:51", "throughput": 704.07, "total_tokens": 394640} +{"current_steps": 720, "total_steps": 179570, "loss": 0.4249, "lr": 2.002004789218689e-06, "epoch": 0.04009578437378181, "percentage": 0.4, "elapsed_time": "0:09:24", "remaining_time": "1 day, 14:57:19", "throughput": 704.17, "total_tokens": 397552} +{"current_steps": 725, "total_steps": 179570, "loss": 0.7996, "lr": 2.0159269365706964e-06, "epoch": 0.040374227320821965, "percentage": 0.4, "elapsed_time": "0:09:28", "remaining_time": "1 day, 14:57:33", "throughput": 704.3, "total_tokens": 400432} +{"current_steps": 730, "total_steps": 179570, "loss": 0.6448, "lr": 2.0298490839227042e-06, "epoch": 0.040652670267862116, "percentage": 0.41, "elapsed_time": "0:09:32", "remaining_time": "1 day, 14:55:43", "throughput": 703.97, "total_tokens": 402704} +{"current_steps": 735, "total_steps": 179570, "loss": 0.4453, "lr": 2.0437712312747116e-06, "epoch": 0.04093111321490227, "percentage": 0.41, "elapsed_time": "0:09:36", "remaining_time": "1 day, 14:56:51", "throughput": 704.1, "total_tokens": 405744} +{"current_steps": 740, "total_steps": 179570, "loss": 0.3771, "lr": 2.0576933786267194e-06, "epoch": 0.04120955616194242, "percentage": 0.41, "elapsed_time": "0:09:40", "remaining_time": "1 day, 14:57:06", "throughput": 704.24, "total_tokens": 408640} +{"current_steps": 745, "total_steps": 179570, "loss": 0.3211, "lr": 2.0716155259787268e-06, "epoch": 0.04148799910898257, "percentage": 0.41, "elapsed_time": "0:09:43", "remaining_time": "1 day, 14:56:13", "throughput": 704.22, "total_tokens": 411248} +{"current_steps": 750, "total_steps": 179570, "loss": 0.3808, "lr": 2.0855376733307346e-06, "epoch": 0.04176644205602272, "percentage": 0.42, "elapsed_time": "0:09:48", "remaining_time": "1 day, 14:56:47", "throughput": 704.13, "total_tokens": 414064} +{"current_steps": 755, "total_steps": 179570, "loss": 0.1852, "lr": 2.099459820682742e-06, "epoch": 0.04204488500306287, "percentage": 0.42, "elapsed_time": "0:09:52", "remaining_time": "1 day, 14:56:51", "throughput": 704.24, "total_tokens": 416912} +{"current_steps": 760, "total_steps": 179570, "loss": 0.174, "lr": 2.1133819680347497e-06, "epoch": 0.042323327950103025, "percentage": 0.42, "elapsed_time": "0:09:56", "remaining_time": "1 day, 14:57:08", "throughput": 704.41, "total_tokens": 419840} +{"current_steps": 765, "total_steps": 179570, "loss": 0.3619, "lr": 2.127304115386757e-06, "epoch": 0.042601770897143176, "percentage": 0.43, "elapsed_time": "0:09:59", "remaining_time": "1 day, 14:56:01", "throughput": 704.44, "total_tokens": 422432} +{"current_steps": 770, "total_steps": 179570, "loss": 0.4019, "lr": 2.141226262738765e-06, "epoch": 0.04288021384418333, "percentage": 0.43, "elapsed_time": "0:10:03", "remaining_time": "1 day, 14:56:28", "throughput": 704.33, "total_tokens": 425216} +{"current_steps": 775, "total_steps": 179570, "loss": 0.1644, "lr": 2.1551484100907723e-06, "epoch": 0.04315865679122348, "percentage": 0.43, "elapsed_time": "0:10:07", "remaining_time": "1 day, 14:55:37", "throughput": 704.31, "total_tokens": 427824} +{"current_steps": 780, "total_steps": 179570, "loss": 0.4606, "lr": 2.16907055744278e-06, "epoch": 0.04343709973826363, "percentage": 0.43, "elapsed_time": "0:10:11", "remaining_time": "1 day, 14:54:32", "throughput": 704.26, "total_tokens": 430368} +{"current_steps": 785, "total_steps": 179570, "loss": 0.2171, "lr": 2.1829927047947874e-06, "epoch": 0.04371554268530378, "percentage": 0.44, "elapsed_time": "0:10:15", "remaining_time": "1 day, 14:56:08", "throughput": 704.3, "total_tokens": 433456} +{"current_steps": 790, "total_steps": 179570, "loss": 0.4178, "lr": 2.1969148521467952e-06, "epoch": 0.043993985632343934, "percentage": 0.44, "elapsed_time": "0:10:19", "remaining_time": "1 day, 14:57:57", "throughput": 704.16, "total_tokens": 436480} +{"current_steps": 795, "total_steps": 179570, "loss": 0.4507, "lr": 2.2108369994988026e-06, "epoch": 0.044272428579384085, "percentage": 0.44, "elapsed_time": "0:10:24", "remaining_time": "1 day, 14:58:59", "throughput": 704.29, "total_tokens": 439536} +{"current_steps": 800, "total_steps": 179570, "loss": 0.7125, "lr": 2.2247591468508104e-06, "epoch": 0.044550871526424236, "percentage": 0.45, "elapsed_time": "0:10:28", "remaining_time": "1 day, 14:59:07", "throughput": 704.32, "total_tokens": 442352} +{"current_steps": 805, "total_steps": 179570, "loss": 0.5682, "lr": 2.238681294202818e-06, "epoch": 0.04482931447346439, "percentage": 0.45, "elapsed_time": "0:10:31", "remaining_time": "1 day, 14:57:17", "throughput": 704.32, "total_tokens": 444784} +{"current_steps": 810, "total_steps": 179570, "loss": 0.2775, "lr": 2.2526034415548256e-06, "epoch": 0.04510775742050454, "percentage": 0.45, "elapsed_time": "0:10:35", "remaining_time": "1 day, 14:57:30", "throughput": 704.47, "total_tokens": 447696} +{"current_steps": 815, "total_steps": 179570, "loss": 0.3974, "lr": 2.2665255889068334e-06, "epoch": 0.04538620036754469, "percentage": 0.45, "elapsed_time": "0:10:39", "remaining_time": "1 day, 14:57:02", "throughput": 704.68, "total_tokens": 450512} +{"current_steps": 820, "total_steps": 179570, "loss": 0.6249, "lr": 2.2804477362588407e-06, "epoch": 0.04566464331458484, "percentage": 0.46, "elapsed_time": "0:10:43", "remaining_time": "1 day, 14:58:19", "throughput": 704.75, "total_tokens": 453584} +{"current_steps": 825, "total_steps": 179570, "loss": 0.8788, "lr": 2.2943698836108485e-06, "epoch": 0.045943086261624994, "percentage": 0.46, "elapsed_time": "0:10:47", "remaining_time": "1 day, 14:58:49", "throughput": 704.88, "total_tokens": 456544} +{"current_steps": 830, "total_steps": 179570, "loss": 0.1893, "lr": 2.308292030962856e-06, "epoch": 0.046221529208665145, "percentage": 0.46, "elapsed_time": "0:10:51", "remaining_time": "1 day, 14:58:33", "throughput": 704.89, "total_tokens": 459280} +{"current_steps": 835, "total_steps": 179570, "loss": 0.3622, "lr": 2.3222141783148637e-06, "epoch": 0.046499972155705296, "percentage": 0.46, "elapsed_time": "0:10:55", "remaining_time": "1 day, 14:58:38", "throughput": 704.85, "total_tokens": 462048} +{"current_steps": 840, "total_steps": 179570, "loss": 0.4299, "lr": 2.336136325666871e-06, "epoch": 0.04677841510274545, "percentage": 0.47, "elapsed_time": "0:10:59", "remaining_time": "1 day, 14:57:32", "throughput": 704.65, "total_tokens": 464480} +{"current_steps": 845, "total_steps": 179570, "loss": 0.3561, "lr": 2.350058473018879e-06, "epoch": 0.0470568580497856, "percentage": 0.47, "elapsed_time": "0:11:03", "remaining_time": "1 day, 14:58:27", "throughput": 704.7, "total_tokens": 467472} +{"current_steps": 850, "total_steps": 179570, "loss": 0.3149, "lr": 2.3639806203708862e-06, "epoch": 0.04733530099682575, "percentage": 0.47, "elapsed_time": "0:11:07", "remaining_time": "1 day, 14:57:41", "throughput": 704.79, "total_tokens": 470160} +{"current_steps": 855, "total_steps": 179570, "loss": 0.3044, "lr": 2.377902767722894e-06, "epoch": 0.0476137439438659, "percentage": 0.48, "elapsed_time": "0:11:11", "remaining_time": "1 day, 14:57:47", "throughput": 704.75, "total_tokens": 472928} +{"current_steps": 860, "total_steps": 179570, "loss": 0.4001, "lr": 2.3918249150749014e-06, "epoch": 0.047892186890906054, "percentage": 0.48, "elapsed_time": "0:11:14", "remaining_time": "1 day, 14:55:02", "throughput": 704.54, "total_tokens": 475008} +{"current_steps": 865, "total_steps": 179570, "loss": 0.1399, "lr": 2.405747062426909e-06, "epoch": 0.048170629837946205, "percentage": 0.48, "elapsed_time": "0:11:18", "remaining_time": "1 day, 14:55:26", "throughput": 704.6, "total_tokens": 477904} +{"current_steps": 870, "total_steps": 179570, "loss": 0.6501, "lr": 2.4196692097789166e-06, "epoch": 0.048449072784986356, "percentage": 0.48, "elapsed_time": "0:11:22", "remaining_time": "1 day, 14:55:46", "throughput": 704.65, "total_tokens": 480784} +{"current_steps": 875, "total_steps": 179570, "loss": 0.5467, "lr": 2.433591357130924e-06, "epoch": 0.04872751573202651, "percentage": 0.49, "elapsed_time": "0:11:26", "remaining_time": "1 day, 14:55:42", "throughput": 704.57, "total_tokens": 483488} +{"current_steps": 880, "total_steps": 179570, "loss": 0.5131, "lr": 2.4475135044829317e-06, "epoch": 0.04900595867906666, "percentage": 0.49, "elapsed_time": "0:11:29", "remaining_time": "1 day, 14:54:55", "throughput": 704.56, "total_tokens": 486096} +{"current_steps": 885, "total_steps": 179570, "loss": 0.4521, "lr": 2.461435651834939e-06, "epoch": 0.04928440162610681, "percentage": 0.49, "elapsed_time": "0:11:33", "remaining_time": "1 day, 14:55:17", "throughput": 704.59, "total_tokens": 488976} +{"current_steps": 890, "total_steps": 179570, "loss": 0.1919, "lr": 2.475357799186947e-06, "epoch": 0.04956284457314696, "percentage": 0.5, "elapsed_time": "0:11:37", "remaining_time": "1 day, 14:55:16", "throughput": 704.59, "total_tokens": 491744} +{"current_steps": 895, "total_steps": 179570, "loss": 0.3635, "lr": 2.4892799465389543e-06, "epoch": 0.049841287520187114, "percentage": 0.5, "elapsed_time": "0:11:41", "remaining_time": "1 day, 14:54:20", "throughput": 704.54, "total_tokens": 494288} +{"current_steps": 900, "total_steps": 179570, "loss": 0.3159, "lr": 2.503202093890962e-06, "epoch": 0.050119730467227265, "percentage": 0.5, "elapsed_time": "0:11:45", "remaining_time": "1 day, 14:54:31", "throughput": 704.63, "total_tokens": 497168} +{"current_steps": 905, "total_steps": 179570, "loss": 1.347, "lr": 2.5171242412429695e-06, "epoch": 0.050398173414267416, "percentage": 0.5, "elapsed_time": "0:11:49", "remaining_time": "1 day, 14:53:06", "throughput": 704.64, "total_tokens": 499648} +{"current_steps": 910, "total_steps": 179570, "loss": 0.4744, "lr": 2.5310463885949772e-06, "epoch": 0.05067661636130757, "percentage": 0.51, "elapsed_time": "0:11:53", "remaining_time": "1 day, 14:53:28", "throughput": 704.72, "total_tokens": 502560} +{"current_steps": 915, "total_steps": 179570, "loss": 0.327, "lr": 2.5449685359469846e-06, "epoch": 0.05095505930834772, "percentage": 0.51, "elapsed_time": "0:11:57", "remaining_time": "1 day, 14:53:35", "throughput": 704.7, "total_tokens": 505344} +{"current_steps": 920, "total_steps": 179570, "loss": 0.044, "lr": 2.5588906832989924e-06, "epoch": 0.05123350225538787, "percentage": 0.51, "elapsed_time": "0:12:01", "remaining_time": "1 day, 14:53:38", "throughput": 704.61, "total_tokens": 508064} +{"current_steps": 925, "total_steps": 179570, "loss": 0.3568, "lr": 2.5728128306509998e-06, "epoch": 0.05151194520242802, "percentage": 0.52, "elapsed_time": "0:12:04", "remaining_time": "1 day, 14:52:41", "throughput": 704.62, "total_tokens": 510640} +{"current_steps": 930, "total_steps": 179570, "loss": 1.0563, "lr": 2.5867349780030076e-06, "epoch": 0.051790388149468174, "percentage": 0.52, "elapsed_time": "0:12:08", "remaining_time": "1 day, 14:50:56", "throughput": 704.37, "total_tokens": 512848} +{"current_steps": 935, "total_steps": 179570, "loss": 0.1651, "lr": 2.600657125355015e-06, "epoch": 0.052068831096508325, "percentage": 0.52, "elapsed_time": "0:12:11", "remaining_time": "1 day, 14:50:38", "throughput": 704.24, "total_tokens": 515456} +{"current_steps": 940, "total_steps": 179570, "loss": 0.0396, "lr": 2.6145792727070228e-06, "epoch": 0.052347274043548477, "percentage": 0.52, "elapsed_time": "0:12:16", "remaining_time": "1 day, 14:52:03", "throughput": 704.37, "total_tokens": 518640} +{"current_steps": 945, "total_steps": 179570, "loss": 0.1697, "lr": 2.62850142005903e-06, "epoch": 0.05262571699058863, "percentage": 0.53, "elapsed_time": "0:12:20", "remaining_time": "1 day, 14:52:39", "throughput": 704.36, "total_tokens": 521536} +{"current_steps": 950, "total_steps": 179570, "loss": 0.0786, "lr": 2.642423567411038e-06, "epoch": 0.05290415993762878, "percentage": 0.53, "elapsed_time": "0:12:24", "remaining_time": "1 day, 14:51:58", "throughput": 704.43, "total_tokens": 524208} +{"current_steps": 955, "total_steps": 179570, "loss": 0.2959, "lr": 2.6563457147630453e-06, "epoch": 0.05318260288466893, "percentage": 0.53, "elapsed_time": "0:12:28", "remaining_time": "1 day, 14:52:30", "throughput": 704.3, "total_tokens": 527008} +{"current_steps": 960, "total_steps": 179570, "loss": 0.467, "lr": 2.6702678621150527e-06, "epoch": 0.05346104583170908, "percentage": 0.53, "elapsed_time": "0:12:32", "remaining_time": "1 day, 14:52:00", "throughput": 704.32, "total_tokens": 529680} +{"current_steps": 965, "total_steps": 179570, "loss": 0.3046, "lr": 2.6841900094670605e-06, "epoch": 0.053739488778749234, "percentage": 0.54, "elapsed_time": "0:12:36", "remaining_time": "1 day, 14:53:44", "throughput": 704.29, "total_tokens": 532832} +{"current_steps": 970, "total_steps": 179570, "loss": 0.1982, "lr": 2.698112156819068e-06, "epoch": 0.054017931725789385, "percentage": 0.54, "elapsed_time": "0:12:40", "remaining_time": "1 day, 14:54:46", "throughput": 704.22, "total_tokens": 535792} +{"current_steps": 975, "total_steps": 179570, "loss": 0.0929, "lr": 2.7120343041710756e-06, "epoch": 0.05429637467282954, "percentage": 0.54, "elapsed_time": "0:12:44", "remaining_time": "1 day, 14:55:10", "throughput": 704.32, "total_tokens": 538736} +{"current_steps": 980, "total_steps": 179570, "loss": 0.2508, "lr": 2.725956451523083e-06, "epoch": 0.05457481761986969, "percentage": 0.55, "elapsed_time": "0:12:49", "remaining_time": "1 day, 14:55:55", "throughput": 704.29, "total_tokens": 541664} +{"current_steps": 985, "total_steps": 179570, "loss": 0.1989, "lr": 2.739878598875091e-06, "epoch": 0.05485326056690984, "percentage": 0.55, "elapsed_time": "0:12:53", "remaining_time": "1 day, 14:56:57", "throughput": 704.25, "total_tokens": 544656} +{"current_steps": 990, "total_steps": 179570, "loss": 0.0996, "lr": 2.753800746227098e-06, "epoch": 0.05513170351394999, "percentage": 0.55, "elapsed_time": "0:12:57", "remaining_time": "1 day, 14:57:18", "throughput": 704.11, "total_tokens": 547408} +{"current_steps": 995, "total_steps": 179570, "loss": 0.4736, "lr": 2.767722893579106e-06, "epoch": 0.05541014646099014, "percentage": 0.55, "elapsed_time": "0:13:01", "remaining_time": "1 day, 14:58:04", "throughput": 704.15, "total_tokens": 550400} +{"current_steps": 1000, "total_steps": 179570, "loss": 0.3705, "lr": 2.7816450409311133e-06, "epoch": 0.055688589408030294, "percentage": 0.56, "elapsed_time": "0:13:05", "remaining_time": "1 day, 14:58:36", "throughput": 704.11, "total_tokens": 553280} +{"current_steps": 1005, "total_steps": 179570, "loss": 0.6464, "lr": 2.795567188283121e-06, "epoch": 0.055967032355070445, "percentage": 0.56, "elapsed_time": "0:13:09", "remaining_time": "1 day, 14:57:07", "throughput": 704.08, "total_tokens": 555680} +{"current_steps": 1010, "total_steps": 179570, "loss": 0.6172, "lr": 2.8094893356351285e-06, "epoch": 0.0562454753021106, "percentage": 0.56, "elapsed_time": "0:13:12", "remaining_time": "1 day, 14:56:26", "throughput": 704.13, "total_tokens": 558336} +{"current_steps": 1015, "total_steps": 179570, "loss": 0.1004, "lr": 2.8234114829871363e-06, "epoch": 0.05652391824915075, "percentage": 0.57, "elapsed_time": "0:13:16", "remaining_time": "1 day, 14:56:21", "throughput": 704.08, "total_tokens": 561056} +{"current_steps": 1020, "total_steps": 179570, "loss": 0.2972, "lr": 2.8373336303391437e-06, "epoch": 0.0568023611961909, "percentage": 0.57, "elapsed_time": "0:13:20", "remaining_time": "1 day, 14:56:43", "throughput": 704.03, "total_tokens": 563888} +{"current_steps": 1025, "total_steps": 179570, "loss": 0.0388, "lr": 2.8512557776911515e-06, "epoch": 0.05708080414323105, "percentage": 0.57, "elapsed_time": "0:13:25", "remaining_time": "1 day, 14:57:05", "throughput": 704.19, "total_tokens": 566880} +{"current_steps": 1030, "total_steps": 179570, "loss": 0.1505, "lr": 2.865177925043159e-06, "epoch": 0.0573592470902712, "percentage": 0.57, "elapsed_time": "0:13:29", "remaining_time": "1 day, 14:57:24", "throughput": 704.31, "total_tokens": 569840} +{"current_steps": 1035, "total_steps": 179570, "loss": 0.7813, "lr": 2.8791000723951666e-06, "epoch": 0.057637690037311354, "percentage": 0.58, "elapsed_time": "0:13:33", "remaining_time": "1 day, 14:59:02", "throughput": 704.39, "total_tokens": 573088} +{"current_steps": 1040, "total_steps": 179570, "loss": 0.0539, "lr": 2.893022219747174e-06, "epoch": 0.057916132984351505, "percentage": 0.58, "elapsed_time": "0:13:37", "remaining_time": "1 day, 14:58:15", "throughput": 704.25, "total_tokens": 575568} +{"current_steps": 1045, "total_steps": 179570, "loss": 0.4731, "lr": 2.9069443670991814e-06, "epoch": 0.05819457593139166, "percentage": 0.58, "elapsed_time": "0:13:40", "remaining_time": "1 day, 14:57:23", "throughput": 704.27, "total_tokens": 578144} +{"current_steps": 1050, "total_steps": 179570, "loss": 0.449, "lr": 2.920866514451189e-06, "epoch": 0.05847301887843181, "percentage": 0.58, "elapsed_time": "0:13:45", "remaining_time": "1 day, 14:58:06", "throughput": 704.32, "total_tokens": 581152} +{"current_steps": 1055, "total_steps": 179570, "loss": 0.3302, "lr": 2.9347886618031966e-06, "epoch": 0.05875146182547196, "percentage": 0.59, "elapsed_time": "0:13:48", "remaining_time": "1 day, 14:57:37", "throughput": 704.35, "total_tokens": 583840} +{"current_steps": 1060, "total_steps": 179570, "loss": 0.321, "lr": 2.9487108091552043e-06, "epoch": 0.05902990477251211, "percentage": 0.59, "elapsed_time": "0:13:52", "remaining_time": "1 day, 14:57:07", "throughput": 704.37, "total_tokens": 586512} +{"current_steps": 1065, "total_steps": 179570, "loss": 0.6716, "lr": 2.9626329565072117e-06, "epoch": 0.05930834771955226, "percentage": 0.59, "elapsed_time": "0:13:56", "remaining_time": "1 day, 14:56:12", "throughput": 704.3, "total_tokens": 589008} +{"current_steps": 1070, "total_steps": 179570, "loss": 0.413, "lr": 2.9765551038592195e-06, "epoch": 0.059586790666592414, "percentage": 0.6, "elapsed_time": "0:14:00", "remaining_time": "1 day, 14:55:45", "throughput": 704.36, "total_tokens": 591728} +{"current_steps": 1075, "total_steps": 179570, "loss": 0.4696, "lr": 2.990477251211227e-06, "epoch": 0.059865233613632565, "percentage": 0.6, "elapsed_time": "0:14:03", "remaining_time": "1 day, 14:55:13", "throughput": 704.3, "total_tokens": 594320} +{"current_steps": 1080, "total_steps": 179570, "loss": 0.3295, "lr": 3.0043993985632347e-06, "epoch": 0.06014367656067272, "percentage": 0.6, "elapsed_time": "0:14:07", "remaining_time": "1 day, 14:55:35", "throughput": 704.48, "total_tokens": 597344} +{"current_steps": 1085, "total_steps": 179570, "loss": 0.4963, "lr": 3.018321545915242e-06, "epoch": 0.06042211950771287, "percentage": 0.6, "elapsed_time": "0:14:11", "remaining_time": "1 day, 14:55:07", "throughput": 704.49, "total_tokens": 600016} +{"current_steps": 1090, "total_steps": 179570, "loss": 0.1659, "lr": 3.03224369326725e-06, "epoch": 0.06070056245475302, "percentage": 0.61, "elapsed_time": "0:14:15", "remaining_time": "1 day, 14:55:29", "throughput": 704.64, "total_tokens": 603024} +{"current_steps": 1095, "total_steps": 179570, "loss": 0.6211, "lr": 3.0461658406192572e-06, "epoch": 0.06097900540179317, "percentage": 0.61, "elapsed_time": "0:14:19", "remaining_time": "1 day, 14:54:17", "throughput": 704.62, "total_tokens": 605472} +{"current_steps": 1100, "total_steps": 179570, "loss": 0.2157, "lr": 3.060087987971265e-06, "epoch": 0.06125744834883332, "percentage": 0.61, "elapsed_time": "0:14:23", "remaining_time": "1 day, 14:54:37", "throughput": 704.72, "total_tokens": 608432} +{"current_steps": 1105, "total_steps": 179570, "loss": 0.1756, "lr": 3.0740101353232724e-06, "epoch": 0.061535891295873474, "percentage": 0.62, "elapsed_time": "0:14:27", "remaining_time": "1 day, 14:54:56", "throughput": 704.83, "total_tokens": 611392} +{"current_steps": 1110, "total_steps": 179570, "loss": 0.3765, "lr": 3.08793228267528e-06, "epoch": 0.061814334242913625, "percentage": 0.62, "elapsed_time": "0:14:31", "remaining_time": "1 day, 14:56:03", "throughput": 704.88, "total_tokens": 614512} +{"current_steps": 1115, "total_steps": 179570, "loss": 0.6331, "lr": 3.1018544300272876e-06, "epoch": 0.06209277718995378, "percentage": 0.62, "elapsed_time": "0:14:35", "remaining_time": "1 day, 14:55:18", "throughput": 704.68, "total_tokens": 616928} +{"current_steps": 1120, "total_steps": 179570, "loss": 0.1464, "lr": 3.1157765773792954e-06, "epoch": 0.06237122013699393, "percentage": 0.62, "elapsed_time": "0:14:39", "remaining_time": "1 day, 14:56:04", "throughput": 704.85, "total_tokens": 620064} +{"current_steps": 1125, "total_steps": 179570, "loss": 0.2895, "lr": 3.1296987247313023e-06, "epoch": 0.06264966308403408, "percentage": 0.63, "elapsed_time": "0:14:43", "remaining_time": "1 day, 14:55:45", "throughput": 704.74, "total_tokens": 622672} +{"current_steps": 1130, "total_steps": 179570, "loss": 0.4752, "lr": 3.1436208720833105e-06, "epoch": 0.06292810603107424, "percentage": 0.63, "elapsed_time": "0:14:47", "remaining_time": "1 day, 14:55:38", "throughput": 704.65, "total_tokens": 625344} +{"current_steps": 1135, "total_steps": 179570, "loss": 0.2394, "lr": 3.1575430194353175e-06, "epoch": 0.06320654897811438, "percentage": 0.63, "elapsed_time": "0:14:51", "remaining_time": "1 day, 14:55:11", "throughput": 704.68, "total_tokens": 628032} +{"current_steps": 1140, "total_steps": 179570, "loss": 0.4542, "lr": 3.1714651667873253e-06, "epoch": 0.06348499192515454, "percentage": 0.63, "elapsed_time": "0:14:55", "remaining_time": "1 day, 14:56:03", "throughput": 704.7, "total_tokens": 631072} +{"current_steps": 1145, "total_steps": 179570, "loss": 0.4661, "lr": 3.1853873141393326e-06, "epoch": 0.06376343487219469, "percentage": 0.64, "elapsed_time": "0:14:59", "remaining_time": "1 day, 14:56:48", "throughput": 704.89, "total_tokens": 634224} +{"current_steps": 1150, "total_steps": 179570, "loss": 0.2145, "lr": 3.1993094614913404e-06, "epoch": 0.06404187781923484, "percentage": 0.64, "elapsed_time": "0:15:03", "remaining_time": "1 day, 14:57:29", "throughput": 705.01, "total_tokens": 637312} +{"current_steps": 1155, "total_steps": 179570, "loss": 0.0521, "lr": 3.213231608843348e-06, "epoch": 0.06432032076627499, "percentage": 0.64, "elapsed_time": "0:15:07", "remaining_time": "1 day, 14:57:27", "throughput": 704.91, "total_tokens": 640000} +{"current_steps": 1160, "total_steps": 179570, "loss": 0.5274, "lr": 3.2271537561953556e-06, "epoch": 0.06459876371331515, "percentage": 0.65, "elapsed_time": "0:15:11", "remaining_time": "1 day, 14:56:45", "throughput": 704.8, "total_tokens": 642496} +{"current_steps": 1165, "total_steps": 179570, "loss": 0.2895, "lr": 3.241075903547363e-06, "epoch": 0.06487720666035529, "percentage": 0.65, "elapsed_time": "0:15:15", "remaining_time": "1 day, 14:56:17", "throughput": 704.8, "total_tokens": 645152} +{"current_steps": 1170, "total_steps": 179570, "loss": 0.1231, "lr": 3.2549980508993708e-06, "epoch": 0.06515564960739545, "percentage": 0.65, "elapsed_time": "0:15:19", "remaining_time": "1 day, 14:56:58", "throughput": 704.9, "total_tokens": 648224} +{"current_steps": 1175, "total_steps": 179570, "loss": 0.4985, "lr": 3.268920198251378e-06, "epoch": 0.0654340925544356, "percentage": 0.65, "elapsed_time": "0:15:23", "remaining_time": "1 day, 14:57:24", "throughput": 704.89, "total_tokens": 651120} +{"current_steps": 1180, "total_steps": 179570, "loss": 0.3694, "lr": 3.282842345603386e-06, "epoch": 0.06571253550147575, "percentage": 0.66, "elapsed_time": "0:15:27", "remaining_time": "1 day, 14:56:56", "throughput": 704.9, "total_tokens": 653792} +{"current_steps": 1185, "total_steps": 179570, "loss": 0.4886, "lr": 3.2967644929553933e-06, "epoch": 0.0659909784485159, "percentage": 0.66, "elapsed_time": "0:15:31", "remaining_time": "1 day, 14:57:44", "throughput": 704.86, "total_tokens": 656768} +{"current_steps": 1190, "total_steps": 179570, "loss": 0.4025, "lr": 3.310686640307401e-06, "epoch": 0.06626942139555606, "percentage": 0.66, "elapsed_time": "0:15:35", "remaining_time": "1 day, 14:57:39", "throughput": 704.9, "total_tokens": 659568} +{"current_steps": 1195, "total_steps": 179570, "loss": 0.7387, "lr": 3.3246087876594085e-06, "epoch": 0.0665478643425962, "percentage": 0.67, "elapsed_time": "0:15:39", "remaining_time": "1 day, 14:57:10", "throughput": 704.83, "total_tokens": 662160} +{"current_steps": 1200, "total_steps": 179570, "loss": 0.2198, "lr": 3.3385309350114163e-06, "epoch": 0.06682630728963636, "percentage": 0.67, "elapsed_time": "0:15:43", "remaining_time": "1 day, 14:57:28", "throughput": 704.94, "total_tokens": 665136} +{"current_steps": 1205, "total_steps": 179570, "loss": 0.2637, "lr": 3.3524530823634237e-06, "epoch": 0.0671047502366765, "percentage": 0.67, "elapsed_time": "0:15:47", "remaining_time": "1 day, 14:57:16", "throughput": 704.81, "total_tokens": 667744} +{"current_steps": 1210, "total_steps": 179570, "loss": 0.3131, "lr": 3.3663752297154315e-06, "epoch": 0.06738319318371666, "percentage": 0.67, "elapsed_time": "0:15:51", "remaining_time": "1 day, 14:57:08", "throughput": 704.76, "total_tokens": 670448} +{"current_steps": 1215, "total_steps": 179570, "loss": 0.298, "lr": 3.380297377067439e-06, "epoch": 0.0676616361307568, "percentage": 0.68, "elapsed_time": "0:15:55", "remaining_time": "1 day, 14:56:41", "throughput": 704.74, "total_tokens": 673088} +{"current_steps": 1220, "total_steps": 179570, "loss": 0.304, "lr": 3.3942195244194466e-06, "epoch": 0.06794007907779696, "percentage": 0.68, "elapsed_time": "0:15:58", "remaining_time": "1 day, 14:56:32", "throughput": 704.61, "total_tokens": 675712} +{"current_steps": 1225, "total_steps": 179570, "loss": 0.1848, "lr": 3.408141671771454e-06, "epoch": 0.06821852202483711, "percentage": 0.68, "elapsed_time": "0:16:02", "remaining_time": "1 day, 14:56:08", "throughput": 704.66, "total_tokens": 678432} +{"current_steps": 1230, "total_steps": 179570, "loss": 0.307, "lr": 3.422063819123462e-06, "epoch": 0.06849696497187727, "percentage": 0.68, "elapsed_time": "0:16:06", "remaining_time": "1 day, 14:55:39", "throughput": 704.56, "total_tokens": 680976} +{"current_steps": 1235, "total_steps": 179570, "loss": 0.737, "lr": 3.435985966475469e-06, "epoch": 0.06877540791891741, "percentage": 0.69, "elapsed_time": "0:16:10", "remaining_time": "1 day, 14:55:12", "throughput": 704.52, "total_tokens": 683600} +{"current_steps": 1240, "total_steps": 179570, "loss": 0.4493, "lr": 3.449908113827477e-06, "epoch": 0.06905385086595757, "percentage": 0.69, "elapsed_time": "0:16:14", "remaining_time": "1 day, 14:55:04", "throughput": 704.41, "total_tokens": 686240} +{"current_steps": 1245, "total_steps": 179570, "loss": 0.0974, "lr": 3.4638302611794843e-06, "epoch": 0.06933229381299771, "percentage": 0.69, "elapsed_time": "0:16:17", "remaining_time": "1 day, 14:54:41", "throughput": 704.49, "total_tokens": 688992} +{"current_steps": 1250, "total_steps": 179570, "loss": 0.1803, "lr": 3.477752408531492e-06, "epoch": 0.06961073676003787, "percentage": 0.7, "elapsed_time": "0:16:22", "remaining_time": "1 day, 14:55:16", "throughput": 704.52, "total_tokens": 691984} +{"current_steps": 1255, "total_steps": 179570, "loss": 0.2713, "lr": 3.4916745558835e-06, "epoch": 0.06988917970707802, "percentage": 0.7, "elapsed_time": "0:16:26", "remaining_time": "1 day, 14:55:56", "throughput": 704.66, "total_tokens": 695104} +{"current_steps": 1260, "total_steps": 179570, "loss": 0.5055, "lr": 3.5055967032355073e-06, "epoch": 0.07016762265411818, "percentage": 0.7, "elapsed_time": "0:16:29", "remaining_time": "1 day, 14:54:52", "throughput": 704.65, "total_tokens": 697568} +{"current_steps": 1265, "total_steps": 179570, "loss": 0.5836, "lr": 3.519518850587515e-06, "epoch": 0.07044606560115832, "percentage": 0.7, "elapsed_time": "0:16:34", "remaining_time": "1 day, 14:55:07", "throughput": 704.72, "total_tokens": 700496} +{"current_steps": 1270, "total_steps": 179570, "loss": 0.2441, "lr": 3.5334409979395225e-06, "epoch": 0.07072450854819848, "percentage": 0.71, "elapsed_time": "0:16:37", "remaining_time": "1 day, 14:53:54", "throughput": 704.7, "total_tokens": 702896} +{"current_steps": 1275, "total_steps": 179570, "loss": 0.6458, "lr": 3.5473631452915303e-06, "epoch": 0.07100295149523862, "percentage": 0.71, "elapsed_time": "0:16:41", "remaining_time": "1 day, 14:54:26", "throughput": 704.66, "total_tokens": 705808} +{"current_steps": 1280, "total_steps": 179570, "loss": 0.2661, "lr": 3.5612852926435376e-06, "epoch": 0.07128139444227878, "percentage": 0.71, "elapsed_time": "0:16:45", "remaining_time": "1 day, 14:54:38", "throughput": 704.69, "total_tokens": 708688} +{"current_steps": 1285, "total_steps": 179570, "loss": 0.3112, "lr": 3.5752074399955454e-06, "epoch": 0.07155983738931893, "percentage": 0.72, "elapsed_time": "0:16:49", "remaining_time": "1 day, 14:54:52", "throughput": 704.78, "total_tokens": 711632} +{"current_steps": 1290, "total_steps": 179570, "loss": 0.3267, "lr": 3.589129587347553e-06, "epoch": 0.07183828033635908, "percentage": 0.72, "elapsed_time": "0:16:53", "remaining_time": "1 day, 14:55:03", "throughput": 704.78, "total_tokens": 714480} +{"current_steps": 1295, "total_steps": 179570, "loss": 0.4555, "lr": 3.6030517346995606e-06, "epoch": 0.07211672328339923, "percentage": 0.72, "elapsed_time": "0:16:58", "remaining_time": "1 day, 14:55:55", "throughput": 704.72, "total_tokens": 717472} +{"current_steps": 1300, "total_steps": 179570, "loss": 0.1757, "lr": 3.616973882051568e-06, "epoch": 0.07239516623043939, "percentage": 0.72, "elapsed_time": "0:17:02", "remaining_time": "1 day, 14:55:53", "throughput": 704.79, "total_tokens": 720320} +{"current_steps": 1305, "total_steps": 179570, "loss": 0.6055, "lr": 3.6308960294035758e-06, "epoch": 0.07267360917747953, "percentage": 0.73, "elapsed_time": "0:17:05", "remaining_time": "1 day, 14:54:49", "throughput": 704.72, "total_tokens": 722720} +{"current_steps": 1310, "total_steps": 179570, "loss": 0.1774, "lr": 3.644818176755583e-06, "epoch": 0.07295205212451969, "percentage": 0.73, "elapsed_time": "0:17:09", "remaining_time": "1 day, 14:55:03", "throughput": 704.79, "total_tokens": 725648} +{"current_steps": 1315, "total_steps": 179570, "loss": 0.6956, "lr": 3.658740324107591e-06, "epoch": 0.07323049507155983, "percentage": 0.73, "elapsed_time": "0:17:13", "remaining_time": "1 day, 14:56:00", "throughput": 704.87, "total_tokens": 728816} +{"current_steps": 1320, "total_steps": 179570, "loss": 0.2059, "lr": 3.672662471459598e-06, "epoch": 0.07350893801859999, "percentage": 0.74, "elapsed_time": "0:17:17", "remaining_time": "1 day, 14:56:05", "throughput": 704.93, "total_tokens": 731696} +{"current_steps": 1325, "total_steps": 179570, "loss": 0.7665, "lr": 3.686584618811606e-06, "epoch": 0.07378738096564014, "percentage": 0.74, "elapsed_time": "0:17:21", "remaining_time": "1 day, 14:56:12", "throughput": 705.04, "total_tokens": 734640} +{"current_steps": 1330, "total_steps": 179570, "loss": 0.8373, "lr": 3.700506766163613e-06, "epoch": 0.0740658239126803, "percentage": 0.74, "elapsed_time": "0:17:25", "remaining_time": "1 day, 14:55:46", "throughput": 704.99, "total_tokens": 737248} +{"current_steps": 1335, "total_steps": 179570, "loss": 0.0638, "lr": 3.7144289135156213e-06, "epoch": 0.07434426685972044, "percentage": 0.74, "elapsed_time": "0:17:30", "remaining_time": "1 day, 14:56:29", "throughput": 704.97, "total_tokens": 740240} +{"current_steps": 1340, "total_steps": 179570, "loss": 0.4418, "lr": 3.7283510608676282e-06, "epoch": 0.0746227098067606, "percentage": 0.75, "elapsed_time": "0:17:33", "remaining_time": "1 day, 14:55:40", "throughput": 704.9, "total_tokens": 742704} +{"current_steps": 1345, "total_steps": 179570, "loss": 0.5665, "lr": 3.7422732082196364e-06, "epoch": 0.07490115275380074, "percentage": 0.75, "elapsed_time": "0:17:37", "remaining_time": "1 day, 14:55:41", "throughput": 704.87, "total_tokens": 745472} +{"current_steps": 1350, "total_steps": 179570, "loss": 0.7774, "lr": 3.7561953555716434e-06, "epoch": 0.0751795957008409, "percentage": 0.75, "elapsed_time": "0:17:40", "remaining_time": "1 day, 14:54:03", "throughput": 704.76, "total_tokens": 747616} +{"current_steps": 1355, "total_steps": 179570, "loss": 0.298, "lr": 3.7701175029236516e-06, "epoch": 0.07545803864788105, "percentage": 0.75, "elapsed_time": "0:17:44", "remaining_time": "1 day, 14:54:16", "throughput": 704.67, "total_tokens": 750384} +{"current_steps": 1360, "total_steps": 179570, "loss": 0.3383, "lr": 3.7840396502756586e-06, "epoch": 0.0757364815949212, "percentage": 0.76, "elapsed_time": "0:17:48", "remaining_time": "1 day, 14:53:17", "throughput": 704.65, "total_tokens": 752832} +{"current_steps": 1365, "total_steps": 179570, "loss": 0.0246, "lr": 3.7979617976276668e-06, "epoch": 0.07601492454196135, "percentage": 0.76, "elapsed_time": "0:17:52", "remaining_time": "1 day, 14:52:51", "throughput": 704.61, "total_tokens": 755440} +{"current_steps": 1370, "total_steps": 179570, "loss": 0.6999, "lr": 3.8118839449796737e-06, "epoch": 0.0762933674890015, "percentage": 0.76, "elapsed_time": "0:17:56", "remaining_time": "1 day, 14:53:22", "throughput": 704.63, "total_tokens": 758416} +{"current_steps": 1375, "total_steps": 179570, "loss": 0.1024, "lr": 3.8258060923316815e-06, "epoch": 0.07657181043604165, "percentage": 0.77, "elapsed_time": "0:18:00", "remaining_time": "1 day, 14:53:27", "throughput": 704.69, "total_tokens": 761296} +{"current_steps": 1380, "total_steps": 179570, "loss": 0.5054, "lr": 3.839728239683689e-06, "epoch": 0.07685025338308181, "percentage": 0.77, "elapsed_time": "0:18:04", "remaining_time": "1 day, 14:53:30", "throughput": 704.73, "total_tokens": 764144} +{"current_steps": 1385, "total_steps": 179570, "loss": 0.1601, "lr": 3.853650387035697e-06, "epoch": 0.07712869633012195, "percentage": 0.77, "elapsed_time": "0:18:07", "remaining_time": "1 day, 14:52:29", "throughput": 704.64, "total_tokens": 766512} +{"current_steps": 1390, "total_steps": 179570, "loss": 0.8524, "lr": 3.8675725343877045e-06, "epoch": 0.07740713927716211, "percentage": 0.77, "elapsed_time": "0:18:11", "remaining_time": "1 day, 14:52:45", "throughput": 704.81, "total_tokens": 769568} +{"current_steps": 1395, "total_steps": 179570, "loss": 0.5549, "lr": 3.881494681739712e-06, "epoch": 0.07768558222420226, "percentage": 0.78, "elapsed_time": "0:18:16", "remaining_time": "1 day, 14:53:38", "throughput": 704.9, "total_tokens": 772752} +{"current_steps": 1400, "total_steps": 179570, "loss": 0.4762, "lr": 3.895416829091719e-06, "epoch": 0.07796402517124242, "percentage": 0.78, "elapsed_time": "0:18:20", "remaining_time": "1 day, 14:54:07", "throughput": 704.88, "total_tokens": 775680} +{"current_steps": 1405, "total_steps": 179570, "loss": 0.3628, "lr": 3.9093389764437275e-06, "epoch": 0.07824246811828256, "percentage": 0.78, "elapsed_time": "0:18:24", "remaining_time": "1 day, 14:54:13", "throughput": 705.0, "total_tokens": 778640} +{"current_steps": 1410, "total_steps": 179570, "loss": 0.3714, "lr": 3.923261123795734e-06, "epoch": 0.07852091106532272, "percentage": 0.79, "elapsed_time": "0:18:28", "remaining_time": "1 day, 14:54:43", "throughput": 705.01, "total_tokens": 781616} +{"current_steps": 1415, "total_steps": 179570, "loss": 0.3394, "lr": 3.937183271147742e-06, "epoch": 0.07879935401236286, "percentage": 0.79, "elapsed_time": "0:18:32", "remaining_time": "1 day, 14:55:07", "throughput": 705.1, "total_tokens": 784640} +{"current_steps": 1420, "total_steps": 179570, "loss": 0.2887, "lr": 3.9511054184997496e-06, "epoch": 0.07907779695940302, "percentage": 0.79, "elapsed_time": "0:18:36", "remaining_time": "1 day, 14:54:45", "throughput": 705.14, "total_tokens": 787360} +{"current_steps": 1425, "total_steps": 179570, "loss": 0.5042, "lr": 3.965027565851758e-06, "epoch": 0.07935623990644317, "percentage": 0.79, "elapsed_time": "0:18:40", "remaining_time": "1 day, 14:54:48", "throughput": 705.19, "total_tokens": 790224} +{"current_steps": 1430, "total_steps": 179570, "loss": 0.4838, "lr": 3.978949713203764e-06, "epoch": 0.07963468285348332, "percentage": 0.8, "elapsed_time": "0:18:44", "remaining_time": "1 day, 14:54:16", "throughput": 705.14, "total_tokens": 792784} +{"current_steps": 1435, "total_steps": 179570, "loss": 0.3392, "lr": 3.9928718605557725e-06, "epoch": 0.07991312580052347, "percentage": 0.8, "elapsed_time": "0:18:48", "remaining_time": "1 day, 14:54:39", "throughput": 705.18, "total_tokens": 795744} +{"current_steps": 1440, "total_steps": 179570, "loss": 0.6348, "lr": 4.00679400790778e-06, "epoch": 0.08019156874756363, "percentage": 0.8, "elapsed_time": "0:18:52", "remaining_time": "1 day, 14:54:06", "throughput": 705.14, "total_tokens": 798320} +{"current_steps": 1445, "total_steps": 179570, "loss": 0.4416, "lr": 4.020716155259788e-06, "epoch": 0.08047001169460377, "percentage": 0.8, "elapsed_time": "0:18:55", "remaining_time": "1 day, 14:53:37", "throughput": 705.17, "total_tokens": 800976} +{"current_steps": 1450, "total_steps": 179570, "loss": 0.5384, "lr": 4.034638302611795e-06, "epoch": 0.08074845464164393, "percentage": 0.81, "elapsed_time": "0:18:59", "remaining_time": "1 day, 14:53:50", "throughput": 705.25, "total_tokens": 803936} +{"current_steps": 1455, "total_steps": 179570, "loss": 0.2047, "lr": 4.048560449963803e-06, "epoch": 0.08102689758868407, "percentage": 0.81, "elapsed_time": "0:19:03", "remaining_time": "1 day, 14:53:32", "throughput": 705.33, "total_tokens": 806720} +{"current_steps": 1460, "total_steps": 179570, "loss": 0.4751, "lr": 4.06248259731581e-06, "epoch": 0.08130534053572423, "percentage": 0.81, "elapsed_time": "0:19:07", "remaining_time": "1 day, 14:53:54", "throughput": 705.36, "total_tokens": 809680} +{"current_steps": 1465, "total_steps": 179570, "loss": 0.21, "lr": 4.076404744667818e-06, "epoch": 0.08158378348276438, "percentage": 0.82, "elapsed_time": "0:19:11", "remaining_time": "1 day, 14:54:03", "throughput": 705.37, "total_tokens": 812528} +{"current_steps": 1470, "total_steps": 179570, "loss": 0.2433, "lr": 4.090326892019825e-06, "epoch": 0.08186222642980454, "percentage": 0.82, "elapsed_time": "0:19:15", "remaining_time": "1 day, 14:53:51", "throughput": 705.36, "total_tokens": 815248} +{"current_steps": 1475, "total_steps": 179570, "loss": 0.2512, "lr": 4.104249039371833e-06, "epoch": 0.08214066937684468, "percentage": 0.82, "elapsed_time": "0:19:19", "remaining_time": "1 day, 14:54:00", "throughput": 705.39, "total_tokens": 818128} +{"current_steps": 1480, "total_steps": 179570, "loss": 0.2614, "lr": 4.118171186723841e-06, "epoch": 0.08241911232388484, "percentage": 0.82, "elapsed_time": "0:19:24", "remaining_time": "1 day, 14:54:33", "throughput": 705.53, "total_tokens": 821280} +{"current_steps": 1485, "total_steps": 179570, "loss": 0.5344, "lr": 4.132093334075848e-06, "epoch": 0.08269755527092498, "percentage": 0.83, "elapsed_time": "0:19:27", "remaining_time": "1 day, 14:54:00", "throughput": 705.45, "total_tokens": 823792} +{"current_steps": 1490, "total_steps": 179570, "loss": 0.2863, "lr": 4.146015481427855e-06, "epoch": 0.08297599821796514, "percentage": 0.83, "elapsed_time": "0:19:31", "remaining_time": "1 day, 14:54:06", "throughput": 705.45, "total_tokens": 826624} +{"current_steps": 1495, "total_steps": 179570, "loss": 0.2529, "lr": 4.1599376287798635e-06, "epoch": 0.08325444116500529, "percentage": 0.83, "elapsed_time": "0:19:35", "remaining_time": "1 day, 14:54:36", "throughput": 705.52, "total_tokens": 829680} +{"current_steps": 1500, "total_steps": 179570, "loss": 0.1776, "lr": 4.173859776131871e-06, "epoch": 0.08353288411204544, "percentage": 0.84, "elapsed_time": "0:19:39", "remaining_time": "1 day, 14:54:40", "throughput": 705.45, "total_tokens": 832416} +{"current_steps": 1505, "total_steps": 179570, "loss": 0.4395, "lr": 4.187781923483878e-06, "epoch": 0.08381132705908559, "percentage": 0.84, "elapsed_time": "0:19:43", "remaining_time": "1 day, 14:54:40", "throughput": 705.58, "total_tokens": 835376} +{"current_steps": 1510, "total_steps": 179570, "loss": 0.1261, "lr": 4.201704070835886e-06, "epoch": 0.08408977000612575, "percentage": 0.84, "elapsed_time": "0:19:48", "remaining_time": "1 day, 14:55:14", "throughput": 705.58, "total_tokens": 838384} +{"current_steps": 1515, "total_steps": 179570, "loss": 0.6805, "lr": 4.215626218187894e-06, "epoch": 0.08436821295316589, "percentage": 0.84, "elapsed_time": "0:19:52", "remaining_time": "1 day, 14:55:25", "throughput": 705.66, "total_tokens": 841344} +{"current_steps": 1520, "total_steps": 179570, "loss": 0.6377, "lr": 4.229548365539901e-06, "epoch": 0.08464665590020605, "percentage": 0.85, "elapsed_time": "0:19:56", "remaining_time": "1 day, 14:55:47", "throughput": 705.73, "total_tokens": 844352} +{"current_steps": 1525, "total_steps": 179570, "loss": 0.5534, "lr": 4.243470512891909e-06, "epoch": 0.0849250988472462, "percentage": 0.85, "elapsed_time": "0:20:00", "remaining_time": "1 day, 14:55:17", "throughput": 705.74, "total_tokens": 846992} +{"current_steps": 1530, "total_steps": 179570, "loss": 0.1407, "lr": 4.257392660243916e-06, "epoch": 0.08520354179428635, "percentage": 0.85, "elapsed_time": "0:20:04", "remaining_time": "1 day, 14:55:34", "throughput": 705.68, "total_tokens": 849824} +{"current_steps": 1535, "total_steps": 179570, "loss": 0.1802, "lr": 4.271314807595924e-06, "epoch": 0.0854819847413265, "percentage": 0.85, "elapsed_time": "0:20:08", "remaining_time": "1 day, 14:55:44", "throughput": 705.71, "total_tokens": 852720} +{"current_steps": 1540, "total_steps": 179570, "loss": 0.481, "lr": 4.285236954947932e-06, "epoch": 0.08576042768836666, "percentage": 0.86, "elapsed_time": "0:20:12", "remaining_time": "1 day, 14:56:03", "throughput": 705.71, "total_tokens": 855632} +{"current_steps": 1545, "total_steps": 179570, "loss": 0.5548, "lr": 4.299159102299939e-06, "epoch": 0.0860388706354068, "percentage": 0.86, "elapsed_time": "0:20:15", "remaining_time": "1 day, 14:55:09", "throughput": 705.65, "total_tokens": 858032} +{"current_steps": 1550, "total_steps": 179570, "loss": 0.174, "lr": 4.313081249651946e-06, "epoch": 0.08631731358244696, "percentage": 0.86, "elapsed_time": "0:20:20", "remaining_time": "1 day, 14:55:30", "throughput": 705.7, "total_tokens": 861024} +{"current_steps": 1555, "total_steps": 179570, "loss": 0.4751, "lr": 4.3270033970039546e-06, "epoch": 0.0865957565294871, "percentage": 0.87, "elapsed_time": "0:20:23", "remaining_time": "1 day, 14:55:07", "throughput": 705.69, "total_tokens": 863680} +{"current_steps": 1560, "total_steps": 179570, "loss": 0.3916, "lr": 4.340925544355962e-06, "epoch": 0.08687419947652726, "percentage": 0.87, "elapsed_time": "0:20:27", "remaining_time": "1 day, 14:54:55", "throughput": 705.65, "total_tokens": 866352} +{"current_steps": 1565, "total_steps": 179570, "loss": 0.4855, "lr": 4.354847691707969e-06, "epoch": 0.0871526424235674, "percentage": 0.87, "elapsed_time": "0:20:31", "remaining_time": "1 day, 14:54:36", "throughput": 705.7, "total_tokens": 869088} +{"current_steps": 1570, "total_steps": 179570, "loss": 0.4066, "lr": 4.368769839059977e-06, "epoch": 0.08743108537060756, "percentage": 0.87, "elapsed_time": "0:20:35", "remaining_time": "1 day, 14:54:57", "throughput": 705.77, "total_tokens": 872112} +{"current_steps": 1575, "total_steps": 179570, "loss": 0.4313, "lr": 4.382691986411985e-06, "epoch": 0.08770952831764771, "percentage": 0.88, "elapsed_time": "0:20:39", "remaining_time": "1 day, 14:54:21", "throughput": 705.71, "total_tokens": 874624} +{"current_steps": 1580, "total_steps": 179570, "loss": 0.2876, "lr": 4.396614133763991e-06, "epoch": 0.08798797126468787, "percentage": 0.88, "elapsed_time": "0:20:42", "remaining_time": "1 day, 14:53:28", "throughput": 705.66, "total_tokens": 877024} +{"current_steps": 1585, "total_steps": 179570, "loss": 0.2217, "lr": 4.410536281116e-06, "epoch": 0.08826641421172801, "percentage": 0.88, "elapsed_time": "0:20:46", "remaining_time": "1 day, 14:53:02", "throughput": 705.57, "total_tokens": 879552} +{"current_steps": 1590, "total_steps": 179570, "loss": 0.4612, "lr": 4.424458428468007e-06, "epoch": 0.08854485715876817, "percentage": 0.89, "elapsed_time": "0:20:50", "remaining_time": "1 day, 14:52:43", "throughput": 705.61, "total_tokens": 882272} +{"current_steps": 1595, "total_steps": 179570, "loss": 0.3296, "lr": 4.438380575820015e-06, "epoch": 0.08882330010580831, "percentage": 0.89, "elapsed_time": "0:20:53", "remaining_time": "1 day, 14:51:54", "throughput": 705.46, "total_tokens": 884576} +{"current_steps": 1600, "total_steps": 179570, "loss": 0.7386, "lr": 4.452302723172022e-06, "epoch": 0.08910174305284847, "percentage": 0.89, "elapsed_time": "0:20:57", "remaining_time": "1 day, 14:51:41", "throughput": 705.42, "total_tokens": 887248} +{"current_steps": 1605, "total_steps": 179570, "loss": 0.0901, "lr": 4.46622487052403e-06, "epoch": 0.08938018599988862, "percentage": 0.89, "elapsed_time": "0:21:01", "remaining_time": "1 day, 14:50:53", "throughput": 705.48, "total_tokens": 889808} +{"current_steps": 1610, "total_steps": 179570, "loss": 0.5498, "lr": 4.480147017876037e-06, "epoch": 0.08965862894692878, "percentage": 0.9, "elapsed_time": "0:21:05", "remaining_time": "1 day, 14:50:52", "throughput": 705.43, "total_tokens": 892544} +{"current_steps": 1615, "total_steps": 179570, "loss": 0.0328, "lr": 4.4940691652280456e-06, "epoch": 0.08993707189396892, "percentage": 0.9, "elapsed_time": "0:21:09", "remaining_time": "1 day, 14:50:48", "throughput": 705.43, "total_tokens": 895312} +{"current_steps": 1620, "total_steps": 179570, "loss": 0.2392, "lr": 4.507991312580052e-06, "epoch": 0.09021551484100908, "percentage": 0.9, "elapsed_time": "0:21:12", "remaining_time": "1 day, 14:50:28", "throughput": 705.48, "total_tokens": 898048} +{"current_steps": 1625, "total_steps": 179570, "loss": 0.4518, "lr": 4.52191345993206e-06, "epoch": 0.09049395778804922, "percentage": 0.9, "elapsed_time": "0:21:17", "remaining_time": "1 day, 14:50:37", "throughput": 705.5, "total_tokens": 900928} +{"current_steps": 1630, "total_steps": 179570, "loss": 0.2707, "lr": 4.535835607284068e-06, "epoch": 0.09077240073508938, "percentage": 0.91, "elapsed_time": "0:21:20", "remaining_time": "1 day, 14:50:39", "throughput": 705.53, "total_tokens": 903776} +{"current_steps": 1635, "total_steps": 179570, "loss": 0.3098, "lr": 4.549757754636076e-06, "epoch": 0.09105084368212953, "percentage": 0.91, "elapsed_time": "0:21:25", "remaining_time": "1 day, 14:50:49", "throughput": 705.58, "total_tokens": 906704} +{"current_steps": 1640, "total_steps": 179570, "loss": 0.3847, "lr": 4.5636799019880824e-06, "epoch": 0.09132928662916968, "percentage": 0.91, "elapsed_time": "0:21:28", "remaining_time": "1 day, 14:50:30", "throughput": 705.64, "total_tokens": 909456} +{"current_steps": 1645, "total_steps": 179570, "loss": 0.7538, "lr": 4.577602049340091e-06, "epoch": 0.09160772957620983, "percentage": 0.92, "elapsed_time": "0:21:32", "remaining_time": "1 day, 14:50:25", "throughput": 705.62, "total_tokens": 912192} +{"current_steps": 1650, "total_steps": 179570, "loss": 0.3889, "lr": 4.591524196692098e-06, "epoch": 0.09188617252324999, "percentage": 0.92, "elapsed_time": "0:21:36", "remaining_time": "1 day, 14:49:25", "throughput": 705.47, "total_tokens": 914400} +{"current_steps": 1655, "total_steps": 179570, "loss": 0.1387, "lr": 4.605446344044105e-06, "epoch": 0.09216461547029013, "percentage": 0.92, "elapsed_time": "0:21:40", "remaining_time": "1 day, 14:49:37", "throughput": 705.53, "total_tokens": 917360} +{"current_steps": 1660, "total_steps": 179570, "loss": 0.3952, "lr": 4.619368491396113e-06, "epoch": 0.09244305841733029, "percentage": 0.92, "elapsed_time": "0:21:44", "remaining_time": "1 day, 14:49:19", "throughput": 705.58, "total_tokens": 920096} +{"current_steps": 1665, "total_steps": 179570, "loss": 0.4615, "lr": 4.633290638748121e-06, "epoch": 0.09272150136437043, "percentage": 0.93, "elapsed_time": "0:21:47", "remaining_time": "1 day, 14:49:07", "throughput": 705.52, "total_tokens": 922736} +{"current_steps": 1670, "total_steps": 179570, "loss": 0.2844, "lr": 4.647212786100128e-06, "epoch": 0.09299994431141059, "percentage": 0.93, "elapsed_time": "0:21:51", "remaining_time": "1 day, 14:48:39", "throughput": 705.49, "total_tokens": 925312} +{"current_steps": 1675, "total_steps": 179570, "loss": 0.1705, "lr": 4.661134933452136e-06, "epoch": 0.09327838725845074, "percentage": 0.93, "elapsed_time": "0:21:55", "remaining_time": "1 day, 14:48:48", "throughput": 705.49, "total_tokens": 928176} +{"current_steps": 1680, "total_steps": 179570, "loss": 0.2031, "lr": 4.675057080804143e-06, "epoch": 0.0935568302054909, "percentage": 0.94, "elapsed_time": "0:21:59", "remaining_time": "1 day, 14:48:59", "throughput": 705.52, "total_tokens": 931072} +{"current_steps": 1685, "total_steps": 179570, "loss": 0.2231, "lr": 4.688979228156151e-06, "epoch": 0.09383527315253104, "percentage": 0.94, "elapsed_time": "0:22:03", "remaining_time": "1 day, 14:49:24", "throughput": 705.52, "total_tokens": 934048} +{"current_steps": 1690, "total_steps": 179570, "loss": 0.1624, "lr": 4.702901375508159e-06, "epoch": 0.0941137160995712, "percentage": 0.94, "elapsed_time": "0:22:07", "remaining_time": "1 day, 14:49:04", "throughput": 705.53, "total_tokens": 936720} +{"current_steps": 1695, "total_steps": 179570, "loss": 0.7219, "lr": 4.716823522860166e-06, "epoch": 0.09439215904661134, "percentage": 0.94, "elapsed_time": "0:22:11", "remaining_time": "1 day, 14:49:04", "throughput": 705.48, "total_tokens": 939456} +{"current_steps": 1700, "total_steps": 179570, "loss": 0.3005, "lr": 4.7307456702121734e-06, "epoch": 0.0946706019936515, "percentage": 0.95, "elapsed_time": "0:22:15", "remaining_time": "1 day, 14:48:59", "throughput": 705.39, "total_tokens": 942096} +{"current_steps": 1705, "total_steps": 179570, "loss": 0.8819, "lr": 4.744667817564182e-06, "epoch": 0.09494904494069165, "percentage": 0.95, "elapsed_time": "0:22:19", "remaining_time": "1 day, 14:49:24", "throughput": 705.42, "total_tokens": 945104} +{"current_steps": 1710, "total_steps": 179570, "loss": 0.3398, "lr": 4.758589964916189e-06, "epoch": 0.0952274878877318, "percentage": 0.95, "elapsed_time": "0:22:23", "remaining_time": "1 day, 14:49:05", "throughput": 705.45, "total_tokens": 947808} +{"current_steps": 1715, "total_steps": 179570, "loss": 0.1938, "lr": 4.772512112268196e-06, "epoch": 0.09550593083477195, "percentage": 0.96, "elapsed_time": "0:22:27", "remaining_time": "1 day, 14:48:45", "throughput": 705.45, "total_tokens": 950480} +{"current_steps": 1720, "total_steps": 179570, "loss": 0.1437, "lr": 4.786434259620204e-06, "epoch": 0.09578437378181211, "percentage": 0.96, "elapsed_time": "0:22:31", "remaining_time": "1 day, 14:49:24", "throughput": 705.44, "total_tokens": 953520} +{"current_steps": 1725, "total_steps": 179570, "loss": 0.4131, "lr": 4.800356406972212e-06, "epoch": 0.09606281672885225, "percentage": 0.96, "elapsed_time": "0:22:35", "remaining_time": "1 day, 14:49:32", "throughput": 705.47, "total_tokens": 956416} +{"current_steps": 1730, "total_steps": 179570, "loss": 0.4565, "lr": 4.814278554324219e-06, "epoch": 0.09634125967589241, "percentage": 0.96, "elapsed_time": "0:22:39", "remaining_time": "1 day, 14:49:04", "throughput": 705.44, "total_tokens": 958976} +{"current_steps": 1735, "total_steps": 179570, "loss": 0.4549, "lr": 4.828200701676227e-06, "epoch": 0.09661970262293255, "percentage": 0.97, "elapsed_time": "0:22:43", "remaining_time": "1 day, 14:49:45", "throughput": 705.51, "total_tokens": 962160} +{"current_steps": 1740, "total_steps": 179570, "loss": 0.7723, "lr": 4.842122849028234e-06, "epoch": 0.09689814556997271, "percentage": 0.97, "elapsed_time": "0:22:47", "remaining_time": "1 day, 14:50:02", "throughput": 705.54, "total_tokens": 965120} +{"current_steps": 1745, "total_steps": 179570, "loss": 0.3673, "lr": 4.856044996380242e-06, "epoch": 0.09717658851701286, "percentage": 0.97, "elapsed_time": "0:22:51", "remaining_time": "1 day, 14:49:30", "throughput": 705.56, "total_tokens": 967728} +{"current_steps": 1750, "total_steps": 179570, "loss": 0.4791, "lr": 4.86996714373225e-06, "epoch": 0.09745503146405302, "percentage": 0.97, "elapsed_time": "0:22:55", "remaining_time": "1 day, 14:49:35", "throughput": 705.68, "total_tokens": 970720} +{"current_steps": 1755, "total_steps": 179570, "loss": 0.1547, "lr": 4.883889291084257e-06, "epoch": 0.09773347441109316, "percentage": 0.98, "elapsed_time": "0:22:59", "remaining_time": "1 day, 14:48:44", "throughput": 705.58, "total_tokens": 973040} +{"current_steps": 1760, "total_steps": 179570, "loss": 0.2857, "lr": 4.8978114384362644e-06, "epoch": 0.09801191735813332, "percentage": 0.98, "elapsed_time": "0:23:02", "remaining_time": "1 day, 14:48:40", "throughput": 705.57, "total_tokens": 975792} +{"current_steps": 1765, "total_steps": 179570, "loss": 0.1467, "lr": 4.911733585788273e-06, "epoch": 0.09829036030517346, "percentage": 0.98, "elapsed_time": "0:23:06", "remaining_time": "1 day, 14:48:42", "throughput": 705.5, "total_tokens": 978512} +{"current_steps": 1770, "total_steps": 179570, "loss": 0.3151, "lr": 4.925655733140279e-06, "epoch": 0.09856880325221362, "percentage": 0.99, "elapsed_time": "0:23:11", "remaining_time": "1 day, 14:49:10", "throughput": 705.61, "total_tokens": 981648} +{"current_steps": 1775, "total_steps": 179570, "loss": 0.257, "lr": 4.939577880492287e-06, "epoch": 0.09884724619925377, "percentage": 0.99, "elapsed_time": "0:23:14", "remaining_time": "1 day, 14:48:45", "throughput": 705.62, "total_tokens": 984288} +{"current_steps": 1780, "total_steps": 179570, "loss": 0.1228, "lr": 4.953500027844295e-06, "epoch": 0.09912568914629392, "percentage": 0.99, "elapsed_time": "0:23:18", "remaining_time": "1 day, 14:48:17", "throughput": 705.55, "total_tokens": 986800} +{"current_steps": 1785, "total_steps": 179570, "loss": 0.5904, "lr": 4.967422175196303e-06, "epoch": 0.09940413209333408, "percentage": 0.99, "elapsed_time": "0:23:22", "remaining_time": "1 day, 14:47:59", "throughput": 705.57, "total_tokens": 989504} +{"current_steps": 1790, "total_steps": 179570, "loss": 0.0877, "lr": 4.9813443225483095e-06, "epoch": 0.09968257504037423, "percentage": 1.0, "elapsed_time": "0:23:26", "remaining_time": "1 day, 14:47:40", "throughput": 705.57, "total_tokens": 992160} +{"current_steps": 1795, "total_steps": 179570, "loss": 0.1362, "lr": 4.995266469900318e-06, "epoch": 0.09996101798741439, "percentage": 1.0, "elapsed_time": "0:23:30", "remaining_time": "1 day, 14:47:42", "throughput": 705.59, "total_tokens": 995008} +{"current_steps": 1800, "total_steps": 179570, "loss": 0.2611, "lr": 5.009188617252325e-06, "epoch": 0.10023946093445453, "percentage": 1.0, "elapsed_time": "0:23:34", "remaining_time": "1 day, 14:48:21", "throughput": 705.6, "total_tokens": 998096} +{"current_steps": 1805, "total_steps": 179570, "loss": 0.0303, "lr": 5.023110764604333e-06, "epoch": 0.10051790388149469, "percentage": 1.01, "elapsed_time": "0:23:38", "remaining_time": "1 day, 14:48:29", "throughput": 705.62, "total_tokens": 1000992} +{"current_steps": 1810, "total_steps": 179570, "loss": 0.3308, "lr": 5.03703291195634e-06, "epoch": 0.10079634682853483, "percentage": 1.01, "elapsed_time": "0:23:42", "remaining_time": "1 day, 14:47:35", "throughput": 705.56, "total_tokens": 1003312} +{"current_steps": 1815, "total_steps": 179570, "loss": 0.2115, "lr": 5.050955059308348e-06, "epoch": 0.10107478977557499, "percentage": 1.01, "elapsed_time": "0:23:45", "remaining_time": "1 day, 14:47:16", "throughput": 705.54, "total_tokens": 1005952} +{"current_steps": 1820, "total_steps": 179570, "loss": 0.8131, "lr": 5.0648772066603555e-06, "epoch": 0.10135323272261514, "percentage": 1.01, "elapsed_time": "0:23:50", "remaining_time": "1 day, 14:47:55", "throughput": 705.59, "total_tokens": 1009104} +{"current_steps": 1825, "total_steps": 179570, "loss": 0.5745, "lr": 5.078799354012363e-06, "epoch": 0.1016316756696553, "percentage": 1.02, "elapsed_time": "0:23:54", "remaining_time": "1 day, 14:47:50", "throughput": 705.58, "total_tokens": 1011856} +{"current_steps": 1830, "total_steps": 179570, "loss": 1.3074, "lr": 5.09272150136437e-06, "epoch": 0.10191011861669544, "percentage": 1.02, "elapsed_time": "0:23:57", "remaining_time": "1 day, 14:47:43", "throughput": 705.5, "total_tokens": 1014480} +{"current_steps": 1835, "total_steps": 179570, "loss": 0.2739, "lr": 5.1066436487163784e-06, "epoch": 0.1021885615637356, "percentage": 1.02, "elapsed_time": "0:24:02", "remaining_time": "1 day, 14:48:22", "throughput": 705.54, "total_tokens": 1017632} +{"current_steps": 1840, "total_steps": 179570, "loss": 0.0958, "lr": 5.120565796068386e-06, "epoch": 0.10246700451077574, "percentage": 1.02, "elapsed_time": "0:24:06", "remaining_time": "1 day, 14:48:04", "throughput": 705.59, "total_tokens": 1020368} +{"current_steps": 1845, "total_steps": 179570, "loss": 0.0743, "lr": 5.134487943420393e-06, "epoch": 0.1027454474578159, "percentage": 1.03, "elapsed_time": "0:24:10", "remaining_time": "1 day, 14:48:14", "throughput": 705.69, "total_tokens": 1023392} +{"current_steps": 1850, "total_steps": 179570, "loss": 0.0939, "lr": 5.1484100907724005e-06, "epoch": 0.10302389040485604, "percentage": 1.03, "elapsed_time": "0:24:13", "remaining_time": "1 day, 14:47:48", "throughput": 705.66, "total_tokens": 1025952} +{"current_steps": 1855, "total_steps": 179570, "loss": 0.5171, "lr": 5.162332238124409e-06, "epoch": 0.1033023333518962, "percentage": 1.03, "elapsed_time": "0:24:17", "remaining_time": "1 day, 14:47:50", "throughput": 705.72, "total_tokens": 1028864} +{"current_steps": 1860, "total_steps": 179570, "loss": 0.3734, "lr": 5.176254385476416e-06, "epoch": 0.10358077629893635, "percentage": 1.04, "elapsed_time": "0:24:21", "remaining_time": "1 day, 14:47:24", "throughput": 705.7, "total_tokens": 1031440} +{"current_steps": 1865, "total_steps": 179570, "loss": 0.042, "lr": 5.1901765328284235e-06, "epoch": 0.1038592192459765, "percentage": 1.04, "elapsed_time": "0:24:25", "remaining_time": "1 day, 14:47:08", "throughput": 705.76, "total_tokens": 1034208} +{"current_steps": 1870, "total_steps": 179570, "loss": 0.0841, "lr": 5.204098680180431e-06, "epoch": 0.10413766219301665, "percentage": 1.04, "elapsed_time": "0:24:29", "remaining_time": "1 day, 14:47:21", "throughput": 705.7, "total_tokens": 1037024} +{"current_steps": 1875, "total_steps": 179570, "loss": 0.5714, "lr": 5.218020827532439e-06, "epoch": 0.10441610514005681, "percentage": 1.04, "elapsed_time": "0:24:33", "remaining_time": "1 day, 14:46:37", "throughput": 705.62, "total_tokens": 1039376} +{"current_steps": 1880, "total_steps": 179570, "loss": 0.2415, "lr": 5.2319429748844465e-06, "epoch": 0.10469454808709695, "percentage": 1.05, "elapsed_time": "0:24:36", "remaining_time": "1 day, 14:46:36", "throughput": 705.65, "total_tokens": 1042224} +{"current_steps": 1885, "total_steps": 179570, "loss": 0.797, "lr": 5.245865122236454e-06, "epoch": 0.10497299103413711, "percentage": 1.05, "elapsed_time": "0:24:40", "remaining_time": "1 day, 14:46:11", "throughput": 705.62, "total_tokens": 1044784} +{"current_steps": 1890, "total_steps": 179570, "loss": 0.7147, "lr": 5.259787269588461e-06, "epoch": 0.10525143398117726, "percentage": 1.05, "elapsed_time": "0:24:44", "remaining_time": "1 day, 14:45:27", "throughput": 705.56, "total_tokens": 1047168} +{"current_steps": 1895, "total_steps": 179570, "loss": 0.091, "lr": 5.2737094169404694e-06, "epoch": 0.10552987692821741, "percentage": 1.06, "elapsed_time": "0:24:48", "remaining_time": "1 day, 14:45:16", "throughput": 705.51, "total_tokens": 1049808} +{"current_steps": 1900, "total_steps": 179570, "loss": 0.2707, "lr": 5.287631564292477e-06, "epoch": 0.10580831987525756, "percentage": 1.06, "elapsed_time": "0:24:51", "remaining_time": "1 day, 14:44:30", "throughput": 705.41, "total_tokens": 1052112} +{"current_steps": 1905, "total_steps": 179570, "loss": 0.2751, "lr": 5.301553711644484e-06, "epoch": 0.10608676282229772, "percentage": 1.06, "elapsed_time": "0:24:55", "remaining_time": "1 day, 14:44:31", "throughput": 705.4, "total_tokens": 1054912} +{"current_steps": 1910, "total_steps": 179570, "loss": 0.0284, "lr": 5.3154758589964916e-06, "epoch": 0.10636520576933786, "percentage": 1.06, "elapsed_time": "0:24:59", "remaining_time": "1 day, 14:44:26", "throughput": 705.4, "total_tokens": 1057664} +{"current_steps": 1915, "total_steps": 179570, "loss": 0.5112, "lr": 5.3293980063485e-06, "epoch": 0.10664364871637802, "percentage": 1.07, "elapsed_time": "0:25:03", "remaining_time": "1 day, 14:44:09", "throughput": 705.42, "total_tokens": 1060368} +{"current_steps": 1920, "total_steps": 179570, "loss": 0.0298, "lr": 5.343320153700507e-06, "epoch": 0.10692209166341816, "percentage": 1.07, "elapsed_time": "0:25:07", "remaining_time": "1 day, 14:43:59", "throughput": 705.39, "total_tokens": 1063040} +{"current_steps": 1925, "total_steps": 179570, "loss": 0.4122, "lr": 5.3572423010525145e-06, "epoch": 0.10720053461045832, "percentage": 1.07, "elapsed_time": "0:25:11", "remaining_time": "1 day, 14:44:16", "throughput": 705.41, "total_tokens": 1066000} +{"current_steps": 1930, "total_steps": 179570, "loss": 0.3517, "lr": 5.371164448404522e-06, "epoch": 0.10747897755749847, "percentage": 1.07, "elapsed_time": "0:25:15", "remaining_time": "1 day, 14:44:25", "throughput": 705.47, "total_tokens": 1068960} +{"current_steps": 1935, "total_steps": 179570, "loss": 0.4795, "lr": 5.38508659575653e-06, "epoch": 0.10775742050453863, "percentage": 1.08, "elapsed_time": "0:25:18", "remaining_time": "1 day, 14:43:57", "throughput": 705.44, "total_tokens": 1071504} +{"current_steps": 1940, "total_steps": 179570, "loss": 0.962, "lr": 5.399008743108537e-06, "epoch": 0.10803586345157877, "percentage": 1.08, "elapsed_time": "0:25:22", "remaining_time": "1 day, 14:43:13", "throughput": 705.4, "total_tokens": 1073904} +{"current_steps": 1945, "total_steps": 179570, "loss": 0.7851, "lr": 5.412930890460545e-06, "epoch": 0.10831430639861893, "percentage": 1.08, "elapsed_time": "0:25:25", "remaining_time": "1 day, 14:42:02", "throughput": 705.25, "total_tokens": 1075920} +{"current_steps": 1950, "total_steps": 179570, "loss": 0.1216, "lr": 5.426853037812552e-06, "epoch": 0.10859274934565907, "percentage": 1.09, "elapsed_time": "0:25:29", "remaining_time": "1 day, 14:42:05", "throughput": 705.3, "total_tokens": 1078816} +{"current_steps": 1955, "total_steps": 179570, "loss": 0.0883, "lr": 5.4407751851645604e-06, "epoch": 0.10887119229269923, "percentage": 1.09, "elapsed_time": "0:25:33", "remaining_time": "1 day, 14:42:00", "throughput": 705.29, "total_tokens": 1081552} +{"current_steps": 1960, "total_steps": 179570, "loss": 0.1365, "lr": 5.454697332516567e-06, "epoch": 0.10914963523973938, "percentage": 1.09, "elapsed_time": "0:25:37", "remaining_time": "1 day, 14:42:38", "throughput": 705.24, "total_tokens": 1084576} +{"current_steps": 1965, "total_steps": 179570, "loss": 0.7108, "lr": 5.468619479868575e-06, "epoch": 0.10942807818677953, "percentage": 1.09, "elapsed_time": "0:25:41", "remaining_time": "1 day, 14:42:39", "throughput": 705.23, "total_tokens": 1087360} +{"current_steps": 1970, "total_steps": 179570, "loss": 0.871, "lr": 5.4825416272205826e-06, "epoch": 0.10970652113381968, "percentage": 1.1, "elapsed_time": "0:25:45", "remaining_time": "1 day, 14:42:22", "throughput": 705.22, "total_tokens": 1090016} +{"current_steps": 1975, "total_steps": 179570, "loss": 0.1722, "lr": 5.496463774572591e-06, "epoch": 0.10998496408085984, "percentage": 1.1, "elapsed_time": "0:25:49", "remaining_time": "1 day, 14:42:19", "throughput": 705.21, "total_tokens": 1092768} +{"current_steps": 1980, "total_steps": 179570, "loss": 0.4469, "lr": 5.510385921924597e-06, "epoch": 0.11026340702789998, "percentage": 1.1, "elapsed_time": "0:25:53", "remaining_time": "1 day, 14:42:35", "throughput": 705.21, "total_tokens": 1095696} +{"current_steps": 1985, "total_steps": 179570, "loss": 0.3278, "lr": 5.5243080692766055e-06, "epoch": 0.11054184997494014, "percentage": 1.11, "elapsed_time": "0:25:57", "remaining_time": "1 day, 14:42:06", "throughput": 705.12, "total_tokens": 1098128} +{"current_steps": 1990, "total_steps": 179570, "loss": 0.3974, "lr": 5.538230216628613e-06, "epoch": 0.11082029292198028, "percentage": 1.11, "elapsed_time": "0:26:01", "remaining_time": "1 day, 14:41:49", "throughput": 705.14, "total_tokens": 1100816} +{"current_steps": 1995, "total_steps": 179570, "loss": 0.466, "lr": 5.55215236398062e-06, "epoch": 0.11109873586902044, "percentage": 1.11, "elapsed_time": "0:26:05", "remaining_time": "1 day, 14:41:56", "throughput": 705.13, "total_tokens": 1103648} +{"current_steps": 2000, "total_steps": 179570, "loss": 0.2291, "lr": 5.566074511332628e-06, "epoch": 0.11137717881606059, "percentage": 1.11, "elapsed_time": "0:26:09", "remaining_time": "1 day, 14:42:10", "throughput": 705.11, "total_tokens": 1106528} +{"current_steps": 2005, "total_steps": 179570, "loss": 0.559, "lr": 5.579996658684636e-06, "epoch": 0.11165562176310075, "percentage": 1.12, "elapsed_time": "0:26:13", "remaining_time": "1 day, 14:42:18", "throughput": 705.12, "total_tokens": 1109408} +{"current_steps": 2010, "total_steps": 179570, "loss": 0.0071, "lr": 5.593918806036643e-06, "epoch": 0.11193406471014089, "percentage": 1.12, "elapsed_time": "0:26:17", "remaining_time": "1 day, 14:42:15", "throughput": 705.11, "total_tokens": 1112160} +{"current_steps": 2015, "total_steps": 179570, "loss": 0.2615, "lr": 5.607840953388651e-06, "epoch": 0.11221250765718105, "percentage": 1.12, "elapsed_time": "0:26:21", "remaining_time": "1 day, 14:42:11", "throughput": 705.09, "total_tokens": 1114896} +{"current_steps": 2020, "total_steps": 179570, "loss": 0.3455, "lr": 5.621763100740658e-06, "epoch": 0.1124909506042212, "percentage": 1.12, "elapsed_time": "0:26:25", "remaining_time": "1 day, 14:42:36", "throughput": 705.2, "total_tokens": 1118064} +{"current_steps": 2025, "total_steps": 179570, "loss": 0.6209, "lr": 5.635685248092666e-06, "epoch": 0.11276939355126135, "percentage": 1.13, "elapsed_time": "0:26:29", "remaining_time": "1 day, 14:42:13", "throughput": 705.22, "total_tokens": 1120720} +{"current_steps": 2030, "total_steps": 179570, "loss": 0.0759, "lr": 5.6496073954446736e-06, "epoch": 0.1130478364983015, "percentage": 1.13, "elapsed_time": "0:26:33", "remaining_time": "1 day, 14:42:22", "throughput": 705.23, "total_tokens": 1123616} +{"current_steps": 2035, "total_steps": 179570, "loss": 0.0501, "lr": 5.663529542796681e-06, "epoch": 0.11332627944534165, "percentage": 1.13, "elapsed_time": "0:26:37", "remaining_time": "1 day, 14:42:05", "throughput": 705.22, "total_tokens": 1126256} +{"current_steps": 2040, "total_steps": 179570, "loss": 0.0432, "lr": 5.677451690148688e-06, "epoch": 0.1136047223923818, "percentage": 1.14, "elapsed_time": "0:26:41", "remaining_time": "1 day, 14:42:15", "throughput": 705.33, "total_tokens": 1129312} +{"current_steps": 2045, "total_steps": 179570, "loss": 0.3484, "lr": 5.6913738375006965e-06, "epoch": 0.11388316533942196, "percentage": 1.14, "elapsed_time": "0:26:45", "remaining_time": "1 day, 14:42:12", "throughput": 705.36, "total_tokens": 1132144} +{"current_steps": 2050, "total_steps": 179570, "loss": 0.1903, "lr": 5.705295984852704e-06, "epoch": 0.1141616082864621, "percentage": 1.14, "elapsed_time": "0:26:49", "remaining_time": "1 day, 14:42:34", "throughput": 705.43, "total_tokens": 1135232} +{"current_steps": 2055, "total_steps": 179570, "loss": 0.1189, "lr": 5.719218132204711e-06, "epoch": 0.11444005123350226, "percentage": 1.14, "elapsed_time": "0:26:53", "remaining_time": "1 day, 14:43:09", "throughput": 705.48, "total_tokens": 1138400} +{"current_steps": 2060, "total_steps": 179570, "loss": 0.1363, "lr": 5.733140279556719e-06, "epoch": 0.1147184941805424, "percentage": 1.15, "elapsed_time": "0:26:57", "remaining_time": "1 day, 14:42:53", "throughput": 705.51, "total_tokens": 1141104} +{"current_steps": 2065, "total_steps": 179570, "loss": 0.3603, "lr": 5.747062426908727e-06, "epoch": 0.11499693712758256, "percentage": 1.15, "elapsed_time": "0:27:01", "remaining_time": "1 day, 14:42:41", "throughput": 705.45, "total_tokens": 1143712} +{"current_steps": 2070, "total_steps": 179570, "loss": 0.2123, "lr": 5.760984574260734e-06, "epoch": 0.11527538007462271, "percentage": 1.15, "elapsed_time": "0:27:05", "remaining_time": "1 day, 14:42:49", "throughput": 705.51, "total_tokens": 1146688} +{"current_steps": 2075, "total_steps": 179570, "loss": 0.5803, "lr": 5.774906721612742e-06, "epoch": 0.11555382302166287, "percentage": 1.16, "elapsed_time": "0:27:09", "remaining_time": "1 day, 14:42:29", "throughput": 705.43, "total_tokens": 1149184} +{"current_steps": 2080, "total_steps": 179570, "loss": 0.7411, "lr": 5.788828868964749e-06, "epoch": 0.11583226596870301, "percentage": 1.16, "elapsed_time": "0:27:13", "remaining_time": "1 day, 14:42:42", "throughput": 705.41, "total_tokens": 1152064} +{"current_steps": 2085, "total_steps": 179570, "loss": 0.4168, "lr": 5.802751016316757e-06, "epoch": 0.11611070891574317, "percentage": 1.16, "elapsed_time": "0:27:17", "remaining_time": "1 day, 14:43:08", "throughput": 705.4, "total_tokens": 1155072} +{"current_steps": 2090, "total_steps": 179570, "loss": 0.5154, "lr": 5.816673163668765e-06, "epoch": 0.11638915186278331, "percentage": 1.16, "elapsed_time": "0:27:21", "remaining_time": "1 day, 14:42:50", "throughput": 705.38, "total_tokens": 1157696} +{"current_steps": 2095, "total_steps": 179570, "loss": 0.8017, "lr": 5.830595311020772e-06, "epoch": 0.11666759480982347, "percentage": 1.17, "elapsed_time": "0:27:25", "remaining_time": "1 day, 14:42:59", "throughput": 705.47, "total_tokens": 1160720} +{"current_steps": 2100, "total_steps": 179570, "loss": 0.3353, "lr": 5.844517458372779e-06, "epoch": 0.11694603775686362, "percentage": 1.17, "elapsed_time": "0:27:29", "remaining_time": "1 day, 14:43:17", "throughput": 705.47, "total_tokens": 1163664} +{"current_steps": 2105, "total_steps": 179570, "loss": 0.3523, "lr": 5.8584396057247875e-06, "epoch": 0.11722448070390377, "percentage": 1.17, "elapsed_time": "0:27:32", "remaining_time": "1 day, 14:42:23", "throughput": 705.35, "total_tokens": 1165824} +{"current_steps": 2110, "total_steps": 179570, "loss": 0.3726, "lr": 5.872361753076795e-06, "epoch": 0.11750292365094392, "percentage": 1.18, "elapsed_time": "0:27:36", "remaining_time": "1 day, 14:42:06", "throughput": 705.36, "total_tokens": 1168496} +{"current_steps": 2115, "total_steps": 179570, "loss": 0.165, "lr": 5.886283900428802e-06, "epoch": 0.11778136659798408, "percentage": 1.18, "elapsed_time": "0:27:40", "remaining_time": "1 day, 14:42:33", "throughput": 705.38, "total_tokens": 1171552} +{"current_steps": 2120, "total_steps": 179570, "loss": 0.3757, "lr": 5.90020604778081e-06, "epoch": 0.11805980954502422, "percentage": 1.18, "elapsed_time": "0:27:45", "remaining_time": "1 day, 14:42:52", "throughput": 705.41, "total_tokens": 1174576} +{"current_steps": 2125, "total_steps": 179570, "loss": 1.372, "lr": 5.914128195132818e-06, "epoch": 0.11833825249206438, "percentage": 1.18, "elapsed_time": "0:27:48", "remaining_time": "1 day, 14:42:29", "throughput": 705.38, "total_tokens": 1177120} +{"current_steps": 2130, "total_steps": 179570, "loss": 0.1504, "lr": 5.928050342484824e-06, "epoch": 0.11861669543910452, "percentage": 1.19, "elapsed_time": "0:27:52", "remaining_time": "1 day, 14:42:36", "throughput": 705.42, "total_tokens": 1180064} +{"current_steps": 2135, "total_steps": 179570, "loss": 0.2108, "lr": 5.941972489836833e-06, "epoch": 0.11889513838614468, "percentage": 1.19, "elapsed_time": "0:27:56", "remaining_time": "1 day, 14:42:12", "throughput": 705.38, "total_tokens": 1182592} +{"current_steps": 2140, "total_steps": 179570, "loss": 0.5116, "lr": 5.955894637188841e-06, "epoch": 0.11917358133318483, "percentage": 1.19, "elapsed_time": "0:28:00", "remaining_time": "1 day, 14:41:55", "throughput": 705.38, "total_tokens": 1185248} +{"current_steps": 2145, "total_steps": 179570, "loss": 1.0755, "lr": 5.969816784540848e-06, "epoch": 0.11945202428022499, "percentage": 1.19, "elapsed_time": "0:28:04", "remaining_time": "1 day, 14:41:54", "throughput": 705.41, "total_tokens": 1188096} +{"current_steps": 2150, "total_steps": 179570, "loss": 0.0926, "lr": 5.983738931892856e-06, "epoch": 0.11973046722726513, "percentage": 1.2, "elapsed_time": "0:28:08", "remaining_time": "1 day, 14:42:14", "throughput": 705.49, "total_tokens": 1191200} +{"current_steps": 2155, "total_steps": 179570, "loss": 0.1291, "lr": 5.997661079244863e-06, "epoch": 0.12000891017430529, "percentage": 1.2, "elapsed_time": "0:28:12", "remaining_time": "1 day, 14:42:00", "throughput": 705.54, "total_tokens": 1193968} +{"current_steps": 2160, "total_steps": 179570, "loss": 0.0992, "lr": 6.011583226596871e-06, "epoch": 0.12028735312134543, "percentage": 1.2, "elapsed_time": "0:28:16", "remaining_time": "1 day, 14:42:18", "throughput": 705.57, "total_tokens": 1196976} +{"current_steps": 2165, "total_steps": 179570, "loss": 0.4629, "lr": 6.0255053739488786e-06, "epoch": 0.12056579606838559, "percentage": 1.21, "elapsed_time": "0:28:19", "remaining_time": "1 day, 14:41:11", "throughput": 705.52, "total_tokens": 1199120} +{"current_steps": 2170, "total_steps": 179570, "loss": 0.84, "lr": 6.039427521300886e-06, "epoch": 0.12084423901542574, "percentage": 1.21, "elapsed_time": "0:28:23", "remaining_time": "1 day, 14:40:55", "throughput": 705.52, "total_tokens": 1201792} +{"current_steps": 2175, "total_steps": 179570, "loss": 0.3223, "lr": 6.053349668652893e-06, "epoch": 0.1211226819624659, "percentage": 1.21, "elapsed_time": "0:28:27", "remaining_time": "1 day, 14:40:56", "throughput": 705.59, "total_tokens": 1204720} +{"current_steps": 2180, "total_steps": 179570, "loss": 0.3948, "lr": 6.0672718160049015e-06, "epoch": 0.12140112490950604, "percentage": 1.21, "elapsed_time": "0:28:31", "remaining_time": "1 day, 14:40:59", "throughput": 705.67, "total_tokens": 1207696} +{"current_steps": 2185, "total_steps": 179570, "loss": 0.5531, "lr": 6.081193963356908e-06, "epoch": 0.1216795678565462, "percentage": 1.22, "elapsed_time": "0:28:34", "remaining_time": "1 day, 14:40:16", "throughput": 705.66, "total_tokens": 1210096} +{"current_steps": 2190, "total_steps": 179570, "loss": 0.4167, "lr": 6.095116110708916e-06, "epoch": 0.12195801080358634, "percentage": 1.22, "elapsed_time": "0:28:38", "remaining_time": "1 day, 14:39:48", "throughput": 705.58, "total_tokens": 1212528} +{"current_steps": 2195, "total_steps": 179570, "loss": 0.5282, "lr": 6.109038258060924e-06, "epoch": 0.1222364537506265, "percentage": 1.22, "elapsed_time": "0:28:42", "remaining_time": "1 day, 14:39:31", "throughput": 705.57, "total_tokens": 1215152} +{"current_steps": 2200, "total_steps": 179570, "loss": 0.4993, "lr": 6.122960405412932e-06, "epoch": 0.12251489669766664, "percentage": 1.23, "elapsed_time": "0:28:46", "remaining_time": "1 day, 14:39:44", "throughput": 705.59, "total_tokens": 1218112} +{"current_steps": 2205, "total_steps": 179570, "loss": 0.541, "lr": 6.136882552764938e-06, "epoch": 0.1227933396447068, "percentage": 1.23, "elapsed_time": "0:28:50", "remaining_time": "1 day, 14:39:51", "throughput": 705.58, "total_tokens": 1220960} +{"current_steps": 2210, "total_steps": 179570, "loss": 0.399, "lr": 6.150804700116947e-06, "epoch": 0.12307178259174695, "percentage": 1.23, "elapsed_time": "0:28:54", "remaining_time": "1 day, 14:40:11", "throughput": 705.61, "total_tokens": 1223984} +{"current_steps": 2215, "total_steps": 179570, "loss": 0.6581, "lr": 6.164726847468954e-06, "epoch": 0.1233502255387871, "percentage": 1.23, "elapsed_time": "0:28:58", "remaining_time": "1 day, 14:39:45", "throughput": 705.57, "total_tokens": 1226496} +{"current_steps": 2220, "total_steps": 179570, "loss": 0.4348, "lr": 6.178648994820962e-06, "epoch": 0.12362866848582725, "percentage": 1.24, "elapsed_time": "0:29:02", "remaining_time": "1 day, 14:39:29", "throughput": 705.57, "total_tokens": 1229152} +{"current_steps": 2225, "total_steps": 179570, "loss": 0.0806, "lr": 6.192571142172969e-06, "epoch": 0.12390711143286741, "percentage": 1.24, "elapsed_time": "0:29:06", "remaining_time": "1 day, 14:39:29", "throughput": 705.63, "total_tokens": 1232064} +{"current_steps": 2230, "total_steps": 179570, "loss": 0.5861, "lr": 6.206493289524977e-06, "epoch": 0.12418555437990755, "percentage": 1.24, "elapsed_time": "0:29:10", "remaining_time": "1 day, 14:39:41", "throughput": 705.59, "total_tokens": 1234896} +{"current_steps": 2235, "total_steps": 179570, "loss": 0.206, "lr": 6.220415436876984e-06, "epoch": 0.12446399732694771, "percentage": 1.24, "elapsed_time": "0:29:14", "remaining_time": "1 day, 14:39:48", "throughput": 705.64, "total_tokens": 1237856} +{"current_steps": 2240, "total_steps": 179570, "loss": 0.1902, "lr": 6.234337584228992e-06, "epoch": 0.12474244027398786, "percentage": 1.25, "elapsed_time": "0:29:18", "remaining_time": "1 day, 14:39:49", "throughput": 705.69, "total_tokens": 1240752} +{"current_steps": 2245, "total_steps": 179570, "loss": 0.0642, "lr": 6.248259731580999e-06, "epoch": 0.125020883221028, "percentage": 1.25, "elapsed_time": "0:29:22", "remaining_time": "1 day, 14:40:01", "throughput": 705.69, "total_tokens": 1243664} +{"current_steps": 2250, "total_steps": 179570, "loss": 0.2384, "lr": 6.262181878933007e-06, "epoch": 0.12529932616806816, "percentage": 1.25, "elapsed_time": "0:29:26", "remaining_time": "1 day, 14:39:38", "throughput": 705.62, "total_tokens": 1246144} +{"current_steps": 2255, "total_steps": 179570, "loss": 0.8364, "lr": 6.2761040262850155e-06, "epoch": 0.12557776911510832, "percentage": 1.26, "elapsed_time": "0:29:29", "remaining_time": "1 day, 14:38:36", "throughput": 705.5, "total_tokens": 1248176} +{"current_steps": 2260, "total_steps": 179570, "loss": 0.0846, "lr": 6.290026173637022e-06, "epoch": 0.12585621206214848, "percentage": 1.26, "elapsed_time": "0:29:33", "remaining_time": "1 day, 14:38:31", "throughput": 705.47, "total_tokens": 1250880} +{"current_steps": 2265, "total_steps": 179570, "loss": 0.0723, "lr": 6.303948320989029e-06, "epoch": 0.1261346550091886, "percentage": 1.26, "elapsed_time": "0:29:36", "remaining_time": "1 day, 14:38:04", "throughput": 705.4, "total_tokens": 1253328} +{"current_steps": 2270, "total_steps": 179570, "loss": 0.3488, "lr": 6.317870468341038e-06, "epoch": 0.12641309795622876, "percentage": 1.26, "elapsed_time": "0:29:40", "remaining_time": "1 day, 14:38:00", "throughput": 705.4, "total_tokens": 1256096} +{"current_steps": 2275, "total_steps": 179570, "loss": 0.74, "lr": 6.331792615693046e-06, "epoch": 0.12669154090326892, "percentage": 1.27, "elapsed_time": "0:29:44", "remaining_time": "1 day, 14:38:15", "throughput": 705.49, "total_tokens": 1259184} +{"current_steps": 2280, "total_steps": 179570, "loss": 0.6303, "lr": 6.345714763045052e-06, "epoch": 0.12696998385030908, "percentage": 1.27, "elapsed_time": "0:29:48", "remaining_time": "1 day, 14:38:16", "throughput": 705.5, "total_tokens": 1262000} +{"current_steps": 2285, "total_steps": 179570, "loss": 0.3102, "lr": 6.35963691039706e-06, "epoch": 0.1272484267973492, "percentage": 1.27, "elapsed_time": "0:29:52", "remaining_time": "1 day, 14:38:22", "throughput": 705.44, "total_tokens": 1264768} +{"current_steps": 2290, "total_steps": 179570, "loss": 0.5955, "lr": 6.373559057749068e-06, "epoch": 0.12752686974438937, "percentage": 1.28, "elapsed_time": "0:29:56", "remaining_time": "1 day, 14:38:23", "throughput": 705.47, "total_tokens": 1267632} +{"current_steps": 2295, "total_steps": 179570, "loss": 0.6098, "lr": 6.387481205101075e-06, "epoch": 0.12780531269142953, "percentage": 1.28, "elapsed_time": "0:30:01", "remaining_time": "1 day, 14:38:53", "throughput": 705.5, "total_tokens": 1270752} +{"current_steps": 2300, "total_steps": 179570, "loss": 0.182, "lr": 6.401403352453082e-06, "epoch": 0.1280837556384697, "percentage": 1.28, "elapsed_time": "0:30:05", "remaining_time": "1 day, 14:38:49", "throughput": 705.49, "total_tokens": 1273504} +{"current_steps": 2305, "total_steps": 179570, "loss": 0.4863, "lr": 6.41532549980509e-06, "epoch": 0.12836219858550982, "percentage": 1.28, "elapsed_time": "0:30:09", "remaining_time": "1 day, 14:38:49", "throughput": 705.45, "total_tokens": 1276240} +{"current_steps": 2310, "total_steps": 179570, "loss": 0.3253, "lr": 6.429247647157098e-06, "epoch": 0.12864064153254998, "percentage": 1.29, "elapsed_time": "0:30:12", "remaining_time": "1 day, 14:38:29", "throughput": 705.45, "total_tokens": 1278864} +{"current_steps": 2315, "total_steps": 179570, "loss": 0.0039, "lr": 6.443169794509106e-06, "epoch": 0.12891908447959013, "percentage": 1.29, "elapsed_time": "0:30:16", "remaining_time": "1 day, 14:38:37", "throughput": 705.52, "total_tokens": 1281872} +{"current_steps": 2320, "total_steps": 179570, "loss": 0.5062, "lr": 6.457091941861112e-06, "epoch": 0.1291975274266303, "percentage": 1.29, "elapsed_time": "0:30:20", "remaining_time": "1 day, 14:38:37", "throughput": 705.55, "total_tokens": 1284720} +{"current_steps": 2325, "total_steps": 179570, "loss": 0.458, "lr": 6.47101408921312e-06, "epoch": 0.12947597037367042, "percentage": 1.29, "elapsed_time": "0:30:24", "remaining_time": "1 day, 14:38:43", "throughput": 705.58, "total_tokens": 1287632} +{"current_steps": 2330, "total_steps": 179570, "loss": 0.0924, "lr": 6.484936236565129e-06, "epoch": 0.12975441332071058, "percentage": 1.3, "elapsed_time": "0:30:29", "remaining_time": "1 day, 14:39:01", "throughput": 705.64, "total_tokens": 1290720} +{"current_steps": 2335, "total_steps": 179570, "loss": 0.2366, "lr": 6.498858383917136e-06, "epoch": 0.13003285626775074, "percentage": 1.3, "elapsed_time": "0:30:33", "remaining_time": "1 day, 14:39:09", "throughput": 705.7, "total_tokens": 1293712} +{"current_steps": 2340, "total_steps": 179570, "loss": 0.2516, "lr": 6.5127805312691425e-06, "epoch": 0.1303112992147909, "percentage": 1.3, "elapsed_time": "0:30:36", "remaining_time": "1 day, 14:38:41", "throughput": 705.61, "total_tokens": 1296096} +{"current_steps": 2345, "total_steps": 179570, "loss": 0.0391, "lr": 6.526702678621151e-06, "epoch": 0.13058974216183103, "percentage": 1.31, "elapsed_time": "0:30:40", "remaining_time": "1 day, 14:38:42", "throughput": 705.63, "total_tokens": 1298944} +{"current_steps": 2350, "total_steps": 179570, "loss": 0.3571, "lr": 6.540624825973159e-06, "epoch": 0.1308681851088712, "percentage": 1.31, "elapsed_time": "0:30:44", "remaining_time": "1 day, 14:38:28", "throughput": 705.65, "total_tokens": 1301664} +{"current_steps": 2355, "total_steps": 179570, "loss": 0.1022, "lr": 6.554546973325166e-06, "epoch": 0.13114662805591135, "percentage": 1.31, "elapsed_time": "0:30:48", "remaining_time": "1 day, 14:38:57", "throughput": 705.66, "total_tokens": 1304768} +{"current_steps": 2360, "total_steps": 179570, "loss": 0.7037, "lr": 6.568469120677173e-06, "epoch": 0.1314250710029515, "percentage": 1.31, "elapsed_time": "0:30:53", "remaining_time": "1 day, 14:39:18", "throughput": 705.59, "total_tokens": 1307632} +{"current_steps": 2365, "total_steps": 179570, "loss": 0.2771, "lr": 6.582391268029181e-06, "epoch": 0.13170351394999164, "percentage": 1.32, "elapsed_time": "0:30:57", "remaining_time": "1 day, 14:39:19", "throughput": 705.61, "total_tokens": 1310480} +{"current_steps": 2370, "total_steps": 179570, "loss": 0.2711, "lr": 6.596313415381189e-06, "epoch": 0.1319819568970318, "percentage": 1.32, "elapsed_time": "0:31:01", "remaining_time": "1 day, 14:39:17", "throughput": 705.56, "total_tokens": 1313184} +{"current_steps": 2375, "total_steps": 179570, "loss": 0.0494, "lr": 6.610235562733197e-06, "epoch": 0.13226039984407195, "percentage": 1.32, "elapsed_time": "0:31:05", "remaining_time": "1 day, 14:39:23", "throughput": 705.59, "total_tokens": 1316112} +{"current_steps": 2380, "total_steps": 179570, "loss": 0.1519, "lr": 6.624157710085203e-06, "epoch": 0.1325388427911121, "percentage": 1.33, "elapsed_time": "0:31:09", "remaining_time": "1 day, 14:39:09", "throughput": 705.63, "total_tokens": 1318848} +{"current_steps": 2385, "total_steps": 179570, "loss": 0.575, "lr": 6.638079857437211e-06, "epoch": 0.13281728573815224, "percentage": 1.33, "elapsed_time": "0:31:12", "remaining_time": "1 day, 14:38:47", "throughput": 705.6, "total_tokens": 1321392} +{"current_steps": 2390, "total_steps": 179570, "loss": 0.1312, "lr": 6.65200200478922e-06, "epoch": 0.1330957286851924, "percentage": 1.33, "elapsed_time": "0:31:17", "remaining_time": "1 day, 14:39:27", "throughput": 705.63, "total_tokens": 1324640} +{"current_steps": 2395, "total_steps": 179570, "loss": 0.2254, "lr": 6.665924152141227e-06, "epoch": 0.13337417163223256, "percentage": 1.33, "elapsed_time": "0:31:21", "remaining_time": "1 day, 14:39:11", "throughput": 705.63, "total_tokens": 1327296} +{"current_steps": 2400, "total_steps": 179570, "loss": 0.0248, "lr": 6.6798462994932335e-06, "epoch": 0.13365261457927272, "percentage": 1.34, "elapsed_time": "0:31:25", "remaining_time": "1 day, 14:39:23", "throughput": 705.66, "total_tokens": 1330272} +{"current_steps": 2405, "total_steps": 179570, "loss": 0.675, "lr": 6.693768446845242e-06, "epoch": 0.13393105752631285, "percentage": 1.34, "elapsed_time": "0:31:29", "remaining_time": "1 day, 14:39:18", "throughput": 705.63, "total_tokens": 1332992} +{"current_steps": 2410, "total_steps": 179570, "loss": 0.4237, "lr": 6.707690594197249e-06, "epoch": 0.134209500473353, "percentage": 1.34, "elapsed_time": "0:31:33", "remaining_time": "1 day, 14:39:25", "throughput": 705.7, "total_tokens": 1335984} +{"current_steps": 2415, "total_steps": 179570, "loss": 0.1612, "lr": 6.721612741549257e-06, "epoch": 0.13448794342039316, "percentage": 1.34, "elapsed_time": "0:31:37", "remaining_time": "1 day, 14:39:25", "throughput": 705.72, "total_tokens": 1338848} +{"current_steps": 2420, "total_steps": 179570, "loss": 0.588, "lr": 6.735534888901264e-06, "epoch": 0.13476638636743332, "percentage": 1.35, "elapsed_time": "0:31:40", "remaining_time": "1 day, 14:39:00", "throughput": 705.67, "total_tokens": 1341312} +{"current_steps": 2425, "total_steps": 179570, "loss": 0.5728, "lr": 6.749457036253272e-06, "epoch": 0.13504482931447345, "percentage": 1.35, "elapsed_time": "0:31:44", "remaining_time": "1 day, 14:38:59", "throughput": 705.68, "total_tokens": 1344128} +{"current_steps": 2430, "total_steps": 179570, "loss": 0.152, "lr": 6.7633791836052795e-06, "epoch": 0.1353232722615136, "percentage": 1.35, "elapsed_time": "0:31:48", "remaining_time": "1 day, 14:39:05", "throughput": 705.7, "total_tokens": 1347040} +{"current_steps": 2435, "total_steps": 179570, "loss": 0.3516, "lr": 6.777301330957288e-06, "epoch": 0.13560171520855377, "percentage": 1.36, "elapsed_time": "0:31:52", "remaining_time": "1 day, 14:38:49", "throughput": 705.69, "total_tokens": 1349680} +{"current_steps": 2440, "total_steps": 179570, "loss": 0.0826, "lr": 6.791223478309294e-06, "epoch": 0.13588015815559393, "percentage": 1.36, "elapsed_time": "0:31:56", "remaining_time": "1 day, 14:38:55", "throughput": 705.73, "total_tokens": 1352608} +{"current_steps": 2445, "total_steps": 179570, "loss": 0.3458, "lr": 6.8051456256613024e-06, "epoch": 0.13615860110263406, "percentage": 1.36, "elapsed_time": "0:32:00", "remaining_time": "1 day, 14:38:28", "throughput": 705.68, "total_tokens": 1355072} +{"current_steps": 2450, "total_steps": 179570, "loss": 0.293, "lr": 6.81906777301331e-06, "epoch": 0.13643704404967422, "percentage": 1.36, "elapsed_time": "0:32:04", "remaining_time": "1 day, 14:38:24", "throughput": 705.67, "total_tokens": 1357824} +{"current_steps": 2455, "total_steps": 179570, "loss": 0.2928, "lr": 6.832989920365318e-06, "epoch": 0.13671548699671437, "percentage": 1.37, "elapsed_time": "0:32:07", "remaining_time": "1 day, 14:38:07", "throughput": 705.64, "total_tokens": 1360400} +{"current_steps": 2460, "total_steps": 179570, "loss": 0.5975, "lr": 6.8469120677173245e-06, "epoch": 0.13699392994375453, "percentage": 1.37, "elapsed_time": "0:32:11", "remaining_time": "1 day, 14:37:31", "throughput": 705.58, "total_tokens": 1362736} +{"current_steps": 2465, "total_steps": 179570, "loss": 0.9972, "lr": 6.860834215069333e-06, "epoch": 0.13727237289079466, "percentage": 1.37, "elapsed_time": "0:32:15", "remaining_time": "1 day, 14:37:31", "throughput": 705.59, "total_tokens": 1365568} +{"current_steps": 2470, "total_steps": 179570, "loss": 0.009, "lr": 6.87475636242134e-06, "epoch": 0.13755081583783482, "percentage": 1.38, "elapsed_time": "0:32:19", "remaining_time": "1 day, 14:37:46", "throughput": 705.61, "total_tokens": 1368560} +{"current_steps": 2475, "total_steps": 179570, "loss": 0.9363, "lr": 6.888678509773348e-06, "epoch": 0.13782925878487498, "percentage": 1.38, "elapsed_time": "0:32:23", "remaining_time": "1 day, 14:37:43", "throughput": 705.63, "total_tokens": 1371376} +{"current_steps": 2480, "total_steps": 179570, "loss": 0.2426, "lr": 6.902600657125355e-06, "epoch": 0.13810770173191514, "percentage": 1.38, "elapsed_time": "0:32:28", "remaining_time": "1 day, 14:38:21", "throughput": 705.66, "total_tokens": 1374624} +{"current_steps": 2485, "total_steps": 179570, "loss": 0.4741, "lr": 6.916522804477363e-06, "epoch": 0.13838614467895527, "percentage": 1.38, "elapsed_time": "0:32:32", "remaining_time": "1 day, 14:38:37", "throughput": 705.68, "total_tokens": 1377632} +{"current_steps": 2490, "total_steps": 179570, "loss": 0.469, "lr": 6.9304449518293705e-06, "epoch": 0.13866458762599543, "percentage": 1.39, "elapsed_time": "0:32:36", "remaining_time": "1 day, 14:38:54", "throughput": 705.73, "total_tokens": 1380704} +{"current_steps": 2495, "total_steps": 179570, "loss": 0.194, "lr": 6.944367099181379e-06, "epoch": 0.1389430305730356, "percentage": 1.39, "elapsed_time": "0:32:40", "remaining_time": "1 day, 14:39:10", "throughput": 705.69, "total_tokens": 1383600} +{"current_steps": 2500, "total_steps": 179570, "loss": 0.3091, "lr": 6.958289246533385e-06, "epoch": 0.13922147352007574, "percentage": 1.39, "elapsed_time": "0:32:44", "remaining_time": "1 day, 14:39:14", "throughput": 705.7, "total_tokens": 1386480} +{"current_steps": 2505, "total_steps": 179570, "loss": 0.0587, "lr": 6.9722113938853934e-06, "epoch": 0.13949991646711588, "percentage": 1.39, "elapsed_time": "0:32:48", "remaining_time": "1 day, 14:38:52", "throughput": 705.69, "total_tokens": 1389040} +{"current_steps": 2510, "total_steps": 179570, "loss": 0.67, "lr": 6.986133541237401e-06, "epoch": 0.13977835941415603, "percentage": 1.4, "elapsed_time": "0:32:51", "remaining_time": "1 day, 14:38:05", "throughput": 705.58, "total_tokens": 1391184} +{"current_steps": 2515, "total_steps": 179570, "loss": 0.5681, "lr": 7.000055688589409e-06, "epoch": 0.1400568023611962, "percentage": 1.4, "elapsed_time": "0:32:55", "remaining_time": "1 day, 14:37:47", "throughput": 705.6, "total_tokens": 1393840} +{"current_steps": 2520, "total_steps": 179570, "loss": 0.0464, "lr": 7.0139778359414156e-06, "epoch": 0.14033524530823635, "percentage": 1.4, "elapsed_time": "0:32:59", "remaining_time": "1 day, 14:38:02", "throughput": 705.63, "total_tokens": 1396864} +{"current_steps": 2525, "total_steps": 179570, "loss": 0.2992, "lr": 7.027899983293424e-06, "epoch": 0.14061368825527648, "percentage": 1.41, "elapsed_time": "0:33:03", "remaining_time": "1 day, 14:38:07", "throughput": 705.66, "total_tokens": 1399776} +{"current_steps": 2530, "total_steps": 179570, "loss": 0.4545, "lr": 7.041822130645431e-06, "epoch": 0.14089213120231664, "percentage": 1.41, "elapsed_time": "0:33:07", "remaining_time": "1 day, 14:37:42", "throughput": 705.61, "total_tokens": 1402240} +{"current_steps": 2535, "total_steps": 179570, "loss": 0.2256, "lr": 7.055744277997439e-06, "epoch": 0.1411705741493568, "percentage": 1.41, "elapsed_time": "0:33:11", "remaining_time": "1 day, 14:37:50", "throughput": 705.54, "total_tokens": 1405008} +{"current_steps": 2540, "total_steps": 179570, "loss": 0.38, "lr": 7.069666425349446e-06, "epoch": 0.14144901709639696, "percentage": 1.41, "elapsed_time": "0:33:15", "remaining_time": "1 day, 14:37:36", "throughput": 705.55, "total_tokens": 1407680} +{"current_steps": 2545, "total_steps": 179570, "loss": 0.298, "lr": 7.083588572701453e-06, "epoch": 0.1417274600434371, "percentage": 1.42, "elapsed_time": "0:33:19", "remaining_time": "1 day, 14:37:51", "throughput": 705.58, "total_tokens": 1410704} +{"current_steps": 2550, "total_steps": 179570, "loss": 0.1154, "lr": 7.0975107200534615e-06, "epoch": 0.14200590299047725, "percentage": 1.42, "elapsed_time": "0:33:23", "remaining_time": "1 day, 14:37:53", "throughput": 705.64, "total_tokens": 1413664} +{"current_steps": 2555, "total_steps": 179570, "loss": 0.1203, "lr": 7.11143286740547e-06, "epoch": 0.1422843459375174, "percentage": 1.42, "elapsed_time": "0:33:27", "remaining_time": "1 day, 14:37:51", "throughput": 705.62, "total_tokens": 1416416} +{"current_steps": 2560, "total_steps": 179570, "loss": 0.3007, "lr": 7.125355014757476e-06, "epoch": 0.14256278888455756, "percentage": 1.43, "elapsed_time": "0:33:31", "remaining_time": "1 day, 14:38:05", "throughput": 705.62, "total_tokens": 1419376} +{"current_steps": 2565, "total_steps": 179570, "loss": 0.0086, "lr": 7.139277162109484e-06, "epoch": 0.1428412318315977, "percentage": 1.43, "elapsed_time": "0:33:35", "remaining_time": "1 day, 14:38:11", "throughput": 705.68, "total_tokens": 1422352} +{"current_steps": 2570, "total_steps": 179570, "loss": 0.3733, "lr": 7.153199309461492e-06, "epoch": 0.14311967477863785, "percentage": 1.43, "elapsed_time": "0:33:39", "remaining_time": "1 day, 14:38:13", "throughput": 705.75, "total_tokens": 1425328} +{"current_steps": 2575, "total_steps": 179570, "loss": 0.2212, "lr": 7.1671214568135e-06, "epoch": 0.143398117725678, "percentage": 1.43, "elapsed_time": "0:33:43", "remaining_time": "1 day, 14:38:03", "throughput": 705.73, "total_tokens": 1428016} +{"current_steps": 2580, "total_steps": 179570, "loss": 0.0822, "lr": 7.1810436041655066e-06, "epoch": 0.14367656067271817, "percentage": 1.44, "elapsed_time": "0:33:47", "remaining_time": "1 day, 14:38:20", "throughput": 705.79, "total_tokens": 1431104} +{"current_steps": 2585, "total_steps": 179570, "loss": 0.1939, "lr": 7.194965751517514e-06, "epoch": 0.1439550036197583, "percentage": 1.44, "elapsed_time": "0:33:51", "remaining_time": "1 day, 14:37:46", "throughput": 705.75, "total_tokens": 1433504} +{"current_steps": 2590, "total_steps": 179570, "loss": 0.1734, "lr": 7.208887898869522e-06, "epoch": 0.14423344656679846, "percentage": 1.44, "elapsed_time": "0:33:55", "remaining_time": "1 day, 14:37:50", "throughput": 705.8, "total_tokens": 1436448} +{"current_steps": 2595, "total_steps": 179570, "loss": 0.1227, "lr": 7.22281004622153e-06, "epoch": 0.14451188951383862, "percentage": 1.45, "elapsed_time": "0:33:59", "remaining_time": "1 day, 14:38:03", "throughput": 705.78, "total_tokens": 1439360} +{"current_steps": 2600, "total_steps": 179570, "loss": 0.0851, "lr": 7.236732193573537e-06, "epoch": 0.14479033246087877, "percentage": 1.45, "elapsed_time": "0:34:03", "remaining_time": "1 day, 14:37:48", "throughput": 705.75, "total_tokens": 1441952} +{"current_steps": 2605, "total_steps": 179570, "loss": 0.6228, "lr": 7.250654340925544e-06, "epoch": 0.1450687754079189, "percentage": 1.45, "elapsed_time": "0:34:07", "remaining_time": "1 day, 14:37:44", "throughput": 705.76, "total_tokens": 1444752} +{"current_steps": 2610, "total_steps": 179570, "loss": 0.3469, "lr": 7.2645764882775525e-06, "epoch": 0.14534721835495906, "percentage": 1.45, "elapsed_time": "0:34:11", "remaining_time": "1 day, 14:37:39", "throughput": 705.73, "total_tokens": 1447456} +{"current_steps": 2615, "total_steps": 179570, "loss": 0.3442, "lr": 7.278498635629561e-06, "epoch": 0.14562566130199922, "percentage": 1.46, "elapsed_time": "0:34:14", "remaining_time": "1 day, 14:37:19", "throughput": 705.7, "total_tokens": 1450000} +{"current_steps": 2620, "total_steps": 179570, "loss": 0.0948, "lr": 7.292420782981567e-06, "epoch": 0.14590410424903938, "percentage": 1.46, "elapsed_time": "0:34:18", "remaining_time": "1 day, 14:37:22", "throughput": 705.69, "total_tokens": 1452832} +{"current_steps": 2625, "total_steps": 179570, "loss": 0.4294, "lr": 7.306342930333575e-06, "epoch": 0.1461825471960795, "percentage": 1.46, "elapsed_time": "0:34:22", "remaining_time": "1 day, 14:37:09", "throughput": 705.72, "total_tokens": 1455568} +{"current_steps": 2630, "total_steps": 179570, "loss": 0.056, "lr": 7.320265077685583e-06, "epoch": 0.14646099014311967, "percentage": 1.46, "elapsed_time": "0:34:26", "remaining_time": "1 day, 14:36:54", "throughput": 705.71, "total_tokens": 1458192} +{"current_steps": 2635, "total_steps": 179570, "loss": 0.4939, "lr": 7.334187225037591e-06, "epoch": 0.14673943309015983, "percentage": 1.47, "elapsed_time": "0:34:29", "remaining_time": "1 day, 14:36:31", "throughput": 705.68, "total_tokens": 1460704} +{"current_steps": 2640, "total_steps": 179570, "loss": 0.3201, "lr": 7.348109372389598e-06, "epoch": 0.14701787603719998, "percentage": 1.47, "elapsed_time": "0:34:34", "remaining_time": "1 day, 14:36:46", "throughput": 705.73, "total_tokens": 1463776} +{"current_steps": 2645, "total_steps": 179570, "loss": 0.8315, "lr": 7.362031519741605e-06, "epoch": 0.14729631898424012, "percentage": 1.47, "elapsed_time": "0:34:38", "remaining_time": "1 day, 14:36:41", "throughput": 705.69, "total_tokens": 1466464} +{"current_steps": 2650, "total_steps": 179570, "loss": 0.4944, "lr": 7.375953667093613e-06, "epoch": 0.14757476193128027, "percentage": 1.48, "elapsed_time": "0:34:41", "remaining_time": "1 day, 14:36:30", "throughput": 705.68, "total_tokens": 1469136} +{"current_steps": 2655, "total_steps": 179570, "loss": 0.7007, "lr": 7.3898758144456205e-06, "epoch": 0.14785320487832043, "percentage": 1.48, "elapsed_time": "0:34:45", "remaining_time": "1 day, 14:36:07", "throughput": 705.63, "total_tokens": 1471600} +{"current_steps": 2660, "total_steps": 179570, "loss": 0.5948, "lr": 7.403797961797627e-06, "epoch": 0.1481316478253606, "percentage": 1.48, "elapsed_time": "0:34:49", "remaining_time": "1 day, 14:36:01", "throughput": 705.6, "total_tokens": 1474288} +{"current_steps": 2665, "total_steps": 179570, "loss": 0.285, "lr": 7.417720109149635e-06, "epoch": 0.14841009077240072, "percentage": 1.48, "elapsed_time": "0:34:53", "remaining_time": "1 day, 14:35:48", "throughput": 705.64, "total_tokens": 1477056} +{"current_steps": 2670, "total_steps": 179570, "loss": 0.4091, "lr": 7.4316422565016435e-06, "epoch": 0.14868853371944088, "percentage": 1.49, "elapsed_time": "0:34:57", "remaining_time": "1 day, 14:36:03", "throughput": 705.59, "total_tokens": 1479920} +{"current_steps": 2675, "total_steps": 179570, "loss": 0.2283, "lr": 7.445564403853651e-06, "epoch": 0.14896697666648104, "percentage": 1.49, "elapsed_time": "0:35:01", "remaining_time": "1 day, 14:35:50", "throughput": 705.62, "total_tokens": 1482640} +{"current_steps": 2680, "total_steps": 179570, "loss": 0.1782, "lr": 7.459486551205657e-06, "epoch": 0.1492454196135212, "percentage": 1.49, "elapsed_time": "0:35:05", "remaining_time": "1 day, 14:35:47", "throughput": 705.56, "total_tokens": 1485312} +{"current_steps": 2685, "total_steps": 179570, "loss": 0.3799, "lr": 7.473408698557666e-06, "epoch": 0.14952386256056135, "percentage": 1.5, "elapsed_time": "0:35:08", "remaining_time": "1 day, 14:35:15", "throughput": 705.57, "total_tokens": 1487792} +{"current_steps": 2690, "total_steps": 179570, "loss": 0.2541, "lr": 7.487330845909674e-06, "epoch": 0.14980230550760149, "percentage": 1.5, "elapsed_time": "0:35:12", "remaining_time": "1 day, 14:35:32", "throughput": 705.66, "total_tokens": 1490992} +{"current_steps": 2695, "total_steps": 179570, "loss": 0.6922, "lr": 7.501252993261681e-06, "epoch": 0.15008074845464164, "percentage": 1.5, "elapsed_time": "0:35:17", "remaining_time": "1 day, 14:35:56", "throughput": 705.66, "total_tokens": 1494048} +{"current_steps": 2700, "total_steps": 179570, "loss": 0.5856, "lr": 7.515175140613688e-06, "epoch": 0.1503591914016818, "percentage": 1.5, "elapsed_time": "0:35:21", "remaining_time": "1 day, 14:35:59", "throughput": 705.66, "total_tokens": 1496896} +{"current_steps": 2705, "total_steps": 179570, "loss": 0.1957, "lr": 7.529097287965696e-06, "epoch": 0.15063763434872196, "percentage": 1.51, "elapsed_time": "0:35:24", "remaining_time": "1 day, 14:35:41", "throughput": 705.68, "total_tokens": 1499552} +{"current_steps": 2710, "total_steps": 179570, "loss": 0.1173, "lr": 7.543019435317704e-06, "epoch": 0.1509160772957621, "percentage": 1.51, "elapsed_time": "0:35:28", "remaining_time": "1 day, 14:35:28", "throughput": 705.7, "total_tokens": 1502272} +{"current_steps": 2715, "total_steps": 179570, "loss": 0.3961, "lr": 7.5569415826697116e-06, "epoch": 0.15119452024280225, "percentage": 1.51, "elapsed_time": "0:35:32", "remaining_time": "1 day, 14:35:27", "throughput": 705.71, "total_tokens": 1505104} +{"current_steps": 2720, "total_steps": 179570, "loss": 0.5388, "lr": 7.570863730021718e-06, "epoch": 0.1514729631898424, "percentage": 1.51, "elapsed_time": "0:35:36", "remaining_time": "1 day, 14:35:31", "throughput": 705.75, "total_tokens": 1508048} +{"current_steps": 2725, "total_steps": 179570, "loss": 0.109, "lr": 7.584785877373726e-06, "epoch": 0.15175140613688257, "percentage": 1.52, "elapsed_time": "0:35:40", "remaining_time": "1 day, 14:35:13", "throughput": 705.74, "total_tokens": 1510640} +{"current_steps": 2730, "total_steps": 179570, "loss": 0.132, "lr": 7.5987080247257345e-06, "epoch": 0.1520298490839227, "percentage": 1.52, "elapsed_time": "0:35:44", "remaining_time": "1 day, 14:35:18", "throughput": 705.79, "total_tokens": 1513616} +{"current_steps": 2735, "total_steps": 179570, "loss": 0.0272, "lr": 7.612630172077742e-06, "epoch": 0.15230829203096286, "percentage": 1.52, "elapsed_time": "0:35:48", "remaining_time": "1 day, 14:35:32", "throughput": 705.81, "total_tokens": 1516640} +{"current_steps": 2740, "total_steps": 179570, "loss": 0.1867, "lr": 7.626552319429748e-06, "epoch": 0.152586734978003, "percentage": 1.53, "elapsed_time": "0:35:52", "remaining_time": "1 day, 14:35:32", "throughput": 705.86, "total_tokens": 1519552} +{"current_steps": 2745, "total_steps": 179570, "loss": 0.3421, "lr": 7.640474466781756e-06, "epoch": 0.15286517792504317, "percentage": 1.53, "elapsed_time": "0:35:56", "remaining_time": "1 day, 14:35:28", "throughput": 705.85, "total_tokens": 1522304} +{"current_steps": 2750, "total_steps": 179570, "loss": 0.5608, "lr": 7.654396614133764e-06, "epoch": 0.1531436208720833, "percentage": 1.53, "elapsed_time": "0:36:00", "remaining_time": "1 day, 14:35:04", "throughput": 705.78, "total_tokens": 1524720} +{"current_steps": 2755, "total_steps": 179570, "loss": 0.0053, "lr": 7.668318761485772e-06, "epoch": 0.15342206381912346, "percentage": 1.53, "elapsed_time": "0:36:04", "remaining_time": "1 day, 14:35:00", "throughput": 705.78, "total_tokens": 1527488} +{"current_steps": 2760, "total_steps": 179570, "loss": 0.2306, "lr": 7.682240908837779e-06, "epoch": 0.15370050676616362, "percentage": 1.54, "elapsed_time": "0:36:07", "remaining_time": "1 day, 14:34:38", "throughput": 705.74, "total_tokens": 1529952} +{"current_steps": 2765, "total_steps": 179570, "loss": 0.1725, "lr": 7.696163056189787e-06, "epoch": 0.15397894971320378, "percentage": 1.54, "elapsed_time": "0:36:11", "remaining_time": "1 day, 14:34:38", "throughput": 705.78, "total_tokens": 1532880} +{"current_steps": 2770, "total_steps": 179570, "loss": 0.2009, "lr": 7.710085203541795e-06, "epoch": 0.1542573926602439, "percentage": 1.54, "elapsed_time": "0:36:15", "remaining_time": "1 day, 14:34:43", "throughput": 705.83, "total_tokens": 1535856} +{"current_steps": 2775, "total_steps": 179570, "loss": 0.2164, "lr": 7.724007350893803e-06, "epoch": 0.15453583560728407, "percentage": 1.55, "elapsed_time": "0:36:20", "remaining_time": "1 day, 14:34:56", "throughput": 705.84, "total_tokens": 1538832} +{"current_steps": 2780, "total_steps": 179570, "loss": 0.587, "lr": 7.73792949824581e-06, "epoch": 0.15481427855432423, "percentage": 1.55, "elapsed_time": "0:36:23", "remaining_time": "1 day, 14:34:06", "throughput": 705.78, "total_tokens": 1540960} +{"current_steps": 2785, "total_steps": 179570, "loss": 0.1072, "lr": 7.751851645597816e-06, "epoch": 0.15509272150136438, "percentage": 1.55, "elapsed_time": "0:36:26", "remaining_time": "1 day, 14:33:41", "throughput": 705.76, "total_tokens": 1543440} +{"current_steps": 2790, "total_steps": 179570, "loss": 0.393, "lr": 7.765773792949825e-06, "epoch": 0.15537116444840451, "percentage": 1.55, "elapsed_time": "0:36:30", "remaining_time": "1 day, 14:33:23", "throughput": 705.75, "total_tokens": 1546048} +{"current_steps": 2795, "total_steps": 179570, "loss": 0.2973, "lr": 7.779695940301833e-06, "epoch": 0.15564960739544467, "percentage": 1.56, "elapsed_time": "0:36:34", "remaining_time": "1 day, 14:33:33", "throughput": 705.79, "total_tokens": 1549072} +{"current_steps": 2800, "total_steps": 179570, "loss": 0.3584, "lr": 7.79361808765384e-06, "epoch": 0.15592805034248483, "percentage": 1.56, "elapsed_time": "0:36:38", "remaining_time": "1 day, 14:33:37", "throughput": 705.81, "total_tokens": 1551968} +{"current_steps": 2805, "total_steps": 179570, "loss": 0.0604, "lr": 7.807540235005848e-06, "epoch": 0.156206493289525, "percentage": 1.56, "elapsed_time": "0:36:42", "remaining_time": "1 day, 14:33:33", "throughput": 705.8, "total_tokens": 1554704} +{"current_steps": 2810, "total_steps": 179570, "loss": 0.6042, "lr": 7.821462382357856e-06, "epoch": 0.15648493623656512, "percentage": 1.56, "elapsed_time": "0:36:46", "remaining_time": "1 day, 14:33:02", "throughput": 705.77, "total_tokens": 1557120} +{"current_steps": 2815, "total_steps": 179570, "loss": 0.3857, "lr": 7.835384529709864e-06, "epoch": 0.15676337918360528, "percentage": 1.57, "elapsed_time": "0:36:50", "remaining_time": "1 day, 14:33:17", "throughput": 705.85, "total_tokens": 1560272} +{"current_steps": 2820, "total_steps": 179570, "loss": 0.1904, "lr": 7.84930667706187e-06, "epoch": 0.15704182213064544, "percentage": 1.57, "elapsed_time": "0:36:54", "remaining_time": "1 day, 14:33:04", "throughput": 705.86, "total_tokens": 1562960} +{"current_steps": 2825, "total_steps": 179570, "loss": 0.3379, "lr": 7.863228824413877e-06, "epoch": 0.1573202650776856, "percentage": 1.57, "elapsed_time": "0:36:58", "remaining_time": "1 day, 14:33:04", "throughput": 705.88, "total_tokens": 1565824} +{"current_steps": 2830, "total_steps": 179570, "loss": 0.3512, "lr": 7.877150971765885e-06, "epoch": 0.15759870802472573, "percentage": 1.58, "elapsed_time": "0:37:02", "remaining_time": "1 day, 14:33:09", "throughput": 705.95, "total_tokens": 1568848} +{"current_steps": 2835, "total_steps": 179570, "loss": 0.1992, "lr": 7.891073119117894e-06, "epoch": 0.15787715097176588, "percentage": 1.58, "elapsed_time": "0:37:06", "remaining_time": "1 day, 14:32:55", "throughput": 705.95, "total_tokens": 1571504} +{"current_steps": 2840, "total_steps": 179570, "loss": 0.0708, "lr": 7.9049952664699e-06, "epoch": 0.15815559391880604, "percentage": 1.58, "elapsed_time": "0:37:09", "remaining_time": "1 day, 14:32:49", "throughput": 705.91, "total_tokens": 1574160} +{"current_steps": 2845, "total_steps": 179570, "loss": 0.5716, "lr": 7.918917413821908e-06, "epoch": 0.1584340368658462, "percentage": 1.58, "elapsed_time": "0:37:13", "remaining_time": "1 day, 14:32:36", "throughput": 705.92, "total_tokens": 1576848} +{"current_steps": 2850, "total_steps": 179570, "loss": 0.1046, "lr": 7.932839561173917e-06, "epoch": 0.15871247981288633, "percentage": 1.59, "elapsed_time": "0:37:17", "remaining_time": "1 day, 14:32:22", "throughput": 705.91, "total_tokens": 1579504} +{"current_steps": 2855, "total_steps": 179570, "loss": 0.3492, "lr": 7.946761708525923e-06, "epoch": 0.1589909227599265, "percentage": 1.59, "elapsed_time": "0:37:21", "remaining_time": "1 day, 14:32:27", "throughput": 705.96, "total_tokens": 1582480} +{"current_steps": 2860, "total_steps": 179570, "loss": 0.9449, "lr": 7.96068385587793e-06, "epoch": 0.15926936570696665, "percentage": 1.59, "elapsed_time": "0:37:25", "remaining_time": "1 day, 14:32:50", "throughput": 705.99, "total_tokens": 1585616} +{"current_steps": 2865, "total_steps": 179570, "loss": 0.1174, "lr": 7.974606003229938e-06, "epoch": 0.1595478086540068, "percentage": 1.6, "elapsed_time": "0:37:30", "remaining_time": "1 day, 14:33:04", "throughput": 706.03, "total_tokens": 1588688} +{"current_steps": 2870, "total_steps": 179570, "loss": 0.4189, "lr": 7.988528150581946e-06, "epoch": 0.15982625160104694, "percentage": 1.6, "elapsed_time": "0:37:34", "remaining_time": "1 day, 14:33:20", "throughput": 706.12, "total_tokens": 1591904} +{"current_steps": 2875, "total_steps": 179570, "loss": 0.5627, "lr": 8.002450297933954e-06, "epoch": 0.1601046945480871, "percentage": 1.6, "elapsed_time": "0:37:38", "remaining_time": "1 day, 14:33:03", "throughput": 706.14, "total_tokens": 1594560} +{"current_steps": 2880, "total_steps": 179570, "loss": 0.1907, "lr": 8.01637244528596e-06, "epoch": 0.16038313749512725, "percentage": 1.6, "elapsed_time": "0:37:42", "remaining_time": "1 day, 14:33:06", "throughput": 706.15, "total_tokens": 1597440} +{"current_steps": 2885, "total_steps": 179570, "loss": 0.2427, "lr": 8.030294592637969e-06, "epoch": 0.1606615804421674, "percentage": 1.61, "elapsed_time": "0:37:46", "remaining_time": "1 day, 14:33:09", "throughput": 706.14, "total_tokens": 1600272} +{"current_steps": 2890, "total_steps": 179570, "loss": 0.12, "lr": 8.044216739989977e-06, "epoch": 0.16094002338920754, "percentage": 1.61, "elapsed_time": "0:37:50", "remaining_time": "1 day, 14:33:08", "throughput": 706.15, "total_tokens": 1603088} +{"current_steps": 2895, "total_steps": 179570, "loss": 0.3484, "lr": 8.058138887341984e-06, "epoch": 0.1612184663362477, "percentage": 1.61, "elapsed_time": "0:37:54", "remaining_time": "1 day, 14:33:16", "throughput": 706.15, "total_tokens": 1606016} +{"current_steps": 2900, "total_steps": 179570, "loss": 0.2726, "lr": 8.07206103469399e-06, "epoch": 0.16149690928328786, "percentage": 1.61, "elapsed_time": "0:37:58", "remaining_time": "1 day, 14:33:29", "throughput": 706.18, "total_tokens": 1609056} +{"current_steps": 2905, "total_steps": 179570, "loss": 0.3611, "lr": 8.085983182045998e-06, "epoch": 0.16177535223032802, "percentage": 1.62, "elapsed_time": "0:38:02", "remaining_time": "1 day, 14:33:10", "throughput": 706.14, "total_tokens": 1611552} +{"current_steps": 2910, "total_steps": 179570, "loss": 0.1952, "lr": 8.099905329398007e-06, "epoch": 0.16205379517736815, "percentage": 1.62, "elapsed_time": "0:38:06", "remaining_time": "1 day, 14:33:13", "throughput": 706.11, "total_tokens": 1614336} +{"current_steps": 2915, "total_steps": 179570, "loss": 0.2803, "lr": 8.113827476750015e-06, "epoch": 0.1623322381244083, "percentage": 1.62, "elapsed_time": "0:38:09", "remaining_time": "1 day, 14:32:55", "throughput": 706.1, "total_tokens": 1616928} +{"current_steps": 2920, "total_steps": 179570, "loss": 0.1073, "lr": 8.127749624102021e-06, "epoch": 0.16261068107144847, "percentage": 1.63, "elapsed_time": "0:38:14", "remaining_time": "1 day, 14:33:16", "throughput": 706.09, "total_tokens": 1619968} +{"current_steps": 2925, "total_steps": 179570, "loss": 0.3504, "lr": 8.14167177145403e-06, "epoch": 0.16288912401848862, "percentage": 1.63, "elapsed_time": "0:38:18", "remaining_time": "1 day, 14:33:16", "throughput": 706.12, "total_tokens": 1622864} +{"current_steps": 2930, "total_steps": 179570, "loss": 0.3852, "lr": 8.155593918806038e-06, "epoch": 0.16316756696552875, "percentage": 1.63, "elapsed_time": "0:38:22", "remaining_time": "1 day, 14:33:39", "throughput": 706.17, "total_tokens": 1626064} +{"current_steps": 2935, "total_steps": 179570, "loss": 0.3654, "lr": 8.169516066158044e-06, "epoch": 0.1634460099125689, "percentage": 1.63, "elapsed_time": "0:38:26", "remaining_time": "1 day, 14:33:39", "throughput": 706.21, "total_tokens": 1628976} +{"current_steps": 2940, "total_steps": 179570, "loss": 0.3166, "lr": 8.183438213510051e-06, "epoch": 0.16372445285960907, "percentage": 1.64, "elapsed_time": "0:38:30", "remaining_time": "1 day, 14:33:52", "throughput": 706.24, "total_tokens": 1632016} +{"current_steps": 2945, "total_steps": 179570, "loss": 0.2019, "lr": 8.19736036086206e-06, "epoch": 0.16400289580664923, "percentage": 1.64, "elapsed_time": "0:38:34", "remaining_time": "1 day, 14:33:43", "throughput": 706.21, "total_tokens": 1634672} +{"current_steps": 2950, "total_steps": 179570, "loss": 0.0242, "lr": 8.211282508214067e-06, "epoch": 0.16428133875368936, "percentage": 1.64, "elapsed_time": "0:38:38", "remaining_time": "1 day, 14:33:28", "throughput": 706.19, "total_tokens": 1637264} +{"current_steps": 2955, "total_steps": 179570, "loss": 0.2654, "lr": 8.225204655566076e-06, "epoch": 0.16455978170072952, "percentage": 1.65, "elapsed_time": "0:38:42", "remaining_time": "1 day, 14:33:38", "throughput": 706.22, "total_tokens": 1640288} +{"current_steps": 2960, "total_steps": 179570, "loss": 0.5861, "lr": 8.239126802918082e-06, "epoch": 0.16483822464776968, "percentage": 1.65, "elapsed_time": "0:38:46", "remaining_time": "1 day, 14:34:01", "throughput": 706.25, "total_tokens": 1643440} +{"current_steps": 2965, "total_steps": 179570, "loss": 0.4249, "lr": 8.25304895027009e-06, "epoch": 0.16511666759480984, "percentage": 1.65, "elapsed_time": "0:38:51", "remaining_time": "1 day, 14:34:08", "throughput": 706.23, "total_tokens": 1646288} +{"current_steps": 2970, "total_steps": 179570, "loss": 0.5063, "lr": 8.266971097622097e-06, "epoch": 0.16539511054184997, "percentage": 1.65, "elapsed_time": "0:38:55", "remaining_time": "1 day, 14:34:12", "throughput": 706.28, "total_tokens": 1649296} +{"current_steps": 2975, "total_steps": 179570, "loss": 0.4636, "lr": 8.280893244974105e-06, "epoch": 0.16567355348889012, "percentage": 1.66, "elapsed_time": "0:38:59", "remaining_time": "1 day, 14:34:06", "throughput": 706.23, "total_tokens": 1651936} +{"current_steps": 2980, "total_steps": 179570, "loss": 0.3362, "lr": 8.294815392326112e-06, "epoch": 0.16595199643593028, "percentage": 1.66, "elapsed_time": "0:39:02", "remaining_time": "1 day, 14:33:48", "throughput": 706.2, "total_tokens": 1654464} +{"current_steps": 2985, "total_steps": 179570, "loss": 0.4359, "lr": 8.30873753967812e-06, "epoch": 0.16623043938297044, "percentage": 1.66, "elapsed_time": "0:39:06", "remaining_time": "1 day, 14:33:34", "throughput": 706.16, "total_tokens": 1657024} +{"current_steps": 2990, "total_steps": 179570, "loss": 0.771, "lr": 8.322659687030128e-06, "epoch": 0.16650888233001057, "percentage": 1.67, "elapsed_time": "0:39:10", "remaining_time": "1 day, 14:33:07", "throughput": 706.14, "total_tokens": 1659472} +{"current_steps": 2995, "total_steps": 179570, "loss": 0.1496, "lr": 8.336581834382136e-06, "epoch": 0.16678732527705073, "percentage": 1.67, "elapsed_time": "0:39:13", "remaining_time": "1 day, 14:32:45", "throughput": 706.11, "total_tokens": 1661968} +{"current_steps": 3000, "total_steps": 179570, "loss": 0.8228, "lr": 8.350503981734143e-06, "epoch": 0.1670657682240909, "percentage": 1.67, "elapsed_time": "0:39:17", "remaining_time": "1 day, 14:32:53", "throughput": 706.09, "total_tokens": 1664832} +{"current_steps": 3005, "total_steps": 179570, "loss": 0.29, "lr": 8.364426129086151e-06, "epoch": 0.16734421117113105, "percentage": 1.67, "elapsed_time": "0:39:21", "remaining_time": "1 day, 14:32:55", "throughput": 706.1, "total_tokens": 1667712} +{"current_steps": 3010, "total_steps": 179570, "loss": 0.161, "lr": 8.378348276438158e-06, "epoch": 0.16762265411817118, "percentage": 1.68, "elapsed_time": "0:39:25", "remaining_time": "1 day, 14:32:46", "throughput": 706.09, "total_tokens": 1670384} +{"current_steps": 3015, "total_steps": 179570, "loss": 0.0206, "lr": 8.392270423790166e-06, "epoch": 0.16790109706521134, "percentage": 1.68, "elapsed_time": "0:39:30", "remaining_time": "1 day, 14:33:07", "throughput": 706.13, "total_tokens": 1673568} +{"current_steps": 3020, "total_steps": 179570, "loss": 0.1423, "lr": 8.406192571142172e-06, "epoch": 0.1681795400122515, "percentage": 1.68, "elapsed_time": "0:39:34", "remaining_time": "1 day, 14:33:06", "throughput": 706.12, "total_tokens": 1676336} +{"current_steps": 3025, "total_steps": 179570, "loss": 0.1735, "lr": 8.42011471849418e-06, "epoch": 0.16845798295929165, "percentage": 1.68, "elapsed_time": "0:39:38", "remaining_time": "1 day, 14:33:10", "throughput": 706.17, "total_tokens": 1679344} +{"current_steps": 3030, "total_steps": 179570, "loss": 0.1008, "lr": 8.434036865846189e-06, "epoch": 0.16873642590633178, "percentage": 1.69, "elapsed_time": "0:39:41", "remaining_time": "1 day, 14:32:58", "throughput": 706.16, "total_tokens": 1682000} +{"current_steps": 3035, "total_steps": 179570, "loss": 0.415, "lr": 8.447959013198197e-06, "epoch": 0.16901486885337194, "percentage": 1.69, "elapsed_time": "0:39:45", "remaining_time": "1 day, 14:33:04", "throughput": 706.13, "total_tokens": 1684816} +{"current_steps": 3040, "total_steps": 179570, "loss": 0.2086, "lr": 8.461881160550205e-06, "epoch": 0.1692933118004121, "percentage": 1.69, "elapsed_time": "0:39:49", "remaining_time": "1 day, 14:33:05", "throughput": 706.16, "total_tokens": 1687728} +{"current_steps": 3045, "total_steps": 179570, "loss": 0.2622, "lr": 8.475803307902212e-06, "epoch": 0.16957175474745226, "percentage": 1.7, "elapsed_time": "0:39:53", "remaining_time": "1 day, 14:32:52", "throughput": 706.17, "total_tokens": 1690416} +{"current_steps": 3050, "total_steps": 179570, "loss": 0.4193, "lr": 8.489725455254218e-06, "epoch": 0.1698501976944924, "percentage": 1.7, "elapsed_time": "0:39:57", "remaining_time": "1 day, 14:32:56", "throughput": 706.21, "total_tokens": 1693392} +{"current_steps": 3055, "total_steps": 179570, "loss": 0.6142, "lr": 8.503647602606226e-06, "epoch": 0.17012864064153255, "percentage": 1.7, "elapsed_time": "0:40:01", "remaining_time": "1 day, 14:33:01", "throughput": 706.25, "total_tokens": 1696352} +{"current_steps": 3060, "total_steps": 179570, "loss": 0.0129, "lr": 8.517569749958235e-06, "epoch": 0.1704070835885727, "percentage": 1.7, "elapsed_time": "0:40:05", "remaining_time": "1 day, 14:33:00", "throughput": 706.27, "total_tokens": 1699216} +{"current_steps": 3065, "total_steps": 179570, "loss": 0.2139, "lr": 8.531491897310241e-06, "epoch": 0.17068552653561286, "percentage": 1.71, "elapsed_time": "0:40:09", "remaining_time": "1 day, 14:33:04", "throughput": 706.31, "total_tokens": 1702192} +{"current_steps": 3070, "total_steps": 179570, "loss": 0.0185, "lr": 8.54541404466225e-06, "epoch": 0.170963969482653, "percentage": 1.71, "elapsed_time": "0:40:14", "remaining_time": "1 day, 14:33:24", "throughput": 706.32, "total_tokens": 1705280} +{"current_steps": 3075, "total_steps": 179570, "loss": 0.013, "lr": 8.559336192014258e-06, "epoch": 0.17124241242969315, "percentage": 1.71, "elapsed_time": "0:40:18", "remaining_time": "1 day, 14:33:18", "throughput": 706.3, "total_tokens": 1708000} +{"current_steps": 3080, "total_steps": 179570, "loss": 0.1961, "lr": 8.573258339366264e-06, "epoch": 0.1715208553767333, "percentage": 1.72, "elapsed_time": "0:40:22", "remaining_time": "1 day, 14:33:25", "throughput": 706.3, "total_tokens": 1710912} +{"current_steps": 3085, "total_steps": 179570, "loss": 0.1259, "lr": 8.58718048671827e-06, "epoch": 0.17179929832377347, "percentage": 1.72, "elapsed_time": "0:40:26", "remaining_time": "1 day, 14:33:35", "throughput": 706.28, "total_tokens": 1713824} +{"current_steps": 3090, "total_steps": 179570, "loss": 0.2324, "lr": 8.601102634070279e-06, "epoch": 0.1720777412708136, "percentage": 1.72, "elapsed_time": "0:40:30", "remaining_time": "1 day, 14:33:38", "throughput": 706.3, "total_tokens": 1716704} +{"current_steps": 3095, "total_steps": 179570, "loss": 0.2445, "lr": 8.615024781422287e-06, "epoch": 0.17235618421785376, "percentage": 1.72, "elapsed_time": "0:40:34", "remaining_time": "1 day, 14:33:42", "throughput": 706.28, "total_tokens": 1719552} +{"current_steps": 3100, "total_steps": 179570, "loss": 0.1552, "lr": 8.628946928774295e-06, "epoch": 0.17263462716489392, "percentage": 1.73, "elapsed_time": "0:40:38", "remaining_time": "1 day, 14:33:39", "throughput": 706.26, "total_tokens": 1722288} +{"current_steps": 3105, "total_steps": 179570, "loss": 0.1101, "lr": 8.642869076126302e-06, "epoch": 0.17291307011193408, "percentage": 1.73, "elapsed_time": "0:40:42", "remaining_time": "1 day, 14:33:22", "throughput": 706.26, "total_tokens": 1724912} +{"current_steps": 3110, "total_steps": 179570, "loss": 0.0494, "lr": 8.65679122347831e-06, "epoch": 0.1731915130589742, "percentage": 1.73, "elapsed_time": "0:40:46", "remaining_time": "1 day, 14:33:21", "throughput": 706.29, "total_tokens": 1727792} +{"current_steps": 3115, "total_steps": 179570, "loss": 0.163, "lr": 8.670713370830318e-06, "epoch": 0.17346995600601436, "percentage": 1.73, "elapsed_time": "0:40:49", "remaining_time": "1 day, 14:32:52", "throughput": 706.25, "total_tokens": 1730160} +{"current_steps": 3120, "total_steps": 179570, "loss": 0.1604, "lr": 8.684635518182325e-06, "epoch": 0.17374839895305452, "percentage": 1.74, "elapsed_time": "0:40:53", "remaining_time": "1 day, 14:32:55", "throughput": 706.22, "total_tokens": 1732944} +{"current_steps": 3125, "total_steps": 179570, "loss": 0.143, "lr": 8.698557665534331e-06, "epoch": 0.17402684190009468, "percentage": 1.74, "elapsed_time": "0:40:57", "remaining_time": "1 day, 14:32:57", "throughput": 706.25, "total_tokens": 1735872} +{"current_steps": 3130, "total_steps": 179570, "loss": 0.3562, "lr": 8.71247981288634e-06, "epoch": 0.1743052848471348, "percentage": 1.74, "elapsed_time": "0:41:01", "remaining_time": "1 day, 14:32:51", "throughput": 706.21, "total_tokens": 1738512} +{"current_steps": 3135, "total_steps": 179570, "loss": 0.4724, "lr": 8.726401960238348e-06, "epoch": 0.17458372779417497, "percentage": 1.75, "elapsed_time": "0:41:05", "remaining_time": "1 day, 14:32:37", "throughput": 706.19, "total_tokens": 1741120} +{"current_steps": 3140, "total_steps": 179570, "loss": 0.5604, "lr": 8.740324107590356e-06, "epoch": 0.17486217074121513, "percentage": 1.75, "elapsed_time": "0:41:09", "remaining_time": "1 day, 14:32:33", "throughput": 706.2, "total_tokens": 1743920} +{"current_steps": 3145, "total_steps": 179570, "loss": 0.2369, "lr": 8.754246254942363e-06, "epoch": 0.1751406136882553, "percentage": 1.75, "elapsed_time": "0:41:13", "remaining_time": "1 day, 14:32:35", "throughput": 706.2, "total_tokens": 1746784} +{"current_steps": 3150, "total_steps": 179570, "loss": 0.1765, "lr": 8.76816840229437e-06, "epoch": 0.17541905663529542, "percentage": 1.75, "elapsed_time": "0:41:17", "remaining_time": "1 day, 14:32:38", "throughput": 706.23, "total_tokens": 1749712} +{"current_steps": 3155, "total_steps": 179570, "loss": 0.2939, "lr": 8.782090549646379e-06, "epoch": 0.17569749958233558, "percentage": 1.76, "elapsed_time": "0:41:21", "remaining_time": "1 day, 14:32:45", "throughput": 706.23, "total_tokens": 1752640} +{"current_steps": 3160, "total_steps": 179570, "loss": 0.1959, "lr": 8.796012696998385e-06, "epoch": 0.17597594252937573, "percentage": 1.76, "elapsed_time": "0:41:25", "remaining_time": "1 day, 14:32:32", "throughput": 706.18, "total_tokens": 1755184} +{"current_steps": 3165, "total_steps": 179570, "loss": 0.1501, "lr": 8.809934844350392e-06, "epoch": 0.1762543854764159, "percentage": 1.76, "elapsed_time": "0:41:29", "remaining_time": "1 day, 14:32:30", "throughput": 706.17, "total_tokens": 1757952} +{"current_steps": 3170, "total_steps": 179570, "loss": 0.7457, "lr": 8.8238569917024e-06, "epoch": 0.17653282842345602, "percentage": 1.77, "elapsed_time": "0:41:33", "remaining_time": "1 day, 14:32:28", "throughput": 706.17, "total_tokens": 1760752} +{"current_steps": 3175, "total_steps": 179570, "loss": 0.1341, "lr": 8.837779139054408e-06, "epoch": 0.17681127137049618, "percentage": 1.77, "elapsed_time": "0:41:37", "remaining_time": "1 day, 14:32:14", "throughput": 706.15, "total_tokens": 1763344} +{"current_steps": 3180, "total_steps": 179570, "loss": 0.5929, "lr": 8.851701286406417e-06, "epoch": 0.17708971431753634, "percentage": 1.77, "elapsed_time": "0:41:41", "remaining_time": "1 day, 14:32:27", "throughput": 706.19, "total_tokens": 1766448} +{"current_steps": 3185, "total_steps": 179570, "loss": 0.5062, "lr": 8.865623433758423e-06, "epoch": 0.1773681572645765, "percentage": 1.77, "elapsed_time": "0:41:45", "remaining_time": "1 day, 14:32:38", "throughput": 706.21, "total_tokens": 1769456} +{"current_steps": 3190, "total_steps": 179570, "loss": 0.2397, "lr": 8.879545581110431e-06, "epoch": 0.17764660021161663, "percentage": 1.78, "elapsed_time": "0:41:49", "remaining_time": "1 day, 14:32:40", "throughput": 706.23, "total_tokens": 1772368} +{"current_steps": 3195, "total_steps": 179570, "loss": 0.0565, "lr": 8.893467728462438e-06, "epoch": 0.1779250431586568, "percentage": 1.78, "elapsed_time": "0:41:53", "remaining_time": "1 day, 14:32:48", "throughput": 706.27, "total_tokens": 1775408} +{"current_steps": 3200, "total_steps": 179570, "loss": 0.4743, "lr": 8.907389875814446e-06, "epoch": 0.17820348610569695, "percentage": 1.78, "elapsed_time": "0:41:57", "remaining_time": "1 day, 14:32:56", "throughput": 706.28, "total_tokens": 1778352} +{"current_steps": 3205, "total_steps": 179570, "loss": 0.18, "lr": 8.921312023166453e-06, "epoch": 0.1784819290527371, "percentage": 1.78, "elapsed_time": "0:42:01", "remaining_time": "1 day, 14:32:55", "throughput": 706.31, "total_tokens": 1781232} +{"current_steps": 3210, "total_steps": 179570, "loss": 0.5982, "lr": 8.935234170518461e-06, "epoch": 0.17876037199977723, "percentage": 1.79, "elapsed_time": "0:42:05", "remaining_time": "1 day, 14:32:27", "throughput": 706.3, "total_tokens": 1783680} +{"current_steps": 3215, "total_steps": 179570, "loss": 0.0273, "lr": 8.949156317870469e-06, "epoch": 0.1790388149468174, "percentage": 1.79, "elapsed_time": "0:42:09", "remaining_time": "1 day, 14:32:18", "throughput": 706.3, "total_tokens": 1786400} +{"current_steps": 3220, "total_steps": 179570, "loss": 0.1135, "lr": 8.963078465222477e-06, "epoch": 0.17931725789385755, "percentage": 1.79, "elapsed_time": "0:42:13", "remaining_time": "1 day, 14:32:05", "throughput": 706.31, "total_tokens": 1789088} +{"current_steps": 3225, "total_steps": 179570, "loss": 0.4276, "lr": 8.977000612574484e-06, "epoch": 0.1795957008408977, "percentage": 1.8, "elapsed_time": "0:42:16", "remaining_time": "1 day, 14:31:22", "throughput": 706.25, "total_tokens": 1791200} +{"current_steps": 3230, "total_steps": 179570, "loss": 0.0763, "lr": 8.990922759926492e-06, "epoch": 0.17987414378793784, "percentage": 1.8, "elapsed_time": "0:42:20", "remaining_time": "1 day, 14:31:28", "throughput": 706.24, "total_tokens": 1794080} +{"current_steps": 3235, "total_steps": 179570, "loss": 0.0922, "lr": 9.004844907278499e-06, "epoch": 0.180152586734978, "percentage": 1.8, "elapsed_time": "0:42:24", "remaining_time": "1 day, 14:31:24", "throughput": 706.23, "total_tokens": 1796848} +{"current_steps": 3240, "total_steps": 179570, "loss": 0.0052, "lr": 9.018767054630507e-06, "epoch": 0.18043102968201816, "percentage": 1.8, "elapsed_time": "0:42:28", "remaining_time": "1 day, 14:31:23", "throughput": 706.27, "total_tokens": 1799776} +{"current_steps": 3245, "total_steps": 179570, "loss": 0.1257, "lr": 9.032689201982513e-06, "epoch": 0.18070947262905832, "percentage": 1.81, "elapsed_time": "0:42:32", "remaining_time": "1 day, 14:31:23", "throughput": 706.31, "total_tokens": 1802688} +{"current_steps": 3250, "total_steps": 179570, "loss": 0.2019, "lr": 9.046611349334522e-06, "epoch": 0.18098791557609845, "percentage": 1.81, "elapsed_time": "0:42:36", "remaining_time": "1 day, 14:31:25", "throughput": 706.28, "total_tokens": 1805456} +{"current_steps": 3255, "total_steps": 179570, "loss": 0.3257, "lr": 9.06053349668653e-06, "epoch": 0.1812663585231386, "percentage": 1.81, "elapsed_time": "0:42:40", "remaining_time": "1 day, 14:31:11", "throughput": 706.26, "total_tokens": 1808064} +{"current_steps": 3260, "total_steps": 179570, "loss": 0.0823, "lr": 9.074455644038538e-06, "epoch": 0.18154480147017876, "percentage": 1.82, "elapsed_time": "0:42:44", "remaining_time": "1 day, 14:31:30", "throughput": 706.25, "total_tokens": 1811104} +{"current_steps": 3265, "total_steps": 179570, "loss": 0.2428, "lr": 9.088377791390545e-06, "epoch": 0.18182324441721892, "percentage": 1.82, "elapsed_time": "0:42:48", "remaining_time": "1 day, 14:31:32", "throughput": 706.28, "total_tokens": 1814064} +{"current_steps": 3270, "total_steps": 179570, "loss": 0.0426, "lr": 9.102299938742553e-06, "epoch": 0.18210168736425905, "percentage": 1.82, "elapsed_time": "0:42:52", "remaining_time": "1 day, 14:31:37", "throughput": 706.36, "total_tokens": 1817136} +{"current_steps": 3275, "total_steps": 179570, "loss": 0.2564, "lr": 9.11622208609456e-06, "epoch": 0.1823801303112992, "percentage": 1.82, "elapsed_time": "0:42:56", "remaining_time": "1 day, 14:31:19", "throughput": 706.3, "total_tokens": 1819584} +{"current_steps": 3280, "total_steps": 179570, "loss": 1.1455, "lr": 9.130144233446568e-06, "epoch": 0.18265857325833937, "percentage": 1.83, "elapsed_time": "0:43:00", "remaining_time": "1 day, 14:31:18", "throughput": 706.34, "total_tokens": 1822496} +{"current_steps": 3285, "total_steps": 179570, "loss": 0.2315, "lr": 9.144066380798574e-06, "epoch": 0.18293701620537953, "percentage": 1.83, "elapsed_time": "0:43:04", "remaining_time": "1 day, 14:31:09", "throughput": 706.3, "total_tokens": 1825104} +{"current_steps": 3290, "total_steps": 179570, "loss": 0.6893, "lr": 9.157988528150582e-06, "epoch": 0.18321545915241966, "percentage": 1.83, "elapsed_time": "0:43:08", "remaining_time": "1 day, 14:31:20", "throughput": 706.32, "total_tokens": 1828144} +{"current_steps": 3295, "total_steps": 179570, "loss": 0.341, "lr": 9.17191067550259e-06, "epoch": 0.18349390209945982, "percentage": 1.83, "elapsed_time": "0:43:12", "remaining_time": "1 day, 14:31:30", "throughput": 706.34, "total_tokens": 1831168} +{"current_steps": 3300, "total_steps": 179570, "loss": 0.3149, "lr": 9.185832822854599e-06, "epoch": 0.18377234504649997, "percentage": 1.84, "elapsed_time": "0:43:16", "remaining_time": "1 day, 14:31:21", "throughput": 706.3, "total_tokens": 1833760} +{"current_steps": 3305, "total_steps": 179570, "loss": 0.1068, "lr": 9.199754970206605e-06, "epoch": 0.18405078799354013, "percentage": 1.84, "elapsed_time": "0:43:20", "remaining_time": "1 day, 14:31:18", "throughput": 706.28, "total_tokens": 1836512} +{"current_steps": 3310, "total_steps": 179570, "loss": 0.133, "lr": 9.213677117558612e-06, "epoch": 0.18432923094058026, "percentage": 1.84, "elapsed_time": "0:43:24", "remaining_time": "1 day, 14:31:22", "throughput": 706.36, "total_tokens": 1839584} +{"current_steps": 3315, "total_steps": 179570, "loss": 0.2503, "lr": 9.22759926491062e-06, "epoch": 0.18460767388762042, "percentage": 1.85, "elapsed_time": "0:43:28", "remaining_time": "1 day, 14:31:11", "throughput": 706.38, "total_tokens": 1842336} +{"current_steps": 3320, "total_steps": 179570, "loss": 0.4147, "lr": 9.241521412262628e-06, "epoch": 0.18488611683466058, "percentage": 1.85, "elapsed_time": "0:43:32", "remaining_time": "1 day, 14:31:10", "throughput": 706.42, "total_tokens": 1845248} +{"current_steps": 3325, "total_steps": 179570, "loss": 0.1141, "lr": 9.255443559614635e-06, "epoch": 0.18516455978170074, "percentage": 1.85, "elapsed_time": "0:43:36", "remaining_time": "1 day, 14:31:05", "throughput": 706.4, "total_tokens": 1847968} +{"current_steps": 3330, "total_steps": 179570, "loss": 0.3201, "lr": 9.269365706966643e-06, "epoch": 0.18544300272874087, "percentage": 1.85, "elapsed_time": "0:43:39", "remaining_time": "1 day, 14:30:54", "throughput": 706.44, "total_tokens": 1850752} +{"current_steps": 3335, "total_steps": 179570, "loss": 0.4515, "lr": 9.283287854318651e-06, "epoch": 0.18572144567578103, "percentage": 1.86, "elapsed_time": "0:43:43", "remaining_time": "1 day, 14:30:37", "throughput": 706.41, "total_tokens": 1853264} +{"current_steps": 3340, "total_steps": 179570, "loss": 0.3089, "lr": 9.29721000167066e-06, "epoch": 0.18599988862282119, "percentage": 1.86, "elapsed_time": "0:43:47", "remaining_time": "1 day, 14:30:18", "throughput": 706.38, "total_tokens": 1855760} +{"current_steps": 3345, "total_steps": 179570, "loss": 0.2171, "lr": 9.311132149022666e-06, "epoch": 0.18627833156986134, "percentage": 1.86, "elapsed_time": "0:43:50", "remaining_time": "1 day, 14:29:50", "throughput": 706.34, "total_tokens": 1858144} +{"current_steps": 3350, "total_steps": 179570, "loss": 0.4145, "lr": 9.325054296374672e-06, "epoch": 0.18655677451690147, "percentage": 1.87, "elapsed_time": "0:43:54", "remaining_time": "1 day, 14:29:39", "throughput": 706.37, "total_tokens": 1860880} +{"current_steps": 3355, "total_steps": 179570, "loss": 0.4528, "lr": 9.33897644372668e-06, "epoch": 0.18683521746394163, "percentage": 1.87, "elapsed_time": "0:43:57", "remaining_time": "1 day, 14:29:08", "throughput": 706.33, "total_tokens": 1863200} +{"current_steps": 3360, "total_steps": 179570, "loss": 0.4628, "lr": 9.352898591078689e-06, "epoch": 0.1871136604109818, "percentage": 1.87, "elapsed_time": "0:44:01", "remaining_time": "1 day, 14:28:43", "throughput": 706.26, "total_tokens": 1865504} +{"current_steps": 3365, "total_steps": 179570, "loss": 0.254, "lr": 9.366820738430695e-06, "epoch": 0.18739210335802195, "percentage": 1.87, "elapsed_time": "0:44:05", "remaining_time": "1 day, 14:28:40", "throughput": 706.3, "total_tokens": 1868384} +{"current_steps": 3370, "total_steps": 179570, "loss": 0.5873, "lr": 9.380742885782704e-06, "epoch": 0.18767054630506208, "percentage": 1.88, "elapsed_time": "0:44:08", "remaining_time": "1 day, 14:28:08", "throughput": 706.26, "total_tokens": 1870688} +{"current_steps": 3375, "total_steps": 179570, "loss": 0.2359, "lr": 9.394665033134712e-06, "epoch": 0.18794898925210224, "percentage": 1.88, "elapsed_time": "0:44:12", "remaining_time": "1 day, 14:27:34", "throughput": 706.23, "total_tokens": 1872976} +{"current_steps": 3380, "total_steps": 179570, "loss": 0.4648, "lr": 9.40858718048672e-06, "epoch": 0.1882274321991424, "percentage": 1.88, "elapsed_time": "0:44:15", "remaining_time": "1 day, 14:26:52", "throughput": 706.14, "total_tokens": 1874992} +{"current_steps": 3385, "total_steps": 179570, "loss": 0.2753, "lr": 9.422509327838727e-06, "epoch": 0.18850587514618256, "percentage": 1.89, "elapsed_time": "0:44:19", "remaining_time": "1 day, 14:26:52", "throughput": 706.19, "total_tokens": 1877952} +{"current_steps": 3390, "total_steps": 179570, "loss": 0.1933, "lr": 9.436431475190733e-06, "epoch": 0.18878431809322269, "percentage": 1.89, "elapsed_time": "0:44:23", "remaining_time": "1 day, 14:26:40", "throughput": 706.2, "total_tokens": 1880656} +{"current_steps": 3395, "total_steps": 179570, "loss": 0.1107, "lr": 9.450353622542741e-06, "epoch": 0.18906276104026284, "percentage": 1.89, "elapsed_time": "0:44:27", "remaining_time": "1 day, 14:26:43", "throughput": 706.23, "total_tokens": 1883600} +{"current_steps": 3400, "total_steps": 179570, "loss": 0.5243, "lr": 9.46427576989475e-06, "epoch": 0.189341203987303, "percentage": 1.89, "elapsed_time": "0:44:31", "remaining_time": "1 day, 14:26:49", "throughput": 706.22, "total_tokens": 1886496} +{"current_steps": 3405, "total_steps": 179570, "loss": 0.1297, "lr": 9.478197917246756e-06, "epoch": 0.18961964693434316, "percentage": 1.9, "elapsed_time": "0:44:35", "remaining_time": "1 day, 14:26:44", "throughput": 706.19, "total_tokens": 1889168} +{"current_steps": 3410, "total_steps": 179570, "loss": 0.1144, "lr": 9.492120064598764e-06, "epoch": 0.1898980898813833, "percentage": 1.9, "elapsed_time": "0:44:39", "remaining_time": "1 day, 14:26:46", "throughput": 706.23, "total_tokens": 1892128} +{"current_steps": 3415, "total_steps": 179570, "loss": 0.1841, "lr": 9.506042211950773e-06, "epoch": 0.19017653282842345, "percentage": 1.9, "elapsed_time": "0:44:43", "remaining_time": "1 day, 14:27:05", "throughput": 706.24, "total_tokens": 1895232} +{"current_steps": 3420, "total_steps": 179570, "loss": 0.2881, "lr": 9.519964359302779e-06, "epoch": 0.1904549757754636, "percentage": 1.9, "elapsed_time": "0:44:47", "remaining_time": "1 day, 14:27:06", "throughput": 706.24, "total_tokens": 1898096} +{"current_steps": 3425, "total_steps": 179570, "loss": 0.2331, "lr": 9.533886506654786e-06, "epoch": 0.19073341872250377, "percentage": 1.91, "elapsed_time": "0:44:51", "remaining_time": "1 day, 14:26:47", "throughput": 706.19, "total_tokens": 1900512} +{"current_steps": 3430, "total_steps": 179570, "loss": 0.707, "lr": 9.547808654006794e-06, "epoch": 0.1910118616695439, "percentage": 1.91, "elapsed_time": "0:44:55", "remaining_time": "1 day, 14:26:49", "throughput": 706.23, "total_tokens": 1903472} +{"current_steps": 3435, "total_steps": 179570, "loss": 0.6001, "lr": 9.561730801358802e-06, "epoch": 0.19129030461658406, "percentage": 1.91, "elapsed_time": "0:44:58", "remaining_time": "1 day, 14:26:34", "throughput": 706.21, "total_tokens": 1906048} +{"current_steps": 3440, "total_steps": 179570, "loss": 0.2032, "lr": 9.57565294871081e-06, "epoch": 0.19156874756362421, "percentage": 1.92, "elapsed_time": "0:45:03", "remaining_time": "1 day, 14:26:44", "throughput": 706.23, "total_tokens": 1909056} +{"current_steps": 3445, "total_steps": 179570, "loss": 0.4455, "lr": 9.589575096062817e-06, "epoch": 0.19184719051066437, "percentage": 1.92, "elapsed_time": "0:45:07", "remaining_time": "1 day, 14:26:45", "throughput": 706.23, "total_tokens": 1911904} +{"current_steps": 3450, "total_steps": 179570, "loss": 0.1509, "lr": 9.603497243414825e-06, "epoch": 0.1921256334577045, "percentage": 1.92, "elapsed_time": "0:45:11", "remaining_time": "1 day, 14:26:52", "throughput": 706.23, "total_tokens": 1914832} +{"current_steps": 3455, "total_steps": 179570, "loss": 0.0435, "lr": 9.617419390766833e-06, "epoch": 0.19240407640474466, "percentage": 1.92, "elapsed_time": "0:45:15", "remaining_time": "1 day, 14:26:51", "throughput": 706.26, "total_tokens": 1917744} +{"current_steps": 3460, "total_steps": 179570, "loss": 0.1128, "lr": 9.63134153811884e-06, "epoch": 0.19268251935178482, "percentage": 1.93, "elapsed_time": "0:45:19", "remaining_time": "1 day, 14:26:46", "throughput": 706.25, "total_tokens": 1920480} +{"current_steps": 3465, "total_steps": 179570, "loss": 0.4398, "lr": 9.645263685470846e-06, "epoch": 0.19296096229882498, "percentage": 1.93, "elapsed_time": "0:45:22", "remaining_time": "1 day, 14:26:30", "throughput": 706.24, "total_tokens": 1923056} +{"current_steps": 3470, "total_steps": 179570, "loss": 0.2881, "lr": 9.659185832822854e-06, "epoch": 0.1932394052458651, "percentage": 1.93, "elapsed_time": "0:45:26", "remaining_time": "1 day, 14:26:26", "throughput": 706.23, "total_tokens": 1925792} +{"current_steps": 3475, "total_steps": 179570, "loss": 0.3614, "lr": 9.673107980174863e-06, "epoch": 0.19351784819290527, "percentage": 1.94, "elapsed_time": "0:45:30", "remaining_time": "1 day, 14:26:00", "throughput": 706.22, "total_tokens": 1928224} +{"current_steps": 3480, "total_steps": 179570, "loss": 0.1714, "lr": 9.687030127526871e-06, "epoch": 0.19379629113994543, "percentage": 1.94, "elapsed_time": "0:45:34", "remaining_time": "1 day, 14:26:18", "throughput": 706.24, "total_tokens": 1931360} +{"current_steps": 3485, "total_steps": 179570, "loss": 0.0472, "lr": 9.700952274878877e-06, "epoch": 0.19407473408698558, "percentage": 1.94, "elapsed_time": "0:45:39", "remaining_time": "1 day, 14:26:36", "throughput": 706.25, "total_tokens": 1934480} +{"current_steps": 3490, "total_steps": 179570, "loss": 0.192, "lr": 9.714874422230886e-06, "epoch": 0.19435317703402571, "percentage": 1.94, "elapsed_time": "0:45:43", "remaining_time": "1 day, 14:26:35", "throughput": 706.28, "total_tokens": 1937376} +{"current_steps": 3495, "total_steps": 179570, "loss": 0.285, "lr": 9.728796569582894e-06, "epoch": 0.19463161998106587, "percentage": 1.95, "elapsed_time": "0:45:46", "remaining_time": "1 day, 14:26:31", "throughput": 706.28, "total_tokens": 1940160} +{"current_steps": 3500, "total_steps": 179570, "loss": 0.136, "lr": 9.7427187169349e-06, "epoch": 0.19491006292810603, "percentage": 1.95, "elapsed_time": "0:45:50", "remaining_time": "1 day, 14:26:30", "throughput": 706.3, "total_tokens": 1943024} +{"current_steps": 3505, "total_steps": 179570, "loss": 0.7501, "lr": 9.756640864286907e-06, "epoch": 0.1951885058751462, "percentage": 1.95, "elapsed_time": "0:45:54", "remaining_time": "1 day, 14:26:15", "throughput": 706.31, "total_tokens": 1945664} +{"current_steps": 3510, "total_steps": 179570, "loss": 0.0322, "lr": 9.770563011638915e-06, "epoch": 0.19546694882218632, "percentage": 1.95, "elapsed_time": "0:45:58", "remaining_time": "1 day, 14:26:16", "throughput": 706.31, "total_tokens": 1948528} +{"current_steps": 3515, "total_steps": 179570, "loss": 0.3684, "lr": 9.784485158990923e-06, "epoch": 0.19574539176922648, "percentage": 1.96, "elapsed_time": "0:46:02", "remaining_time": "1 day, 14:25:51", "throughput": 706.26, "total_tokens": 1950848} +{"current_steps": 3520, "total_steps": 179570, "loss": 0.2202, "lr": 9.798407306342932e-06, "epoch": 0.19602383471626664, "percentage": 1.96, "elapsed_time": "0:46:05", "remaining_time": "1 day, 14:25:36", "throughput": 706.28, "total_tokens": 1953536} +{"current_steps": 3525, "total_steps": 179570, "loss": 0.4125, "lr": 9.812329453694938e-06, "epoch": 0.1963022776633068, "percentage": 1.96, "elapsed_time": "0:46:09", "remaining_time": "1 day, 14:25:07", "throughput": 706.27, "total_tokens": 1955920} +{"current_steps": 3530, "total_steps": 179570, "loss": 0.2624, "lr": 9.826251601046946e-06, "epoch": 0.19658072061034693, "percentage": 1.97, "elapsed_time": "0:46:13", "remaining_time": "1 day, 14:25:13", "throughput": 706.26, "total_tokens": 1958816} +{"current_steps": 3535, "total_steps": 179570, "loss": 0.1914, "lr": 9.840173748398953e-06, "epoch": 0.19685916355738708, "percentage": 1.97, "elapsed_time": "0:46:16", "remaining_time": "1 day, 14:24:46", "throughput": 706.21, "total_tokens": 1961136} +{"current_steps": 3540, "total_steps": 179570, "loss": 0.4811, "lr": 9.854095895750961e-06, "epoch": 0.19713760650442724, "percentage": 1.97, "elapsed_time": "0:46:20", "remaining_time": "1 day, 14:24:33", "throughput": 706.18, "total_tokens": 1963696} +{"current_steps": 3545, "total_steps": 179570, "loss": 0.0372, "lr": 9.868018043102968e-06, "epoch": 0.1974160494514674, "percentage": 1.97, "elapsed_time": "0:46:24", "remaining_time": "1 day, 14:24:23", "throughput": 706.2, "total_tokens": 1966432} +{"current_steps": 3550, "total_steps": 179570, "loss": 0.2068, "lr": 9.881940190454976e-06, "epoch": 0.19769449239850753, "percentage": 1.98, "elapsed_time": "0:46:28", "remaining_time": "1 day, 14:24:21", "throughput": 706.21, "total_tokens": 1969264} +{"current_steps": 3555, "total_steps": 179570, "loss": 0.4634, "lr": 9.895862337806984e-06, "epoch": 0.1979729353455477, "percentage": 1.98, "elapsed_time": "0:46:32", "remaining_time": "1 day, 14:24:06", "throughput": 706.22, "total_tokens": 1971888} +{"current_steps": 3560, "total_steps": 179570, "loss": 0.5716, "lr": 9.909784485158992e-06, "epoch": 0.19825137829258785, "percentage": 1.98, "elapsed_time": "0:46:36", "remaining_time": "1 day, 14:24:10", "throughput": 706.17, "total_tokens": 1974640} +{"current_steps": 3565, "total_steps": 179570, "loss": 0.1711, "lr": 9.923706632510999e-06, "epoch": 0.198529821239628, "percentage": 1.99, "elapsed_time": "0:46:40", "remaining_time": "1 day, 14:24:17", "throughput": 706.2, "total_tokens": 1977664} +{"current_steps": 3570, "total_steps": 179570, "loss": 0.244, "lr": 9.937628779863007e-06, "epoch": 0.19880826418666817, "percentage": 1.99, "elapsed_time": "0:46:44", "remaining_time": "1 day, 14:24:07", "throughput": 706.22, "total_tokens": 1980400} +{"current_steps": 3575, "total_steps": 179570, "loss": 0.2806, "lr": 9.951550927215014e-06, "epoch": 0.1990867071337083, "percentage": 1.99, "elapsed_time": "0:46:48", "remaining_time": "1 day, 14:24:10", "throughput": 706.21, "total_tokens": 1983248} +{"current_steps": 3580, "total_steps": 179570, "loss": 0.2008, "lr": 9.965473074567022e-06, "epoch": 0.19936515008074845, "percentage": 1.99, "elapsed_time": "0:46:52", "remaining_time": "1 day, 14:24:13", "throughput": 706.2, "total_tokens": 1986080} +{"current_steps": 3585, "total_steps": 179570, "loss": 0.4249, "lr": 9.979395221919028e-06, "epoch": 0.1996435930277886, "percentage": 2.0, "elapsed_time": "0:46:55", "remaining_time": "1 day, 14:23:44", "throughput": 706.18, "total_tokens": 1988464} +{"current_steps": 3590, "total_steps": 179570, "loss": 0.4639, "lr": 9.993317369271036e-06, "epoch": 0.19992203597482877, "percentage": 2.0, "elapsed_time": "0:46:59", "remaining_time": "1 day, 14:23:48", "throughput": 706.24, "total_tokens": 1991488} +{"current_steps": 3595, "total_steps": 179570, "loss": 0.3538, "lr": 1.0007239516623045e-05, "epoch": 0.2002004789218689, "percentage": 2.0, "elapsed_time": "0:47:03", "remaining_time": "1 day, 14:23:33", "throughput": 706.24, "total_tokens": 1994112} +{"current_steps": 3600, "total_steps": 179570, "loss": 0.3489, "lr": 1.0021161663975053e-05, "epoch": 0.20047892186890906, "percentage": 2.0, "elapsed_time": "0:47:07", "remaining_time": "1 day, 14:23:16", "throughput": 706.23, "total_tokens": 1996656} +{"current_steps": 3605, "total_steps": 179570, "loss": 0.1765, "lr": 1.003508381132706e-05, "epoch": 0.20075736481594922, "percentage": 2.01, "elapsed_time": "0:47:10", "remaining_time": "1 day, 14:22:40", "throughput": 706.16, "total_tokens": 1998800} +{"current_steps": 3610, "total_steps": 179570, "loss": 0.3826, "lr": 1.0049005958679068e-05, "epoch": 0.20103580776298938, "percentage": 2.01, "elapsed_time": "0:47:14", "remaining_time": "1 day, 14:22:22", "throughput": 706.16, "total_tokens": 2001360} +{"current_steps": 3615, "total_steps": 179570, "loss": 0.2304, "lr": 1.0062928106031074e-05, "epoch": 0.2013142507100295, "percentage": 2.01, "elapsed_time": "0:47:18", "remaining_time": "1 day, 14:22:31", "throughput": 706.14, "total_tokens": 2004240} +{"current_steps": 3620, "total_steps": 179570, "loss": 0.0929, "lr": 1.0076850253383082e-05, "epoch": 0.20159269365706967, "percentage": 2.02, "elapsed_time": "0:47:22", "remaining_time": "1 day, 14:22:39", "throughput": 706.13, "total_tokens": 2007168} +{"current_steps": 3625, "total_steps": 179570, "loss": 0.3427, "lr": 1.0090772400735089e-05, "epoch": 0.20187113660410982, "percentage": 2.02, "elapsed_time": "0:47:26", "remaining_time": "1 day, 14:22:38", "throughput": 706.12, "total_tokens": 2009952} +{"current_steps": 3630, "total_steps": 179570, "loss": 0.1365, "lr": 1.0104694548087097e-05, "epoch": 0.20214957955114998, "percentage": 2.02, "elapsed_time": "0:47:30", "remaining_time": "1 day, 14:22:56", "throughput": 706.16, "total_tokens": 2013168} +{"current_steps": 3635, "total_steps": 179570, "loss": 0.177, "lr": 1.0118616695439105e-05, "epoch": 0.2024280224981901, "percentage": 2.02, "elapsed_time": "0:47:34", "remaining_time": "1 day, 14:22:57", "throughput": 706.16, "total_tokens": 2016000} +{"current_steps": 3640, "total_steps": 179570, "loss": 0.5399, "lr": 1.0132538842791114e-05, "epoch": 0.20270646544523027, "percentage": 2.03, "elapsed_time": "0:47:38", "remaining_time": "1 day, 14:22:31", "throughput": 706.08, "total_tokens": 2018224} +{"current_steps": 3645, "total_steps": 179570, "loss": 0.0759, "lr": 1.014646099014312e-05, "epoch": 0.20298490839227043, "percentage": 2.03, "elapsed_time": "0:47:42", "remaining_time": "1 day, 14:22:23", "throughput": 706.04, "total_tokens": 2020832} +{"current_steps": 3650, "total_steps": 179570, "loss": 0.4276, "lr": 1.0160383137495128e-05, "epoch": 0.2032633513393106, "percentage": 2.03, "elapsed_time": "0:47:46", "remaining_time": "1 day, 14:22:26", "throughput": 706.08, "total_tokens": 2023824} +{"current_steps": 3655, "total_steps": 179570, "loss": 0.7186, "lr": 1.0174305284847135e-05, "epoch": 0.20354179428635072, "percentage": 2.04, "elapsed_time": "0:47:50", "remaining_time": "1 day, 14:22:13", "throughput": 706.06, "total_tokens": 2026416} +{"current_steps": 3660, "total_steps": 179570, "loss": 0.257, "lr": 1.0188227432199143e-05, "epoch": 0.20382023723339088, "percentage": 2.04, "elapsed_time": "0:47:53", "remaining_time": "1 day, 14:22:09", "throughput": 706.08, "total_tokens": 2029216} +{"current_steps": 3665, "total_steps": 179570, "loss": 0.1447, "lr": 1.020214957955115e-05, "epoch": 0.20409868018043104, "percentage": 2.04, "elapsed_time": "0:47:57", "remaining_time": "1 day, 14:22:04", "throughput": 706.07, "total_tokens": 2031952} +{"current_steps": 3670, "total_steps": 179570, "loss": 0.4909, "lr": 1.0216071726903158e-05, "epoch": 0.2043771231274712, "percentage": 2.04, "elapsed_time": "0:48:01", "remaining_time": "1 day, 14:21:36", "throughput": 706.06, "total_tokens": 2034336} +{"current_steps": 3675, "total_steps": 179570, "loss": 0.5318, "lr": 1.0229993874255166e-05, "epoch": 0.20465556607451132, "percentage": 2.05, "elapsed_time": "0:48:05", "remaining_time": "1 day, 14:21:36", "throughput": 706.09, "total_tokens": 2037248} +{"current_steps": 3680, "total_steps": 179570, "loss": 0.1427, "lr": 1.0243916021607174e-05, "epoch": 0.20493400902155148, "percentage": 2.05, "elapsed_time": "0:48:09", "remaining_time": "1 day, 14:21:45", "throughput": 706.11, "total_tokens": 2040288} +{"current_steps": 3685, "total_steps": 179570, "loss": 0.3239, "lr": 1.025783816895918e-05, "epoch": 0.20521245196859164, "percentage": 2.05, "elapsed_time": "0:48:13", "remaining_time": "1 day, 14:21:41", "throughput": 706.1, "total_tokens": 2043024} +{"current_steps": 3690, "total_steps": 179570, "loss": 0.2346, "lr": 1.0271760316311187e-05, "epoch": 0.2054908949156318, "percentage": 2.05, "elapsed_time": "0:48:17", "remaining_time": "1 day, 14:21:37", "throughput": 706.09, "total_tokens": 2045760} +{"current_steps": 3695, "total_steps": 179570, "loss": 0.3114, "lr": 1.0285682463663196e-05, "epoch": 0.20576933786267193, "percentage": 2.06, "elapsed_time": "0:48:20", "remaining_time": "1 day, 14:21:18", "throughput": 706.06, "total_tokens": 2048240} +{"current_steps": 3700, "total_steps": 179570, "loss": 0.0576, "lr": 1.0299604611015204e-05, "epoch": 0.2060477808097121, "percentage": 2.06, "elapsed_time": "0:48:24", "remaining_time": "1 day, 14:21:05", "throughput": 706.08, "total_tokens": 2050928} +{"current_steps": 3705, "total_steps": 179570, "loss": 0.0935, "lr": 1.031352675836721e-05, "epoch": 0.20632622375675225, "percentage": 2.06, "elapsed_time": "0:48:28", "remaining_time": "1 day, 14:21:02", "throughput": 706.06, "total_tokens": 2053664} +{"current_steps": 3710, "total_steps": 179570, "loss": 0.1683, "lr": 1.0327448905719218e-05, "epoch": 0.2066046667037924, "percentage": 2.07, "elapsed_time": "0:48:32", "remaining_time": "1 day, 14:20:58", "throughput": 706.04, "total_tokens": 2056352} +{"current_steps": 3715, "total_steps": 179570, "loss": 0.3733, "lr": 1.0341371053071227e-05, "epoch": 0.20688310965083254, "percentage": 2.07, "elapsed_time": "0:48:36", "remaining_time": "1 day, 14:21:09", "throughput": 706.08, "total_tokens": 2059472} +{"current_steps": 3720, "total_steps": 179570, "loss": 0.0151, "lr": 1.0355293200423235e-05, "epoch": 0.2071615525978727, "percentage": 2.07, "elapsed_time": "0:48:40", "remaining_time": "1 day, 14:21:12", "throughput": 706.12, "total_tokens": 2062480} +{"current_steps": 3725, "total_steps": 179570, "loss": 0.6031, "lr": 1.0369215347775241e-05, "epoch": 0.20743999554491285, "percentage": 2.07, "elapsed_time": "0:48:44", "remaining_time": "1 day, 14:21:12", "throughput": 706.15, "total_tokens": 2065376} +{"current_steps": 3730, "total_steps": 179570, "loss": 0.0085, "lr": 1.0383137495127248e-05, "epoch": 0.207718438491953, "percentage": 2.08, "elapsed_time": "0:48:49", "remaining_time": "1 day, 14:21:22", "throughput": 706.18, "total_tokens": 2068432} +{"current_steps": 3735, "total_steps": 179570, "loss": 0.1913, "lr": 1.0397059642479256e-05, "epoch": 0.20799688143899314, "percentage": 2.08, "elapsed_time": "0:48:53", "remaining_time": "1 day, 14:21:27", "throughput": 706.16, "total_tokens": 2071296} +{"current_steps": 3740, "total_steps": 179570, "loss": 0.2344, "lr": 1.0410981789831264e-05, "epoch": 0.2082753243860333, "percentage": 2.08, "elapsed_time": "0:48:57", "remaining_time": "1 day, 14:21:41", "throughput": 706.18, "total_tokens": 2074384} +{"current_steps": 3745, "total_steps": 179570, "loss": 0.782, "lr": 1.0424903937183271e-05, "epoch": 0.20855376733307346, "percentage": 2.09, "elapsed_time": "0:49:01", "remaining_time": "1 day, 14:21:37", "throughput": 706.16, "total_tokens": 2077104} +{"current_steps": 3750, "total_steps": 179570, "loss": 0.0607, "lr": 1.043882608453528e-05, "epoch": 0.20883221028011362, "percentage": 2.09, "elapsed_time": "0:49:05", "remaining_time": "1 day, 14:21:52", "throughput": 706.15, "total_tokens": 2080128} +{"current_steps": 3755, "total_steps": 179570, "loss": 0.6189, "lr": 1.0452748231887287e-05, "epoch": 0.20911065322715375, "percentage": 2.09, "elapsed_time": "0:49:09", "remaining_time": "1 day, 14:21:41", "throughput": 706.16, "total_tokens": 2082832} +{"current_steps": 3760, "total_steps": 179570, "loss": 0.4794, "lr": 1.0466670379239296e-05, "epoch": 0.2093890961741939, "percentage": 2.09, "elapsed_time": "0:49:13", "remaining_time": "1 day, 14:21:38", "throughput": 706.18, "total_tokens": 2085680} +{"current_steps": 3765, "total_steps": 179570, "loss": 0.0953, "lr": 1.0480592526591302e-05, "epoch": 0.20966753912123406, "percentage": 2.1, "elapsed_time": "0:49:17", "remaining_time": "1 day, 14:21:58", "throughput": 706.17, "total_tokens": 2088800} +{"current_steps": 3770, "total_steps": 179570, "loss": 0.4521, "lr": 1.0494514673943309e-05, "epoch": 0.20994598206827422, "percentage": 2.1, "elapsed_time": "0:49:21", "remaining_time": "1 day, 14:21:55", "throughput": 706.2, "total_tokens": 2091648} +{"current_steps": 3775, "total_steps": 179570, "loss": 0.2082, "lr": 1.0508436821295317e-05, "epoch": 0.21022442501531435, "percentage": 2.1, "elapsed_time": "0:49:25", "remaining_time": "1 day, 14:21:57", "throughput": 706.24, "total_tokens": 2094656} +{"current_steps": 3780, "total_steps": 179570, "loss": 0.0809, "lr": 1.0522358968647325e-05, "epoch": 0.2105028679623545, "percentage": 2.11, "elapsed_time": "0:49:30", "remaining_time": "1 day, 14:22:08", "throughput": 706.3, "total_tokens": 2097840} +{"current_steps": 3785, "total_steps": 179570, "loss": 0.1338, "lr": 1.0536281115999332e-05, "epoch": 0.21078131090939467, "percentage": 2.11, "elapsed_time": "0:49:34", "remaining_time": "1 day, 14:22:11", "throughput": 706.35, "total_tokens": 2100848} +{"current_steps": 3790, "total_steps": 179570, "loss": 0.0623, "lr": 1.055020326335134e-05, "epoch": 0.21105975385643483, "percentage": 2.11, "elapsed_time": "0:49:38", "remaining_time": "1 day, 14:22:00", "throughput": 706.36, "total_tokens": 2103568} +{"current_steps": 3795, "total_steps": 179570, "loss": 0.3727, "lr": 1.0564125410703348e-05, "epoch": 0.21133819680347496, "percentage": 2.11, "elapsed_time": "0:49:42", "remaining_time": "1 day, 14:22:02", "throughput": 706.38, "total_tokens": 2106480} +{"current_steps": 3800, "total_steps": 179570, "loss": 0.0215, "lr": 1.0578047558055355e-05, "epoch": 0.21161663975051512, "percentage": 2.12, "elapsed_time": "0:49:46", "remaining_time": "1 day, 14:22:08", "throughput": 706.39, "total_tokens": 2109440} +{"current_steps": 3805, "total_steps": 179570, "loss": 0.4596, "lr": 1.0591969705407361e-05, "epoch": 0.21189508269755528, "percentage": 2.12, "elapsed_time": "0:49:49", "remaining_time": "1 day, 14:21:54", "throughput": 706.41, "total_tokens": 2112112} +{"current_steps": 3810, "total_steps": 179570, "loss": 0.108, "lr": 1.060589185275937e-05, "epoch": 0.21217352564459543, "percentage": 2.12, "elapsed_time": "0:49:53", "remaining_time": "1 day, 14:21:26", "throughput": 706.35, "total_tokens": 2114352} +{"current_steps": 3815, "total_steps": 179570, "loss": 0.0507, "lr": 1.0619814000111378e-05, "epoch": 0.21245196859163556, "percentage": 2.12, "elapsed_time": "0:49:57", "remaining_time": "1 day, 14:21:28", "throughput": 706.37, "total_tokens": 2117280} +{"current_steps": 3820, "total_steps": 179570, "loss": 0.0436, "lr": 1.0633736147463386e-05, "epoch": 0.21273041153867572, "percentage": 2.13, "elapsed_time": "0:50:01", "remaining_time": "1 day, 14:21:17", "throughput": 706.37, "total_tokens": 2119936} +{"current_steps": 3825, "total_steps": 179570, "loss": 0.3332, "lr": 1.0647658294815392e-05, "epoch": 0.21300885448571588, "percentage": 2.13, "elapsed_time": "0:50:05", "remaining_time": "1 day, 14:21:09", "throughput": 706.34, "total_tokens": 2122560} +{"current_steps": 3830, "total_steps": 179570, "loss": 0.1185, "lr": 1.06615804421674e-05, "epoch": 0.21328729743275604, "percentage": 2.13, "elapsed_time": "0:50:09", "remaining_time": "1 day, 14:21:18", "throughput": 706.38, "total_tokens": 2125664} +{"current_steps": 3835, "total_steps": 179570, "loss": 0.2863, "lr": 1.0675502589519409e-05, "epoch": 0.21356574037979617, "percentage": 2.14, "elapsed_time": "0:50:13", "remaining_time": "1 day, 14:21:21", "throughput": 706.43, "total_tokens": 2128688} +{"current_steps": 3840, "total_steps": 179570, "loss": 0.1248, "lr": 1.0689424736871415e-05, "epoch": 0.21384418332683633, "percentage": 2.14, "elapsed_time": "0:50:17", "remaining_time": "1 day, 14:21:31", "throughput": 706.47, "total_tokens": 2131792} +{"current_steps": 3845, "total_steps": 179570, "loss": 0.2235, "lr": 1.0703346884223422e-05, "epoch": 0.2141226262738765, "percentage": 2.14, "elapsed_time": "0:50:21", "remaining_time": "1 day, 14:21:28", "throughput": 706.5, "total_tokens": 2134688} +{"current_steps": 3850, "total_steps": 179570, "loss": 0.3968, "lr": 1.071726903157543e-05, "epoch": 0.21440106922091665, "percentage": 2.14, "elapsed_time": "0:50:25", "remaining_time": "1 day, 14:21:26", "throughput": 706.52, "total_tokens": 2137536} +{"current_steps": 3855, "total_steps": 179570, "loss": 0.0998, "lr": 1.0731191178927438e-05, "epoch": 0.21467951216795678, "percentage": 2.15, "elapsed_time": "0:50:28", "remaining_time": "1 day, 14:21:03", "throughput": 706.52, "total_tokens": 2140032} +{"current_steps": 3860, "total_steps": 179570, "loss": 0.4214, "lr": 1.0745113326279446e-05, "epoch": 0.21495795511499693, "percentage": 2.15, "elapsed_time": "0:50:32", "remaining_time": "1 day, 14:20:59", "throughput": 706.51, "total_tokens": 2142752} +{"current_steps": 3865, "total_steps": 179570, "loss": 0.1836, "lr": 1.0759035473631453e-05, "epoch": 0.2152363980620371, "percentage": 2.15, "elapsed_time": "0:50:36", "remaining_time": "1 day, 14:21:01", "throughput": 706.54, "total_tokens": 2145712} +{"current_steps": 3870, "total_steps": 179570, "loss": 0.3122, "lr": 1.0772957620983461e-05, "epoch": 0.21551484100907725, "percentage": 2.16, "elapsed_time": "0:50:40", "remaining_time": "1 day, 14:20:34", "throughput": 706.53, "total_tokens": 2148112} +{"current_steps": 3875, "total_steps": 179570, "loss": 0.2294, "lr": 1.078687976833547e-05, "epoch": 0.21579328395611738, "percentage": 2.16, "elapsed_time": "0:50:44", "remaining_time": "1 day, 14:20:50", "throughput": 706.53, "total_tokens": 2151200} +{"current_steps": 3880, "total_steps": 179570, "loss": 0.6255, "lr": 1.0800801915687476e-05, "epoch": 0.21607172690315754, "percentage": 2.16, "elapsed_time": "0:50:48", "remaining_time": "1 day, 14:20:41", "throughput": 706.49, "total_tokens": 2153760} +{"current_steps": 3885, "total_steps": 179570, "loss": 0.3932, "lr": 1.0814724063039482e-05, "epoch": 0.2163501698501977, "percentage": 2.16, "elapsed_time": "0:50:52", "remaining_time": "1 day, 14:20:26", "throughput": 706.46, "total_tokens": 2156272} +{"current_steps": 3890, "total_steps": 179570, "loss": 0.1497, "lr": 1.082864621039149e-05, "epoch": 0.21662861279723786, "percentage": 2.17, "elapsed_time": "0:50:55", "remaining_time": "1 day, 14:20:11", "throughput": 706.42, "total_tokens": 2158768} +{"current_steps": 3895, "total_steps": 179570, "loss": 0.0724, "lr": 1.0842568357743499e-05, "epoch": 0.216907055744278, "percentage": 2.17, "elapsed_time": "0:50:59", "remaining_time": "1 day, 14:20:13", "throughput": 706.46, "total_tokens": 2161776} +{"current_steps": 3900, "total_steps": 179570, "loss": 0.354, "lr": 1.0856490505095507e-05, "epoch": 0.21718549869131815, "percentage": 2.17, "elapsed_time": "0:51:03", "remaining_time": "1 day, 14:19:59", "throughput": 706.43, "total_tokens": 2164288} +{"current_steps": 3905, "total_steps": 179570, "loss": 0.0373, "lr": 1.0870412652447514e-05, "epoch": 0.2174639416383583, "percentage": 2.17, "elapsed_time": "0:51:07", "remaining_time": "1 day, 14:19:58", "throughput": 706.46, "total_tokens": 2167200} +{"current_steps": 3910, "total_steps": 179570, "loss": 0.0134, "lr": 1.0884334799799522e-05, "epoch": 0.21774238458539846, "percentage": 2.18, "elapsed_time": "0:51:11", "remaining_time": "1 day, 14:20:00", "throughput": 706.49, "total_tokens": 2170160} +{"current_steps": 3915, "total_steps": 179570, "loss": 0.3511, "lr": 1.0898256947151528e-05, "epoch": 0.2180208275324386, "percentage": 2.18, "elapsed_time": "0:51:15", "remaining_time": "1 day, 14:20:01", "throughput": 706.51, "total_tokens": 2173088} +{"current_steps": 3920, "total_steps": 179570, "loss": 0.1662, "lr": 1.0912179094503537e-05, "epoch": 0.21829927047947875, "percentage": 2.18, "elapsed_time": "0:51:19", "remaining_time": "1 day, 14:20:02", "throughput": 706.49, "total_tokens": 2175872} +{"current_steps": 3925, "total_steps": 179570, "loss": 0.4377, "lr": 1.0926101241855545e-05, "epoch": 0.2185777134265189, "percentage": 2.19, "elapsed_time": "0:51:23", "remaining_time": "1 day, 14:19:55", "throughput": 706.48, "total_tokens": 2178544} +{"current_steps": 3930, "total_steps": 179570, "loss": 0.0791, "lr": 1.0940023389207551e-05, "epoch": 0.21885615637355907, "percentage": 2.19, "elapsed_time": "0:51:28", "remaining_time": "1 day, 14:20:11", "throughput": 706.51, "total_tokens": 2181744} +{"current_steps": 3935, "total_steps": 179570, "loss": 0.1148, "lr": 1.095394553655956e-05, "epoch": 0.2191345993205992, "percentage": 2.19, "elapsed_time": "0:51:31", "remaining_time": "1 day, 14:19:57", "throughput": 706.51, "total_tokens": 2184352} +{"current_steps": 3940, "total_steps": 179570, "loss": 0.0637, "lr": 1.0967867683911568e-05, "epoch": 0.21941304226763936, "percentage": 2.19, "elapsed_time": "0:51:35", "remaining_time": "1 day, 14:20:00", "throughput": 706.49, "total_tokens": 2187184} +{"current_steps": 3945, "total_steps": 179570, "loss": 0.2387, "lr": 1.0981789831263576e-05, "epoch": 0.21969148521467952, "percentage": 2.2, "elapsed_time": "0:51:39", "remaining_time": "1 day, 14:19:49", "throughput": 706.5, "total_tokens": 2189872} +{"current_steps": 3950, "total_steps": 179570, "loss": 0.2034, "lr": 1.0995711978615583e-05, "epoch": 0.21996992816171967, "percentage": 2.2, "elapsed_time": "0:51:43", "remaining_time": "1 day, 14:19:38", "throughput": 706.51, "total_tokens": 2192576} +{"current_steps": 3955, "total_steps": 179570, "loss": 0.0588, "lr": 1.1009634125967589e-05, "epoch": 0.2202483711087598, "percentage": 2.2, "elapsed_time": "0:51:47", "remaining_time": "1 day, 14:19:28", "throughput": 706.54, "total_tokens": 2195344} +{"current_steps": 3960, "total_steps": 179570, "loss": 0.2516, "lr": 1.1023556273319597e-05, "epoch": 0.22052681405579996, "percentage": 2.21, "elapsed_time": "0:51:51", "remaining_time": "1 day, 14:19:24", "throughput": 706.53, "total_tokens": 2198096} +{"current_steps": 3965, "total_steps": 179570, "loss": 0.0412, "lr": 1.1037478420671605e-05, "epoch": 0.22080525700284012, "percentage": 2.21, "elapsed_time": "0:51:55", "remaining_time": "1 day, 14:19:23", "throughput": 706.55, "total_tokens": 2200960} +{"current_steps": 3970, "total_steps": 179570, "loss": 0.4226, "lr": 1.1051400568023612e-05, "epoch": 0.22108369994988028, "percentage": 2.21, "elapsed_time": "0:51:59", "remaining_time": "1 day, 14:19:20", "throughput": 706.53, "total_tokens": 2203696} +{"current_steps": 3975, "total_steps": 179570, "loss": 0.2005, "lr": 1.106532271537562e-05, "epoch": 0.2213621428969204, "percentage": 2.21, "elapsed_time": "0:52:02", "remaining_time": "1 day, 14:19:01", "throughput": 706.5, "total_tokens": 2206144} +{"current_steps": 3980, "total_steps": 179570, "loss": 0.0262, "lr": 1.1079244862727628e-05, "epoch": 0.22164058584396057, "percentage": 2.22, "elapsed_time": "0:52:06", "remaining_time": "1 day, 14:19:08", "throughput": 706.5, "total_tokens": 2209072} +{"current_steps": 3985, "total_steps": 179570, "loss": 0.2494, "lr": 1.1093167010079637e-05, "epoch": 0.22191902879100073, "percentage": 2.22, "elapsed_time": "0:52:10", "remaining_time": "1 day, 14:18:38", "throughput": 706.46, "total_tokens": 2211312} +{"current_steps": 3990, "total_steps": 179570, "loss": 0.4967, "lr": 1.1107089157431643e-05, "epoch": 0.22219747173804089, "percentage": 2.22, "elapsed_time": "0:52:14", "remaining_time": "1 day, 14:18:34", "throughput": 706.46, "total_tokens": 2214080} +{"current_steps": 3995, "total_steps": 179570, "loss": 0.5218, "lr": 1.112101130478365e-05, "epoch": 0.22247591468508102, "percentage": 2.22, "elapsed_time": "0:52:18", "remaining_time": "1 day, 14:18:45", "throughput": 706.43, "total_tokens": 2217024} +{"current_steps": 4000, "total_steps": 179570, "loss": 0.007, "lr": 1.1134933452135658e-05, "epoch": 0.22275435763212117, "percentage": 2.23, "elapsed_time": "0:52:22", "remaining_time": "1 day, 14:19:01", "throughput": 706.48, "total_tokens": 2220256} +{"current_steps": 4005, "total_steps": 179570, "loss": 0.232, "lr": 1.1148855599487666e-05, "epoch": 0.22303280057916133, "percentage": 2.23, "elapsed_time": "0:52:26", "remaining_time": "1 day, 14:19:11", "throughput": 706.53, "total_tokens": 2223424} +{"current_steps": 4010, "total_steps": 179570, "loss": 0.0077, "lr": 1.1162777746839673e-05, "epoch": 0.2233112435262015, "percentage": 2.23, "elapsed_time": "0:52:30", "remaining_time": "1 day, 14:18:58", "throughput": 706.55, "total_tokens": 2226112} +{"current_steps": 4015, "total_steps": 179570, "loss": 0.1895, "lr": 1.1176699894191681e-05, "epoch": 0.22358968647324162, "percentage": 2.24, "elapsed_time": "0:52:34", "remaining_time": "1 day, 14:18:39", "throughput": 706.53, "total_tokens": 2228560} +{"current_steps": 4020, "total_steps": 179570, "loss": 0.3948, "lr": 1.1190622041543689e-05, "epoch": 0.22386812942028178, "percentage": 2.24, "elapsed_time": "0:52:38", "remaining_time": "1 day, 14:18:29", "throughput": 706.56, "total_tokens": 2231376} +{"current_steps": 4025, "total_steps": 179570, "loss": 0.0101, "lr": 1.1204544188895696e-05, "epoch": 0.22414657236732194, "percentage": 2.24, "elapsed_time": "0:52:42", "remaining_time": "1 day, 14:18:38", "throughput": 706.59, "total_tokens": 2234432} +{"current_steps": 4030, "total_steps": 179570, "loss": 0.1426, "lr": 1.1218466336247702e-05, "epoch": 0.2244250153143621, "percentage": 2.24, "elapsed_time": "0:52:46", "remaining_time": "1 day, 14:18:46", "throughput": 706.61, "total_tokens": 2237456} +{"current_steps": 4035, "total_steps": 179570, "loss": 0.0076, "lr": 1.123238848359971e-05, "epoch": 0.22470345826140223, "percentage": 2.25, "elapsed_time": "0:52:50", "remaining_time": "1 day, 14:19:01", "throughput": 706.63, "total_tokens": 2240608} +{"current_steps": 4040, "total_steps": 179570, "loss": 0.5032, "lr": 1.1246310630951719e-05, "epoch": 0.2249819012084424, "percentage": 2.25, "elapsed_time": "0:52:54", "remaining_time": "1 day, 14:18:54", "throughput": 706.61, "total_tokens": 2243280} +{"current_steps": 4045, "total_steps": 179570, "loss": 0.1906, "lr": 1.1260232778303727e-05, "epoch": 0.22526034415548254, "percentage": 2.25, "elapsed_time": "0:52:58", "remaining_time": "1 day, 14:18:43", "throughput": 706.6, "total_tokens": 2245888} +{"current_steps": 4050, "total_steps": 179570, "loss": 0.2403, "lr": 1.1274154925655733e-05, "epoch": 0.2255387871025227, "percentage": 2.26, "elapsed_time": "0:53:02", "remaining_time": "1 day, 14:18:41", "throughput": 706.62, "total_tokens": 2248784} +{"current_steps": 4055, "total_steps": 179570, "loss": 0.6933, "lr": 1.1288077073007742e-05, "epoch": 0.22581723004956283, "percentage": 2.26, "elapsed_time": "0:53:05", "remaining_time": "1 day, 14:18:18", "throughput": 706.59, "total_tokens": 2251168} +{"current_steps": 4060, "total_steps": 179570, "loss": 0.0584, "lr": 1.130199922035975e-05, "epoch": 0.226095672996603, "percentage": 2.26, "elapsed_time": "0:53:09", "remaining_time": "1 day, 14:18:09", "throughput": 706.62, "total_tokens": 2253920} +{"current_steps": 4065, "total_steps": 179570, "loss": 0.126, "lr": 1.1315921367711756e-05, "epoch": 0.22637411594364315, "percentage": 2.26, "elapsed_time": "0:53:13", "remaining_time": "1 day, 14:18:17", "throughput": 706.65, "total_tokens": 2257024} +{"current_steps": 4070, "total_steps": 179570, "loss": 0.0264, "lr": 1.1329843515063763e-05, "epoch": 0.2266525588906833, "percentage": 2.27, "elapsed_time": "0:53:18", "remaining_time": "1 day, 14:18:26", "throughput": 706.68, "total_tokens": 2260080} +{"current_steps": 4075, "total_steps": 179570, "loss": 0.1445, "lr": 1.1343765662415771e-05, "epoch": 0.22693100183772344, "percentage": 2.27, "elapsed_time": "0:53:21", "remaining_time": "1 day, 14:18:16", "throughput": 706.68, "total_tokens": 2262768} +{"current_steps": 4080, "total_steps": 179570, "loss": 0.153, "lr": 1.135768780976778e-05, "epoch": 0.2272094447847636, "percentage": 2.27, "elapsed_time": "0:53:26", "remaining_time": "1 day, 14:18:17", "throughput": 706.7, "total_tokens": 2265696} +{"current_steps": 4085, "total_steps": 179570, "loss": 0.1086, "lr": 1.1371609957119788e-05, "epoch": 0.22748788773180376, "percentage": 2.27, "elapsed_time": "0:53:30", "remaining_time": "1 day, 14:18:18", "throughput": 706.71, "total_tokens": 2268576} +{"current_steps": 4090, "total_steps": 179570, "loss": 0.0552, "lr": 1.1385532104471794e-05, "epoch": 0.22776633067884391, "percentage": 2.28, "elapsed_time": "0:53:34", "remaining_time": "1 day, 14:18:34", "throughput": 706.76, "total_tokens": 2271840} +{"current_steps": 4095, "total_steps": 179570, "loss": 0.2039, "lr": 1.1399454251823802e-05, "epoch": 0.22804477362588405, "percentage": 2.28, "elapsed_time": "0:53:37", "remaining_time": "1 day, 14:18:11", "throughput": 706.72, "total_tokens": 2274176} +{"current_steps": 4100, "total_steps": 179570, "loss": 0.206, "lr": 1.141337639917581e-05, "epoch": 0.2283232165729242, "percentage": 2.28, "elapsed_time": "0:53:42", "remaining_time": "1 day, 14:18:16", "throughput": 706.74, "total_tokens": 2277152} +{"current_steps": 4105, "total_steps": 179570, "loss": 0.5148, "lr": 1.1427298546527817e-05, "epoch": 0.22860165951996436, "percentage": 2.29, "elapsed_time": "0:53:45", "remaining_time": "1 day, 14:18:04", "throughput": 706.71, "total_tokens": 2279712} +{"current_steps": 4110, "total_steps": 179570, "loss": 0.4565, "lr": 1.1441220693879824e-05, "epoch": 0.22888010246700452, "percentage": 2.29, "elapsed_time": "0:53:49", "remaining_time": "1 day, 14:17:38", "throughput": 706.68, "total_tokens": 2282032} +{"current_steps": 4115, "total_steps": 179570, "loss": 0.1811, "lr": 1.1455142841231832e-05, "epoch": 0.22915854541404465, "percentage": 2.29, "elapsed_time": "0:53:53", "remaining_time": "1 day, 14:17:29", "throughput": 706.7, "total_tokens": 2284784} +{"current_steps": 4120, "total_steps": 179570, "loss": 0.2612, "lr": 1.146906498858384e-05, "epoch": 0.2294369883610848, "percentage": 2.29, "elapsed_time": "0:53:57", "remaining_time": "1 day, 14:17:30", "throughput": 706.72, "total_tokens": 2287696} +{"current_steps": 4125, "total_steps": 179570, "loss": 0.0092, "lr": 1.1482987135935848e-05, "epoch": 0.22971543130812497, "percentage": 2.3, "elapsed_time": "0:54:01", "remaining_time": "1 day, 14:17:44", "throughput": 706.72, "total_tokens": 2290784} +{"current_steps": 4130, "total_steps": 179570, "loss": 0.1587, "lr": 1.1496909283287855e-05, "epoch": 0.22999387425516513, "percentage": 2.3, "elapsed_time": "0:54:05", "remaining_time": "1 day, 14:17:52", "throughput": 706.74, "total_tokens": 2293808} +{"current_steps": 4135, "total_steps": 179570, "loss": 0.3539, "lr": 1.1510831430639863e-05, "epoch": 0.23027231720220526, "percentage": 2.3, "elapsed_time": "0:54:09", "remaining_time": "1 day, 14:17:51", "throughput": 706.71, "total_tokens": 2296544} +{"current_steps": 4140, "total_steps": 179570, "loss": 0.0779, "lr": 1.152475357799187e-05, "epoch": 0.23055076014924542, "percentage": 2.31, "elapsed_time": "0:54:13", "remaining_time": "1 day, 14:17:48", "throughput": 706.69, "total_tokens": 2299264} +{"current_steps": 4145, "total_steps": 179570, "loss": 0.0073, "lr": 1.1538675725343878e-05, "epoch": 0.23082920309628557, "percentage": 2.31, "elapsed_time": "0:54:17", "remaining_time": "1 day, 14:17:48", "throughput": 706.69, "total_tokens": 2302096} +{"current_steps": 4150, "total_steps": 179570, "loss": 0.0285, "lr": 1.1552597872695884e-05, "epoch": 0.23110764604332573, "percentage": 2.31, "elapsed_time": "0:54:21", "remaining_time": "1 day, 14:17:50", "throughput": 706.72, "total_tokens": 2305088} +{"current_steps": 4155, "total_steps": 179570, "loss": 0.3132, "lr": 1.1566520020047892e-05, "epoch": 0.23138608899036586, "percentage": 2.31, "elapsed_time": "0:54:25", "remaining_time": "1 day, 14:17:31", "throughput": 706.7, "total_tokens": 2307568} +{"current_steps": 4160, "total_steps": 179570, "loss": 0.2504, "lr": 1.15804421673999e-05, "epoch": 0.23166453193740602, "percentage": 2.32, "elapsed_time": "0:54:29", "remaining_time": "1 day, 14:17:30", "throughput": 706.73, "total_tokens": 2310464} +{"current_steps": 4165, "total_steps": 179570, "loss": 0.1094, "lr": 1.1594364314751909e-05, "epoch": 0.23194297488444618, "percentage": 2.32, "elapsed_time": "0:54:33", "remaining_time": "1 day, 14:17:27", "throughput": 706.71, "total_tokens": 2313216} +{"current_steps": 4170, "total_steps": 179570, "loss": 0.4361, "lr": 1.1608286462103915e-05, "epoch": 0.23222141783148634, "percentage": 2.32, "elapsed_time": "0:54:36", "remaining_time": "1 day, 14:17:16", "throughput": 706.68, "total_tokens": 2315760} +{"current_steps": 4175, "total_steps": 179570, "loss": 0.0186, "lr": 1.1622208609455924e-05, "epoch": 0.23249986077852647, "percentage": 2.32, "elapsed_time": "0:54:40", "remaining_time": "1 day, 14:17:02", "throughput": 706.68, "total_tokens": 2318368} +{"current_steps": 4180, "total_steps": 179570, "loss": 0.1423, "lr": 1.163613075680793e-05, "epoch": 0.23277830372556663, "percentage": 2.33, "elapsed_time": "0:54:44", "remaining_time": "1 day, 14:17:04", "throughput": 706.71, "total_tokens": 2321328} +{"current_steps": 4185, "total_steps": 179570, "loss": 0.0729, "lr": 1.1650052904159938e-05, "epoch": 0.23305674667260678, "percentage": 2.33, "elapsed_time": "0:54:48", "remaining_time": "1 day, 14:17:01", "throughput": 706.69, "total_tokens": 2324080} +{"current_steps": 4190, "total_steps": 179570, "loss": 0.2716, "lr": 1.1663975051511945e-05, "epoch": 0.23333518961964694, "percentage": 2.33, "elapsed_time": "0:54:52", "remaining_time": "1 day, 14:17:07", "throughput": 706.72, "total_tokens": 2327104} +{"current_steps": 4195, "total_steps": 179570, "loss": 0.4666, "lr": 1.1677897198863953e-05, "epoch": 0.23361363256668707, "percentage": 2.34, "elapsed_time": "0:54:56", "remaining_time": "1 day, 14:16:44", "throughput": 706.69, "total_tokens": 2329472} +{"current_steps": 4200, "total_steps": 179570, "loss": 0.3503, "lr": 1.1691819346215961e-05, "epoch": 0.23389207551372723, "percentage": 2.34, "elapsed_time": "0:55:00", "remaining_time": "1 day, 14:16:58", "throughput": 706.7, "total_tokens": 2332576} +{"current_steps": 4205, "total_steps": 179570, "loss": 0.7066, "lr": 1.170574149356797e-05, "epoch": 0.2341705184607674, "percentage": 2.34, "elapsed_time": "0:55:04", "remaining_time": "1 day, 14:16:42", "throughput": 706.64, "total_tokens": 2334976} +{"current_steps": 4210, "total_steps": 179570, "loss": 0.0603, "lr": 1.1719663640919976e-05, "epoch": 0.23444896140780755, "percentage": 2.34, "elapsed_time": "0:55:08", "remaining_time": "1 day, 14:16:45", "throughput": 706.68, "total_tokens": 2337984} +{"current_steps": 4215, "total_steps": 179570, "loss": 0.0522, "lr": 1.1733585788271984e-05, "epoch": 0.23472740435484768, "percentage": 2.35, "elapsed_time": "0:55:12", "remaining_time": "1 day, 14:16:32", "throughput": 706.69, "total_tokens": 2340624} +{"current_steps": 4220, "total_steps": 179570, "loss": 0.1384, "lr": 1.174750793562399e-05, "epoch": 0.23500584730188784, "percentage": 2.35, "elapsed_time": "0:55:15", "remaining_time": "1 day, 14:16:21", "throughput": 706.68, "total_tokens": 2343248} +{"current_steps": 4225, "total_steps": 179570, "loss": 0.1365, "lr": 1.1761430082975999e-05, "epoch": 0.235284290248928, "percentage": 2.35, "elapsed_time": "0:55:19", "remaining_time": "1 day, 14:16:23", "throughput": 706.71, "total_tokens": 2346240} +{"current_steps": 4230, "total_steps": 179570, "loss": 0.3761, "lr": 1.1775352230328006e-05, "epoch": 0.23556273319596815, "percentage": 2.36, "elapsed_time": "0:55:23", "remaining_time": "1 day, 14:16:24", "throughput": 706.74, "total_tokens": 2349184} +{"current_steps": 4235, "total_steps": 179570, "loss": 0.2606, "lr": 1.1789274377680014e-05, "epoch": 0.23584117614300829, "percentage": 2.36, "elapsed_time": "0:55:27", "remaining_time": "1 day, 14:16:20", "throughput": 706.73, "total_tokens": 2351952} +{"current_steps": 4240, "total_steps": 179570, "loss": 0.2778, "lr": 1.1803196525032022e-05, "epoch": 0.23611961909004844, "percentage": 2.36, "elapsed_time": "0:55:31", "remaining_time": "1 day, 14:16:08", "throughput": 706.75, "total_tokens": 2354640} +{"current_steps": 4245, "total_steps": 179570, "loss": 0.115, "lr": 1.181711867238403e-05, "epoch": 0.2363980620370886, "percentage": 2.36, "elapsed_time": "0:55:36", "remaining_time": "1 day, 14:16:22", "throughput": 706.77, "total_tokens": 2357776} +{"current_steps": 4250, "total_steps": 179570, "loss": 0.3765, "lr": 1.1831040819736037e-05, "epoch": 0.23667650498412876, "percentage": 2.37, "elapsed_time": "0:55:39", "remaining_time": "1 day, 14:16:19", "throughput": 706.79, "total_tokens": 2360640} +{"current_steps": 4255, "total_steps": 179570, "loss": 0.1481, "lr": 1.1844962967088043e-05, "epoch": 0.2369549479311689, "percentage": 2.37, "elapsed_time": "0:55:44", "remaining_time": "1 day, 14:16:21", "throughput": 706.83, "total_tokens": 2363680} +{"current_steps": 4260, "total_steps": 179570, "loss": 0.4526, "lr": 1.1858885114440051e-05, "epoch": 0.23723339087820905, "percentage": 2.37, "elapsed_time": "0:55:48", "remaining_time": "1 day, 14:16:22", "throughput": 706.85, "total_tokens": 2366608} +{"current_steps": 4265, "total_steps": 179570, "loss": 0.4736, "lr": 1.187280726179206e-05, "epoch": 0.2375118338252492, "percentage": 2.38, "elapsed_time": "0:55:52", "remaining_time": "1 day, 14:16:24", "throughput": 706.84, "total_tokens": 2369440} +{"current_steps": 4270, "total_steps": 179570, "loss": 0.3366, "lr": 1.1886729409144066e-05, "epoch": 0.23779027677228937, "percentage": 2.38, "elapsed_time": "0:55:55", "remaining_time": "1 day, 14:16:01", "throughput": 706.81, "total_tokens": 2371792} +{"current_steps": 4275, "total_steps": 179570, "loss": 0.2471, "lr": 1.1900651556496074e-05, "epoch": 0.2380687197193295, "percentage": 2.38, "elapsed_time": "0:55:59", "remaining_time": "1 day, 14:16:12", "throughput": 706.82, "total_tokens": 2374848} +{"current_steps": 4280, "total_steps": 179570, "loss": 0.2337, "lr": 1.1914573703848083e-05, "epoch": 0.23834716266636966, "percentage": 2.38, "elapsed_time": "0:56:03", "remaining_time": "1 day, 14:16:08", "throughput": 706.81, "total_tokens": 2377600} +{"current_steps": 4285, "total_steps": 179570, "loss": 0.1394, "lr": 1.1928495851200091e-05, "epoch": 0.2386256056134098, "percentage": 2.39, "elapsed_time": "0:56:07", "remaining_time": "1 day, 14:16:10", "throughput": 706.84, "total_tokens": 2380576} +{"current_steps": 4290, "total_steps": 179570, "loss": 0.1711, "lr": 1.1942417998552097e-05, "epoch": 0.23890404856044997, "percentage": 2.39, "elapsed_time": "0:56:12", "remaining_time": "1 day, 14:16:17", "throughput": 706.85, "total_tokens": 2383600} +{"current_steps": 4295, "total_steps": 179570, "loss": 0.0693, "lr": 1.1956340145904104e-05, "epoch": 0.2391824915074901, "percentage": 2.39, "elapsed_time": "0:56:16", "remaining_time": "1 day, 14:16:19", "throughput": 706.89, "total_tokens": 2386592} +{"current_steps": 4300, "total_steps": 179570, "loss": 0.0189, "lr": 1.1970262293256112e-05, "epoch": 0.23946093445453026, "percentage": 2.39, "elapsed_time": "0:56:20", "remaining_time": "1 day, 14:16:17", "throughput": 706.89, "total_tokens": 2389424} +{"current_steps": 4305, "total_steps": 179570, "loss": 0.5493, "lr": 1.198418444060812e-05, "epoch": 0.23973937740157042, "percentage": 2.4, "elapsed_time": "0:56:24", "remaining_time": "1 day, 14:16:19", "throughput": 706.94, "total_tokens": 2392464} +{"current_steps": 4310, "total_steps": 179570, "loss": 0.3715, "lr": 1.1998106587960127e-05, "epoch": 0.24001782034861058, "percentage": 2.4, "elapsed_time": "0:56:28", "remaining_time": "1 day, 14:16:26", "throughput": 706.95, "total_tokens": 2395472} +{"current_steps": 4315, "total_steps": 179570, "loss": 0.3996, "lr": 1.2012028735312135e-05, "epoch": 0.2402962632956507, "percentage": 2.4, "elapsed_time": "0:56:32", "remaining_time": "1 day, 14:16:13", "throughput": 706.95, "total_tokens": 2398080} +{"current_steps": 4320, "total_steps": 179570, "loss": 0.4103, "lr": 1.2025950882664143e-05, "epoch": 0.24057470624269087, "percentage": 2.41, "elapsed_time": "0:56:35", "remaining_time": "1 day, 14:16:02", "throughput": 706.93, "total_tokens": 2400672} +{"current_steps": 4325, "total_steps": 179570, "loss": 0.3672, "lr": 1.2039873030016152e-05, "epoch": 0.24085314918973103, "percentage": 2.41, "elapsed_time": "0:56:39", "remaining_time": "1 day, 14:15:53", "throughput": 706.95, "total_tokens": 2403408} +{"current_steps": 4330, "total_steps": 179570, "loss": 0.4364, "lr": 1.2053795177368158e-05, "epoch": 0.24113159213677118, "percentage": 2.41, "elapsed_time": "0:56:43", "remaining_time": "1 day, 14:15:47", "throughput": 706.9, "total_tokens": 2406000} +{"current_steps": 4335, "total_steps": 179570, "loss": 0.1427, "lr": 1.2067717324720165e-05, "epoch": 0.24141003508381131, "percentage": 2.41, "elapsed_time": "0:56:47", "remaining_time": "1 day, 14:15:49", "throughput": 706.89, "total_tokens": 2408864} +{"current_steps": 4340, "total_steps": 179570, "loss": 0.7309, "lr": 1.2081639472072173e-05, "epoch": 0.24168847803085147, "percentage": 2.42, "elapsed_time": "0:56:51", "remaining_time": "1 day, 14:15:26", "throughput": 706.83, "total_tokens": 2411072} +{"current_steps": 4345, "total_steps": 179570, "loss": 0.0669, "lr": 1.2095561619424181e-05, "epoch": 0.24196692097789163, "percentage": 2.42, "elapsed_time": "0:56:55", "remaining_time": "1 day, 14:15:26", "throughput": 706.82, "total_tokens": 2413920} +{"current_steps": 4350, "total_steps": 179570, "loss": 0.3153, "lr": 1.2109483766776188e-05, "epoch": 0.2422453639249318, "percentage": 2.42, "elapsed_time": "0:56:59", "remaining_time": "1 day, 14:15:37", "throughput": 706.83, "total_tokens": 2416976} +{"current_steps": 4355, "total_steps": 179570, "loss": 0.1219, "lr": 1.2123405914128196e-05, "epoch": 0.24252380687197192, "percentage": 2.43, "elapsed_time": "0:57:03", "remaining_time": "1 day, 14:15:40", "throughput": 706.82, "total_tokens": 2419856} +{"current_steps": 4360, "total_steps": 179570, "loss": 0.012, "lr": 1.2137328061480204e-05, "epoch": 0.24280224981901208, "percentage": 2.43, "elapsed_time": "0:57:07", "remaining_time": "1 day, 14:15:31", "throughput": 706.84, "total_tokens": 2422608} +{"current_steps": 4365, "total_steps": 179570, "loss": 0.2071, "lr": 1.215125020883221e-05, "epoch": 0.24308069276605224, "percentage": 2.43, "elapsed_time": "0:57:11", "remaining_time": "1 day, 14:15:38", "throughput": 706.86, "total_tokens": 2425648} +{"current_steps": 4370, "total_steps": 179570, "loss": 0.0867, "lr": 1.2165172356184217e-05, "epoch": 0.2433591357130924, "percentage": 2.43, "elapsed_time": "0:57:15", "remaining_time": "1 day, 14:15:45", "throughput": 706.88, "total_tokens": 2428688} +{"current_steps": 4375, "total_steps": 179570, "loss": 0.3933, "lr": 1.2179094503536225e-05, "epoch": 0.24363757866013253, "percentage": 2.44, "elapsed_time": "0:57:19", "remaining_time": "1 day, 14:15:52", "throughput": 706.89, "total_tokens": 2431696} +{"current_steps": 4380, "total_steps": 179570, "loss": 0.1064, "lr": 1.2193016650888234e-05, "epoch": 0.24391602160717268, "percentage": 2.44, "elapsed_time": "0:57:23", "remaining_time": "1 day, 14:15:42", "throughput": 706.9, "total_tokens": 2434384} +{"current_steps": 4385, "total_steps": 179570, "loss": 0.3366, "lr": 1.2206938798240242e-05, "epoch": 0.24419446455421284, "percentage": 2.44, "elapsed_time": "0:57:27", "remaining_time": "1 day, 14:15:33", "throughput": 706.91, "total_tokens": 2437104} +{"current_steps": 4390, "total_steps": 179570, "loss": 0.4194, "lr": 1.2220860945592248e-05, "epoch": 0.244472907501253, "percentage": 2.44, "elapsed_time": "0:57:31", "remaining_time": "1 day, 14:15:39", "throughput": 706.91, "total_tokens": 2440096} +{"current_steps": 4395, "total_steps": 179570, "loss": 0.1409, "lr": 1.2234783092944256e-05, "epoch": 0.24475135044829313, "percentage": 2.45, "elapsed_time": "0:57:35", "remaining_time": "1 day, 14:15:30", "throughput": 706.93, "total_tokens": 2442816} +{"current_steps": 4400, "total_steps": 179570, "loss": 0.6795, "lr": 1.2248705240296265e-05, "epoch": 0.2450297933953333, "percentage": 2.45, "elapsed_time": "0:57:39", "remaining_time": "1 day, 14:15:29", "throughput": 706.95, "total_tokens": 2445728} +{"current_steps": 4405, "total_steps": 179570, "loss": 0.0244, "lr": 1.2262627387648271e-05, "epoch": 0.24530823634237345, "percentage": 2.45, "elapsed_time": "0:57:43", "remaining_time": "1 day, 14:15:33", "throughput": 706.93, "total_tokens": 2448592} +{"current_steps": 4410, "total_steps": 179570, "loss": 0.0239, "lr": 1.2276549535000278e-05, "epoch": 0.2455866792894136, "percentage": 2.46, "elapsed_time": "0:57:47", "remaining_time": "1 day, 14:15:34", "throughput": 706.95, "total_tokens": 2451504} +{"current_steps": 4415, "total_steps": 179570, "loss": 0.014, "lr": 1.2290471682352286e-05, "epoch": 0.24586512223645374, "percentage": 2.46, "elapsed_time": "0:57:51", "remaining_time": "1 day, 14:15:24", "throughput": 706.94, "total_tokens": 2454160} +{"current_steps": 4420, "total_steps": 179570, "loss": 0.0125, "lr": 1.2304393829704294e-05, "epoch": 0.2461435651834939, "percentage": 2.46, "elapsed_time": "0:57:55", "remaining_time": "1 day, 14:15:22", "throughput": 706.94, "total_tokens": 2456976} +{"current_steps": 4425, "total_steps": 179570, "loss": 0.4014, "lr": 1.2318315977056302e-05, "epoch": 0.24642200813053405, "percentage": 2.46, "elapsed_time": "0:57:59", "remaining_time": "1 day, 14:15:08", "throughput": 706.91, "total_tokens": 2459472} +{"current_steps": 4430, "total_steps": 179570, "loss": 0.1167, "lr": 1.2332238124408309e-05, "epoch": 0.2467004510775742, "percentage": 2.47, "elapsed_time": "0:58:03", "remaining_time": "1 day, 14:15:12", "throughput": 706.92, "total_tokens": 2462416} +{"current_steps": 4435, "total_steps": 179570, "loss": 0.141, "lr": 1.2346160271760317e-05, "epoch": 0.24697889402461434, "percentage": 2.47, "elapsed_time": "0:58:07", "remaining_time": "1 day, 14:14:59", "throughput": 706.91, "total_tokens": 2465008} +{"current_steps": 4440, "total_steps": 179570, "loss": 0.1356, "lr": 1.2360082419112325e-05, "epoch": 0.2472573369716545, "percentage": 2.47, "elapsed_time": "0:58:10", "remaining_time": "1 day, 14:14:49", "throughput": 706.9, "total_tokens": 2467648} +{"current_steps": 4445, "total_steps": 179570, "loss": 0.3584, "lr": 1.2374004566464332e-05, "epoch": 0.24753577991869466, "percentage": 2.48, "elapsed_time": "0:58:14", "remaining_time": "1 day, 14:14:38", "throughput": 706.87, "total_tokens": 2470192} +{"current_steps": 4450, "total_steps": 179570, "loss": 0.5609, "lr": 1.2387926713816338e-05, "epoch": 0.24781422286573482, "percentage": 2.48, "elapsed_time": "0:58:18", "remaining_time": "1 day, 14:14:34", "throughput": 706.89, "total_tokens": 2473024} +{"current_steps": 4455, "total_steps": 179570, "loss": 0.0116, "lr": 1.2401848861168347e-05, "epoch": 0.24809266581277498, "percentage": 2.48, "elapsed_time": "0:58:22", "remaining_time": "1 day, 14:14:24", "throughput": 706.88, "total_tokens": 2475680} +{"current_steps": 4460, "total_steps": 179570, "loss": 0.0064, "lr": 1.2415771008520355e-05, "epoch": 0.2483711087598151, "percentage": 2.48, "elapsed_time": "0:58:26", "remaining_time": "1 day, 14:14:29", "throughput": 706.85, "total_tokens": 2478512} +{"current_steps": 4465, "total_steps": 179570, "loss": 0.119, "lr": 1.2429693155872363e-05, "epoch": 0.24864955170685527, "percentage": 2.49, "elapsed_time": "0:58:30", "remaining_time": "1 day, 14:14:16", "throughput": 706.84, "total_tokens": 2481088} +{"current_steps": 4470, "total_steps": 179570, "loss": 0.2532, "lr": 1.244361530322437e-05, "epoch": 0.24892799465389542, "percentage": 2.49, "elapsed_time": "0:58:34", "remaining_time": "1 day, 14:14:17", "throughput": 706.86, "total_tokens": 2484000} +{"current_steps": 4475, "total_steps": 179570, "loss": 0.0462, "lr": 1.2457537450576378e-05, "epoch": 0.24920643760093558, "percentage": 2.49, "elapsed_time": "0:58:38", "remaining_time": "1 day, 14:14:13", "throughput": 706.85, "total_tokens": 2486768} +{"current_steps": 4480, "total_steps": 179570, "loss": 0.2553, "lr": 1.2471459597928386e-05, "epoch": 0.2494848805479757, "percentage": 2.49, "elapsed_time": "0:58:42", "remaining_time": "1 day, 14:14:20", "throughput": 706.9, "total_tokens": 2489904} +{"current_steps": 4485, "total_steps": 179570, "loss": 0.1593, "lr": 1.2485381745280393e-05, "epoch": 0.24976332349501587, "percentage": 2.5, "elapsed_time": "0:58:46", "remaining_time": "1 day, 14:14:10", "throughput": 706.89, "total_tokens": 2492544} +{"current_steps": 4490, "total_steps": 179570, "loss": 0.3545, "lr": 1.2499303892632399e-05, "epoch": 0.250041766442056, "percentage": 2.5, "elapsed_time": "0:58:49", "remaining_time": "1 day, 14:14:00", "throughput": 706.91, "total_tokens": 2495280} +{"current_steps": 4495, "total_steps": 179570, "loss": 0.2858, "lr": 1.2513226039984407e-05, "epoch": 0.25032020938909616, "percentage": 2.5, "elapsed_time": "0:58:53", "remaining_time": "1 day, 14:13:28", "throughput": 706.88, "total_tokens": 2497456} +{"current_steps": 4500, "total_steps": 179570, "loss": 0.2049, "lr": 1.2527148187336416e-05, "epoch": 0.2505986523361363, "percentage": 2.51, "elapsed_time": "0:58:56", "remaining_time": "1 day, 14:13:14", "throughput": 706.84, "total_tokens": 2499904} +{"current_steps": 4505, "total_steps": 179570, "loss": 0.1657, "lr": 1.2541070334688424e-05, "epoch": 0.2508770952831765, "percentage": 2.51, "elapsed_time": "0:59:00", "remaining_time": "1 day, 14:13:22", "throughput": 706.88, "total_tokens": 2503024} +{"current_steps": 4510, "total_steps": 179570, "loss": 0.3222, "lr": 1.2554992482040432e-05, "epoch": 0.25115553823021664, "percentage": 2.51, "elapsed_time": "0:59:05", "remaining_time": "1 day, 14:13:26", "throughput": 706.88, "total_tokens": 2505952} +{"current_steps": 4515, "total_steps": 179570, "loss": 0.154, "lr": 1.2568914629392438e-05, "epoch": 0.2514339811772568, "percentage": 2.51, "elapsed_time": "0:59:08", "remaining_time": "1 day, 14:13:16", "throughput": 706.89, "total_tokens": 2508672} +{"current_steps": 4520, "total_steps": 179570, "loss": 0.5075, "lr": 1.2582836776744445e-05, "epoch": 0.25171242412429695, "percentage": 2.52, "elapsed_time": "0:59:12", "remaining_time": "1 day, 14:13:17", "throughput": 706.92, "total_tokens": 2511648} +{"current_steps": 4525, "total_steps": 179570, "loss": 0.0031, "lr": 1.2596758924096452e-05, "epoch": 0.2519908670713371, "percentage": 2.52, "elapsed_time": "0:59:16", "remaining_time": "1 day, 14:13:18", "throughput": 706.95, "total_tokens": 2514608} +{"current_steps": 4530, "total_steps": 179570, "loss": 0.0052, "lr": 1.261068107144846e-05, "epoch": 0.2522693100183772, "percentage": 2.52, "elapsed_time": "0:59:20", "remaining_time": "1 day, 14:13:09", "throughput": 706.97, "total_tokens": 2517360} +{"current_steps": 4535, "total_steps": 179570, "loss": 0.537, "lr": 1.2624603218800468e-05, "epoch": 0.25254775296541737, "percentage": 2.53, "elapsed_time": "0:59:24", "remaining_time": "1 day, 14:13:03", "throughput": 706.95, "total_tokens": 2520064} +{"current_steps": 4540, "total_steps": 179570, "loss": 0.4642, "lr": 1.2638525366152476e-05, "epoch": 0.25282619591245753, "percentage": 2.53, "elapsed_time": "0:59:28", "remaining_time": "1 day, 14:13:01", "throughput": 706.95, "total_tokens": 2522864} +{"current_steps": 4545, "total_steps": 179570, "loss": 0.03, "lr": 1.2652447513504484e-05, "epoch": 0.2531046388594977, "percentage": 2.53, "elapsed_time": "0:59:32", "remaining_time": "1 day, 14:13:02", "throughput": 706.96, "total_tokens": 2525744} +{"current_steps": 4550, "total_steps": 179570, "loss": 0.0624, "lr": 1.2666369660856493e-05, "epoch": 0.25338308180653785, "percentage": 2.53, "elapsed_time": "0:59:36", "remaining_time": "1 day, 14:13:02", "throughput": 706.96, "total_tokens": 2528592} +{"current_steps": 4555, "total_steps": 179570, "loss": 0.2372, "lr": 1.26802918082085e-05, "epoch": 0.253661524753578, "percentage": 2.54, "elapsed_time": "0:59:40", "remaining_time": "1 day, 14:12:52", "throughput": 706.96, "total_tokens": 2531264} +{"current_steps": 4560, "total_steps": 179570, "loss": 0.4138, "lr": 1.2694213955560506e-05, "epoch": 0.25393996770061816, "percentage": 2.54, "elapsed_time": "0:59:44", "remaining_time": "1 day, 14:12:53", "throughput": 706.99, "total_tokens": 2534272} +{"current_steps": 4565, "total_steps": 179570, "loss": 0.3453, "lr": 1.2708136102912512e-05, "epoch": 0.2542184106476583, "percentage": 2.54, "elapsed_time": "0:59:48", "remaining_time": "1 day, 14:12:58", "throughput": 707.02, "total_tokens": 2537296} +{"current_steps": 4570, "total_steps": 179570, "loss": 0.4475, "lr": 1.272205825026452e-05, "epoch": 0.2544968535946984, "percentage": 2.54, "elapsed_time": "0:59:52", "remaining_time": "1 day, 14:12:54", "throughput": 707.01, "total_tokens": 2540048} +{"current_steps": 4575, "total_steps": 179570, "loss": 0.1897, "lr": 1.2735980397616529e-05, "epoch": 0.2547752965417386, "percentage": 2.55, "elapsed_time": "0:59:56", "remaining_time": "1 day, 14:12:54", "throughput": 707.03, "total_tokens": 2542992} +{"current_steps": 4580, "total_steps": 179570, "loss": 0.2139, "lr": 1.2749902544968537e-05, "epoch": 0.25505373948877874, "percentage": 2.55, "elapsed_time": "1:00:00", "remaining_time": "1 day, 14:12:55", "throughput": 707.04, "total_tokens": 2545856} +{"current_steps": 4585, "total_steps": 179570, "loss": 0.308, "lr": 1.2763824692320545e-05, "epoch": 0.2553321824358189, "percentage": 2.55, "elapsed_time": "1:00:04", "remaining_time": "1 day, 14:12:53", "throughput": 707.06, "total_tokens": 2548768} +{"current_steps": 4590, "total_steps": 179570, "loss": 0.5638, "lr": 1.2777746839672553e-05, "epoch": 0.25561062538285906, "percentage": 2.56, "elapsed_time": "1:00:08", "remaining_time": "1 day, 14:12:43", "throughput": 707.05, "total_tokens": 2551392} +{"current_steps": 4595, "total_steps": 179570, "loss": 0.0953, "lr": 1.279166898702456e-05, "epoch": 0.2558890683298992, "percentage": 2.56, "elapsed_time": "1:00:12", "remaining_time": "1 day, 14:12:33", "throughput": 707.06, "total_tokens": 2554096} +{"current_steps": 4600, "total_steps": 179570, "loss": 0.5159, "lr": 1.2805591134376566e-05, "epoch": 0.2561675112769394, "percentage": 2.56, "elapsed_time": "1:00:16", "remaining_time": "1 day, 14:12:23", "throughput": 707.07, "total_tokens": 2556800} +{"current_steps": 4605, "total_steps": 179570, "loss": 0.3632, "lr": 1.2819513281728573e-05, "epoch": 0.25644595422397953, "percentage": 2.56, "elapsed_time": "1:00:19", "remaining_time": "1 day, 14:11:58", "throughput": 707.03, "total_tokens": 2559056} +{"current_steps": 4610, "total_steps": 179570, "loss": 0.0041, "lr": 1.2833435429080581e-05, "epoch": 0.25672439717101964, "percentage": 2.57, "elapsed_time": "1:00:23", "remaining_time": "1 day, 14:11:55", "throughput": 707.06, "total_tokens": 2561936} +{"current_steps": 4615, "total_steps": 179570, "loss": 0.0294, "lr": 1.284735757643259e-05, "epoch": 0.2570028401180598, "percentage": 2.57, "elapsed_time": "1:00:27", "remaining_time": "1 day, 14:11:51", "throughput": 707.07, "total_tokens": 2564768} +{"current_steps": 4620, "total_steps": 179570, "loss": 0.3829, "lr": 1.2861279723784598e-05, "epoch": 0.25728128306509995, "percentage": 2.57, "elapsed_time": "1:00:31", "remaining_time": "1 day, 14:11:39", "throughput": 707.06, "total_tokens": 2567344} +{"current_steps": 4625, "total_steps": 179570, "loss": 0.1533, "lr": 1.2875201871136606e-05, "epoch": 0.2575597260121401, "percentage": 2.58, "elapsed_time": "1:00:34", "remaining_time": "1 day, 14:11:35", "throughput": 707.07, "total_tokens": 2570144} +{"current_steps": 4630, "total_steps": 179570, "loss": 0.1653, "lr": 1.2889124018488612e-05, "epoch": 0.25783816895918027, "percentage": 2.58, "elapsed_time": "1:00:39", "remaining_time": "1 day, 14:11:37", "throughput": 707.06, "total_tokens": 2573008} +{"current_steps": 4635, "total_steps": 179570, "loss": 0.1949, "lr": 1.290304616584062e-05, "epoch": 0.25811661190622043, "percentage": 2.58, "elapsed_time": "1:00:43", "remaining_time": "1 day, 14:11:40", "throughput": 707.07, "total_tokens": 2575968} +{"current_steps": 4640, "total_steps": 179570, "loss": 0.3139, "lr": 1.2916968313192625e-05, "epoch": 0.2583950548532606, "percentage": 2.58, "elapsed_time": "1:00:47", "remaining_time": "1 day, 14:11:40", "throughput": 707.07, "total_tokens": 2578816} +{"current_steps": 4645, "total_steps": 179570, "loss": 0.2792, "lr": 1.2930890460544634e-05, "epoch": 0.25867349780030074, "percentage": 2.59, "elapsed_time": "1:00:51", "remaining_time": "1 day, 14:11:41", "throughput": 707.07, "total_tokens": 2581696} +{"current_steps": 4650, "total_steps": 179570, "loss": 0.1235, "lr": 1.2944812607896642e-05, "epoch": 0.25895194074734085, "percentage": 2.59, "elapsed_time": "1:00:54", "remaining_time": "1 day, 14:11:20", "throughput": 707.04, "total_tokens": 2584016} +{"current_steps": 4655, "total_steps": 179570, "loss": 0.0792, "lr": 1.295873475524865e-05, "epoch": 0.259230383694381, "percentage": 2.59, "elapsed_time": "1:00:58", "remaining_time": "1 day, 14:11:22", "throughput": 707.05, "total_tokens": 2586944} +{"current_steps": 4660, "total_steps": 179570, "loss": 0.1352, "lr": 1.2972656902600658e-05, "epoch": 0.25950882664142116, "percentage": 2.6, "elapsed_time": "1:01:02", "remaining_time": "1 day, 14:11:11", "throughput": 707.04, "total_tokens": 2589568} +{"current_steps": 4665, "total_steps": 179570, "loss": 0.005, "lr": 1.2986579049952666e-05, "epoch": 0.2597872695884613, "percentage": 2.6, "elapsed_time": "1:01:06", "remaining_time": "1 day, 14:11:00", "throughput": 707.04, "total_tokens": 2592224} +{"current_steps": 4670, "total_steps": 179570, "loss": 0.2958, "lr": 1.3000501197304673e-05, "epoch": 0.2600657125355015, "percentage": 2.6, "elapsed_time": "1:01:10", "remaining_time": "1 day, 14:11:01", "throughput": 707.08, "total_tokens": 2595248} +{"current_steps": 4675, "total_steps": 179570, "loss": 0.1309, "lr": 1.3014423344656681e-05, "epoch": 0.26034415548254164, "percentage": 2.6, "elapsed_time": "1:01:14", "remaining_time": "1 day, 14:10:52", "throughput": 707.08, "total_tokens": 2597936} +{"current_steps": 4680, "total_steps": 179570, "loss": 0.176, "lr": 1.3028345492008686e-05, "epoch": 0.2606225984295818, "percentage": 2.61, "elapsed_time": "1:01:17", "remaining_time": "1 day, 14:10:43", "throughput": 707.08, "total_tokens": 2600608} +{"current_steps": 4685, "total_steps": 179570, "loss": 0.3906, "lr": 1.3042267639360694e-05, "epoch": 0.26090104137662196, "percentage": 2.61, "elapsed_time": "1:01:21", "remaining_time": "1 day, 14:10:43", "throughput": 707.09, "total_tokens": 2603472} +{"current_steps": 4690, "total_steps": 179570, "loss": 0.2143, "lr": 1.3056189786712702e-05, "epoch": 0.26117948432366206, "percentage": 2.61, "elapsed_time": "1:01:26", "remaining_time": "1 day, 14:10:48", "throughput": 707.06, "total_tokens": 2606320} +{"current_steps": 4695, "total_steps": 179570, "loss": 0.0689, "lr": 1.307011193406471e-05, "epoch": 0.2614579272707022, "percentage": 2.61, "elapsed_time": "1:01:29", "remaining_time": "1 day, 14:10:40", "throughput": 707.02, "total_tokens": 2608896} +{"current_steps": 4700, "total_steps": 179570, "loss": 0.6059, "lr": 1.3084034081416719e-05, "epoch": 0.2617363702177424, "percentage": 2.62, "elapsed_time": "1:01:34", "remaining_time": "1 day, 14:10:43", "throughput": 707.02, "total_tokens": 2611808} +{"current_steps": 4705, "total_steps": 179570, "loss": 0.2673, "lr": 1.3097956228768727e-05, "epoch": 0.26201481316478253, "percentage": 2.62, "elapsed_time": "1:01:38", "remaining_time": "1 day, 14:10:43", "throughput": 707.01, "total_tokens": 2614608} +{"current_steps": 4710, "total_steps": 179570, "loss": 0.1822, "lr": 1.3111878376120734e-05, "epoch": 0.2622932561118227, "percentage": 2.62, "elapsed_time": "1:01:41", "remaining_time": "1 day, 14:10:21", "throughput": 706.96, "total_tokens": 2616848} +{"current_steps": 4715, "total_steps": 179570, "loss": 0.4521, "lr": 1.3125800523472742e-05, "epoch": 0.26257169905886285, "percentage": 2.63, "elapsed_time": "1:01:45", "remaining_time": "1 day, 14:10:15", "throughput": 706.95, "total_tokens": 2619536} +{"current_steps": 4720, "total_steps": 179570, "loss": 0.0923, "lr": 1.3139722670824747e-05, "epoch": 0.262850142005903, "percentage": 2.63, "elapsed_time": "1:01:49", "remaining_time": "1 day, 14:10:15", "throughput": 706.95, "total_tokens": 2622400} +{"current_steps": 4725, "total_steps": 179570, "loss": 0.0383, "lr": 1.3153644818176755e-05, "epoch": 0.26312858495294317, "percentage": 2.63, "elapsed_time": "1:01:53", "remaining_time": "1 day, 14:10:10", "throughput": 706.94, "total_tokens": 2625136} +{"current_steps": 4730, "total_steps": 179570, "loss": 0.0503, "lr": 1.3167566965528763e-05, "epoch": 0.26340702789998327, "percentage": 2.63, "elapsed_time": "1:01:56", "remaining_time": "1 day, 14:09:45", "throughput": 706.9, "total_tokens": 2627344} +{"current_steps": 4735, "total_steps": 179570, "loss": 0.4221, "lr": 1.3181489112880771e-05, "epoch": 0.26368547084702343, "percentage": 2.64, "elapsed_time": "1:02:00", "remaining_time": "1 day, 14:09:49", "throughput": 706.91, "total_tokens": 2630320} +{"current_steps": 4740, "total_steps": 179570, "loss": 0.0308, "lr": 1.319541126023278e-05, "epoch": 0.2639639137940636, "percentage": 2.64, "elapsed_time": "1:02:04", "remaining_time": "1 day, 14:09:50", "throughput": 706.92, "total_tokens": 2633248} +{"current_steps": 4745, "total_steps": 179570, "loss": 0.1271, "lr": 1.3209333407584786e-05, "epoch": 0.26424235674110375, "percentage": 2.64, "elapsed_time": "1:02:08", "remaining_time": "1 day, 14:09:45", "throughput": 706.92, "total_tokens": 2635984} +{"current_steps": 4750, "total_steps": 179570, "loss": 0.0367, "lr": 1.3223255554936794e-05, "epoch": 0.2645207996881439, "percentage": 2.65, "elapsed_time": "1:02:13", "remaining_time": "1 day, 14:09:51", "throughput": 706.93, "total_tokens": 2638992} +{"current_steps": 4755, "total_steps": 179570, "loss": 0.4432, "lr": 1.3237177702288803e-05, "epoch": 0.26479924263518406, "percentage": 2.65, "elapsed_time": "1:02:17", "remaining_time": "1 day, 14:09:55", "throughput": 706.94, "total_tokens": 2641952} +{"current_steps": 4760, "total_steps": 179570, "loss": 0.2474, "lr": 1.3251099849640807e-05, "epoch": 0.2650776855822242, "percentage": 2.65, "elapsed_time": "1:02:21", "remaining_time": "1 day, 14:09:59", "throughput": 706.95, "total_tokens": 2644928} +{"current_steps": 4765, "total_steps": 179570, "loss": 0.2041, "lr": 1.3265021996992816e-05, "epoch": 0.2653561285292644, "percentage": 2.65, "elapsed_time": "1:02:24", "remaining_time": "1 day, 14:09:46", "throughput": 706.92, "total_tokens": 2647424} +{"current_steps": 4770, "total_steps": 179570, "loss": 0.2411, "lr": 1.3278944144344824e-05, "epoch": 0.2656345714763045, "percentage": 2.66, "elapsed_time": "1:02:29", "remaining_time": "1 day, 14:09:51", "throughput": 706.92, "total_tokens": 2650368} +{"current_steps": 4775, "total_steps": 179570, "loss": 0.245, "lr": 1.3292866291696832e-05, "epoch": 0.26591301442334464, "percentage": 2.66, "elapsed_time": "1:02:32", "remaining_time": "1 day, 14:09:38", "throughput": 706.92, "total_tokens": 2652976} +{"current_steps": 4780, "total_steps": 179570, "loss": 0.9155, "lr": 1.330678843904884e-05, "epoch": 0.2661914573703848, "percentage": 2.66, "elapsed_time": "1:02:36", "remaining_time": "1 day, 14:09:39", "throughput": 706.96, "total_tokens": 2656000} +{"current_steps": 4785, "total_steps": 179570, "loss": 0.0516, "lr": 1.3320710586400847e-05, "epoch": 0.26646990031742496, "percentage": 2.66, "elapsed_time": "1:02:41", "remaining_time": "1 day, 14:09:51", "throughput": 706.97, "total_tokens": 2659120} +{"current_steps": 4790, "total_steps": 179570, "loss": 0.5077, "lr": 1.3334632733752855e-05, "epoch": 0.2667483432644651, "percentage": 2.67, "elapsed_time": "1:02:45", "remaining_time": "1 day, 14:09:41", "throughput": 706.97, "total_tokens": 2661808} +{"current_steps": 4795, "total_steps": 179570, "loss": 0.2205, "lr": 1.3348554881104863e-05, "epoch": 0.2670267862115053, "percentage": 2.67, "elapsed_time": "1:02:49", "remaining_time": "1 day, 14:09:41", "throughput": 706.97, "total_tokens": 2664656} +{"current_steps": 4800, "total_steps": 179570, "loss": 0.309, "lr": 1.3362477028456868e-05, "epoch": 0.26730522915854543, "percentage": 2.67, "elapsed_time": "1:02:52", "remaining_time": "1 day, 14:09:32", "throughput": 706.99, "total_tokens": 2667392} +{"current_steps": 4805, "total_steps": 179570, "loss": 0.1744, "lr": 1.3376399175808876e-05, "epoch": 0.2675836721055856, "percentage": 2.68, "elapsed_time": "1:02:57", "remaining_time": "1 day, 14:09:38", "throughput": 707.01, "total_tokens": 2670448} +{"current_steps": 4810, "total_steps": 179570, "loss": 0.2528, "lr": 1.3390321323160884e-05, "epoch": 0.2678621150526257, "percentage": 2.68, "elapsed_time": "1:03:01", "remaining_time": "1 day, 14:09:42", "throughput": 707.03, "total_tokens": 2673440} +{"current_steps": 4815, "total_steps": 179570, "loss": 0.2389, "lr": 1.3404243470512893e-05, "epoch": 0.26814055799966585, "percentage": 2.68, "elapsed_time": "1:03:05", "remaining_time": "1 day, 14:09:41", "throughput": 707.05, "total_tokens": 2676368} +{"current_steps": 4820, "total_steps": 179570, "loss": 0.2917, "lr": 1.3418165617864901e-05, "epoch": 0.268419000946706, "percentage": 2.68, "elapsed_time": "1:03:08", "remaining_time": "1 day, 14:09:29", "throughput": 707.05, "total_tokens": 2678992} +{"current_steps": 4825, "total_steps": 179570, "loss": 0.3338, "lr": 1.3432087765216907e-05, "epoch": 0.26869744389374617, "percentage": 2.69, "elapsed_time": "1:03:12", "remaining_time": "1 day, 14:09:19", "throughput": 707.07, "total_tokens": 2681744} +{"current_steps": 4830, "total_steps": 179570, "loss": 0.1642, "lr": 1.3446009912568916e-05, "epoch": 0.2689758868407863, "percentage": 2.69, "elapsed_time": "1:03:16", "remaining_time": "1 day, 14:09:21", "throughput": 707.1, "total_tokens": 2684736} +{"current_steps": 4835, "total_steps": 179570, "loss": 0.2087, "lr": 1.3459932059920924e-05, "epoch": 0.2692543297878265, "percentage": 2.69, "elapsed_time": "1:03:20", "remaining_time": "1 day, 14:09:13", "throughput": 707.08, "total_tokens": 2687360} +{"current_steps": 4840, "total_steps": 179570, "loss": 0.0543, "lr": 1.3473854207272932e-05, "epoch": 0.26953277273486664, "percentage": 2.7, "elapsed_time": "1:03:24", "remaining_time": "1 day, 14:09:04", "throughput": 707.05, "total_tokens": 2689920} +{"current_steps": 4845, "total_steps": 179570, "loss": 0.5123, "lr": 1.3487776354624937e-05, "epoch": 0.2698112156819068, "percentage": 2.7, "elapsed_time": "1:03:28", "remaining_time": "1 day, 14:08:54", "throughput": 707.05, "total_tokens": 2692560} +{"current_steps": 4850, "total_steps": 179570, "loss": 0.4965, "lr": 1.3501698501976945e-05, "epoch": 0.2700896586289469, "percentage": 2.7, "elapsed_time": "1:03:32", "remaining_time": "1 day, 14:08:48", "throughput": 707.04, "total_tokens": 2695280} +{"current_steps": 4855, "total_steps": 179570, "loss": 0.2023, "lr": 1.3515620649328953e-05, "epoch": 0.27036810157598706, "percentage": 2.7, "elapsed_time": "1:03:35", "remaining_time": "1 day, 14:08:29", "throughput": 707.02, "total_tokens": 2697680} +{"current_steps": 4860, "total_steps": 179570, "loss": 0.1252, "lr": 1.352954279668096e-05, "epoch": 0.2706465445230272, "percentage": 2.71, "elapsed_time": "1:03:39", "remaining_time": "1 day, 14:08:41", "throughput": 707.04, "total_tokens": 2700848} +{"current_steps": 4865, "total_steps": 179570, "loss": 0.0578, "lr": 1.3543464944032968e-05, "epoch": 0.2709249874700674, "percentage": 2.71, "elapsed_time": "1:03:44", "remaining_time": "1 day, 14:08:47", "throughput": 707.07, "total_tokens": 2703936} +{"current_steps": 4870, "total_steps": 179570, "loss": 0.1337, "lr": 1.3557387091384976e-05, "epoch": 0.27120343041710754, "percentage": 2.71, "elapsed_time": "1:03:48", "remaining_time": "1 day, 14:08:51", "throughput": 707.08, "total_tokens": 2706896} +{"current_steps": 4875, "total_steps": 179570, "loss": 0.1243, "lr": 1.3571309238736985e-05, "epoch": 0.2714818733641477, "percentage": 2.71, "elapsed_time": "1:03:52", "remaining_time": "1 day, 14:08:39", "throughput": 707.1, "total_tokens": 2709616} +{"current_steps": 4880, "total_steps": 179570, "loss": 0.0296, "lr": 1.3585231386088993e-05, "epoch": 0.27176031631118786, "percentage": 2.72, "elapsed_time": "1:03:55", "remaining_time": "1 day, 14:08:31", "throughput": 707.13, "total_tokens": 2712448} +{"current_steps": 4885, "total_steps": 179570, "loss": 0.0031, "lr": 1.3599153533440998e-05, "epoch": 0.272038759258228, "percentage": 2.72, "elapsed_time": "1:03:59", "remaining_time": "1 day, 14:08:34", "throughput": 707.12, "total_tokens": 2715312} +{"current_steps": 4890, "total_steps": 179570, "loss": 0.244, "lr": 1.3613075680793006e-05, "epoch": 0.2723172022052681, "percentage": 2.72, "elapsed_time": "1:04:04", "remaining_time": "1 day, 14:08:40", "throughput": 707.15, "total_tokens": 2718400} +{"current_steps": 4895, "total_steps": 179570, "loss": 0.2215, "lr": 1.3626997828145014e-05, "epoch": 0.2725956451523083, "percentage": 2.73, "elapsed_time": "1:04:08", "remaining_time": "1 day, 14:08:45", "throughput": 707.14, "total_tokens": 2721328} +{"current_steps": 4900, "total_steps": 179570, "loss": 0.294, "lr": 1.364091997549702e-05, "epoch": 0.27287408809934843, "percentage": 2.73, "elapsed_time": "1:04:12", "remaining_time": "1 day, 14:08:49", "throughput": 707.14, "total_tokens": 2724256} +{"current_steps": 4905, "total_steps": 179570, "loss": 0.1319, "lr": 1.3654842122849029e-05, "epoch": 0.2731525310463886, "percentage": 2.73, "elapsed_time": "1:04:16", "remaining_time": "1 day, 14:08:39", "throughput": 707.13, "total_tokens": 2726880} +{"current_steps": 4910, "total_steps": 179570, "loss": 0.2973, "lr": 1.3668764270201037e-05, "epoch": 0.27343097399342875, "percentage": 2.73, "elapsed_time": "1:04:19", "remaining_time": "1 day, 14:08:27", "throughput": 707.14, "total_tokens": 2729552} +{"current_steps": 4915, "total_steps": 179570, "loss": 0.1188, "lr": 1.3682686417553045e-05, "epoch": 0.2737094169404689, "percentage": 2.74, "elapsed_time": "1:04:23", "remaining_time": "1 day, 14:08:24", "throughput": 707.17, "total_tokens": 2732432} +{"current_steps": 4920, "total_steps": 179570, "loss": 0.2362, "lr": 1.3696608564905053e-05, "epoch": 0.27398785988750907, "percentage": 2.74, "elapsed_time": "1:04:27", "remaining_time": "1 day, 14:08:16", "throughput": 707.2, "total_tokens": 2735232} +{"current_steps": 4925, "total_steps": 179570, "loss": 0.0394, "lr": 1.3710530712257058e-05, "epoch": 0.2742663028345492, "percentage": 2.74, "elapsed_time": "1:04:31", "remaining_time": "1 day, 14:08:17", "throughput": 707.25, "total_tokens": 2738336} +{"current_steps": 4930, "total_steps": 179570, "loss": 0.2061, "lr": 1.3724452859609066e-05, "epoch": 0.2745447457815893, "percentage": 2.75, "elapsed_time": "1:04:35", "remaining_time": "1 day, 14:08:18", "throughput": 707.26, "total_tokens": 2741248} +{"current_steps": 4935, "total_steps": 179570, "loss": 0.1691, "lr": 1.3738375006961075e-05, "epoch": 0.2748231887286295, "percentage": 2.75, "elapsed_time": "1:04:39", "remaining_time": "1 day, 14:08:13", "throughput": 707.25, "total_tokens": 2743952} +{"current_steps": 4940, "total_steps": 179570, "loss": 0.1901, "lr": 1.3752297154313081e-05, "epoch": 0.27510163167566964, "percentage": 2.75, "elapsed_time": "1:04:43", "remaining_time": "1 day, 14:08:04", "throughput": 707.26, "total_tokens": 2746672} +{"current_steps": 4945, "total_steps": 179570, "loss": 0.0872, "lr": 1.376621930166509e-05, "epoch": 0.2753800746227098, "percentage": 2.75, "elapsed_time": "1:04:47", "remaining_time": "1 day, 14:07:55", "throughput": 707.26, "total_tokens": 2749376} +{"current_steps": 4950, "total_steps": 179570, "loss": 0.2249, "lr": 1.3780141449017098e-05, "epoch": 0.27565851756974996, "percentage": 2.76, "elapsed_time": "1:04:51", "remaining_time": "1 day, 14:07:55", "throughput": 707.29, "total_tokens": 2752336} +{"current_steps": 4955, "total_steps": 179570, "loss": 0.1159, "lr": 1.3794063596369106e-05, "epoch": 0.2759369605167901, "percentage": 2.76, "elapsed_time": "1:04:55", "remaining_time": "1 day, 14:07:47", "throughput": 707.32, "total_tokens": 2755136} +{"current_steps": 4960, "total_steps": 179570, "loss": 0.1421, "lr": 1.3807985743721114e-05, "epoch": 0.2762154034638303, "percentage": 2.76, "elapsed_time": "1:04:59", "remaining_time": "1 day, 14:07:51", "throughput": 707.32, "total_tokens": 2758096} +{"current_steps": 4965, "total_steps": 179570, "loss": 0.0858, "lr": 1.3821907891073119e-05, "epoch": 0.27649384641087044, "percentage": 2.76, "elapsed_time": "1:05:03", "remaining_time": "1 day, 14:07:51", "throughput": 707.35, "total_tokens": 2761088} +{"current_steps": 4970, "total_steps": 179570, "loss": 0.0059, "lr": 1.3835830038425127e-05, "epoch": 0.27677228935791054, "percentage": 2.77, "elapsed_time": "1:05:07", "remaining_time": "1 day, 14:08:04", "throughput": 707.39, "total_tokens": 2764336} +{"current_steps": 4975, "total_steps": 179570, "loss": 0.4701, "lr": 1.3849752185777134e-05, "epoch": 0.2770507323049507, "percentage": 2.77, "elapsed_time": "1:05:11", "remaining_time": "1 day, 14:08:05", "throughput": 707.42, "total_tokens": 2767344} +{"current_steps": 4980, "total_steps": 179570, "loss": 0.2293, "lr": 1.3863674333129142e-05, "epoch": 0.27732917525199086, "percentage": 2.77, "elapsed_time": "1:05:15", "remaining_time": "1 day, 14:07:54", "throughput": 707.39, "total_tokens": 2769872} +{"current_steps": 4985, "total_steps": 179570, "loss": 0.707, "lr": 1.387759648048115e-05, "epoch": 0.277607618199031, "percentage": 2.78, "elapsed_time": "1:05:19", "remaining_time": "1 day, 14:07:52", "throughput": 707.4, "total_tokens": 2772736} +{"current_steps": 4990, "total_steps": 179570, "loss": 0.299, "lr": 1.3891518627833158e-05, "epoch": 0.2778860611460712, "percentage": 2.78, "elapsed_time": "1:05:23", "remaining_time": "1 day, 14:07:54", "throughput": 707.4, "total_tokens": 2775632} +{"current_steps": 4995, "total_steps": 179570, "loss": 0.4883, "lr": 1.3905440775185167e-05, "epoch": 0.27816450409311133, "percentage": 2.78, "elapsed_time": "1:05:27", "remaining_time": "1 day, 14:07:45", "throughput": 707.41, "total_tokens": 2778352} +{"current_steps": 5000, "total_steps": 179570, "loss": 0.1688, "lr": 1.3919362922537175e-05, "epoch": 0.2784429470401515, "percentage": 2.78, "elapsed_time": "1:05:31", "remaining_time": "1 day, 14:07:35", "throughput": 707.39, "total_tokens": 2780944} +{"current_steps": 5005, "total_steps": 179570, "loss": 0.1823, "lr": 1.393328506988918e-05, "epoch": 0.27872138998719165, "percentage": 2.79, "elapsed_time": "1:05:35", "remaining_time": "1 day, 14:07:25", "throughput": 707.37, "total_tokens": 2783520} +{"current_steps": 5010, "total_steps": 179570, "loss": 0.3299, "lr": 1.3947207217241188e-05, "epoch": 0.27899983293423175, "percentage": 2.79, "elapsed_time": "1:05:39", "remaining_time": "1 day, 14:07:41", "throughput": 707.37, "total_tokens": 2786672} +{"current_steps": 5015, "total_steps": 179570, "loss": 0.1534, "lr": 1.3961129364593194e-05, "epoch": 0.2792782758812719, "percentage": 2.79, "elapsed_time": "1:05:43", "remaining_time": "1 day, 14:07:43", "throughput": 707.42, "total_tokens": 2789792} +{"current_steps": 5020, "total_steps": 179570, "loss": 0.5199, "lr": 1.3975051511945203e-05, "epoch": 0.27955671882831207, "percentage": 2.8, "elapsed_time": "1:05:47", "remaining_time": "1 day, 14:07:41", "throughput": 707.44, "total_tokens": 2792672} +{"current_steps": 5025, "total_steps": 179570, "loss": 0.0794, "lr": 1.398897365929721e-05, "epoch": 0.2798351617753522, "percentage": 2.8, "elapsed_time": "1:05:51", "remaining_time": "1 day, 14:07:39", "throughput": 707.46, "total_tokens": 2795600} +{"current_steps": 5030, "total_steps": 179570, "loss": 0.1539, "lr": 1.4002895806649219e-05, "epoch": 0.2801136047223924, "percentage": 2.8, "elapsed_time": "1:05:55", "remaining_time": "1 day, 14:07:34", "throughput": 707.44, "total_tokens": 2798256} +{"current_steps": 5035, "total_steps": 179570, "loss": 0.1477, "lr": 1.4016817954001227e-05, "epoch": 0.28039204766943254, "percentage": 2.8, "elapsed_time": "1:05:59", "remaining_time": "1 day, 14:07:22", "throughput": 707.41, "total_tokens": 2800752} +{"current_steps": 5040, "total_steps": 179570, "loss": 0.0053, "lr": 1.4030740101353235e-05, "epoch": 0.2806704906164727, "percentage": 2.81, "elapsed_time": "1:06:03", "remaining_time": "1 day, 14:07:22", "throughput": 707.42, "total_tokens": 2803680} +{"current_steps": 5045, "total_steps": 179570, "loss": 0.1528, "lr": 1.404466224870524e-05, "epoch": 0.28094893356351286, "percentage": 2.81, "elapsed_time": "1:06:06", "remaining_time": "1 day, 14:07:07", "throughput": 707.38, "total_tokens": 2806080} +{"current_steps": 5050, "total_steps": 179570, "loss": 0.0488, "lr": 1.4058584396057249e-05, "epoch": 0.28122737651055296, "percentage": 2.81, "elapsed_time": "1:06:10", "remaining_time": "1 day, 14:07:04", "throughput": 707.37, "total_tokens": 2808848} +{"current_steps": 5055, "total_steps": 179570, "loss": 0.0666, "lr": 1.4072506543409255e-05, "epoch": 0.2815058194575931, "percentage": 2.82, "elapsed_time": "1:06:14", "remaining_time": "1 day, 14:06:55", "throughput": 707.38, "total_tokens": 2811536} +{"current_steps": 5060, "total_steps": 179570, "loss": 0.461, "lr": 1.4086428690761263e-05, "epoch": 0.2817842624046333, "percentage": 2.82, "elapsed_time": "1:06:18", "remaining_time": "1 day, 14:06:45", "throughput": 707.36, "total_tokens": 2814096} +{"current_steps": 5065, "total_steps": 179570, "loss": 0.1169, "lr": 1.4100350838113271e-05, "epoch": 0.28206270535167344, "percentage": 2.82, "elapsed_time": "1:06:22", "remaining_time": "1 day, 14:06:36", "throughput": 707.37, "total_tokens": 2816832} +{"current_steps": 5070, "total_steps": 179570, "loss": 0.1352, "lr": 1.411427298546528e-05, "epoch": 0.2823411482987136, "percentage": 2.82, "elapsed_time": "1:06:25", "remaining_time": "1 day, 14:06:29", "throughput": 707.36, "total_tokens": 2819520} +{"current_steps": 5075, "total_steps": 179570, "loss": 0.2331, "lr": 1.4128195132817288e-05, "epoch": 0.28261959124575375, "percentage": 2.83, "elapsed_time": "1:06:29", "remaining_time": "1 day, 14:06:22", "throughput": 707.33, "total_tokens": 2822128} +{"current_steps": 5080, "total_steps": 179570, "loss": 0.2731, "lr": 1.4142117280169294e-05, "epoch": 0.2828980341927939, "percentage": 2.83, "elapsed_time": "1:06:33", "remaining_time": "1 day, 14:06:25", "throughput": 707.32, "total_tokens": 2825008} +{"current_steps": 5085, "total_steps": 179570, "loss": 0.1101, "lr": 1.4156039427521301e-05, "epoch": 0.28317647713983407, "percentage": 2.83, "elapsed_time": "1:06:38", "remaining_time": "1 day, 14:06:35", "throughput": 707.32, "total_tokens": 2828048} +{"current_steps": 5090, "total_steps": 179570, "loss": 0.3783, "lr": 1.4169961574873308e-05, "epoch": 0.2834549200868742, "percentage": 2.83, "elapsed_time": "1:06:41", "remaining_time": "1 day, 14:06:15", "throughput": 707.31, "total_tokens": 2830464} +{"current_steps": 5095, "total_steps": 179570, "loss": 0.28, "lr": 1.4183883722225316e-05, "epoch": 0.28373336303391433, "percentage": 2.84, "elapsed_time": "1:06:45", "remaining_time": "1 day, 14:06:14", "throughput": 707.3, "total_tokens": 2833264} +{"current_steps": 5100, "total_steps": 179570, "loss": 0.0042, "lr": 1.4197805869577324e-05, "epoch": 0.2840118059809545, "percentage": 2.84, "elapsed_time": "1:06:50", "remaining_time": "1 day, 14:06:24", "throughput": 707.28, "total_tokens": 2836256} +{"current_steps": 5105, "total_steps": 179570, "loss": 0.3816, "lr": 1.4211728016929332e-05, "epoch": 0.28429024892799465, "percentage": 2.84, "elapsed_time": "1:06:54", "remaining_time": "1 day, 14:06:25", "throughput": 707.31, "total_tokens": 2839248} +{"current_steps": 5110, "total_steps": 179570, "loss": 0.1172, "lr": 1.422565016428134e-05, "epoch": 0.2845686918750348, "percentage": 2.85, "elapsed_time": "1:06:58", "remaining_time": "1 day, 14:06:18", "throughput": 707.27, "total_tokens": 2841840} +{"current_steps": 5115, "total_steps": 179570, "loss": 0.121, "lr": 1.4239572311633349e-05, "epoch": 0.28484713482207497, "percentage": 2.85, "elapsed_time": "1:07:02", "remaining_time": "1 day, 14:06:23", "throughput": 707.27, "total_tokens": 2844800} +{"current_steps": 5120, "total_steps": 179570, "loss": 0.015, "lr": 1.4253494458985355e-05, "epoch": 0.2851255777691151, "percentage": 2.85, "elapsed_time": "1:07:06", "remaining_time": "1 day, 14:06:39", "throughput": 707.27, "total_tokens": 2847952} +{"current_steps": 5125, "total_steps": 179570, "loss": 0.3393, "lr": 1.4267416606337362e-05, "epoch": 0.2854040207161553, "percentage": 2.85, "elapsed_time": "1:07:10", "remaining_time": "1 day, 14:06:32", "throughput": 707.27, "total_tokens": 2850704} +{"current_steps": 5130, "total_steps": 179570, "loss": 0.0702, "lr": 1.4281338753689368e-05, "epoch": 0.2856824636631954, "percentage": 2.86, "elapsed_time": "1:07:14", "remaining_time": "1 day, 14:06:36", "throughput": 707.29, "total_tokens": 2853696} +{"current_steps": 5135, "total_steps": 179570, "loss": 0.143, "lr": 1.4295260901041376e-05, "epoch": 0.28596090661023554, "percentage": 2.86, "elapsed_time": "1:07:18", "remaining_time": "1 day, 14:06:36", "throughput": 707.29, "total_tokens": 2856592} +{"current_steps": 5140, "total_steps": 179570, "loss": 0.2163, "lr": 1.4309183048393385e-05, "epoch": 0.2862393495572757, "percentage": 2.86, "elapsed_time": "1:07:22", "remaining_time": "1 day, 14:06:36", "throughput": 707.32, "total_tokens": 2859568} +{"current_steps": 5145, "total_steps": 179570, "loss": 0.6511, "lr": 1.4323105195745393e-05, "epoch": 0.28651779250431586, "percentage": 2.87, "elapsed_time": "1:07:26", "remaining_time": "1 day, 14:06:35", "throughput": 707.31, "total_tokens": 2862400} +{"current_steps": 5150, "total_steps": 179570, "loss": 0.3117, "lr": 1.4337027343097401e-05, "epoch": 0.286796235451356, "percentage": 2.87, "elapsed_time": "1:07:30", "remaining_time": "1 day, 14:06:33", "throughput": 707.32, "total_tokens": 2865232} +{"current_steps": 5155, "total_steps": 179570, "loss": 0.1154, "lr": 1.435094949044941e-05, "epoch": 0.2870746783983962, "percentage": 2.87, "elapsed_time": "1:07:34", "remaining_time": "1 day, 14:06:31", "throughput": 707.34, "total_tokens": 2868128} +{"current_steps": 5160, "total_steps": 179570, "loss": 0.2216, "lr": 1.4364871637801416e-05, "epoch": 0.28735312134543634, "percentage": 2.87, "elapsed_time": "1:07:38", "remaining_time": "1 day, 14:06:21", "throughput": 707.32, "total_tokens": 2870720} +{"current_steps": 5165, "total_steps": 179570, "loss": 0.2031, "lr": 1.4378793785153422e-05, "epoch": 0.2876315642924765, "percentage": 2.88, "elapsed_time": "1:07:42", "remaining_time": "1 day, 14:06:13", "throughput": 707.35, "total_tokens": 2873552} +{"current_steps": 5170, "total_steps": 179570, "loss": 0.1469, "lr": 1.4392715932505429e-05, "epoch": 0.2879100072395166, "percentage": 2.88, "elapsed_time": "1:07:46", "remaining_time": "1 day, 14:06:11", "throughput": 707.35, "total_tokens": 2876368} +{"current_steps": 5175, "total_steps": 179570, "loss": 0.2423, "lr": 1.4406638079857437e-05, "epoch": 0.28818845018655675, "percentage": 2.88, "elapsed_time": "1:07:50", "remaining_time": "1 day, 14:06:05", "throughput": 707.33, "total_tokens": 2879008} +{"current_steps": 5180, "total_steps": 179570, "loss": 0.0537, "lr": 1.4420560227209445e-05, "epoch": 0.2884668931335969, "percentage": 2.88, "elapsed_time": "1:07:53", "remaining_time": "1 day, 14:05:48", "throughput": 707.3, "total_tokens": 2881376} +{"current_steps": 5185, "total_steps": 179570, "loss": 0.1626, "lr": 1.4434482374561454e-05, "epoch": 0.28874533608063707, "percentage": 2.89, "elapsed_time": "1:07:57", "remaining_time": "1 day, 14:05:46", "throughput": 707.31, "total_tokens": 2884240} +{"current_steps": 5190, "total_steps": 179570, "loss": 0.0098, "lr": 1.4448404521913462e-05, "epoch": 0.28902377902767723, "percentage": 2.89, "elapsed_time": "1:08:01", "remaining_time": "1 day, 14:05:43", "throughput": 707.3, "total_tokens": 2886992} +{"current_steps": 5195, "total_steps": 179570, "loss": 0.1062, "lr": 1.4462326669265468e-05, "epoch": 0.2893022219747174, "percentage": 2.89, "elapsed_time": "1:08:05", "remaining_time": "1 day, 14:05:46", "throughput": 707.3, "total_tokens": 2889952} +{"current_steps": 5200, "total_steps": 179570, "loss": 0.0104, "lr": 1.4476248816617476e-05, "epoch": 0.28958066492175755, "percentage": 2.9, "elapsed_time": "1:08:09", "remaining_time": "1 day, 14:05:44", "throughput": 707.34, "total_tokens": 2892944} +{"current_steps": 5205, "total_steps": 179570, "loss": 0.0221, "lr": 1.4490170963969481e-05, "epoch": 0.2898591078687977, "percentage": 2.9, "elapsed_time": "1:08:13", "remaining_time": "1 day, 14:05:44", "throughput": 707.34, "total_tokens": 2895808} +{"current_steps": 5210, "total_steps": 179570, "loss": 0.0131, "lr": 1.450409311132149e-05, "epoch": 0.2901375508158378, "percentage": 2.9, "elapsed_time": "1:08:17", "remaining_time": "1 day, 14:05:44", "throughput": 707.35, "total_tokens": 2898720} +{"current_steps": 5215, "total_steps": 179570, "loss": 0.0634, "lr": 1.4518015258673498e-05, "epoch": 0.29041599376287797, "percentage": 2.9, "elapsed_time": "1:08:22", "remaining_time": "1 day, 14:05:47", "throughput": 707.35, "total_tokens": 2901632} +{"current_steps": 5220, "total_steps": 179570, "loss": 0.0028, "lr": 1.4531937406025506e-05, "epoch": 0.2906944367099181, "percentage": 2.91, "elapsed_time": "1:08:25", "remaining_time": "1 day, 14:05:35", "throughput": 707.35, "total_tokens": 2904256} +{"current_steps": 5225, "total_steps": 179570, "loss": 0.3734, "lr": 1.4545859553377514e-05, "epoch": 0.2909728796569583, "percentage": 2.91, "elapsed_time": "1:08:29", "remaining_time": "1 day, 14:05:24", "throughput": 707.36, "total_tokens": 2906912} +{"current_steps": 5230, "total_steps": 179570, "loss": 0.0818, "lr": 1.4559781700729522e-05, "epoch": 0.29125132260399844, "percentage": 2.91, "elapsed_time": "1:08:33", "remaining_time": "1 day, 14:05:20", "throughput": 707.35, "total_tokens": 2909664} +{"current_steps": 5235, "total_steps": 179570, "loss": 0.1988, "lr": 1.4573703848081529e-05, "epoch": 0.2915297655510386, "percentage": 2.92, "elapsed_time": "1:08:37", "remaining_time": "1 day, 14:05:20", "throughput": 707.35, "total_tokens": 2912528} +{"current_steps": 5240, "total_steps": 179570, "loss": 0.2492, "lr": 1.4587625995433537e-05, "epoch": 0.29180820849807876, "percentage": 2.92, "elapsed_time": "1:08:40", "remaining_time": "1 day, 14:04:58", "throughput": 707.32, "total_tokens": 2914800} +{"current_steps": 5245, "total_steps": 179570, "loss": 0.0308, "lr": 1.4601548142785542e-05, "epoch": 0.2920866514451189, "percentage": 2.92, "elapsed_time": "1:08:44", "remaining_time": "1 day, 14:04:50", "throughput": 707.35, "total_tokens": 2917632} +{"current_steps": 5250, "total_steps": 179570, "loss": 0.135, "lr": 1.461547029013755e-05, "epoch": 0.292365094392159, "percentage": 2.92, "elapsed_time": "1:08:48", "remaining_time": "1 day, 14:04:50", "throughput": 707.36, "total_tokens": 2920528} +{"current_steps": 5255, "total_steps": 179570, "loss": 0.111, "lr": 1.4629392437489558e-05, "epoch": 0.2926435373391992, "percentage": 2.93, "elapsed_time": "1:08:52", "remaining_time": "1 day, 14:04:55", "throughput": 707.38, "total_tokens": 2923568} +{"current_steps": 5260, "total_steps": 179570, "loss": 0.0475, "lr": 1.4643314584841567e-05, "epoch": 0.29292198028623934, "percentage": 2.93, "elapsed_time": "1:08:56", "remaining_time": "1 day, 14:04:53", "throughput": 707.39, "total_tokens": 2926432} +{"current_steps": 5265, "total_steps": 179570, "loss": 0.256, "lr": 1.4657236732193575e-05, "epoch": 0.2932004232332795, "percentage": 2.93, "elapsed_time": "1:09:01", "remaining_time": "1 day, 14:04:53", "throughput": 707.4, "total_tokens": 2929344} +{"current_steps": 5270, "total_steps": 179570, "loss": 0.4761, "lr": 1.4671158879545583e-05, "epoch": 0.29347886618031965, "percentage": 2.93, "elapsed_time": "1:09:04", "remaining_time": "1 day, 14:04:49", "throughput": 707.39, "total_tokens": 2932080} +{"current_steps": 5275, "total_steps": 179570, "loss": 0.0562, "lr": 1.468508102689759e-05, "epoch": 0.2937573091273598, "percentage": 2.94, "elapsed_time": "1:09:09", "remaining_time": "1 day, 14:04:51", "throughput": 707.39, "total_tokens": 2935008} +{"current_steps": 5280, "total_steps": 179570, "loss": 0.1054, "lr": 1.4699003174249598e-05, "epoch": 0.29403575207439997, "percentage": 2.94, "elapsed_time": "1:09:12", "remaining_time": "1 day, 14:04:38", "throughput": 707.39, "total_tokens": 2937568} +{"current_steps": 5285, "total_steps": 179570, "loss": 0.6048, "lr": 1.4712925321601603e-05, "epoch": 0.29431419502144013, "percentage": 2.94, "elapsed_time": "1:09:16", "remaining_time": "1 day, 14:04:29", "throughput": 707.36, "total_tokens": 2940144} +{"current_steps": 5290, "total_steps": 179570, "loss": 0.2314, "lr": 1.4726847468953611e-05, "epoch": 0.29459263796848023, "percentage": 2.95, "elapsed_time": "1:09:20", "remaining_time": "1 day, 14:04:20", "throughput": 707.37, "total_tokens": 2942816} +{"current_steps": 5295, "total_steps": 179570, "loss": 0.1533, "lr": 1.4740769616305619e-05, "epoch": 0.2948710809155204, "percentage": 2.95, "elapsed_time": "1:09:24", "remaining_time": "1 day, 14:04:14", "throughput": 707.38, "total_tokens": 2945600} +{"current_steps": 5300, "total_steps": 179570, "loss": 0.035, "lr": 1.4754691763657627e-05, "epoch": 0.29514952386256055, "percentage": 2.95, "elapsed_time": "1:09:28", "remaining_time": "1 day, 14:04:12", "throughput": 707.41, "total_tokens": 2948560} +{"current_steps": 5305, "total_steps": 179570, "loss": 0.2398, "lr": 1.4768613911009636e-05, "epoch": 0.2954279668096007, "percentage": 2.95, "elapsed_time": "1:09:31", "remaining_time": "1 day, 14:04:03", "throughput": 707.41, "total_tokens": 2951248} +{"current_steps": 5310, "total_steps": 179570, "loss": 0.4273, "lr": 1.4782536058361644e-05, "epoch": 0.29570640975664086, "percentage": 2.96, "elapsed_time": "1:09:35", "remaining_time": "1 day, 14:03:54", "throughput": 707.42, "total_tokens": 2953936} +{"current_steps": 5315, "total_steps": 179570, "loss": 0.2298, "lr": 1.479645820571365e-05, "epoch": 0.295984852703681, "percentage": 2.96, "elapsed_time": "1:09:39", "remaining_time": "1 day, 14:03:54", "throughput": 707.42, "total_tokens": 2956832} +{"current_steps": 5320, "total_steps": 179570, "loss": 0.1254, "lr": 1.4810380353065658e-05, "epoch": 0.2962632956507212, "percentage": 2.96, "elapsed_time": "1:09:43", "remaining_time": "1 day, 14:03:44", "throughput": 707.41, "total_tokens": 2959440} +{"current_steps": 5325, "total_steps": 179570, "loss": 0.0423, "lr": 1.4824302500417663e-05, "epoch": 0.29654173859776134, "percentage": 2.97, "elapsed_time": "1:09:47", "remaining_time": "1 day, 14:03:49", "throughput": 707.42, "total_tokens": 2962448} +{"current_steps": 5330, "total_steps": 179570, "loss": 0.4715, "lr": 1.4838224647769672e-05, "epoch": 0.29682018154480144, "percentage": 2.97, "elapsed_time": "1:09:51", "remaining_time": "1 day, 14:03:27", "throughput": 707.4, "total_tokens": 2964736} +{"current_steps": 5335, "total_steps": 179570, "loss": 0.5734, "lr": 1.485214679512168e-05, "epoch": 0.2970986244918416, "percentage": 2.97, "elapsed_time": "1:09:54", "remaining_time": "1 day, 14:03:18", "throughput": 707.41, "total_tokens": 2967472} +{"current_steps": 5340, "total_steps": 179570, "loss": 0.1804, "lr": 1.4866068942473688e-05, "epoch": 0.29737706743888176, "percentage": 2.97, "elapsed_time": "1:09:58", "remaining_time": "1 day, 14:03:19", "throughput": 707.44, "total_tokens": 2970464} +{"current_steps": 5345, "total_steps": 179570, "loss": 0.047, "lr": 1.4879991089825696e-05, "epoch": 0.2976555103859219, "percentage": 2.98, "elapsed_time": "1:10:02", "remaining_time": "1 day, 14:03:08", "throughput": 707.43, "total_tokens": 2973072} +{"current_steps": 5350, "total_steps": 179570, "loss": 0.1055, "lr": 1.4893913237177703e-05, "epoch": 0.2979339533329621, "percentage": 2.98, "elapsed_time": "1:10:06", "remaining_time": "1 day, 14:03:06", "throughput": 707.47, "total_tokens": 2976048} +{"current_steps": 5355, "total_steps": 179570, "loss": 0.3503, "lr": 1.4907835384529711e-05, "epoch": 0.29821239628000223, "percentage": 2.98, "elapsed_time": "1:10:10", "remaining_time": "1 day, 14:02:59", "throughput": 707.45, "total_tokens": 2978688} +{"current_steps": 5360, "total_steps": 179570, "loss": 0.0796, "lr": 1.492175753188172e-05, "epoch": 0.2984908392270424, "percentage": 2.98, "elapsed_time": "1:10:14", "remaining_time": "1 day, 14:03:04", "throughput": 707.45, "total_tokens": 2981680} +{"current_steps": 5365, "total_steps": 179570, "loss": 0.2874, "lr": 1.4935679679233724e-05, "epoch": 0.29876928217408255, "percentage": 2.99, "elapsed_time": "1:10:18", "remaining_time": "1 day, 14:02:50", "throughput": 707.43, "total_tokens": 2984144} +{"current_steps": 5370, "total_steps": 179570, "loss": 0.0007, "lr": 1.4949601826585732e-05, "epoch": 0.2990477251211227, "percentage": 2.99, "elapsed_time": "1:10:22", "remaining_time": "1 day, 14:02:55", "throughput": 707.42, "total_tokens": 2987088} +{"current_steps": 5375, "total_steps": 179570, "loss": 0.0334, "lr": 1.496352397393774e-05, "epoch": 0.2993261680681628, "percentage": 2.99, "elapsed_time": "1:10:26", "remaining_time": "1 day, 14:02:48", "throughput": 707.41, "total_tokens": 2989744} +{"current_steps": 5380, "total_steps": 179570, "loss": 0.4641, "lr": 1.4977446121289749e-05, "epoch": 0.29960461101520297, "percentage": 3.0, "elapsed_time": "1:10:30", "remaining_time": "1 day, 14:02:46", "throughput": 707.44, "total_tokens": 2992688} +{"current_steps": 5385, "total_steps": 179570, "loss": 0.0313, "lr": 1.4991368268641757e-05, "epoch": 0.29988305396224313, "percentage": 3.0, "elapsed_time": "1:10:34", "remaining_time": "1 day, 14:02:46", "throughput": 707.44, "total_tokens": 2995584} +{"current_steps": 5390, "total_steps": 179570, "loss": 0.1926, "lr": 1.5005290415993763e-05, "epoch": 0.3001614969092833, "percentage": 3.0, "elapsed_time": "1:10:38", "remaining_time": "1 day, 14:02:39", "throughput": 707.42, "total_tokens": 2998192} +{"current_steps": 5395, "total_steps": 179570, "loss": 0.499, "lr": 1.5019212563345772e-05, "epoch": 0.30043993985632345, "percentage": 3.0, "elapsed_time": "1:10:41", "remaining_time": "1 day, 14:02:29", "throughput": 707.4, "total_tokens": 3000768} +{"current_steps": 5400, "total_steps": 179570, "loss": 0.2083, "lr": 1.503313471069778e-05, "epoch": 0.3007183828033636, "percentage": 3.01, "elapsed_time": "1:10:45", "remaining_time": "1 day, 14:02:28", "throughput": 707.42, "total_tokens": 3003664} +{"current_steps": 5405, "total_steps": 179570, "loss": 0.3221, "lr": 1.5047056858049785e-05, "epoch": 0.30099682575040376, "percentage": 3.01, "elapsed_time": "1:10:50", "remaining_time": "1 day, 14:02:33", "throughput": 707.44, "total_tokens": 3006752} +{"current_steps": 5410, "total_steps": 179570, "loss": 0.0733, "lr": 1.5060979005401793e-05, "epoch": 0.3012752686974439, "percentage": 3.01, "elapsed_time": "1:10:54", "remaining_time": "1 day, 14:02:38", "throughput": 707.45, "total_tokens": 3009760} +{"current_steps": 5415, "total_steps": 179570, "loss": 0.0216, "lr": 1.5074901152753801e-05, "epoch": 0.301553711644484, "percentage": 3.02, "elapsed_time": "1:10:58", "remaining_time": "1 day, 14:02:34", "throughput": 707.44, "total_tokens": 3012512} +{"current_steps": 5420, "total_steps": 179570, "loss": 0.1412, "lr": 1.508882330010581e-05, "epoch": 0.3018321545915242, "percentage": 3.02, "elapsed_time": "1:11:02", "remaining_time": "1 day, 14:02:25", "throughput": 707.45, "total_tokens": 3015232} +{"current_steps": 5425, "total_steps": 179570, "loss": 0.0219, "lr": 1.5102745447457818e-05, "epoch": 0.30211059753856434, "percentage": 3.02, "elapsed_time": "1:11:05", "remaining_time": "1 day, 14:02:19", "throughput": 707.45, "total_tokens": 3017936} +{"current_steps": 5430, "total_steps": 179570, "loss": 0.122, "lr": 1.5116667594809824e-05, "epoch": 0.3023890404856045, "percentage": 3.02, "elapsed_time": "1:11:09", "remaining_time": "1 day, 14:02:15", "throughput": 707.45, "total_tokens": 3020736} +{"current_steps": 5435, "total_steps": 179570, "loss": 0.1786, "lr": 1.5130589742161832e-05, "epoch": 0.30266748343264466, "percentage": 3.03, "elapsed_time": "1:11:13", "remaining_time": "1 day, 14:02:01", "throughput": 707.43, "total_tokens": 3023200} +{"current_steps": 5440, "total_steps": 179570, "loss": 0.0766, "lr": 1.514451188951384e-05, "epoch": 0.3029459263796848, "percentage": 3.03, "elapsed_time": "1:11:17", "remaining_time": "1 day, 14:01:54", "throughput": 707.42, "total_tokens": 3025888} +{"current_steps": 5445, "total_steps": 179570, "loss": 0.5595, "lr": 1.5158434036865845e-05, "epoch": 0.303224369326725, "percentage": 3.03, "elapsed_time": "1:11:21", "remaining_time": "1 day, 14:01:45", "throughput": 707.4, "total_tokens": 3028480} +{"current_steps": 5450, "total_steps": 179570, "loss": 0.0941, "lr": 1.5172356184217854e-05, "epoch": 0.30350281227376513, "percentage": 3.04, "elapsed_time": "1:11:25", "remaining_time": "1 day, 14:01:41", "throughput": 707.39, "total_tokens": 3031216} +{"current_steps": 5455, "total_steps": 179570, "loss": 0.0627, "lr": 1.5186278331569862e-05, "epoch": 0.30378125522080524, "percentage": 3.04, "elapsed_time": "1:11:29", "remaining_time": "1 day, 14:01:38", "throughput": 707.38, "total_tokens": 3033968} +{"current_steps": 5460, "total_steps": 179570, "loss": 0.2782, "lr": 1.520020047892187e-05, "epoch": 0.3040596981678454, "percentage": 3.04, "elapsed_time": "1:11:33", "remaining_time": "1 day, 14:01:39", "throughput": 707.42, "total_tokens": 3037008} +{"current_steps": 5465, "total_steps": 179570, "loss": 0.1227, "lr": 1.5214122626273877e-05, "epoch": 0.30433814111488555, "percentage": 3.04, "elapsed_time": "1:11:37", "remaining_time": "1 day, 14:01:39", "throughput": 707.41, "total_tokens": 3039856} +{"current_steps": 5470, "total_steps": 179570, "loss": 0.4562, "lr": 1.5228044773625885e-05, "epoch": 0.3046165840619257, "percentage": 3.05, "elapsed_time": "1:11:40", "remaining_time": "1 day, 14:01:19", "throughput": 707.38, "total_tokens": 3042160} +{"current_steps": 5475, "total_steps": 179570, "loss": 0.4174, "lr": 1.5241966920977893e-05, "epoch": 0.30489502700896587, "percentage": 3.05, "elapsed_time": "1:11:44", "remaining_time": "1 day, 14:01:06", "throughput": 707.37, "total_tokens": 3044656} +{"current_steps": 5480, "total_steps": 179570, "loss": 0.5927, "lr": 1.5255889068329901e-05, "epoch": 0.305173469956006, "percentage": 3.05, "elapsed_time": "1:11:48", "remaining_time": "1 day, 14:01:11", "throughput": 707.39, "total_tokens": 3047760} +{"current_steps": 5485, "total_steps": 179570, "loss": 0.6154, "lr": 1.5269811215681908e-05, "epoch": 0.3054519129030462, "percentage": 3.05, "elapsed_time": "1:11:51", "remaining_time": "1 day, 14:00:53", "throughput": 707.37, "total_tokens": 3050112} +{"current_steps": 5490, "total_steps": 179570, "loss": 0.5359, "lr": 1.5283733363033914e-05, "epoch": 0.30573035585008634, "percentage": 3.06, "elapsed_time": "1:11:55", "remaining_time": "1 day, 14:00:45", "throughput": 707.38, "total_tokens": 3052848} +{"current_steps": 5495, "total_steps": 179570, "loss": 0.2469, "lr": 1.529765551038592e-05, "epoch": 0.30600879879712645, "percentage": 3.06, "elapsed_time": "1:11:59", "remaining_time": "1 day, 14:00:36", "throughput": 707.39, "total_tokens": 3055552} +{"current_steps": 5500, "total_steps": 179570, "loss": 0.2703, "lr": 1.531157765773793e-05, "epoch": 0.3062872417441666, "percentage": 3.06, "elapsed_time": "1:12:02", "remaining_time": "1 day, 14:00:18", "throughput": 707.38, "total_tokens": 3058000} +{"current_steps": 5505, "total_steps": 179570, "loss": 0.0019, "lr": 1.5325499805089937e-05, "epoch": 0.30656568469120676, "percentage": 3.07, "elapsed_time": "1:12:07", "remaining_time": "1 day, 14:00:28", "throughput": 707.4, "total_tokens": 3061184} +{"current_steps": 5510, "total_steps": 179570, "loss": 0.0294, "lr": 1.5339421952441947e-05, "epoch": 0.3068441276382469, "percentage": 3.07, "elapsed_time": "1:12:11", "remaining_time": "1 day, 14:00:38", "throughput": 707.4, "total_tokens": 3064272} +{"current_steps": 5515, "total_steps": 179570, "loss": 0.3875, "lr": 1.5353344099793954e-05, "epoch": 0.3071225705852871, "percentage": 3.07, "elapsed_time": "1:12:15", "remaining_time": "1 day, 14:00:39", "throughput": 707.42, "total_tokens": 3067232} +{"current_steps": 5520, "total_steps": 179570, "loss": 0.211, "lr": 1.536726624714596e-05, "epoch": 0.30740101353232724, "percentage": 3.07, "elapsed_time": "1:12:19", "remaining_time": "1 day, 14:00:22", "throughput": 707.41, "total_tokens": 3069696} +{"current_steps": 5525, "total_steps": 179570, "loss": 0.2255, "lr": 1.5381188394497967e-05, "epoch": 0.3076794564793674, "percentage": 3.08, "elapsed_time": "1:12:23", "remaining_time": "1 day, 14:00:19", "throughput": 707.39, "total_tokens": 3072400} +{"current_steps": 5530, "total_steps": 179570, "loss": 0.022, "lr": 1.5395110541849973e-05, "epoch": 0.30795789942640756, "percentage": 3.08, "elapsed_time": "1:12:27", "remaining_time": "1 day, 14:00:24", "throughput": 707.4, "total_tokens": 3075408} +{"current_steps": 5535, "total_steps": 179570, "loss": 0.1925, "lr": 1.5409032689201983e-05, "epoch": 0.30823634237344766, "percentage": 3.08, "elapsed_time": "1:12:31", "remaining_time": "1 day, 14:00:16", "throughput": 707.36, "total_tokens": 3077936} +{"current_steps": 5540, "total_steps": 179570, "loss": 0.4943, "lr": 1.542295483655399e-05, "epoch": 0.3085147853204878, "percentage": 3.09, "elapsed_time": "1:12:35", "remaining_time": "1 day, 14:00:08", "throughput": 707.33, "total_tokens": 3080512} +{"current_steps": 5545, "total_steps": 179570, "loss": 0.0467, "lr": 1.5436876983906e-05, "epoch": 0.308793228267528, "percentage": 3.09, "elapsed_time": "1:12:39", "remaining_time": "1 day, 14:00:08", "throughput": 707.35, "total_tokens": 3083424} +{"current_steps": 5550, "total_steps": 179570, "loss": 0.148, "lr": 1.5450799131258006e-05, "epoch": 0.30907167121456813, "percentage": 3.09, "elapsed_time": "1:12:43", "remaining_time": "1 day, 14:00:10", "throughput": 707.35, "total_tokens": 3086368} +{"current_steps": 5555, "total_steps": 179570, "loss": 0.0211, "lr": 1.5464721278610013e-05, "epoch": 0.3093501141616083, "percentage": 3.09, "elapsed_time": "1:12:47", "remaining_time": "1 day, 14:00:10", "throughput": 707.38, "total_tokens": 3089376} +{"current_steps": 5560, "total_steps": 179570, "loss": 0.1822, "lr": 1.5478643425962023e-05, "epoch": 0.30962855710864845, "percentage": 3.1, "elapsed_time": "1:12:51", "remaining_time": "1 day, 14:00:14", "throughput": 707.37, "total_tokens": 3092288} +{"current_steps": 5565, "total_steps": 179570, "loss": 0.1945, "lr": 1.5492565573314026e-05, "epoch": 0.3099070000556886, "percentage": 3.1, "elapsed_time": "1:12:55", "remaining_time": "1 day, 14:00:03", "throughput": 707.35, "total_tokens": 3094800} +{"current_steps": 5570, "total_steps": 179570, "loss": 0.2475, "lr": 1.5506487720666036e-05, "epoch": 0.31018544300272877, "percentage": 3.1, "elapsed_time": "1:12:59", "remaining_time": "1 day, 13:59:54", "throughput": 707.37, "total_tokens": 3097584} +{"current_steps": 5575, "total_steps": 179570, "loss": 0.2784, "lr": 1.5520409868018042e-05, "epoch": 0.31046388594976887, "percentage": 3.1, "elapsed_time": "1:13:03", "remaining_time": "1 day, 13:59:55", "throughput": 707.39, "total_tokens": 3100528} +{"current_steps": 5580, "total_steps": 179570, "loss": 0.3391, "lr": 1.5534332015370052e-05, "epoch": 0.31074232889680903, "percentage": 3.11, "elapsed_time": "1:13:07", "remaining_time": "1 day, 13:59:57", "throughput": 707.39, "total_tokens": 3103440} +{"current_steps": 5585, "total_steps": 179570, "loss": 0.0111, "lr": 1.554825416272206e-05, "epoch": 0.3110207718438492, "percentage": 3.11, "elapsed_time": "1:13:11", "remaining_time": "1 day, 13:59:57", "throughput": 707.42, "total_tokens": 3106464} +{"current_steps": 5590, "total_steps": 179570, "loss": 0.0011, "lr": 1.556217631007407e-05, "epoch": 0.31129921479088934, "percentage": 3.11, "elapsed_time": "1:13:15", "remaining_time": "1 day, 14:00:02", "throughput": 707.44, "total_tokens": 3109568} +{"current_steps": 5595, "total_steps": 179570, "loss": 0.5245, "lr": 1.5576098457426075e-05, "epoch": 0.3115776577379295, "percentage": 3.12, "elapsed_time": "1:13:19", "remaining_time": "1 day, 13:59:54", "throughput": 707.46, "total_tokens": 3112304} +{"current_steps": 5600, "total_steps": 179570, "loss": 0.0666, "lr": 1.559002060477808e-05, "epoch": 0.31185610068496966, "percentage": 3.12, "elapsed_time": "1:13:23", "remaining_time": "1 day, 13:59:59", "throughput": 707.47, "total_tokens": 3115360} +{"current_steps": 5605, "total_steps": 179570, "loss": 0.3244, "lr": 1.5603942752130088e-05, "epoch": 0.3121345436320098, "percentage": 3.12, "elapsed_time": "1:13:27", "remaining_time": "1 day, 13:59:48", "throughput": 707.46, "total_tokens": 3117920} +{"current_steps": 5610, "total_steps": 179570, "loss": 0.3515, "lr": 1.5617864899482095e-05, "epoch": 0.31241298657905, "percentage": 3.12, "elapsed_time": "1:13:31", "remaining_time": "1 day, 13:59:43", "throughput": 707.45, "total_tokens": 3120624} +{"current_steps": 5615, "total_steps": 179570, "loss": 0.1628, "lr": 1.5631787046834104e-05, "epoch": 0.3126914295260901, "percentage": 3.13, "elapsed_time": "1:13:35", "remaining_time": "1 day, 13:59:48", "throughput": 707.48, "total_tokens": 3123728} +{"current_steps": 5620, "total_steps": 179570, "loss": 0.1063, "lr": 1.564570919418611e-05, "epoch": 0.31296987247313024, "percentage": 3.13, "elapsed_time": "1:13:39", "remaining_time": "1 day, 13:59:45", "throughput": 707.48, "total_tokens": 3126560} +{"current_steps": 5625, "total_steps": 179570, "loss": 0.1669, "lr": 1.565963134153812e-05, "epoch": 0.3132483154201704, "percentage": 3.13, "elapsed_time": "1:13:42", "remaining_time": "1 day, 13:59:33", "throughput": 707.49, "total_tokens": 3129216} +{"current_steps": 5630, "total_steps": 179570, "loss": 0.0186, "lr": 1.5673553488890127e-05, "epoch": 0.31352675836721056, "percentage": 3.14, "elapsed_time": "1:13:46", "remaining_time": "1 day, 13:59:23", "throughput": 707.5, "total_tokens": 3131904} +{"current_steps": 5635, "total_steps": 179570, "loss": 0.0451, "lr": 1.5687475636242134e-05, "epoch": 0.3138052013142507, "percentage": 3.14, "elapsed_time": "1:13:50", "remaining_time": "1 day, 13:59:13", "throughput": 707.52, "total_tokens": 3134608} +{"current_steps": 5640, "total_steps": 179570, "loss": 0.0167, "lr": 1.5701397783594144e-05, "epoch": 0.3140836442612909, "percentage": 3.14, "elapsed_time": "1:13:54", "remaining_time": "1 day, 13:59:05", "throughput": 707.54, "total_tokens": 3137360} +{"current_steps": 5645, "total_steps": 179570, "loss": 0.0113, "lr": 1.5715319930946147e-05, "epoch": 0.31436208720833103, "percentage": 3.14, "elapsed_time": "1:13:58", "remaining_time": "1 day, 13:59:10", "throughput": 707.56, "total_tokens": 3140448} +{"current_steps": 5650, "total_steps": 179570, "loss": 0.0711, "lr": 1.5729242078298157e-05, "epoch": 0.3146405301553712, "percentage": 3.15, "elapsed_time": "1:14:02", "remaining_time": "1 day, 13:59:02", "throughput": 707.52, "total_tokens": 3142992} +{"current_steps": 5655, "total_steps": 179570, "loss": 0.2875, "lr": 1.5743164225650163e-05, "epoch": 0.3149189731024113, "percentage": 3.15, "elapsed_time": "1:14:06", "remaining_time": "1 day, 13:59:06", "throughput": 707.5, "total_tokens": 3145824} +{"current_steps": 5660, "total_steps": 179570, "loss": 0.345, "lr": 1.5757086373002173e-05, "epoch": 0.31519741604945145, "percentage": 3.15, "elapsed_time": "1:14:10", "remaining_time": "1 day, 13:59:00", "throughput": 707.48, "total_tokens": 3148496} +{"current_steps": 5665, "total_steps": 179570, "loss": 0.3596, "lr": 1.577100852035418e-05, "epoch": 0.3154758589964916, "percentage": 3.15, "elapsed_time": "1:14:14", "remaining_time": "1 day, 13:58:53", "throughput": 707.47, "total_tokens": 3151168} +{"current_steps": 5670, "total_steps": 179570, "loss": 0.077, "lr": 1.5784930667706186e-05, "epoch": 0.31575430194353177, "percentage": 3.16, "elapsed_time": "1:14:18", "remaining_time": "1 day, 13:58:53", "throughput": 707.49, "total_tokens": 3154112} +{"current_steps": 5675, "total_steps": 179570, "loss": 0.3089, "lr": 1.5798852815058196e-05, "epoch": 0.3160327448905719, "percentage": 3.16, "elapsed_time": "1:14:21", "remaining_time": "1 day, 13:58:42", "throughput": 707.48, "total_tokens": 3156688} +{"current_steps": 5680, "total_steps": 179570, "loss": 0.2155, "lr": 1.5812774962410203e-05, "epoch": 0.3163111878376121, "percentage": 3.16, "elapsed_time": "1:14:25", "remaining_time": "1 day, 13:58:42", "throughput": 707.5, "total_tokens": 3159632} +{"current_steps": 5685, "total_steps": 179570, "loss": 0.299, "lr": 1.582669710976221e-05, "epoch": 0.31658963078465224, "percentage": 3.17, "elapsed_time": "1:14:30", "remaining_time": "1 day, 13:58:56", "throughput": 707.51, "total_tokens": 3162912} +{"current_steps": 5690, "total_steps": 179570, "loss": 0.1427, "lr": 1.5840619257114216e-05, "epoch": 0.3168680737316924, "percentage": 3.17, "elapsed_time": "1:14:34", "remaining_time": "1 day, 13:58:56", "throughput": 707.54, "total_tokens": 3165936} +{"current_steps": 5695, "total_steps": 179570, "loss": 0.08, "lr": 1.5854541404466226e-05, "epoch": 0.3171465166787325, "percentage": 3.17, "elapsed_time": "1:14:38", "remaining_time": "1 day, 13:58:47", "throughput": 707.54, "total_tokens": 3168560} +{"current_steps": 5700, "total_steps": 179570, "loss": 0.1252, "lr": 1.5868463551818232e-05, "epoch": 0.31742495962577266, "percentage": 3.17, "elapsed_time": "1:14:42", "remaining_time": "1 day, 13:58:46", "throughput": 707.52, "total_tokens": 3171360} +{"current_steps": 5705, "total_steps": 179570, "loss": 0.0787, "lr": 1.5882385699170242e-05, "epoch": 0.3177034025728128, "percentage": 3.18, "elapsed_time": "1:14:46", "remaining_time": "1 day, 13:58:56", "throughput": 707.55, "total_tokens": 3174560} +{"current_steps": 5710, "total_steps": 179570, "loss": 0.1015, "lr": 1.589630784652225e-05, "epoch": 0.317981845519853, "percentage": 3.18, "elapsed_time": "1:14:50", "remaining_time": "1 day, 13:58:56", "throughput": 707.57, "total_tokens": 3177552} +{"current_steps": 5715, "total_steps": 179570, "loss": 0.4215, "lr": 1.5910229993874255e-05, "epoch": 0.31826028846689314, "percentage": 3.18, "elapsed_time": "1:14:54", "remaining_time": "1 day, 13:58:39", "throughput": 707.56, "total_tokens": 3179968} +{"current_steps": 5720, "total_steps": 179570, "loss": 0.144, "lr": 1.5924152141226265e-05, "epoch": 0.3185387314139333, "percentage": 3.19, "elapsed_time": "1:14:58", "remaining_time": "1 day, 13:58:44", "throughput": 707.58, "total_tokens": 3183040} +{"current_steps": 5725, "total_steps": 179570, "loss": 0.002, "lr": 1.5938074288578272e-05, "epoch": 0.31881717436097345, "percentage": 3.19, "elapsed_time": "1:15:02", "remaining_time": "1 day, 13:58:35", "throughput": 707.59, "total_tokens": 3185744} +{"current_steps": 5730, "total_steps": 179570, "loss": 0.1704, "lr": 1.5951996435930278e-05, "epoch": 0.3190956173080136, "percentage": 3.19, "elapsed_time": "1:15:06", "remaining_time": "1 day, 13:58:44", "throughput": 707.6, "total_tokens": 3188896} +{"current_steps": 5735, "total_steps": 179570, "loss": 0.2772, "lr": 1.5965918583282285e-05, "epoch": 0.3193740602550537, "percentage": 3.19, "elapsed_time": "1:15:10", "remaining_time": "1 day, 13:58:31", "throughput": 707.59, "total_tokens": 3191392} +{"current_steps": 5740, "total_steps": 179570, "loss": 0.7914, "lr": 1.5979840730634295e-05, "epoch": 0.3196525032020939, "percentage": 3.2, "elapsed_time": "1:15:14", "remaining_time": "1 day, 13:58:26", "throughput": 707.58, "total_tokens": 3194112} +{"current_steps": 5745, "total_steps": 179570, "loss": 0.4019, "lr": 1.59937628779863e-05, "epoch": 0.31993094614913403, "percentage": 3.2, "elapsed_time": "1:15:18", "remaining_time": "1 day, 13:58:26", "throughput": 707.6, "total_tokens": 3197104} +{"current_steps": 5750, "total_steps": 179570, "loss": 0.0165, "lr": 1.6007685025338308e-05, "epoch": 0.3202093890961742, "percentage": 3.2, "elapsed_time": "1:15:22", "remaining_time": "1 day, 13:58:26", "throughput": 707.61, "total_tokens": 3200032} +{"current_steps": 5755, "total_steps": 179570, "loss": 0.1902, "lr": 1.6021607172690318e-05, "epoch": 0.32048783204321435, "percentage": 3.2, "elapsed_time": "1:15:26", "remaining_time": "1 day, 13:58:30", "throughput": 707.61, "total_tokens": 3202992} +{"current_steps": 5760, "total_steps": 179570, "loss": 0.2189, "lr": 1.6035529320042324e-05, "epoch": 0.3207662749902545, "percentage": 3.21, "elapsed_time": "1:15:30", "remaining_time": "1 day, 13:58:20", "throughput": 707.59, "total_tokens": 3205520} +{"current_steps": 5765, "total_steps": 179570, "loss": 0.0211, "lr": 1.6049451467394334e-05, "epoch": 0.32104471793729467, "percentage": 3.21, "elapsed_time": "1:15:33", "remaining_time": "1 day, 13:58:03", "throughput": 707.56, "total_tokens": 3207872} +{"current_steps": 5770, "total_steps": 179570, "loss": 0.007, "lr": 1.6063373614746337e-05, "epoch": 0.3213231608843348, "percentage": 3.21, "elapsed_time": "1:15:37", "remaining_time": "1 day, 13:57:55", "throughput": 707.57, "total_tokens": 3210608} +{"current_steps": 5775, "total_steps": 179570, "loss": 0.5135, "lr": 1.6077295762098347e-05, "epoch": 0.3216016038313749, "percentage": 3.22, "elapsed_time": "1:15:41", "remaining_time": "1 day, 13:57:55", "throughput": 707.59, "total_tokens": 3213568} +{"current_steps": 5780, "total_steps": 179570, "loss": 0.1586, "lr": 1.6091217909450354e-05, "epoch": 0.3218800467784151, "percentage": 3.22, "elapsed_time": "1:15:45", "remaining_time": "1 day, 13:57:51", "throughput": 707.58, "total_tokens": 3216288} +{"current_steps": 5785, "total_steps": 179570, "loss": 0.1942, "lr": 1.6105140056802364e-05, "epoch": 0.32215848972545524, "percentage": 3.22, "elapsed_time": "1:15:49", "remaining_time": "1 day, 13:57:51", "throughput": 707.58, "total_tokens": 3219168} +{"current_steps": 5790, "total_steps": 179570, "loss": 0.0109, "lr": 1.611906220415437e-05, "epoch": 0.3224369326724954, "percentage": 3.22, "elapsed_time": "1:15:53", "remaining_time": "1 day, 13:57:48", "throughput": 707.59, "total_tokens": 3222016} +{"current_steps": 5795, "total_steps": 179570, "loss": 0.1772, "lr": 1.6132984351506377e-05, "epoch": 0.32271537561953556, "percentage": 3.23, "elapsed_time": "1:15:57", "remaining_time": "1 day, 13:57:49", "throughput": 707.57, "total_tokens": 3224816} +{"current_steps": 5800, "total_steps": 179570, "loss": 0.2947, "lr": 1.6146906498858387e-05, "epoch": 0.3229938185665757, "percentage": 3.23, "elapsed_time": "1:16:01", "remaining_time": "1 day, 13:57:40", "throughput": 707.57, "total_tokens": 3227488} +{"current_steps": 5805, "total_steps": 179570, "loss": 0.2075, "lr": 1.6160828646210393e-05, "epoch": 0.3232722615136159, "percentage": 3.23, "elapsed_time": "1:16:05", "remaining_time": "1 day, 13:57:31", "throughput": 707.55, "total_tokens": 3230064} +{"current_steps": 5810, "total_steps": 179570, "loss": 0.2066, "lr": 1.61747507935624e-05, "epoch": 0.32355070446065604, "percentage": 3.24, "elapsed_time": "1:16:09", "remaining_time": "1 day, 13:57:30", "throughput": 707.56, "total_tokens": 3232992} +{"current_steps": 5815, "total_steps": 179570, "loss": 0.0061, "lr": 1.6188672940914406e-05, "epoch": 0.32382914740769614, "percentage": 3.24, "elapsed_time": "1:16:13", "remaining_time": "1 day, 13:57:38", "throughput": 707.56, "total_tokens": 3236016} +{"current_steps": 5820, "total_steps": 179570, "loss": 0.2038, "lr": 1.6202595088266416e-05, "epoch": 0.3241075903547363, "percentage": 3.24, "elapsed_time": "1:16:17", "remaining_time": "1 day, 13:57:36", "throughput": 707.55, "total_tokens": 3238816} +{"current_steps": 5825, "total_steps": 179570, "loss": 0.1718, "lr": 1.6216517235618423e-05, "epoch": 0.32438603330177646, "percentage": 3.24, "elapsed_time": "1:16:21", "remaining_time": "1 day, 13:57:27", "throughput": 707.55, "total_tokens": 3241456} +{"current_steps": 5830, "total_steps": 179570, "loss": 0.3783, "lr": 1.623043938297043e-05, "epoch": 0.3246644762488166, "percentage": 3.25, "elapsed_time": "1:16:25", "remaining_time": "1 day, 13:57:18", "throughput": 707.55, "total_tokens": 3244128} +{"current_steps": 5835, "total_steps": 179570, "loss": 0.0402, "lr": 1.624436153032244e-05, "epoch": 0.32494291919585677, "percentage": 3.25, "elapsed_time": "1:16:29", "remaining_time": "1 day, 13:57:23", "throughput": 707.58, "total_tokens": 3247248} +{"current_steps": 5840, "total_steps": 179570, "loss": 0.0166, "lr": 1.6258283677674446e-05, "epoch": 0.32522136214289693, "percentage": 3.25, "elapsed_time": "1:16:33", "remaining_time": "1 day, 13:57:18", "throughput": 707.54, "total_tokens": 3249856} +{"current_steps": 5845, "total_steps": 179570, "loss": 0.0157, "lr": 1.6272205825026455e-05, "epoch": 0.3254998050899371, "percentage": 3.25, "elapsed_time": "1:16:37", "remaining_time": "1 day, 13:57:12", "throughput": 707.56, "total_tokens": 3252656} +{"current_steps": 5850, "total_steps": 179570, "loss": 0.2019, "lr": 1.628612797237846e-05, "epoch": 0.32577824803697725, "percentage": 3.26, "elapsed_time": "1:16:40", "remaining_time": "1 day, 13:57:09", "throughput": 707.56, "total_tokens": 3255456} +{"current_steps": 5855, "total_steps": 179570, "loss": 0.2561, "lr": 1.630005011973047e-05, "epoch": 0.32605669098401735, "percentage": 3.26, "elapsed_time": "1:16:44", "remaining_time": "1 day, 13:56:56", "throughput": 707.53, "total_tokens": 3257904} +{"current_steps": 5860, "total_steps": 179570, "loss": 0.3236, "lr": 1.6313972267082475e-05, "epoch": 0.3263351339310575, "percentage": 3.26, "elapsed_time": "1:16:48", "remaining_time": "1 day, 13:56:58", "throughput": 707.53, "total_tokens": 3260816} +{"current_steps": 5865, "total_steps": 179570, "loss": 0.0941, "lr": 1.632789441443448e-05, "epoch": 0.32661357687809767, "percentage": 3.27, "elapsed_time": "1:16:52", "remaining_time": "1 day, 13:56:49", "throughput": 707.52, "total_tokens": 3263424} +{"current_steps": 5870, "total_steps": 179570, "loss": 0.1728, "lr": 1.634181656178649e-05, "epoch": 0.3268920198251378, "percentage": 3.27, "elapsed_time": "1:16:56", "remaining_time": "1 day, 13:56:44", "throughput": 707.51, "total_tokens": 3266176} +{"current_steps": 5875, "total_steps": 179570, "loss": 0.1974, "lr": 1.6355738709138498e-05, "epoch": 0.327170462772178, "percentage": 3.27, "elapsed_time": "1:17:00", "remaining_time": "1 day, 13:56:43", "throughput": 707.51, "total_tokens": 3269024} +{"current_steps": 5880, "total_steps": 179570, "loss": 0.3138, "lr": 1.6369660856490508e-05, "epoch": 0.32744890571921814, "percentage": 3.27, "elapsed_time": "1:17:03", "remaining_time": "1 day, 13:56:18", "throughput": 707.49, "total_tokens": 3271168} +{"current_steps": 5885, "total_steps": 179570, "loss": 0.0202, "lr": 1.6383583003842514e-05, "epoch": 0.3277273486662583, "percentage": 3.28, "elapsed_time": "1:17:07", "remaining_time": "1 day, 13:56:09", "throughput": 707.48, "total_tokens": 3273824} +{"current_steps": 5890, "total_steps": 179570, "loss": 0.2139, "lr": 1.639750515119452e-05, "epoch": 0.32800579161329846, "percentage": 3.28, "elapsed_time": "1:17:11", "remaining_time": "1 day, 13:56:06", "throughput": 707.49, "total_tokens": 3276624} +{"current_steps": 5895, "total_steps": 179570, "loss": 0.1494, "lr": 1.6411427298546528e-05, "epoch": 0.32828423456033856, "percentage": 3.28, "elapsed_time": "1:17:15", "remaining_time": "1 day, 13:55:53", "throughput": 707.47, "total_tokens": 3279136} +{"current_steps": 5900, "total_steps": 179570, "loss": 0.526, "lr": 1.6425349445898537e-05, "epoch": 0.3285626775073787, "percentage": 3.29, "elapsed_time": "1:17:18", "remaining_time": "1 day, 13:55:50", "throughput": 707.5, "total_tokens": 3282080} +{"current_steps": 5905, "total_steps": 179570, "loss": 0.0205, "lr": 1.6439271593250544e-05, "epoch": 0.3288411204544189, "percentage": 3.29, "elapsed_time": "1:17:22", "remaining_time": "1 day, 13:55:34", "throughput": 707.49, "total_tokens": 3284512} +{"current_steps": 5910, "total_steps": 179570, "loss": 0.2474, "lr": 1.645319374060255e-05, "epoch": 0.32911956340145904, "percentage": 3.29, "elapsed_time": "1:17:26", "remaining_time": "1 day, 13:55:26", "throughput": 707.51, "total_tokens": 3287264} +{"current_steps": 5915, "total_steps": 179570, "loss": 0.2701, "lr": 1.646711588795456e-05, "epoch": 0.3293980063484992, "percentage": 3.29, "elapsed_time": "1:17:30", "remaining_time": "1 day, 13:55:17", "throughput": 707.5, "total_tokens": 3289872} +{"current_steps": 5920, "total_steps": 179570, "loss": 0.0722, "lr": 1.6481038035306567e-05, "epoch": 0.32967644929553935, "percentage": 3.3, "elapsed_time": "1:17:33", "remaining_time": "1 day, 13:55:13", "throughput": 707.5, "total_tokens": 3292656} +{"current_steps": 5925, "total_steps": 179570, "loss": 0.087, "lr": 1.6494960182658577e-05, "epoch": 0.3299548922425795, "percentage": 3.3, "elapsed_time": "1:17:37", "remaining_time": "1 day, 13:55:10", "throughput": 707.49, "total_tokens": 3295440} +{"current_steps": 5930, "total_steps": 179570, "loss": 0.5468, "lr": 1.650888233001058e-05, "epoch": 0.33023333518961967, "percentage": 3.3, "elapsed_time": "1:17:41", "remaining_time": "1 day, 13:55:10", "throughput": 707.5, "total_tokens": 3298368} +{"current_steps": 5935, "total_steps": 179570, "loss": 0.1432, "lr": 1.652280447736259e-05, "epoch": 0.3305117781366598, "percentage": 3.31, "elapsed_time": "1:17:45", "remaining_time": "1 day, 13:55:07", "throughput": 707.52, "total_tokens": 3301248} +{"current_steps": 5940, "total_steps": 179570, "loss": 0.0643, "lr": 1.6536726624714596e-05, "epoch": 0.33079022108369993, "percentage": 3.31, "elapsed_time": "1:17:50", "remaining_time": "1 day, 13:55:07", "throughput": 707.53, "total_tokens": 3304192} +{"current_steps": 5945, "total_steps": 179570, "loss": 0.2051, "lr": 1.6550648772066603e-05, "epoch": 0.3310686640307401, "percentage": 3.31, "elapsed_time": "1:17:54", "remaining_time": "1 day, 13:55:07", "throughput": 707.54, "total_tokens": 3307104} +{"current_steps": 5950, "total_steps": 179570, "loss": 0.1093, "lr": 1.6564570919418613e-05, "epoch": 0.33134710697778025, "percentage": 3.31, "elapsed_time": "1:17:58", "remaining_time": "1 day, 13:55:03", "throughput": 707.53, "total_tokens": 3309824} +{"current_steps": 5955, "total_steps": 179570, "loss": 0.5254, "lr": 1.657849306677062e-05, "epoch": 0.3316255499248204, "percentage": 3.32, "elapsed_time": "1:18:01", "remaining_time": "1 day, 13:54:51", "throughput": 707.5, "total_tokens": 3312272} +{"current_steps": 5960, "total_steps": 179570, "loss": 0.2788, "lr": 1.659241521412263e-05, "epoch": 0.33190399287186056, "percentage": 3.32, "elapsed_time": "1:18:05", "remaining_time": "1 day, 13:54:34", "throughput": 707.48, "total_tokens": 3314656} +{"current_steps": 5965, "total_steps": 179570, "loss": 0.1341, "lr": 1.6606337361474636e-05, "epoch": 0.3321824358189007, "percentage": 3.32, "elapsed_time": "1:18:09", "remaining_time": "1 day, 13:54:38", "throughput": 707.5, "total_tokens": 3317696} +{"current_steps": 5970, "total_steps": 179570, "loss": 0.3897, "lr": 1.6620259508826642e-05, "epoch": 0.3324608787659409, "percentage": 3.32, "elapsed_time": "1:18:13", "remaining_time": "1 day, 13:54:43", "throughput": 707.52, "total_tokens": 3320816} +{"current_steps": 5975, "total_steps": 179570, "loss": 0.1917, "lr": 1.663418165617865e-05, "epoch": 0.332739321712981, "percentage": 3.33, "elapsed_time": "1:18:17", "remaining_time": "1 day, 13:54:42", "throughput": 707.54, "total_tokens": 3323776} +{"current_steps": 5980, "total_steps": 179570, "loss": 0.0006, "lr": 1.6648103803530655e-05, "epoch": 0.33301776466002114, "percentage": 3.33, "elapsed_time": "1:18:21", "remaining_time": "1 day, 13:54:24", "throughput": 707.54, "total_tokens": 3326192} +{"current_steps": 5985, "total_steps": 179570, "loss": 0.0118, "lr": 1.6662025950882665e-05, "epoch": 0.3332962076070613, "percentage": 3.33, "elapsed_time": "1:18:25", "remaining_time": "1 day, 13:54:25", "throughput": 707.53, "total_tokens": 3329072} +{"current_steps": 5990, "total_steps": 179570, "loss": 0.1979, "lr": 1.6675948098234672e-05, "epoch": 0.33357465055410146, "percentage": 3.34, "elapsed_time": "1:18:28", "remaining_time": "1 day, 13:54:14", "throughput": 707.54, "total_tokens": 3331680} +{"current_steps": 5995, "total_steps": 179570, "loss": 0.1086, "lr": 1.6689870245586682e-05, "epoch": 0.3338530935011416, "percentage": 3.34, "elapsed_time": "1:18:32", "remaining_time": "1 day, 13:54:16", "throughput": 707.55, "total_tokens": 3334672} +{"current_steps": 6000, "total_steps": 179570, "loss": 0.0005, "lr": 1.6703792392938688e-05, "epoch": 0.3341315364481818, "percentage": 3.34, "elapsed_time": "1:18:37", "remaining_time": "1 day, 13:54:16", "throughput": 707.53, "total_tokens": 3337472} +{"current_steps": 6005, "total_steps": 179570, "loss": 0.0189, "lr": 1.6717714540290698e-05, "epoch": 0.33440997939522193, "percentage": 3.34, "elapsed_time": "1:18:41", "remaining_time": "1 day, 13:54:24", "throughput": 707.54, "total_tokens": 3340576} +{"current_steps": 6010, "total_steps": 179570, "loss": 0.2803, "lr": 1.67316366876427e-05, "epoch": 0.3346884223422621, "percentage": 3.35, "elapsed_time": "1:18:45", "remaining_time": "1 day, 13:54:33", "throughput": 707.56, "total_tokens": 3343760} +{"current_steps": 6015, "total_steps": 179570, "loss": 0.0007, "lr": 1.674555883499471e-05, "epoch": 0.3349668652893022, "percentage": 3.35, "elapsed_time": "1:18:49", "remaining_time": "1 day, 13:54:37", "throughput": 707.56, "total_tokens": 3346736} +{"current_steps": 6020, "total_steps": 179570, "loss": 0.1703, "lr": 1.6759480982346718e-05, "epoch": 0.33524530823634235, "percentage": 3.35, "elapsed_time": "1:18:54", "remaining_time": "1 day, 13:54:39", "throughput": 707.57, "total_tokens": 3349744} +{"current_steps": 6025, "total_steps": 179570, "loss": 0.3927, "lr": 1.6773403129698724e-05, "epoch": 0.3355237511833825, "percentage": 3.36, "elapsed_time": "1:18:58", "remaining_time": "1 day, 13:54:39", "throughput": 707.59, "total_tokens": 3352672} +{"current_steps": 6030, "total_steps": 179570, "loss": 0.1071, "lr": 1.6787325277050734e-05, "epoch": 0.33580219413042267, "percentage": 3.36, "elapsed_time": "1:19:01", "remaining_time": "1 day, 13:54:14", "throughput": 707.55, "total_tokens": 3354768} +{"current_steps": 6035, "total_steps": 179570, "loss": 0.1653, "lr": 1.680124742440274e-05, "epoch": 0.33608063707746283, "percentage": 3.36, "elapsed_time": "1:19:05", "remaining_time": "1 day, 13:54:04", "throughput": 707.55, "total_tokens": 3357408} +{"current_steps": 6040, "total_steps": 179570, "loss": 0.3117, "lr": 1.681516957175475e-05, "epoch": 0.336359080024503, "percentage": 3.36, "elapsed_time": "1:19:09", "remaining_time": "1 day, 13:54:04", "throughput": 707.56, "total_tokens": 3360336} +{"current_steps": 6045, "total_steps": 179570, "loss": 0.0437, "lr": 1.6829091719106757e-05, "epoch": 0.33663752297154315, "percentage": 3.37, "elapsed_time": "1:19:13", "remaining_time": "1 day, 13:54:01", "throughput": 707.55, "total_tokens": 3363088} +{"current_steps": 6050, "total_steps": 179570, "loss": 0.1162, "lr": 1.6843013866458764e-05, "epoch": 0.3369159659185833, "percentage": 3.37, "elapsed_time": "1:19:17", "remaining_time": "1 day, 13:54:05", "throughput": 707.56, "total_tokens": 3366112} +{"current_steps": 6055, "total_steps": 179570, "loss": 0.8107, "lr": 1.685693601381077e-05, "epoch": 0.3371944088656234, "percentage": 3.37, "elapsed_time": "1:19:21", "remaining_time": "1 day, 13:54:05", "throughput": 707.57, "total_tokens": 3369056} +{"current_steps": 6060, "total_steps": 179570, "loss": 0.0243, "lr": 1.6870858161162777e-05, "epoch": 0.33747285181266357, "percentage": 3.37, "elapsed_time": "1:19:25", "remaining_time": "1 day, 13:54:01", "throughput": 707.58, "total_tokens": 3371872} +{"current_steps": 6065, "total_steps": 179570, "loss": 0.1897, "lr": 1.6884780308514787e-05, "epoch": 0.3377512947597037, "percentage": 3.38, "elapsed_time": "1:19:29", "remaining_time": "1 day, 13:54:05", "throughput": 707.61, "total_tokens": 3374976} +{"current_steps": 6070, "total_steps": 179570, "loss": 0.0717, "lr": 1.6898702455866793e-05, "epoch": 0.3380297377067439, "percentage": 3.38, "elapsed_time": "1:19:33", "remaining_time": "1 day, 13:53:59", "throughput": 707.58, "total_tokens": 3377584} +{"current_steps": 6075, "total_steps": 179570, "loss": 0.3021, "lr": 1.6912624603218803e-05, "epoch": 0.33830818065378404, "percentage": 3.38, "elapsed_time": "1:19:37", "remaining_time": "1 day, 13:53:47", "throughput": 707.56, "total_tokens": 3380080} +{"current_steps": 6080, "total_steps": 179570, "loss": 0.3704, "lr": 1.692654675057081e-05, "epoch": 0.3385866236008242, "percentage": 3.39, "elapsed_time": "1:19:41", "remaining_time": "1 day, 13:53:47", "throughput": 707.57, "total_tokens": 3383008} +{"current_steps": 6085, "total_steps": 179570, "loss": 0.0092, "lr": 1.6940468897922816e-05, "epoch": 0.33886506654786436, "percentage": 3.39, "elapsed_time": "1:19:44", "remaining_time": "1 day, 13:53:38", "throughput": 707.56, "total_tokens": 3385584} +{"current_steps": 6090, "total_steps": 179570, "loss": 0.4146, "lr": 1.6954391045274823e-05, "epoch": 0.3391435094949045, "percentage": 3.39, "elapsed_time": "1:19:48", "remaining_time": "1 day, 13:53:27", "throughput": 707.54, "total_tokens": 3388128} +{"current_steps": 6095, "total_steps": 179570, "loss": 0.0099, "lr": 1.696831319262683e-05, "epoch": 0.3394219524419446, "percentage": 3.39, "elapsed_time": "1:19:52", "remaining_time": "1 day, 13:53:34", "throughput": 707.53, "total_tokens": 3391104} +{"current_steps": 6100, "total_steps": 179570, "loss": 0.0081, "lr": 1.698223533997884e-05, "epoch": 0.3397003953889848, "percentage": 3.4, "elapsed_time": "1:19:56", "remaining_time": "1 day, 13:53:31", "throughput": 707.54, "total_tokens": 3393952} +{"current_steps": 6105, "total_steps": 179570, "loss": 0.3516, "lr": 1.6996157487330846e-05, "epoch": 0.33997883833602494, "percentage": 3.4, "elapsed_time": "1:20:00", "remaining_time": "1 day, 13:53:30", "throughput": 707.53, "total_tokens": 3396752} +{"current_steps": 6110, "total_steps": 179570, "loss": 0.229, "lr": 1.7010079634682856e-05, "epoch": 0.3402572812830651, "percentage": 3.4, "elapsed_time": "1:20:04", "remaining_time": "1 day, 13:53:20", "throughput": 707.5, "total_tokens": 3399264} +{"current_steps": 6115, "total_steps": 179570, "loss": 0.0425, "lr": 1.7024001782034862e-05, "epoch": 0.34053572423010525, "percentage": 3.41, "elapsed_time": "1:20:08", "remaining_time": "1 day, 13:53:15", "throughput": 707.5, "total_tokens": 3402000} +{"current_steps": 6120, "total_steps": 179570, "loss": 0.1035, "lr": 1.7037923929386872e-05, "epoch": 0.3408141671771454, "percentage": 3.41, "elapsed_time": "1:20:12", "remaining_time": "1 day, 13:53:15", "throughput": 707.51, "total_tokens": 3404928} +{"current_steps": 6125, "total_steps": 179570, "loss": 0.3663, "lr": 1.705184607673888e-05, "epoch": 0.34109261012418557, "percentage": 3.41, "elapsed_time": "1:20:16", "remaining_time": "1 day, 13:53:12", "throughput": 707.52, "total_tokens": 3407808} +{"current_steps": 6130, "total_steps": 179570, "loss": 0.2188, "lr": 1.7065768224090885e-05, "epoch": 0.3413710530712257, "percentage": 3.41, "elapsed_time": "1:20:20", "remaining_time": "1 day, 13:53:20", "throughput": 707.53, "total_tokens": 3410912} +{"current_steps": 6135, "total_steps": 179570, "loss": 0.4858, "lr": 1.707969037144289e-05, "epoch": 0.34164949601826583, "percentage": 3.42, "elapsed_time": "1:20:24", "remaining_time": "1 day, 13:53:20", "throughput": 707.54, "total_tokens": 3413872} +{"current_steps": 6140, "total_steps": 179570, "loss": 0.1128, "lr": 1.7093612518794898e-05, "epoch": 0.341927938965306, "percentage": 3.42, "elapsed_time": "1:20:28", "remaining_time": "1 day, 13:53:01", "throughput": 707.51, "total_tokens": 3416128} +{"current_steps": 6145, "total_steps": 179570, "loss": 0.6326, "lr": 1.7107534666146908e-05, "epoch": 0.34220638191234615, "percentage": 3.42, "elapsed_time": "1:20:32", "remaining_time": "1 day, 13:52:57", "throughput": 707.53, "total_tokens": 3418976} +{"current_steps": 6150, "total_steps": 179570, "loss": 0.1477, "lr": 1.7121456813498915e-05, "epoch": 0.3424848248593863, "percentage": 3.42, "elapsed_time": "1:20:35", "remaining_time": "1 day, 13:52:39", "throughput": 707.5, "total_tokens": 3421280} +{"current_steps": 6155, "total_steps": 179570, "loss": 0.0731, "lr": 1.7135378960850924e-05, "epoch": 0.34276326780642646, "percentage": 3.43, "elapsed_time": "1:20:39", "remaining_time": "1 day, 13:52:23", "throughput": 707.51, "total_tokens": 3423776} +{"current_steps": 6160, "total_steps": 179570, "loss": 0.4733, "lr": 1.714930110820293e-05, "epoch": 0.3430417107534666, "percentage": 3.43, "elapsed_time": "1:20:42", "remaining_time": "1 day, 13:52:06", "throughput": 707.48, "total_tokens": 3426112} +{"current_steps": 6165, "total_steps": 179570, "loss": 0.081, "lr": 1.7163223255554937e-05, "epoch": 0.3433201537005068, "percentage": 3.43, "elapsed_time": "1:20:47", "remaining_time": "1 day, 13:52:15", "throughput": 707.5, "total_tokens": 3429296} +{"current_steps": 6170, "total_steps": 179570, "loss": 0.1264, "lr": 1.7177145402906944e-05, "epoch": 0.34359859664754694, "percentage": 3.44, "elapsed_time": "1:20:51", "remaining_time": "1 day, 13:52:14", "throughput": 707.5, "total_tokens": 3432176} +{"current_steps": 6175, "total_steps": 179570, "loss": 0.4357, "lr": 1.719106755025895e-05, "epoch": 0.34387703959458704, "percentage": 3.44, "elapsed_time": "1:20:54", "remaining_time": "1 day, 13:52:01", "throughput": 707.47, "total_tokens": 3434592} +{"current_steps": 6180, "total_steps": 179570, "loss": 0.0028, "lr": 1.720498969761096e-05, "epoch": 0.3441554825416272, "percentage": 3.44, "elapsed_time": "1:20:58", "remaining_time": "1 day, 13:52:01", "throughput": 707.49, "total_tokens": 3437536} +{"current_steps": 6185, "total_steps": 179570, "loss": 0.3463, "lr": 1.7218911844962967e-05, "epoch": 0.34443392548866736, "percentage": 3.44, "elapsed_time": "1:21:02", "remaining_time": "1 day, 13:51:57", "throughput": 707.48, "total_tokens": 3440256} +{"current_steps": 6190, "total_steps": 179570, "loss": 0.3856, "lr": 1.7232833992314977e-05, "epoch": 0.3447123684357075, "percentage": 3.45, "elapsed_time": "1:21:06", "remaining_time": "1 day, 13:51:59", "throughput": 707.48, "total_tokens": 3443200} +{"current_steps": 6195, "total_steps": 179570, "loss": 0.0035, "lr": 1.7246756139666983e-05, "epoch": 0.3449908113827477, "percentage": 3.45, "elapsed_time": "1:21:11", "remaining_time": "1 day, 13:52:02", "throughput": 707.48, "total_tokens": 3446192} +{"current_steps": 6200, "total_steps": 179570, "loss": 0.3875, "lr": 1.726067828701899e-05, "epoch": 0.34526925432978783, "percentage": 3.45, "elapsed_time": "1:21:15", "remaining_time": "1 day, 13:51:59", "throughput": 707.51, "total_tokens": 3449120} +{"current_steps": 6205, "total_steps": 179570, "loss": 0.7704, "lr": 1.7274600434371e-05, "epoch": 0.345547697276828, "percentage": 3.46, "elapsed_time": "1:21:18", "remaining_time": "1 day, 13:51:49", "throughput": 707.52, "total_tokens": 3451792} +{"current_steps": 6210, "total_steps": 179570, "loss": 0.1927, "lr": 1.7288522581723003e-05, "epoch": 0.34582614022386815, "percentage": 3.46, "elapsed_time": "1:21:22", "remaining_time": "1 day, 13:51:37", "throughput": 707.5, "total_tokens": 3454256} +{"current_steps": 6215, "total_steps": 179570, "loss": 0.145, "lr": 1.7302444729075013e-05, "epoch": 0.34610458317090825, "percentage": 3.46, "elapsed_time": "1:21:26", "remaining_time": "1 day, 13:51:32", "throughput": 707.5, "total_tokens": 3457024} +{"current_steps": 6220, "total_steps": 179570, "loss": 0.2395, "lr": 1.731636687642702e-05, "epoch": 0.3463830261179484, "percentage": 3.46, "elapsed_time": "1:21:30", "remaining_time": "1 day, 13:51:36", "throughput": 707.51, "total_tokens": 3460048} +{"current_steps": 6225, "total_steps": 179570, "loss": 0.4243, "lr": 1.733028902377903e-05, "epoch": 0.34666146906498857, "percentage": 3.47, "elapsed_time": "1:21:34", "remaining_time": "1 day, 13:51:40", "throughput": 707.53, "total_tokens": 3463152} +{"current_steps": 6230, "total_steps": 179570, "loss": 0.2382, "lr": 1.7344211171131036e-05, "epoch": 0.34693991201202873, "percentage": 3.47, "elapsed_time": "1:21:38", "remaining_time": "1 day, 13:51:43", "throughput": 707.5, "total_tokens": 3465968} +{"current_steps": 6235, "total_steps": 179570, "loss": 0.0408, "lr": 1.7358133318483046e-05, "epoch": 0.3472183549590689, "percentage": 3.47, "elapsed_time": "1:21:42", "remaining_time": "1 day, 13:51:38", "throughput": 707.49, "total_tokens": 3468688} +{"current_steps": 6240, "total_steps": 179570, "loss": 0.0604, "lr": 1.7372055465835052e-05, "epoch": 0.34749679790610905, "percentage": 3.47, "elapsed_time": "1:21:46", "remaining_time": "1 day, 13:51:38", "throughput": 707.52, "total_tokens": 3471680} +{"current_steps": 6245, "total_steps": 179570, "loss": 0.1572, "lr": 1.738597761318706e-05, "epoch": 0.3477752408531492, "percentage": 3.48, "elapsed_time": "1:21:50", "remaining_time": "1 day, 13:51:29", "throughput": 707.49, "total_tokens": 3474208} +{"current_steps": 6250, "total_steps": 179570, "loss": 0.1168, "lr": 1.7399899760539065e-05, "epoch": 0.34805368380018936, "percentage": 3.48, "elapsed_time": "1:21:54", "remaining_time": "1 day, 13:51:30", "throughput": 707.49, "total_tokens": 3477088} +{"current_steps": 6255, "total_steps": 179570, "loss": 0.1653, "lr": 1.7413821907891072e-05, "epoch": 0.3483321267472295, "percentage": 3.48, "elapsed_time": "1:21:58", "remaining_time": "1 day, 13:51:22", "throughput": 707.48, "total_tokens": 3479696} +{"current_steps": 6260, "total_steps": 179570, "loss": 0.7666, "lr": 1.7427744055243082e-05, "epoch": 0.3486105696942696, "percentage": 3.49, "elapsed_time": "1:22:02", "remaining_time": "1 day, 13:51:20", "throughput": 707.5, "total_tokens": 3482640} +{"current_steps": 6265, "total_steps": 179570, "loss": 0.3852, "lr": 1.744166620259509e-05, "epoch": 0.3488890126413098, "percentage": 3.49, "elapsed_time": "1:22:06", "remaining_time": "1 day, 13:51:31", "throughput": 707.49, "total_tokens": 3485760} +{"current_steps": 6270, "total_steps": 179570, "loss": 0.2719, "lr": 1.7455588349947098e-05, "epoch": 0.34916745558834994, "percentage": 3.49, "elapsed_time": "1:22:11", "remaining_time": "1 day, 13:51:31", "throughput": 707.52, "total_tokens": 3488784} +{"current_steps": 6275, "total_steps": 179570, "loss": 0.2587, "lr": 1.7469510497299105e-05, "epoch": 0.3494458985353901, "percentage": 3.49, "elapsed_time": "1:22:15", "remaining_time": "1 day, 13:51:35", "throughput": 707.54, "total_tokens": 3491872} +{"current_steps": 6280, "total_steps": 179570, "loss": 0.1403, "lr": 1.748343264465111e-05, "epoch": 0.34972434148243026, "percentage": 3.5, "elapsed_time": "1:22:19", "remaining_time": "1 day, 13:51:31", "throughput": 707.54, "total_tokens": 3494672} +{"current_steps": 6285, "total_steps": 179570, "loss": 0.006, "lr": 1.749735479200312e-05, "epoch": 0.3500027844294704, "percentage": 3.5, "elapsed_time": "1:22:23", "remaining_time": "1 day, 13:51:26", "throughput": 707.54, "total_tokens": 3497424} +{"current_steps": 6290, "total_steps": 179570, "loss": 0.2014, "lr": 1.7511276939355124e-05, "epoch": 0.3502812273765106, "percentage": 3.5, "elapsed_time": "1:22:27", "remaining_time": "1 day, 13:51:25", "throughput": 707.55, "total_tokens": 3500320} +{"current_steps": 6295, "total_steps": 179570, "loss": 0.156, "lr": 1.7525199086707134e-05, "epoch": 0.35055967032355073, "percentage": 3.51, "elapsed_time": "1:22:30", "remaining_time": "1 day, 13:51:16", "throughput": 707.55, "total_tokens": 3502976} +{"current_steps": 6300, "total_steps": 179570, "loss": 0.059, "lr": 1.753912123405914e-05, "epoch": 0.35083811327059083, "percentage": 3.51, "elapsed_time": "1:22:34", "remaining_time": "1 day, 13:51:15", "throughput": 707.56, "total_tokens": 3505856} +{"current_steps": 6305, "total_steps": 179570, "loss": 0.0134, "lr": 1.755304338141115e-05, "epoch": 0.351116556217631, "percentage": 3.51, "elapsed_time": "1:22:38", "remaining_time": "1 day, 13:51:11", "throughput": 707.54, "total_tokens": 3508576} +{"current_steps": 6310, "total_steps": 179570, "loss": 0.0125, "lr": 1.7566965528763157e-05, "epoch": 0.35139499916467115, "percentage": 3.51, "elapsed_time": "1:22:42", "remaining_time": "1 day, 13:51:07", "throughput": 707.53, "total_tokens": 3511296} +{"current_steps": 6315, "total_steps": 179570, "loss": 0.2516, "lr": 1.7580887676115164e-05, "epoch": 0.3516734421117113, "percentage": 3.52, "elapsed_time": "1:22:46", "remaining_time": "1 day, 13:50:56", "throughput": 707.52, "total_tokens": 3513856} +{"current_steps": 6320, "total_steps": 179570, "loss": 0.3862, "lr": 1.7594809823467174e-05, "epoch": 0.35195188505875147, "percentage": 3.52, "elapsed_time": "1:22:50", "remaining_time": "1 day, 13:50:54", "throughput": 707.53, "total_tokens": 3516704} +{"current_steps": 6325, "total_steps": 179570, "loss": 0.2034, "lr": 1.760873197081918e-05, "epoch": 0.3522303280057916, "percentage": 3.52, "elapsed_time": "1:22:54", "remaining_time": "1 day, 13:50:50", "throughput": 707.53, "total_tokens": 3519520} +{"current_steps": 6330, "total_steps": 179570, "loss": 0.0029, "lr": 1.7622654118171187e-05, "epoch": 0.3525087709528318, "percentage": 3.53, "elapsed_time": "1:22:58", "remaining_time": "1 day, 13:50:46", "throughput": 707.53, "total_tokens": 3522288} +{"current_steps": 6335, "total_steps": 179570, "loss": 0.0844, "lr": 1.7636576265523193e-05, "epoch": 0.35278721389987194, "percentage": 3.53, "elapsed_time": "1:23:01", "remaining_time": "1 day, 13:50:33", "throughput": 707.53, "total_tokens": 3524848} +{"current_steps": 6340, "total_steps": 179570, "loss": 0.0344, "lr": 1.7650498412875203e-05, "epoch": 0.35306565684691205, "percentage": 3.53, "elapsed_time": "1:23:05", "remaining_time": "1 day, 13:50:23", "throughput": 707.52, "total_tokens": 3527440} +{"current_steps": 6345, "total_steps": 179570, "loss": 0.2925, "lr": 1.766442056022721e-05, "epoch": 0.3533440997939522, "percentage": 3.53, "elapsed_time": "1:23:09", "remaining_time": "1 day, 13:50:27", "throughput": 707.53, "total_tokens": 3530432} +{"current_steps": 6350, "total_steps": 179570, "loss": 0.0711, "lr": 1.767834270757922e-05, "epoch": 0.35362254274099236, "percentage": 3.54, "elapsed_time": "1:23:13", "remaining_time": "1 day, 13:50:26", "throughput": 707.53, "total_tokens": 3533328} +{"current_steps": 6355, "total_steps": 179570, "loss": 0.0075, "lr": 1.7692264854931226e-05, "epoch": 0.3539009856880325, "percentage": 3.54, "elapsed_time": "1:23:18", "remaining_time": "1 day, 13:50:29", "throughput": 707.55, "total_tokens": 3536368} +{"current_steps": 6360, "total_steps": 179570, "loss": 0.661, "lr": 1.7706187002283233e-05, "epoch": 0.3541794286350727, "percentage": 3.54, "elapsed_time": "1:23:21", "remaining_time": "1 day, 13:50:06", "throughput": 707.53, "total_tokens": 3538544} +{"current_steps": 6365, "total_steps": 179570, "loss": 0.1442, "lr": 1.7720109149635243e-05, "epoch": 0.35445787158211284, "percentage": 3.54, "elapsed_time": "1:23:24", "remaining_time": "1 day, 13:49:55", "throughput": 707.52, "total_tokens": 3541104} +{"current_steps": 6370, "total_steps": 179570, "loss": 0.0416, "lr": 1.7734031296987246e-05, "epoch": 0.354736314529153, "percentage": 3.55, "elapsed_time": "1:23:28", "remaining_time": "1 day, 13:49:51", "throughput": 707.53, "total_tokens": 3543920} +{"current_steps": 6375, "total_steps": 179570, "loss": 0.3744, "lr": 1.7747953444339256e-05, "epoch": 0.35501475747619315, "percentage": 3.55, "elapsed_time": "1:23:32", "remaining_time": "1 day, 13:49:35", "throughput": 707.5, "total_tokens": 3546240} +{"current_steps": 6380, "total_steps": 179570, "loss": 0.2027, "lr": 1.7761875591691262e-05, "epoch": 0.35529320042323326, "percentage": 3.55, "elapsed_time": "1:23:35", "remaining_time": "1 day, 13:49:19", "throughput": 707.48, "total_tokens": 3548640} +{"current_steps": 6385, "total_steps": 179570, "loss": 0.3666, "lr": 1.7775797739043272e-05, "epoch": 0.3555716433702734, "percentage": 3.56, "elapsed_time": "1:23:40", "remaining_time": "1 day, 13:49:24", "throughput": 707.49, "total_tokens": 3551696} +{"current_steps": 6390, "total_steps": 179570, "loss": 0.0087, "lr": 1.778971988639528e-05, "epoch": 0.3558500863173136, "percentage": 3.56, "elapsed_time": "1:23:44", "remaining_time": "1 day, 13:49:24", "throughput": 707.5, "total_tokens": 3554608} +{"current_steps": 6395, "total_steps": 179570, "loss": 0.1663, "lr": 1.7803642033747285e-05, "epoch": 0.35612852926435373, "percentage": 3.56, "elapsed_time": "1:23:48", "remaining_time": "1 day, 13:49:20", "throughput": 707.48, "total_tokens": 3557312} +{"current_steps": 6400, "total_steps": 179570, "loss": 0.1173, "lr": 1.7817564181099295e-05, "epoch": 0.3564069722113939, "percentage": 3.56, "elapsed_time": "1:23:52", "remaining_time": "1 day, 13:49:20", "throughput": 707.51, "total_tokens": 3560320} +{"current_steps": 6405, "total_steps": 179570, "loss": 0.0107, "lr": 1.78314863284513e-05, "epoch": 0.35668541515843405, "percentage": 3.57, "elapsed_time": "1:23:56", "remaining_time": "1 day, 13:49:24", "throughput": 707.52, "total_tokens": 3563360} +{"current_steps": 6410, "total_steps": 179570, "loss": 0.1666, "lr": 1.7845408475803308e-05, "epoch": 0.3569638581054742, "percentage": 3.57, "elapsed_time": "1:24:00", "remaining_time": "1 day, 13:49:15", "throughput": 707.51, "total_tokens": 3566000} +{"current_steps": 6415, "total_steps": 179570, "loss": 0.2592, "lr": 1.7859330623155315e-05, "epoch": 0.35724230105251437, "percentage": 3.57, "elapsed_time": "1:24:04", "remaining_time": "1 day, 13:49:15", "throughput": 707.53, "total_tokens": 3568944} +{"current_steps": 6420, "total_steps": 179570, "loss": 0.0293, "lr": 1.7873252770507324e-05, "epoch": 0.35752074399955447, "percentage": 3.58, "elapsed_time": "1:24:07", "remaining_time": "1 day, 13:48:58", "throughput": 707.5, "total_tokens": 3571232} +{"current_steps": 6425, "total_steps": 179570, "loss": 0.1934, "lr": 1.788717491785933e-05, "epoch": 0.3577991869465946, "percentage": 3.58, "elapsed_time": "1:24:11", "remaining_time": "1 day, 13:48:55", "throughput": 707.5, "total_tokens": 3574048} +{"current_steps": 6430, "total_steps": 179570, "loss": 0.0213, "lr": 1.7901097065211338e-05, "epoch": 0.3580776298936348, "percentage": 3.58, "elapsed_time": "1:24:15", "remaining_time": "1 day, 13:48:54", "throughput": 707.52, "total_tokens": 3577040} +{"current_steps": 6435, "total_steps": 179570, "loss": 0.1885, "lr": 1.7915019212563347e-05, "epoch": 0.35835607284067494, "percentage": 3.58, "elapsed_time": "1:24:19", "remaining_time": "1 day, 13:48:54", "throughput": 707.55, "total_tokens": 3580048} +{"current_steps": 6440, "total_steps": 179570, "loss": 0.1354, "lr": 1.7928941359915354e-05, "epoch": 0.3586345157877151, "percentage": 3.59, "elapsed_time": "1:24:24", "remaining_time": "1 day, 13:49:02", "throughput": 707.56, "total_tokens": 3583168} +{"current_steps": 6445, "total_steps": 179570, "loss": 0.1776, "lr": 1.7942863507267364e-05, "epoch": 0.35891295873475526, "percentage": 3.59, "elapsed_time": "1:24:28", "remaining_time": "1 day, 13:49:13", "throughput": 707.56, "total_tokens": 3586384} +{"current_steps": 6450, "total_steps": 179570, "loss": 0.7466, "lr": 1.7956785654619367e-05, "epoch": 0.3591914016817954, "percentage": 3.59, "elapsed_time": "1:24:32", "remaining_time": "1 day, 13:49:17", "throughput": 707.58, "total_tokens": 3589488} +{"current_steps": 6455, "total_steps": 179570, "loss": 0.0552, "lr": 1.7970707801971377e-05, "epoch": 0.3594698446288356, "percentage": 3.59, "elapsed_time": "1:24:36", "remaining_time": "1 day, 13:49:08", "throughput": 707.59, "total_tokens": 3592176} +{"current_steps": 6460, "total_steps": 179570, "loss": 0.001, "lr": 1.7984629949323383e-05, "epoch": 0.3597482875758757, "percentage": 3.6, "elapsed_time": "1:24:40", "remaining_time": "1 day, 13:49:07", "throughput": 707.59, "total_tokens": 3595040} +{"current_steps": 6465, "total_steps": 179570, "loss": 0.2025, "lr": 1.7998552096675393e-05, "epoch": 0.36002673052291584, "percentage": 3.6, "elapsed_time": "1:24:44", "remaining_time": "1 day, 13:49:08", "throughput": 707.58, "total_tokens": 3597888} +{"current_steps": 6470, "total_steps": 179570, "loss": 0.349, "lr": 1.80124742440274e-05, "epoch": 0.360305173469956, "percentage": 3.6, "elapsed_time": "1:24:48", "remaining_time": "1 day, 13:48:52", "throughput": 707.56, "total_tokens": 3600256} +{"current_steps": 6475, "total_steps": 179570, "loss": 0.2189, "lr": 1.8026396391379406e-05, "epoch": 0.36058361641699616, "percentage": 3.61, "elapsed_time": "1:24:52", "remaining_time": "1 day, 13:48:53", "throughput": 707.54, "total_tokens": 3603088} +{"current_steps": 6480, "total_steps": 179570, "loss": 0.1473, "lr": 1.8040318538731416e-05, "epoch": 0.3608620593640363, "percentage": 3.61, "elapsed_time": "1:24:56", "remaining_time": "1 day, 13:48:54", "throughput": 707.59, "total_tokens": 3606208} +{"current_steps": 6485, "total_steps": 179570, "loss": 0.0007, "lr": 1.8054240686083423e-05, "epoch": 0.3611405023110765, "percentage": 3.61, "elapsed_time": "1:25:00", "remaining_time": "1 day, 13:49:02", "throughput": 707.59, "total_tokens": 3609328} +{"current_steps": 6490, "total_steps": 179570, "loss": 0.2319, "lr": 1.806816283343543e-05, "epoch": 0.36141894525811663, "percentage": 3.61, "elapsed_time": "1:25:04", "remaining_time": "1 day, 13:49:01", "throughput": 707.59, "total_tokens": 3612192} +{"current_steps": 6495, "total_steps": 179570, "loss": 0.6967, "lr": 1.8082084980787436e-05, "epoch": 0.3616973882051568, "percentage": 3.62, "elapsed_time": "1:25:08", "remaining_time": "1 day, 13:48:49", "throughput": 707.58, "total_tokens": 3614688} +{"current_steps": 6500, "total_steps": 179570, "loss": 0.2763, "lr": 1.8096007128139446e-05, "epoch": 0.3619758311521969, "percentage": 3.62, "elapsed_time": "1:25:12", "remaining_time": "1 day, 13:48:37", "throughput": 707.54, "total_tokens": 3617088} +{"current_steps": 6505, "total_steps": 179570, "loss": 0.4021, "lr": 1.8109929275491452e-05, "epoch": 0.36225427409923705, "percentage": 3.62, "elapsed_time": "1:25:16", "remaining_time": "1 day, 13:48:34", "throughput": 707.54, "total_tokens": 3619888} +{"current_steps": 6510, "total_steps": 179570, "loss": 0.4302, "lr": 1.812385142284346e-05, "epoch": 0.3625327170462772, "percentage": 3.63, "elapsed_time": "1:25:20", "remaining_time": "1 day, 13:48:34", "throughput": 707.52, "total_tokens": 3622656} +{"current_steps": 6515, "total_steps": 179570, "loss": 0.0172, "lr": 1.813777357019547e-05, "epoch": 0.36281115999331737, "percentage": 3.63, "elapsed_time": "1:25:23", "remaining_time": "1 day, 13:48:17", "throughput": 707.5, "total_tokens": 3624976} +{"current_steps": 6520, "total_steps": 179570, "loss": 0.3249, "lr": 1.8151695717547475e-05, "epoch": 0.3630896029403575, "percentage": 3.63, "elapsed_time": "1:25:27", "remaining_time": "1 day, 13:48:08", "throughput": 707.48, "total_tokens": 3627520} +{"current_steps": 6525, "total_steps": 179570, "loss": 0.184, "lr": 1.8165617864899485e-05, "epoch": 0.3633680458873977, "percentage": 3.63, "elapsed_time": "1:25:31", "remaining_time": "1 day, 13:48:12", "throughput": 707.5, "total_tokens": 3630608} +{"current_steps": 6530, "total_steps": 179570, "loss": 0.0195, "lr": 1.817954001225149e-05, "epoch": 0.36364648883443784, "percentage": 3.64, "elapsed_time": "1:25:35", "remaining_time": "1 day, 13:48:16", "throughput": 707.51, "total_tokens": 3633664} +{"current_steps": 6535, "total_steps": 179570, "loss": 0.1808, "lr": 1.8193462159603498e-05, "epoch": 0.363924931781478, "percentage": 3.64, "elapsed_time": "1:25:39", "remaining_time": "1 day, 13:48:05", "throughput": 707.5, "total_tokens": 3636240} +{"current_steps": 6540, "total_steps": 179570, "loss": 0.1923, "lr": 1.8207384306955505e-05, "epoch": 0.3642033747285181, "percentage": 3.64, "elapsed_time": "1:25:43", "remaining_time": "1 day, 13:47:57", "throughput": 707.49, "total_tokens": 3638848} +{"current_steps": 6545, "total_steps": 179570, "loss": 0.1899, "lr": 1.822130645430751e-05, "epoch": 0.36448181767555826, "percentage": 3.64, "elapsed_time": "1:25:47", "remaining_time": "1 day, 13:48:04", "throughput": 707.49, "total_tokens": 3641904} +{"current_steps": 6550, "total_steps": 179570, "loss": 0.2003, "lr": 1.823522860165952e-05, "epoch": 0.3647602606225984, "percentage": 3.65, "elapsed_time": "1:25:51", "remaining_time": "1 day, 13:47:56", "throughput": 707.49, "total_tokens": 3644560} +{"current_steps": 6555, "total_steps": 179570, "loss": 0.2085, "lr": 1.8249150749011528e-05, "epoch": 0.3650387035696386, "percentage": 3.65, "elapsed_time": "1:25:55", "remaining_time": "1 day, 13:47:48", "throughput": 707.5, "total_tokens": 3647312} +{"current_steps": 6560, "total_steps": 179570, "loss": 0.2839, "lr": 1.8263072896363538e-05, "epoch": 0.36531714651667874, "percentage": 3.65, "elapsed_time": "1:25:59", "remaining_time": "1 day, 13:47:46", "throughput": 707.51, "total_tokens": 3650192} +{"current_steps": 6565, "total_steps": 179570, "loss": 0.1968, "lr": 1.8276995043715544e-05, "epoch": 0.3655955894637189, "percentage": 3.66, "elapsed_time": "1:26:02", "remaining_time": "1 day, 13:47:37", "throughput": 707.51, "total_tokens": 3652880} +{"current_steps": 6570, "total_steps": 179570, "loss": 0.3316, "lr": 1.829091719106755e-05, "epoch": 0.36587403241075905, "percentage": 3.66, "elapsed_time": "1:26:07", "remaining_time": "1 day, 13:47:44", "throughput": 707.5, "total_tokens": 3655872} +{"current_steps": 6575, "total_steps": 179570, "loss": 0.4487, "lr": 1.8304839338419557e-05, "epoch": 0.3661524753577992, "percentage": 3.66, "elapsed_time": "1:26:11", "remaining_time": "1 day, 13:47:49", "throughput": 707.5, "total_tokens": 3658896} +{"current_steps": 6580, "total_steps": 179570, "loss": 0.0465, "lr": 1.8318761485771567e-05, "epoch": 0.3664309183048393, "percentage": 3.66, "elapsed_time": "1:26:15", "remaining_time": "1 day, 13:47:41", "throughput": 707.49, "total_tokens": 3661520} +{"current_steps": 6585, "total_steps": 179570, "loss": 0.0006, "lr": 1.8332683633123574e-05, "epoch": 0.3667093612518795, "percentage": 3.67, "elapsed_time": "1:26:19", "remaining_time": "1 day, 13:47:44", "throughput": 707.5, "total_tokens": 3664528} +{"current_steps": 6590, "total_steps": 179570, "loss": 0.1331, "lr": 1.834660578047558e-05, "epoch": 0.36698780419891963, "percentage": 3.67, "elapsed_time": "1:26:23", "remaining_time": "1 day, 13:47:38", "throughput": 707.49, "total_tokens": 3667216} +{"current_steps": 6595, "total_steps": 179570, "loss": 0.3472, "lr": 1.836052792782759e-05, "epoch": 0.3672662471459598, "percentage": 3.67, "elapsed_time": "1:26:27", "remaining_time": "1 day, 13:47:37", "throughput": 707.52, "total_tokens": 3670224} +{"current_steps": 6600, "total_steps": 179570, "loss": 0.3228, "lr": 1.8374450075179597e-05, "epoch": 0.36754469009299995, "percentage": 3.68, "elapsed_time": "1:26:31", "remaining_time": "1 day, 13:47:41", "throughput": 707.54, "total_tokens": 3673296} +{"current_steps": 6605, "total_steps": 179570, "loss": 0.1293, "lr": 1.8388372222531607e-05, "epoch": 0.3678231330400401, "percentage": 3.68, "elapsed_time": "1:26:35", "remaining_time": "1 day, 13:47:33", "throughput": 707.54, "total_tokens": 3675984} +{"current_steps": 6610, "total_steps": 179570, "loss": 0.0289, "lr": 1.8402294369883613e-05, "epoch": 0.36810157598708027, "percentage": 3.68, "elapsed_time": "1:26:39", "remaining_time": "1 day, 13:47:36", "throughput": 707.56, "total_tokens": 3679056} +{"current_steps": 6615, "total_steps": 179570, "loss": 0.0638, "lr": 1.841621651723562e-05, "epoch": 0.3683800189341204, "percentage": 3.68, "elapsed_time": "1:26:43", "remaining_time": "1 day, 13:47:40", "throughput": 707.58, "total_tokens": 3682192} +{"current_steps": 6620, "total_steps": 179570, "loss": 0.4823, "lr": 1.8430138664587626e-05, "epoch": 0.3686584618811605, "percentage": 3.69, "elapsed_time": "1:26:48", "remaining_time": "1 day, 13:47:43", "throughput": 707.59, "total_tokens": 3685184} +{"current_steps": 6625, "total_steps": 179570, "loss": 0.0783, "lr": 1.8444060811939633e-05, "epoch": 0.3689369048282007, "percentage": 3.69, "elapsed_time": "1:26:51", "remaining_time": "1 day, 13:47:36", "throughput": 707.57, "total_tokens": 3687776} +{"current_steps": 6630, "total_steps": 179570, "loss": 0.3627, "lr": 1.8457982959291643e-05, "epoch": 0.36921534777524084, "percentage": 3.69, "elapsed_time": "1:26:55", "remaining_time": "1 day, 13:47:26", "throughput": 707.57, "total_tokens": 3690384} +{"current_steps": 6635, "total_steps": 179570, "loss": 0.0022, "lr": 1.847190510664365e-05, "epoch": 0.369493790722281, "percentage": 3.69, "elapsed_time": "1:26:59", "remaining_time": "1 day, 13:47:25", "throughput": 707.58, "total_tokens": 3693344} +{"current_steps": 6640, "total_steps": 179570, "loss": 0.0129, "lr": 1.848582725399566e-05, "epoch": 0.36977223366932116, "percentage": 3.7, "elapsed_time": "1:27:03", "remaining_time": "1 day, 13:47:17", "throughput": 707.58, "total_tokens": 3696032} +{"current_steps": 6645, "total_steps": 179570, "loss": 0.2871, "lr": 1.8499749401347666e-05, "epoch": 0.3700506766163613, "percentage": 3.7, "elapsed_time": "1:27:07", "remaining_time": "1 day, 13:47:09", "throughput": 707.56, "total_tokens": 3698592} +{"current_steps": 6650, "total_steps": 179570, "loss": 0.3901, "lr": 1.8513671548699672e-05, "epoch": 0.3703291195634015, "percentage": 3.7, "elapsed_time": "1:27:11", "remaining_time": "1 day, 13:47:10", "throughput": 707.57, "total_tokens": 3701552} +{"current_steps": 6655, "total_steps": 179570, "loss": 0.051, "lr": 1.852759369605168e-05, "epoch": 0.37060756251044163, "percentage": 3.71, "elapsed_time": "1:27:15", "remaining_time": "1 day, 13:47:14", "throughput": 707.61, "total_tokens": 3704720} +{"current_steps": 6660, "total_steps": 179570, "loss": 0.1209, "lr": 1.8541515843403685e-05, "epoch": 0.37088600545748174, "percentage": 3.71, "elapsed_time": "1:27:19", "remaining_time": "1 day, 13:47:02", "throughput": 707.59, "total_tokens": 3707216} +{"current_steps": 6665, "total_steps": 179570, "loss": 0.0045, "lr": 1.8555437990755695e-05, "epoch": 0.3711644484045219, "percentage": 3.71, "elapsed_time": "1:27:23", "remaining_time": "1 day, 13:47:00", "throughput": 707.6, "total_tokens": 3710064} +{"current_steps": 6670, "total_steps": 179570, "loss": 0.0566, "lr": 1.85693601381077e-05, "epoch": 0.37144289135156205, "percentage": 3.71, "elapsed_time": "1:27:26", "remaining_time": "1 day, 13:46:52", "throughput": 707.6, "total_tokens": 3712752} +{"current_steps": 6675, "total_steps": 179570, "loss": 0.1611, "lr": 1.858328228545971e-05, "epoch": 0.3717213342986022, "percentage": 3.72, "elapsed_time": "1:27:31", "remaining_time": "1 day, 13:46:51", "throughput": 707.61, "total_tokens": 3715680} +{"current_steps": 6680, "total_steps": 179570, "loss": 0.1597, "lr": 1.8597204432811718e-05, "epoch": 0.37199977724564237, "percentage": 3.72, "elapsed_time": "1:27:34", "remaining_time": "1 day, 13:46:41", "throughput": 707.6, "total_tokens": 3718256} +{"current_steps": 6685, "total_steps": 179570, "loss": 0.1667, "lr": 1.8611126580163728e-05, "epoch": 0.37227822019268253, "percentage": 3.72, "elapsed_time": "1:27:38", "remaining_time": "1 day, 13:46:33", "throughput": 707.62, "total_tokens": 3721056} +{"current_steps": 6690, "total_steps": 179570, "loss": 0.4909, "lr": 1.8625048727515734e-05, "epoch": 0.3725566631397227, "percentage": 3.73, "elapsed_time": "1:27:42", "remaining_time": "1 day, 13:46:25", "throughput": 707.62, "total_tokens": 3723696} +{"current_steps": 6695, "total_steps": 179570, "loss": 0.2867, "lr": 1.863897087486774e-05, "epoch": 0.37283510608676285, "percentage": 3.73, "elapsed_time": "1:27:46", "remaining_time": "1 day, 13:46:21", "throughput": 707.62, "total_tokens": 3726480} +{"current_steps": 6700, "total_steps": 179570, "loss": 0.0262, "lr": 1.8652893022219748e-05, "epoch": 0.37311354903380295, "percentage": 3.73, "elapsed_time": "1:27:50", "remaining_time": "1 day, 13:46:17", "throughput": 707.63, "total_tokens": 3729296} +{"current_steps": 6705, "total_steps": 179570, "loss": 0.0934, "lr": 1.8666815169571754e-05, "epoch": 0.3733919919808431, "percentage": 3.73, "elapsed_time": "1:27:54", "remaining_time": "1 day, 13:46:15", "throughput": 707.63, "total_tokens": 3732144} +{"current_steps": 6710, "total_steps": 179570, "loss": 0.7696, "lr": 1.8680737316923764e-05, "epoch": 0.37367043492788327, "percentage": 3.74, "elapsed_time": "1:27:57", "remaining_time": "1 day, 13:46:08", "throughput": 707.64, "total_tokens": 3734880} +{"current_steps": 6715, "total_steps": 179570, "loss": 0.1158, "lr": 1.869465946427577e-05, "epoch": 0.3739488778749234, "percentage": 3.74, "elapsed_time": "1:28:02", "remaining_time": "1 day, 13:46:07", "throughput": 707.66, "total_tokens": 3737888} +{"current_steps": 6720, "total_steps": 179570, "loss": 0.1657, "lr": 1.870858161162778e-05, "epoch": 0.3742273208219636, "percentage": 3.74, "elapsed_time": "1:28:05", "remaining_time": "1 day, 13:46:00", "throughput": 707.67, "total_tokens": 3740624} +{"current_steps": 6725, "total_steps": 179570, "loss": 0.1313, "lr": 1.8722503758979787e-05, "epoch": 0.37450576376900374, "percentage": 3.75, "elapsed_time": "1:28:09", "remaining_time": "1 day, 13:45:51", "throughput": 707.66, "total_tokens": 3743232} +{"current_steps": 6730, "total_steps": 179570, "loss": 0.1059, "lr": 1.8736425906331793e-05, "epoch": 0.3747842067160439, "percentage": 3.75, "elapsed_time": "1:28:13", "remaining_time": "1 day, 13:45:51", "throughput": 707.68, "total_tokens": 3746176} +{"current_steps": 6735, "total_steps": 179570, "loss": 0.1693, "lr": 1.87503480536838e-05, "epoch": 0.37506264966308406, "percentage": 3.75, "elapsed_time": "1:28:17", "remaining_time": "1 day, 13:45:53", "throughput": 707.66, "total_tokens": 3749056} +{"current_steps": 6740, "total_steps": 179570, "loss": 0.0122, "lr": 1.8764270201035806e-05, "epoch": 0.37534109261012416, "percentage": 3.75, "elapsed_time": "1:28:21", "remaining_time": "1 day, 13:45:55", "throughput": 707.65, "total_tokens": 3751968} +{"current_steps": 6745, "total_steps": 179570, "loss": 0.1197, "lr": 1.8778192348387816e-05, "epoch": 0.3756195355571643, "percentage": 3.76, "elapsed_time": "1:28:26", "remaining_time": "1 day, 13:45:57", "throughput": 707.63, "total_tokens": 3754800} +{"current_steps": 6750, "total_steps": 179570, "loss": 0.0042, "lr": 1.8792114495739823e-05, "epoch": 0.3758979785042045, "percentage": 3.76, "elapsed_time": "1:28:30", "remaining_time": "1 day, 13:45:57", "throughput": 707.66, "total_tokens": 3757808} +{"current_steps": 6755, "total_steps": 179570, "loss": 0.0008, "lr": 1.8806036643091833e-05, "epoch": 0.37617642145124464, "percentage": 3.76, "elapsed_time": "1:28:34", "remaining_time": "1 day, 13:45:56", "throughput": 707.67, "total_tokens": 3760752} +{"current_steps": 6760, "total_steps": 179570, "loss": 0.1523, "lr": 1.881995879044384e-05, "epoch": 0.3764548643982848, "percentage": 3.76, "elapsed_time": "1:28:38", "remaining_time": "1 day, 13:45:50", "throughput": 707.67, "total_tokens": 3763488} +{"current_steps": 6765, "total_steps": 179570, "loss": 0.3218, "lr": 1.8833880937795846e-05, "epoch": 0.37673330734532495, "percentage": 3.77, "elapsed_time": "1:28:42", "remaining_time": "1 day, 13:45:50", "throughput": 707.68, "total_tokens": 3766400} +{"current_steps": 6770, "total_steps": 179570, "loss": 0.0011, "lr": 1.8847803085147856e-05, "epoch": 0.3770117502923651, "percentage": 3.77, "elapsed_time": "1:28:46", "remaining_time": "1 day, 13:45:46", "throughput": 707.68, "total_tokens": 3769200} +{"current_steps": 6775, "total_steps": 179570, "loss": 0.0108, "lr": 1.886172523249986e-05, "epoch": 0.37729019323940527, "percentage": 3.77, "elapsed_time": "1:28:50", "remaining_time": "1 day, 13:45:45", "throughput": 707.7, "total_tokens": 3772176} +{"current_steps": 6780, "total_steps": 179570, "loss": 0.5369, "lr": 1.887564737985187e-05, "epoch": 0.37756863618644537, "percentage": 3.78, "elapsed_time": "1:28:54", "remaining_time": "1 day, 13:45:41", "throughput": 707.67, "total_tokens": 3774816} +{"current_steps": 6785, "total_steps": 179570, "loss": 0.0185, "lr": 1.8889569527203875e-05, "epoch": 0.37784707913348553, "percentage": 3.78, "elapsed_time": "1:28:58", "remaining_time": "1 day, 13:45:40", "throughput": 707.68, "total_tokens": 3777712} +{"current_steps": 6790, "total_steps": 179570, "loss": 0.0267, "lr": 1.8903491674555885e-05, "epoch": 0.3781255220805257, "percentage": 3.78, "elapsed_time": "1:29:02", "remaining_time": "1 day, 13:45:47", "throughput": 707.68, "total_tokens": 3780784} +{"current_steps": 6795, "total_steps": 179570, "loss": 0.3046, "lr": 1.8917413821907892e-05, "epoch": 0.37840396502756585, "percentage": 3.78, "elapsed_time": "1:29:06", "remaining_time": "1 day, 13:45:49", "throughput": 707.69, "total_tokens": 3783808} +{"current_steps": 6800, "total_steps": 179570, "loss": 0.0076, "lr": 1.8931335969259902e-05, "epoch": 0.378682407974606, "percentage": 3.79, "elapsed_time": "1:29:10", "remaining_time": "1 day, 13:45:49", "throughput": 707.72, "total_tokens": 3786848} +{"current_steps": 6805, "total_steps": 179570, "loss": 0.1312, "lr": 1.8945258116611908e-05, "epoch": 0.37896085092164616, "percentage": 3.79, "elapsed_time": "1:29:14", "remaining_time": "1 day, 13:45:41", "throughput": 707.7, "total_tokens": 3789440} +{"current_steps": 6810, "total_steps": 179570, "loss": 0.2526, "lr": 1.8959180263963915e-05, "epoch": 0.3792392938686863, "percentage": 3.79, "elapsed_time": "1:29:18", "remaining_time": "1 day, 13:45:38", "throughput": 707.71, "total_tokens": 3792320} +{"current_steps": 6815, "total_steps": 179570, "loss": 0.0007, "lr": 1.897310241131592e-05, "epoch": 0.3795177368157265, "percentage": 3.8, "elapsed_time": "1:29:22", "remaining_time": "1 day, 13:45:33", "throughput": 707.72, "total_tokens": 3795104} +{"current_steps": 6820, "total_steps": 179570, "loss": 0.2927, "lr": 1.8987024558667928e-05, "epoch": 0.3797961797627666, "percentage": 3.8, "elapsed_time": "1:29:26", "remaining_time": "1 day, 13:45:32", "throughput": 707.75, "total_tokens": 3798128} +{"current_steps": 6825, "total_steps": 179570, "loss": 0.1612, "lr": 1.9000946706019938e-05, "epoch": 0.38007462270980674, "percentage": 3.8, "elapsed_time": "1:29:30", "remaining_time": "1 day, 13:45:33", "throughput": 707.72, "total_tokens": 3800896} +{"current_steps": 6830, "total_steps": 179570, "loss": 0.0026, "lr": 1.9014868853371944e-05, "epoch": 0.3803530656568469, "percentage": 3.8, "elapsed_time": "1:29:34", "remaining_time": "1 day, 13:45:28", "throughput": 707.73, "total_tokens": 3803680} +{"current_steps": 6835, "total_steps": 179570, "loss": 0.0089, "lr": 1.9028791000723954e-05, "epoch": 0.38063150860388706, "percentage": 3.81, "elapsed_time": "1:29:38", "remaining_time": "1 day, 13:45:25", "throughput": 707.74, "total_tokens": 3806560} +{"current_steps": 6840, "total_steps": 179570, "loss": 0.1817, "lr": 1.904271314807596e-05, "epoch": 0.3809099515509272, "percentage": 3.81, "elapsed_time": "1:29:42", "remaining_time": "1 day, 13:45:21", "throughput": 707.73, "total_tokens": 3809280} +{"current_steps": 6845, "total_steps": 179570, "loss": 0.4966, "lr": 1.9056635295427967e-05, "epoch": 0.3811883944979674, "percentage": 3.81, "elapsed_time": "1:29:46", "remaining_time": "1 day, 13:45:13", "throughput": 707.73, "total_tokens": 3811968} +{"current_steps": 6850, "total_steps": 179570, "loss": 0.0952, "lr": 1.9070557442779977e-05, "epoch": 0.38146683744500753, "percentage": 3.81, "elapsed_time": "1:29:50", "remaining_time": "1 day, 13:45:09", "throughput": 707.73, "total_tokens": 3814720} +{"current_steps": 6855, "total_steps": 179570, "loss": 0.2057, "lr": 1.908447959013198e-05, "epoch": 0.3817452803920477, "percentage": 3.82, "elapsed_time": "1:29:54", "remaining_time": "1 day, 13:45:13", "throughput": 707.76, "total_tokens": 3817888} +{"current_steps": 6860, "total_steps": 179570, "loss": 0.3779, "lr": 1.909840173748399e-05, "epoch": 0.3820237233390878, "percentage": 3.82, "elapsed_time": "1:29:57", "remaining_time": "1 day, 13:44:57", "throughput": 707.73, "total_tokens": 3820224} +{"current_steps": 6865, "total_steps": 179570, "loss": 0.0765, "lr": 1.9112323884835997e-05, "epoch": 0.38230216628612795, "percentage": 3.82, "elapsed_time": "1:30:02", "remaining_time": "1 day, 13:45:00", "throughput": 707.74, "total_tokens": 3823248} +{"current_steps": 6870, "total_steps": 179570, "loss": 0.2066, "lr": 1.9126246032188007e-05, "epoch": 0.3825806092331681, "percentage": 3.83, "elapsed_time": "1:30:06", "remaining_time": "1 day, 13:44:58", "throughput": 707.76, "total_tokens": 3826144} +{"current_steps": 6875, "total_steps": 179570, "loss": 0.0864, "lr": 1.9140168179540013e-05, "epoch": 0.38285905218020827, "percentage": 3.83, "elapsed_time": "1:30:09", "remaining_time": "1 day, 13:44:53", "throughput": 707.74, "total_tokens": 3828832} +{"current_steps": 6880, "total_steps": 179570, "loss": 0.0004, "lr": 1.915409032689202e-05, "epoch": 0.38313749512724843, "percentage": 3.83, "elapsed_time": "1:30:13", "remaining_time": "1 day, 13:44:49", "throughput": 707.74, "total_tokens": 3831600} +{"current_steps": 6885, "total_steps": 179570, "loss": 0.4337, "lr": 1.916801247424403e-05, "epoch": 0.3834159380742886, "percentage": 3.83, "elapsed_time": "1:30:17", "remaining_time": "1 day, 13:44:48", "throughput": 707.77, "total_tokens": 3834624} +{"current_steps": 6890, "total_steps": 179570, "loss": 0.0341, "lr": 1.9181934621596036e-05, "epoch": 0.38369438102132875, "percentage": 3.84, "elapsed_time": "1:30:22", "remaining_time": "1 day, 13:44:48", "throughput": 707.8, "total_tokens": 3837680} +{"current_steps": 6895, "total_steps": 179570, "loss": 0.3234, "lr": 1.9195856768948043e-05, "epoch": 0.3839728239683689, "percentage": 3.84, "elapsed_time": "1:30:25", "remaining_time": "1 day, 13:44:39", "throughput": 707.8, "total_tokens": 3840304} +{"current_steps": 6900, "total_steps": 179570, "loss": 0.2588, "lr": 1.920977891630005e-05, "epoch": 0.384251266915409, "percentage": 3.84, "elapsed_time": "1:30:29", "remaining_time": "1 day, 13:44:35", "throughput": 707.8, "total_tokens": 3843120} +{"current_steps": 6905, "total_steps": 179570, "loss": 0.2851, "lr": 1.922370106365206e-05, "epoch": 0.38452970986244916, "percentage": 3.85, "elapsed_time": "1:30:33", "remaining_time": "1 day, 13:44:19", "throughput": 707.78, "total_tokens": 3845456} +{"current_steps": 6910, "total_steps": 179570, "loss": 0.0462, "lr": 1.9237623211004066e-05, "epoch": 0.3848081528094893, "percentage": 3.85, "elapsed_time": "1:30:37", "remaining_time": "1 day, 13:44:16", "throughput": 707.78, "total_tokens": 3848272} +{"current_steps": 6915, "total_steps": 179570, "loss": 0.0006, "lr": 1.9251545358356076e-05, "epoch": 0.3850865957565295, "percentage": 3.85, "elapsed_time": "1:30:41", "remaining_time": "1 day, 13:44:23", "throughput": 707.78, "total_tokens": 3851360} +{"current_steps": 6920, "total_steps": 179570, "loss": 0.0987, "lr": 1.9265467505708082e-05, "epoch": 0.38536503870356964, "percentage": 3.85, "elapsed_time": "1:30:45", "remaining_time": "1 day, 13:44:22", "throughput": 707.78, "total_tokens": 3854240} +{"current_steps": 6925, "total_steps": 179570, "loss": 0.1678, "lr": 1.927938965306009e-05, "epoch": 0.3856434816506098, "percentage": 3.86, "elapsed_time": "1:30:49", "remaining_time": "1 day, 13:44:22", "throughput": 707.78, "total_tokens": 3857120} +{"current_steps": 6930, "total_steps": 179570, "loss": 0.254, "lr": 1.92933118004121e-05, "epoch": 0.38592192459764996, "percentage": 3.86, "elapsed_time": "1:30:53", "remaining_time": "1 day, 13:44:21", "throughput": 707.78, "total_tokens": 3860000} +{"current_steps": 6935, "total_steps": 179570, "loss": 0.2531, "lr": 1.93072339477641e-05, "epoch": 0.3862003675446901, "percentage": 3.86, "elapsed_time": "1:30:57", "remaining_time": "1 day, 13:44:24", "throughput": 707.8, "total_tokens": 3863120} +{"current_steps": 6940, "total_steps": 179570, "loss": 0.2399, "lr": 1.932115609511611e-05, "epoch": 0.3864788104917302, "percentage": 3.86, "elapsed_time": "1:31:01", "remaining_time": "1 day, 13:44:20", "throughput": 707.78, "total_tokens": 3865760} +{"current_steps": 6945, "total_steps": 179570, "loss": 0.0038, "lr": 1.9335078242468118e-05, "epoch": 0.3867572534387704, "percentage": 3.87, "elapsed_time": "1:31:05", "remaining_time": "1 day, 13:44:18", "throughput": 707.81, "total_tokens": 3868768} +{"current_steps": 6950, "total_steps": 179570, "loss": 0.1677, "lr": 1.9349000389820128e-05, "epoch": 0.38703569638581053, "percentage": 3.87, "elapsed_time": "1:31:09", "remaining_time": "1 day, 13:44:15", "throughput": 707.83, "total_tokens": 3871664} +{"current_steps": 6955, "total_steps": 179570, "loss": 0.4538, "lr": 1.9362922537172135e-05, "epoch": 0.3873141393328507, "percentage": 3.87, "elapsed_time": "1:31:13", "remaining_time": "1 day, 13:44:10", "throughput": 707.82, "total_tokens": 3874368} +{"current_steps": 6960, "total_steps": 179570, "loss": 0.1902, "lr": 1.937684468452414e-05, "epoch": 0.38759258227989085, "percentage": 3.88, "elapsed_time": "1:31:17", "remaining_time": "1 day, 13:44:06", "throughput": 707.82, "total_tokens": 3877184} +{"current_steps": 6965, "total_steps": 179570, "loss": 0.3047, "lr": 1.939076683187615e-05, "epoch": 0.387871025226931, "percentage": 3.88, "elapsed_time": "1:31:21", "remaining_time": "1 day, 13:43:58", "throughput": 707.81, "total_tokens": 3879776} +{"current_steps": 6970, "total_steps": 179570, "loss": 0.0682, "lr": 1.9404688979228157e-05, "epoch": 0.38814946817397117, "percentage": 3.88, "elapsed_time": "1:31:25", "remaining_time": "1 day, 13:43:59", "throughput": 707.82, "total_tokens": 3882784} +{"current_steps": 6975, "total_steps": 179570, "loss": 0.4045, "lr": 1.9418611126580164e-05, "epoch": 0.3884279111210113, "percentage": 3.88, "elapsed_time": "1:31:29", "remaining_time": "1 day, 13:43:44", "throughput": 707.81, "total_tokens": 3885184} +{"current_steps": 6980, "total_steps": 179570, "loss": 0.2189, "lr": 1.943253327393217e-05, "epoch": 0.38870635406805143, "percentage": 3.89, "elapsed_time": "1:31:32", "remaining_time": "1 day, 13:43:34", "throughput": 707.81, "total_tokens": 3887776} +{"current_steps": 6985, "total_steps": 179570, "loss": 0.29, "lr": 1.944645542128418e-05, "epoch": 0.3889847970150916, "percentage": 3.89, "elapsed_time": "1:31:36", "remaining_time": "1 day, 13:43:15", "throughput": 707.78, "total_tokens": 3890000} +{"current_steps": 6990, "total_steps": 179570, "loss": 0.5462, "lr": 1.9460377568636187e-05, "epoch": 0.38926323996213175, "percentage": 3.89, "elapsed_time": "1:31:40", "remaining_time": "1 day, 13:43:18", "throughput": 707.79, "total_tokens": 3893008} +{"current_steps": 6995, "total_steps": 179570, "loss": 0.099, "lr": 1.9474299715988193e-05, "epoch": 0.3895416829091719, "percentage": 3.9, "elapsed_time": "1:31:44", "remaining_time": "1 day, 13:43:25", "throughput": 707.8, "total_tokens": 3896176} +{"current_steps": 7000, "total_steps": 179570, "loss": 0.2238, "lr": 1.9488221863340203e-05, "epoch": 0.38982012585621206, "percentage": 3.9, "elapsed_time": "1:31:48", "remaining_time": "1 day, 13:43:18", "throughput": 707.82, "total_tokens": 3898960} +{"current_steps": 7005, "total_steps": 179570, "loss": 0.1953, "lr": 1.950214401069221e-05, "epoch": 0.3900985688032522, "percentage": 3.9, "elapsed_time": "1:31:52", "remaining_time": "1 day, 13:43:10", "throughput": 707.82, "total_tokens": 3901616} +{"current_steps": 7010, "total_steps": 179570, "loss": 0.3515, "lr": 1.951606615804422e-05, "epoch": 0.3903770117502924, "percentage": 3.9, "elapsed_time": "1:31:56", "remaining_time": "1 day, 13:43:07", "throughput": 707.81, "total_tokens": 3904416} +{"current_steps": 7015, "total_steps": 179570, "loss": 0.3722, "lr": 1.9529988305396223e-05, "epoch": 0.39065545469733254, "percentage": 3.91, "elapsed_time": "1:32:00", "remaining_time": "1 day, 13:43:03", "throughput": 707.8, "total_tokens": 3907104} +{"current_steps": 7020, "total_steps": 179570, "loss": 0.1039, "lr": 1.9543910452748233e-05, "epoch": 0.39093389764437264, "percentage": 3.91, "elapsed_time": "1:32:03", "remaining_time": "1 day, 13:42:53", "throughput": 707.79, "total_tokens": 3909664} +{"current_steps": 7025, "total_steps": 179570, "loss": 0.1154, "lr": 1.955783260010024e-05, "epoch": 0.3912123405914128, "percentage": 3.91, "elapsed_time": "1:32:07", "remaining_time": "1 day, 13:42:55", "throughput": 707.8, "total_tokens": 3912688} +{"current_steps": 7030, "total_steps": 179570, "loss": 0.109, "lr": 1.957175474745225e-05, "epoch": 0.39149078353845296, "percentage": 3.91, "elapsed_time": "1:32:12", "remaining_time": "1 day, 13:42:57", "throughput": 707.8, "total_tokens": 3915680} +{"current_steps": 7035, "total_steps": 179570, "loss": 0.3114, "lr": 1.9585676894804256e-05, "epoch": 0.3917692264854931, "percentage": 3.92, "elapsed_time": "1:32:16", "remaining_time": "1 day, 13:43:01", "throughput": 707.79, "total_tokens": 3918640} +{"current_steps": 7040, "total_steps": 179570, "loss": 0.4895, "lr": 1.9599599042156262e-05, "epoch": 0.3920476694325333, "percentage": 3.92, "elapsed_time": "1:32:19", "remaining_time": "1 day, 13:42:47", "throughput": 707.78, "total_tokens": 3921008} +{"current_steps": 7045, "total_steps": 179570, "loss": 0.0831, "lr": 1.9613521189508272e-05, "epoch": 0.39232611237957343, "percentage": 3.92, "elapsed_time": "1:32:24", "remaining_time": "1 day, 13:42:49", "throughput": 707.78, "total_tokens": 3924016} +{"current_steps": 7050, "total_steps": 179570, "loss": 0.1711, "lr": 1.962744333686028e-05, "epoch": 0.3926045553266136, "percentage": 3.93, "elapsed_time": "1:32:28", "remaining_time": "1 day, 13:42:49", "throughput": 707.81, "total_tokens": 3927056} +{"current_steps": 7055, "total_steps": 179570, "loss": 0.037, "lr": 1.9641365484212285e-05, "epoch": 0.39288299827365375, "percentage": 3.93, "elapsed_time": "1:32:32", "remaining_time": "1 day, 13:42:51", "throughput": 707.81, "total_tokens": 3930032} +{"current_steps": 7060, "total_steps": 179570, "loss": 0.1496, "lr": 1.9655287631564292e-05, "epoch": 0.39316144122069385, "percentage": 3.93, "elapsed_time": "1:32:36", "remaining_time": "1 day, 13:42:58", "throughput": 707.82, "total_tokens": 3933184} +{"current_steps": 7065, "total_steps": 179570, "loss": 0.0316, "lr": 1.9669209778916302e-05, "epoch": 0.393439884167734, "percentage": 3.93, "elapsed_time": "1:32:40", "remaining_time": "1 day, 13:42:57", "throughput": 707.83, "total_tokens": 3936096} +{"current_steps": 7070, "total_steps": 179570, "loss": 0.1881, "lr": 1.968313192626831e-05, "epoch": 0.39371832711477417, "percentage": 3.94, "elapsed_time": "1:32:44", "remaining_time": "1 day, 13:42:56", "throughput": 707.85, "total_tokens": 3939104} +{"current_steps": 7075, "total_steps": 179570, "loss": 0.144, "lr": 1.9697054073620315e-05, "epoch": 0.3939967700618143, "percentage": 3.94, "elapsed_time": "1:32:48", "remaining_time": "1 day, 13:42:53", "throughput": 707.85, "total_tokens": 3941888} +{"current_steps": 7080, "total_steps": 179570, "loss": 0.2005, "lr": 1.9710976220972325e-05, "epoch": 0.3942752130088545, "percentage": 3.94, "elapsed_time": "1:32:52", "remaining_time": "1 day, 13:42:48", "throughput": 707.84, "total_tokens": 3944624} +{"current_steps": 7085, "total_steps": 179570, "loss": 0.0035, "lr": 1.972489836832433e-05, "epoch": 0.39455365595589464, "percentage": 3.95, "elapsed_time": "1:32:56", "remaining_time": "1 day, 13:42:48", "throughput": 707.84, "total_tokens": 3947504} +{"current_steps": 7090, "total_steps": 179570, "loss": 0.4133, "lr": 1.973882051567634e-05, "epoch": 0.3948320989029348, "percentage": 3.95, "elapsed_time": "1:33:00", "remaining_time": "1 day, 13:42:31", "throughput": 707.82, "total_tokens": 3949776} +{"current_steps": 7095, "total_steps": 179570, "loss": 0.1082, "lr": 1.9752742663028344e-05, "epoch": 0.39511054184997496, "percentage": 3.95, "elapsed_time": "1:33:04", "remaining_time": "1 day, 13:42:32", "throughput": 707.83, "total_tokens": 3952800} +{"current_steps": 7100, "total_steps": 179570, "loss": 0.0562, "lr": 1.9766664810380354e-05, "epoch": 0.39538898479701506, "percentage": 3.95, "elapsed_time": "1:33:08", "remaining_time": "1 day, 13:42:32", "throughput": 707.86, "total_tokens": 3955840} +{"current_steps": 7105, "total_steps": 179570, "loss": 0.1979, "lr": 1.978058695773236e-05, "epoch": 0.3956674277440552, "percentage": 3.96, "elapsed_time": "1:33:12", "remaining_time": "1 day, 13:42:38", "throughput": 707.87, "total_tokens": 3959008} +{"current_steps": 7110, "total_steps": 179570, "loss": 0.1051, "lr": 1.9794509105084367e-05, "epoch": 0.3959458706910954, "percentage": 3.96, "elapsed_time": "1:33:17", "remaining_time": "1 day, 13:42:41", "throughput": 707.88, "total_tokens": 3962000} +{"current_steps": 7115, "total_steps": 179570, "loss": 0.0198, "lr": 1.9808431252436377e-05, "epoch": 0.39622431363813554, "percentage": 3.96, "elapsed_time": "1:33:21", "remaining_time": "1 day, 13:42:39", "throughput": 707.89, "total_tokens": 3964928} +{"current_steps": 7120, "total_steps": 179570, "loss": 0.0042, "lr": 1.9822353399788384e-05, "epoch": 0.3965027565851757, "percentage": 3.97, "elapsed_time": "1:33:25", "remaining_time": "1 day, 13:42:36", "throughput": 707.9, "total_tokens": 3967808} +{"current_steps": 7125, "total_steps": 179570, "loss": 0.0003, "lr": 1.9836275547140394e-05, "epoch": 0.39678119953221586, "percentage": 3.97, "elapsed_time": "1:33:29", "remaining_time": "1 day, 13:42:35", "throughput": 707.93, "total_tokens": 3970816} +{"current_steps": 7130, "total_steps": 179570, "loss": 0.2182, "lr": 1.98501976944924e-05, "epoch": 0.397059642479256, "percentage": 3.97, "elapsed_time": "1:33:33", "remaining_time": "1 day, 13:42:39", "throughput": 707.96, "total_tokens": 3974000} +{"current_steps": 7135, "total_steps": 179570, "loss": 0.2156, "lr": 1.9864119841844407e-05, "epoch": 0.3973380854262962, "percentage": 3.97, "elapsed_time": "1:33:37", "remaining_time": "1 day, 13:42:38", "throughput": 707.97, "total_tokens": 3976928} +{"current_steps": 7140, "total_steps": 179570, "loss": 0.4957, "lr": 1.9878041989196413e-05, "epoch": 0.39761652837333633, "percentage": 3.98, "elapsed_time": "1:33:41", "remaining_time": "1 day, 13:42:28", "throughput": 707.94, "total_tokens": 3979424} +{"current_steps": 7145, "total_steps": 179570, "loss": 0.163, "lr": 1.9891964136548423e-05, "epoch": 0.39789497132037643, "percentage": 3.98, "elapsed_time": "1:33:45", "remaining_time": "1 day, 13:42:33", "throughput": 707.94, "total_tokens": 3982464} +{"current_steps": 7150, "total_steps": 179570, "loss": 0.1552, "lr": 1.990588628390043e-05, "epoch": 0.3981734142674166, "percentage": 3.98, "elapsed_time": "1:33:49", "remaining_time": "1 day, 13:42:30", "throughput": 707.95, "total_tokens": 3985312} +{"current_steps": 7155, "total_steps": 179570, "loss": 0.5968, "lr": 1.9919808431252436e-05, "epoch": 0.39845185721445675, "percentage": 3.98, "elapsed_time": "1:33:53", "remaining_time": "1 day, 13:42:32", "throughput": 707.95, "total_tokens": 3988288} +{"current_steps": 7160, "total_steps": 179570, "loss": 0.0519, "lr": 1.9933730578604446e-05, "epoch": 0.3987303001614969, "percentage": 3.99, "elapsed_time": "1:33:57", "remaining_time": "1 day, 13:42:25", "throughput": 707.96, "total_tokens": 3991008} +{"current_steps": 7165, "total_steps": 179570, "loss": 0.002, "lr": 1.9947652725956453e-05, "epoch": 0.39900874310853707, "percentage": 3.99, "elapsed_time": "1:34:01", "remaining_time": "1 day, 13:42:28", "throughput": 707.97, "total_tokens": 3994064} +{"current_steps": 7170, "total_steps": 179570, "loss": 0.2727, "lr": 1.9961574873308463e-05, "epoch": 0.3992871860555772, "percentage": 3.99, "elapsed_time": "1:34:05", "remaining_time": "1 day, 13:42:28", "throughput": 707.99, "total_tokens": 3997072} +{"current_steps": 7175, "total_steps": 179570, "loss": 0.0188, "lr": 1.9975497020660466e-05, "epoch": 0.3995656290026174, "percentage": 4.0, "elapsed_time": "1:34:09", "remaining_time": "1 day, 13:42:28", "throughput": 707.99, "total_tokens": 4000000} +{"current_steps": 7180, "total_steps": 179570, "loss": 0.228, "lr": 1.9989419168012476e-05, "epoch": 0.39984407194965754, "percentage": 4.0, "elapsed_time": "1:34:13", "remaining_time": "1 day, 13:42:24", "throughput": 707.98, "total_tokens": 4002720} +{"current_steps": 7185, "total_steps": 179570, "loss": 0.4783, "lr": 2.0003341315364482e-05, "epoch": 0.40012251489669765, "percentage": 4.0, "elapsed_time": "1:34:17", "remaining_time": "1 day, 13:42:09", "throughput": 707.95, "total_tokens": 4005008} +{"current_steps": 7190, "total_steps": 179570, "loss": 0.3611, "lr": 2.001726346271649e-05, "epoch": 0.4004009578437378, "percentage": 4.0, "elapsed_time": "1:34:21", "remaining_time": "1 day, 13:42:05", "throughput": 707.95, "total_tokens": 4007808} +{"current_steps": 7195, "total_steps": 179570, "loss": 0.0014, "lr": 2.00311856100685e-05, "epoch": 0.40067940079077796, "percentage": 4.01, "elapsed_time": "1:34:25", "remaining_time": "1 day, 13:42:04", "throughput": 707.96, "total_tokens": 4010720} +{"current_steps": 7200, "total_steps": 179570, "loss": 0.241, "lr": 2.0045107757420505e-05, "epoch": 0.4009578437378181, "percentage": 4.01, "elapsed_time": "1:34:29", "remaining_time": "1 day, 13:42:00", "throughput": 707.95, "total_tokens": 4013456} +{"current_steps": 7205, "total_steps": 179570, "loss": 0.1533, "lr": 2.0059029904772515e-05, "epoch": 0.4012362866848583, "percentage": 4.01, "elapsed_time": "1:34:33", "remaining_time": "1 day, 13:42:02", "throughput": 707.95, "total_tokens": 4016448} +{"current_steps": 7210, "total_steps": 179570, "loss": 0.2932, "lr": 2.007295205212452e-05, "epoch": 0.40151472963189844, "percentage": 4.02, "elapsed_time": "1:34:37", "remaining_time": "1 day, 13:42:01", "throughput": 707.97, "total_tokens": 4019424} +{"current_steps": 7215, "total_steps": 179570, "loss": 0.0129, "lr": 2.0086874199476528e-05, "epoch": 0.4017931725789386, "percentage": 4.02, "elapsed_time": "1:34:40", "remaining_time": "1 day, 13:41:44", "throughput": 707.94, "total_tokens": 4021664} +{"current_steps": 7220, "total_steps": 179570, "loss": 0.5987, "lr": 2.0100796346828535e-05, "epoch": 0.40207161552597875, "percentage": 4.02, "elapsed_time": "1:34:44", "remaining_time": "1 day, 13:41:41", "throughput": 707.92, "total_tokens": 4024320} +{"current_steps": 7225, "total_steps": 179570, "loss": 0.0003, "lr": 2.011471849418054e-05, "epoch": 0.40235005847301886, "percentage": 4.02, "elapsed_time": "1:34:48", "remaining_time": "1 day, 13:41:40", "throughput": 707.94, "total_tokens": 4027328} +{"current_steps": 7230, "total_steps": 179570, "loss": 0.271, "lr": 2.012864064153255e-05, "epoch": 0.402628501420059, "percentage": 4.03, "elapsed_time": "1:34:52", "remaining_time": "1 day, 13:41:23", "throughput": 707.92, "total_tokens": 4029600} +{"current_steps": 7235, "total_steps": 179570, "loss": 0.2298, "lr": 2.0142562788884558e-05, "epoch": 0.4029069443670992, "percentage": 4.03, "elapsed_time": "1:34:56", "remaining_time": "1 day, 13:41:19", "throughput": 707.92, "total_tokens": 4032400} +{"current_steps": 7240, "total_steps": 179570, "loss": 0.3234, "lr": 2.0156484936236567e-05, "epoch": 0.40318538731413933, "percentage": 4.03, "elapsed_time": "1:35:00", "remaining_time": "1 day, 13:41:18", "throughput": 707.93, "total_tokens": 4035344} +{"current_steps": 7245, "total_steps": 179570, "loss": 0.3172, "lr": 2.0170407083588574e-05, "epoch": 0.4034638302611795, "percentage": 4.03, "elapsed_time": "1:35:04", "remaining_time": "1 day, 13:41:17", "throughput": 707.95, "total_tokens": 4038336} +{"current_steps": 7250, "total_steps": 179570, "loss": 0.0046, "lr": 2.0184329230940584e-05, "epoch": 0.40374227320821965, "percentage": 4.04, "elapsed_time": "1:35:08", "remaining_time": "1 day, 13:41:13", "throughput": 707.95, "total_tokens": 4041136} +{"current_steps": 7255, "total_steps": 179570, "loss": 0.1561, "lr": 2.0198251378292587e-05, "epoch": 0.4040207161552598, "percentage": 4.04, "elapsed_time": "1:35:11", "remaining_time": "1 day, 13:40:59", "throughput": 707.94, "total_tokens": 4043504} +{"current_steps": 7260, "total_steps": 179570, "loss": 0.0358, "lr": 2.0212173525644597e-05, "epoch": 0.40429915910229997, "percentage": 4.04, "elapsed_time": "1:35:15", "remaining_time": "1 day, 13:40:58", "throughput": 707.95, "total_tokens": 4046480} +{"current_steps": 7265, "total_steps": 179570, "loss": 0.2442, "lr": 2.0226095672996603e-05, "epoch": 0.40457760204934007, "percentage": 4.05, "elapsed_time": "1:35:19", "remaining_time": "1 day, 13:40:53", "throughput": 707.95, "total_tokens": 4049248} +{"current_steps": 7270, "total_steps": 179570, "loss": 0.208, "lr": 2.024001782034861e-05, "epoch": 0.4048560449963802, "percentage": 4.05, "elapsed_time": "1:35:23", "remaining_time": "1 day, 13:40:42", "throughput": 707.94, "total_tokens": 4051728} +{"current_steps": 7275, "total_steps": 179570, "loss": 0.3215, "lr": 2.025393996770062e-05, "epoch": 0.4051344879434204, "percentage": 4.05, "elapsed_time": "1:35:26", "remaining_time": "1 day, 13:40:32", "throughput": 707.93, "total_tokens": 4054272} +{"current_steps": 7280, "total_steps": 179570, "loss": 0.0512, "lr": 2.0267862115052626e-05, "epoch": 0.40541293089046054, "percentage": 4.05, "elapsed_time": "1:35:30", "remaining_time": "1 day, 13:40:27", "throughput": 707.9, "total_tokens": 4056880} +{"current_steps": 7285, "total_steps": 179570, "loss": 0.0791, "lr": 2.0281784262404636e-05, "epoch": 0.4056913738375007, "percentage": 4.06, "elapsed_time": "1:35:35", "remaining_time": "1 day, 13:40:30", "throughput": 707.92, "total_tokens": 4059968} +{"current_steps": 7290, "total_steps": 179570, "loss": 0.6075, "lr": 2.0295706409756643e-05, "epoch": 0.40596981678454086, "percentage": 4.06, "elapsed_time": "1:35:38", "remaining_time": "1 day, 13:40:21", "throughput": 707.9, "total_tokens": 4062528} +{"current_steps": 7295, "total_steps": 179570, "loss": 0.3387, "lr": 2.030962855710865e-05, "epoch": 0.406248259731581, "percentage": 4.06, "elapsed_time": "1:35:42", "remaining_time": "1 day, 13:40:20", "throughput": 707.92, "total_tokens": 4065488} +{"current_steps": 7300, "total_steps": 179570, "loss": 0.0199, "lr": 2.0323550704460656e-05, "epoch": 0.4065267026786212, "percentage": 4.07, "elapsed_time": "1:35:47", "remaining_time": "1 day, 13:40:26", "throughput": 707.93, "total_tokens": 4068624} +{"current_steps": 7305, "total_steps": 179570, "loss": 0.0734, "lr": 2.0337472851812662e-05, "epoch": 0.4068051456256613, "percentage": 4.07, "elapsed_time": "1:35:50", "remaining_time": "1 day, 13:40:17", "throughput": 707.92, "total_tokens": 4071184} +{"current_steps": 7310, "total_steps": 179570, "loss": 0.199, "lr": 2.0351394999164672e-05, "epoch": 0.40708358857270144, "percentage": 4.07, "elapsed_time": "1:35:55", "remaining_time": "1 day, 13:40:22", "throughput": 707.91, "total_tokens": 4074208} +{"current_steps": 7315, "total_steps": 179570, "loss": 0.1539, "lr": 2.036531714651668e-05, "epoch": 0.4073620315197416, "percentage": 4.07, "elapsed_time": "1:35:59", "remaining_time": "1 day, 13:40:21", "throughput": 707.93, "total_tokens": 4077232} +{"current_steps": 7320, "total_steps": 179570, "loss": 0.2518, "lr": 2.037923929386869e-05, "epoch": 0.40764047446678175, "percentage": 4.08, "elapsed_time": "1:36:03", "remaining_time": "1 day, 13:40:27", "throughput": 707.94, "total_tokens": 4080320} +{"current_steps": 7325, "total_steps": 179570, "loss": 0.0942, "lr": 2.0393161441220695e-05, "epoch": 0.4079189174138219, "percentage": 4.08, "elapsed_time": "1:36:07", "remaining_time": "1 day, 13:40:19", "throughput": 707.92, "total_tokens": 4082912} +{"current_steps": 7330, "total_steps": 179570, "loss": 0.0285, "lr": 2.0407083588572702e-05, "epoch": 0.40819736036086207, "percentage": 4.08, "elapsed_time": "1:36:11", "remaining_time": "1 day, 13:40:21", "throughput": 707.93, "total_tokens": 4085904} +{"current_steps": 7335, "total_steps": 179570, "loss": 0.1098, "lr": 2.042100573592471e-05, "epoch": 0.40847580330790223, "percentage": 4.08, "elapsed_time": "1:36:15", "remaining_time": "1 day, 13:40:13", "throughput": 707.95, "total_tokens": 4088656} +{"current_steps": 7340, "total_steps": 179570, "loss": 0.1993, "lr": 2.0434927883276715e-05, "epoch": 0.4087542462549424, "percentage": 4.09, "elapsed_time": "1:36:19", "remaining_time": "1 day, 13:40:09", "throughput": 707.95, "total_tokens": 4091472} +{"current_steps": 7345, "total_steps": 179570, "loss": 0.1313, "lr": 2.0448850030628725e-05, "epoch": 0.4090326892019825, "percentage": 4.09, "elapsed_time": "1:36:23", "remaining_time": "1 day, 13:40:08", "throughput": 707.98, "total_tokens": 4094496} +{"current_steps": 7350, "total_steps": 179570, "loss": 0.0813, "lr": 2.046277217798073e-05, "epoch": 0.40931113214902265, "percentage": 4.09, "elapsed_time": "1:36:27", "remaining_time": "1 day, 13:40:10", "throughput": 707.97, "total_tokens": 4097456} +{"current_steps": 7355, "total_steps": 179570, "loss": 0.0853, "lr": 2.047669432533274e-05, "epoch": 0.4095895750960628, "percentage": 4.1, "elapsed_time": "1:36:31", "remaining_time": "1 day, 13:40:09", "throughput": 708.0, "total_tokens": 4100464} +{"current_steps": 7360, "total_steps": 179570, "loss": 0.1772, "lr": 2.0490616472684748e-05, "epoch": 0.40986801804310297, "percentage": 4.1, "elapsed_time": "1:36:35", "remaining_time": "1 day, 13:40:12", "throughput": 708.01, "total_tokens": 4103552} +{"current_steps": 7365, "total_steps": 179570, "loss": 0.0016, "lr": 2.0504538620036758e-05, "epoch": 0.4101464609901431, "percentage": 4.1, "elapsed_time": "1:36:39", "remaining_time": "1 day, 13:40:09", "throughput": 708.01, "total_tokens": 4106368} +{"current_steps": 7370, "total_steps": 179570, "loss": 0.0583, "lr": 2.0518460767388764e-05, "epoch": 0.4104249039371833, "percentage": 4.1, "elapsed_time": "1:36:44", "remaining_time": "1 day, 13:40:15", "throughput": 708.03, "total_tokens": 4109552} +{"current_steps": 7375, "total_steps": 179570, "loss": 0.2647, "lr": 2.053238291474077e-05, "epoch": 0.41070334688422344, "percentage": 4.11, "elapsed_time": "1:36:48", "remaining_time": "1 day, 13:40:14", "throughput": 708.03, "total_tokens": 4112448} +{"current_steps": 7380, "total_steps": 179570, "loss": 0.1222, "lr": 2.0546305062092777e-05, "epoch": 0.4109817898312636, "percentage": 4.11, "elapsed_time": "1:36:52", "remaining_time": "1 day, 13:40:12", "throughput": 708.04, "total_tokens": 4115344} +{"current_steps": 7385, "total_steps": 179570, "loss": 0.5649, "lr": 2.0560227209444784e-05, "epoch": 0.4112602327783037, "percentage": 4.11, "elapsed_time": "1:36:56", "remaining_time": "1 day, 13:40:04", "throughput": 708.02, "total_tokens": 4117920} +{"current_steps": 7390, "total_steps": 179570, "loss": 0.1169, "lr": 2.0574149356796794e-05, "epoch": 0.41153867572534386, "percentage": 4.12, "elapsed_time": "1:36:59", "remaining_time": "1 day, 13:40:00", "throughput": 708.02, "total_tokens": 4120688} +{"current_steps": 7395, "total_steps": 179570, "loss": 0.1174, "lr": 2.05880715041488e-05, "epoch": 0.411817118672384, "percentage": 4.12, "elapsed_time": "1:37:03", "remaining_time": "1 day, 13:39:57", "throughput": 708.02, "total_tokens": 4123504} +{"current_steps": 7400, "total_steps": 179570, "loss": 0.4229, "lr": 2.060199365150081e-05, "epoch": 0.4120955616194242, "percentage": 4.12, "elapsed_time": "1:37:07", "remaining_time": "1 day, 13:39:54", "throughput": 708.03, "total_tokens": 4126336} +{"current_steps": 7405, "total_steps": 179570, "loss": 0.0455, "lr": 2.0615915798852817e-05, "epoch": 0.41237400456646434, "percentage": 4.12, "elapsed_time": "1:37:12", "remaining_time": "1 day, 13:40:00", "throughput": 708.04, "total_tokens": 4129520} +{"current_steps": 7410, "total_steps": 179570, "loss": 0.1398, "lr": 2.0629837946204823e-05, "epoch": 0.4126524475135045, "percentage": 4.13, "elapsed_time": "1:37:15", "remaining_time": "1 day, 13:39:39", "throughput": 708.02, "total_tokens": 4131680} +{"current_steps": 7415, "total_steps": 179570, "loss": 0.243, "lr": 2.064376009355683e-05, "epoch": 0.41293089046054465, "percentage": 4.13, "elapsed_time": "1:37:19", "remaining_time": "1 day, 13:39:38", "throughput": 708.04, "total_tokens": 4134672} +{"current_steps": 7420, "total_steps": 179570, "loss": 0.5957, "lr": 2.0657682240908836e-05, "epoch": 0.4132093334075848, "percentage": 4.13, "elapsed_time": "1:37:23", "remaining_time": "1 day, 13:39:31", "throughput": 708.05, "total_tokens": 4137408} +{"current_steps": 7425, "total_steps": 179570, "loss": 0.0525, "lr": 2.0671604388260846e-05, "epoch": 0.4134877763546249, "percentage": 4.13, "elapsed_time": "1:37:27", "remaining_time": "1 day, 13:39:27", "throughput": 708.07, "total_tokens": 4140320} +{"current_steps": 7430, "total_steps": 179570, "loss": 0.1172, "lr": 2.0685526535612853e-05, "epoch": 0.4137662193016651, "percentage": 4.14, "elapsed_time": "1:37:30", "remaining_time": "1 day, 13:39:12", "throughput": 708.03, "total_tokens": 4142528} +{"current_steps": 7435, "total_steps": 179570, "loss": 0.2363, "lr": 2.0699448682964863e-05, "epoch": 0.41404466224870523, "percentage": 4.14, "elapsed_time": "1:37:34", "remaining_time": "1 day, 13:39:07", "throughput": 708.03, "total_tokens": 4145296} +{"current_steps": 7440, "total_steps": 179570, "loss": 0.2673, "lr": 2.071337083031687e-05, "epoch": 0.4143231051957454, "percentage": 4.14, "elapsed_time": "1:37:38", "remaining_time": "1 day, 13:39:08", "throughput": 708.04, "total_tokens": 4148288} +{"current_steps": 7445, "total_steps": 179570, "loss": 0.0556, "lr": 2.0727292977668876e-05, "epoch": 0.41460154814278555, "percentage": 4.15, "elapsed_time": "1:37:41", "remaining_time": "1 day, 13:38:45", "throughput": 708.01, "total_tokens": 4150320} +{"current_steps": 7450, "total_steps": 179570, "loss": 0.2281, "lr": 2.0741215125020886e-05, "epoch": 0.4148799910898257, "percentage": 4.15, "elapsed_time": "1:37:46", "remaining_time": "1 day, 13:38:47", "throughput": 708.02, "total_tokens": 4153360} +{"current_steps": 7455, "total_steps": 179570, "loss": 0.4131, "lr": 2.0755137272372892e-05, "epoch": 0.41515843403686586, "percentage": 4.15, "elapsed_time": "1:37:49", "remaining_time": "1 day, 13:38:35", "throughput": 708.0, "total_tokens": 4155728} +{"current_steps": 7460, "total_steps": 179570, "loss": 0.1702, "lr": 2.07690594197249e-05, "epoch": 0.415436876983906, "percentage": 4.15, "elapsed_time": "1:37:53", "remaining_time": "1 day, 13:38:34", "throughput": 708.01, "total_tokens": 4158688} +{"current_steps": 7465, "total_steps": 179570, "loss": 0.0017, "lr": 2.0782981567076905e-05, "epoch": 0.4157153199309461, "percentage": 4.16, "elapsed_time": "1:37:57", "remaining_time": "1 day, 13:38:30", "throughput": 708.01, "total_tokens": 4161488} +{"current_steps": 7470, "total_steps": 179570, "loss": 0.1151, "lr": 2.0796903714428915e-05, "epoch": 0.4159937628779863, "percentage": 4.16, "elapsed_time": "1:38:01", "remaining_time": "1 day, 13:38:30", "throughput": 708.02, "total_tokens": 4164464} +{"current_steps": 7475, "total_steps": 179570, "loss": 0.038, "lr": 2.081082586178092e-05, "epoch": 0.41627220582502644, "percentage": 4.16, "elapsed_time": "1:38:05", "remaining_time": "1 day, 13:38:22", "throughput": 708.01, "total_tokens": 4167040} +{"current_steps": 7480, "total_steps": 179570, "loss": 0.0496, "lr": 2.082474800913293e-05, "epoch": 0.4165506487720666, "percentage": 4.17, "elapsed_time": "1:38:09", "remaining_time": "1 day, 13:38:21", "throughput": 708.02, "total_tokens": 4170016} +{"current_steps": 7485, "total_steps": 179570, "loss": 0.0785, "lr": 2.0838670156484938e-05, "epoch": 0.41682909171910676, "percentage": 4.17, "elapsed_time": "1:38:13", "remaining_time": "1 day, 13:38:19", "throughput": 708.03, "total_tokens": 4172912} +{"current_steps": 7490, "total_steps": 179570, "loss": 0.4276, "lr": 2.0852592303836945e-05, "epoch": 0.4171075346661469, "percentage": 4.17, "elapsed_time": "1:38:17", "remaining_time": "1 day, 13:38:12", "throughput": 708.02, "total_tokens": 4175536} +{"current_steps": 7495, "total_steps": 179570, "loss": 0.0039, "lr": 2.0866514451188954e-05, "epoch": 0.4173859776131871, "percentage": 4.17, "elapsed_time": "1:38:21", "remaining_time": "1 day, 13:38:12", "throughput": 708.02, "total_tokens": 4178432} +{"current_steps": 7500, "total_steps": 179570, "loss": 0.0167, "lr": 2.0880436598540958e-05, "epoch": 0.41766442056022723, "percentage": 4.18, "elapsed_time": "1:38:25", "remaining_time": "1 day, 13:38:10", "throughput": 708.02, "total_tokens": 4181296} +{"current_steps": 7505, "total_steps": 179570, "loss": 0.5754, "lr": 2.0894358745892968e-05, "epoch": 0.41794286350726734, "percentage": 4.18, "elapsed_time": "1:38:29", "remaining_time": "1 day, 13:37:56", "throughput": 708.01, "total_tokens": 4183728} +{"current_steps": 7510, "total_steps": 179570, "loss": 0.0304, "lr": 2.0908280893244974e-05, "epoch": 0.4182213064543075, "percentage": 4.18, "elapsed_time": "1:38:32", "remaining_time": "1 day, 13:37:49", "throughput": 708.02, "total_tokens": 4186480} +{"current_steps": 7515, "total_steps": 179570, "loss": 0.2509, "lr": 2.0922203040596984e-05, "epoch": 0.41849974940134765, "percentage": 4.18, "elapsed_time": "1:38:36", "remaining_time": "1 day, 13:37:39", "throughput": 708.0, "total_tokens": 4188976} +{"current_steps": 7520, "total_steps": 179570, "loss": 0.0921, "lr": 2.093612518794899e-05, "epoch": 0.4187781923483878, "percentage": 4.19, "elapsed_time": "1:38:40", "remaining_time": "1 day, 13:37:33", "throughput": 707.98, "total_tokens": 4191568} +{"current_steps": 7525, "total_steps": 179570, "loss": 0.0919, "lr": 2.0950047335300997e-05, "epoch": 0.41905663529542797, "percentage": 4.19, "elapsed_time": "1:38:44", "remaining_time": "1 day, 13:37:36", "throughput": 708.01, "total_tokens": 4194720} +{"current_steps": 7530, "total_steps": 179570, "loss": 0.0108, "lr": 2.0963969482653007e-05, "epoch": 0.41933507824246813, "percentage": 4.19, "elapsed_time": "1:38:48", "remaining_time": "1 day, 13:37:30", "throughput": 708.01, "total_tokens": 4197424} +{"current_steps": 7535, "total_steps": 179570, "loss": 0.0075, "lr": 2.0977891630005013e-05, "epoch": 0.4196135211895083, "percentage": 4.2, "elapsed_time": "1:38:52", "remaining_time": "1 day, 13:37:27", "throughput": 708.01, "total_tokens": 4200240} +{"current_steps": 7540, "total_steps": 179570, "loss": 0.4187, "lr": 2.099181377735702e-05, "epoch": 0.41989196413654845, "percentage": 4.2, "elapsed_time": "1:38:56", "remaining_time": "1 day, 13:37:19", "throughput": 707.97, "total_tokens": 4202704} +{"current_steps": 7545, "total_steps": 179570, "loss": 0.041, "lr": 2.1005735924709026e-05, "epoch": 0.42017040708358855, "percentage": 4.2, "elapsed_time": "1:39:00", "remaining_time": "1 day, 13:37:15", "throughput": 707.97, "total_tokens": 4205472} +{"current_steps": 7550, "total_steps": 179570, "loss": 0.083, "lr": 2.1019658072061036e-05, "epoch": 0.4204488500306287, "percentage": 4.2, "elapsed_time": "1:39:03", "remaining_time": "1 day, 13:37:03", "throughput": 707.96, "total_tokens": 4207952} +{"current_steps": 7555, "total_steps": 179570, "loss": 0.4187, "lr": 2.1033580219413043e-05, "epoch": 0.42072729297766887, "percentage": 4.21, "elapsed_time": "1:39:07", "remaining_time": "1 day, 13:37:05", "throughput": 707.98, "total_tokens": 4211040} +{"current_steps": 7560, "total_steps": 179570, "loss": 0.1144, "lr": 2.1047502366765053e-05, "epoch": 0.421005735924709, "percentage": 4.21, "elapsed_time": "1:39:12", "remaining_time": "1 day, 13:37:04", "throughput": 707.99, "total_tokens": 4213952} +{"current_steps": 7565, "total_steps": 179570, "loss": 0.3354, "lr": 2.106142451411706e-05, "epoch": 0.4212841788717492, "percentage": 4.21, "elapsed_time": "1:39:15", "remaining_time": "1 day, 13:36:55", "throughput": 707.99, "total_tokens": 4216592} +{"current_steps": 7570, "total_steps": 179570, "loss": 0.303, "lr": 2.1075346661469066e-05, "epoch": 0.42156262181878934, "percentage": 4.22, "elapsed_time": "1:39:19", "remaining_time": "1 day, 13:36:54", "throughput": 708.01, "total_tokens": 4219584} +{"current_steps": 7575, "total_steps": 179570, "loss": 0.5095, "lr": 2.1089268808821076e-05, "epoch": 0.4218410647658295, "percentage": 4.22, "elapsed_time": "1:39:23", "remaining_time": "1 day, 13:36:46", "throughput": 708.0, "total_tokens": 4222240} +{"current_steps": 7580, "total_steps": 179570, "loss": 0.0275, "lr": 2.110319095617308e-05, "epoch": 0.42211950771286966, "percentage": 4.22, "elapsed_time": "1:39:27", "remaining_time": "1 day, 13:36:39", "throughput": 708.01, "total_tokens": 4224992} +{"current_steps": 7585, "total_steps": 179570, "loss": 0.002, "lr": 2.111711310352509e-05, "epoch": 0.42239795065990976, "percentage": 4.22, "elapsed_time": "1:39:30", "remaining_time": "1 day, 13:36:25", "throughput": 707.99, "total_tokens": 4227296} +{"current_steps": 7590, "total_steps": 179570, "loss": 0.1029, "lr": 2.1131035250877095e-05, "epoch": 0.4226763936069499, "percentage": 4.23, "elapsed_time": "1:39:34", "remaining_time": "1 day, 13:36:15", "throughput": 707.99, "total_tokens": 4229904} +{"current_steps": 7595, "total_steps": 179570, "loss": 0.0995, "lr": 2.1144957398229105e-05, "epoch": 0.4229548365539901, "percentage": 4.23, "elapsed_time": "1:39:38", "remaining_time": "1 day, 13:36:15", "throughput": 708.01, "total_tokens": 4232912} +{"current_steps": 7600, "total_steps": 179570, "loss": 0.3508, "lr": 2.1158879545581112e-05, "epoch": 0.42323327950103024, "percentage": 4.23, "elapsed_time": "1:39:42", "remaining_time": "1 day, 13:36:14", "throughput": 708.03, "total_tokens": 4235904} +{"current_steps": 7605, "total_steps": 179570, "loss": 0.4708, "lr": 2.117280169293312e-05, "epoch": 0.4235117224480704, "percentage": 4.24, "elapsed_time": "1:39:46", "remaining_time": "1 day, 13:36:00", "throughput": 708.03, "total_tokens": 4238384} +{"current_steps": 7610, "total_steps": 179570, "loss": 0.1371, "lr": 2.1186723840285128e-05, "epoch": 0.42379016539511055, "percentage": 4.24, "elapsed_time": "1:39:49", "remaining_time": "1 day, 13:35:44", "throughput": 708.01, "total_tokens": 4240736} +{"current_steps": 7615, "total_steps": 179570, "loss": 0.2964, "lr": 2.1200645987637135e-05, "epoch": 0.4240686083421507, "percentage": 4.24, "elapsed_time": "1:39:53", "remaining_time": "1 day, 13:35:47", "throughput": 708.02, "total_tokens": 4243776} +{"current_steps": 7620, "total_steps": 179570, "loss": 0.3237, "lr": 2.121456813498914e-05, "epoch": 0.42434705128919087, "percentage": 4.24, "elapsed_time": "1:39:58", "remaining_time": "1 day, 13:35:49", "throughput": 708.05, "total_tokens": 4246912} +{"current_steps": 7625, "total_steps": 179570, "loss": 0.7996, "lr": 2.1228490282341148e-05, "epoch": 0.42462549423623097, "percentage": 4.25, "elapsed_time": "1:40:01", "remaining_time": "1 day, 13:35:34", "throughput": 708.04, "total_tokens": 4249280} +{"current_steps": 7630, "total_steps": 179570, "loss": 0.3314, "lr": 2.1242412429693158e-05, "epoch": 0.42490393718327113, "percentage": 4.25, "elapsed_time": "1:40:05", "remaining_time": "1 day, 13:35:32", "throughput": 708.04, "total_tokens": 4252160} +{"current_steps": 7635, "total_steps": 179570, "loss": 0.0323, "lr": 2.1256334577045164e-05, "epoch": 0.4251823801303113, "percentage": 4.25, "elapsed_time": "1:40:09", "remaining_time": "1 day, 13:35:32", "throughput": 708.07, "total_tokens": 4255200} +{"current_steps": 7640, "total_steps": 179570, "loss": 0.3644, "lr": 2.127025672439717e-05, "epoch": 0.42546082307735145, "percentage": 4.25, "elapsed_time": "1:40:13", "remaining_time": "1 day, 13:35:31", "throughput": 708.08, "total_tokens": 4258160} +{"current_steps": 7645, "total_steps": 179570, "loss": 0.1321, "lr": 2.128417887174918e-05, "epoch": 0.4257392660243916, "percentage": 4.26, "elapsed_time": "1:40:17", "remaining_time": "1 day, 13:35:28", "throughput": 708.08, "total_tokens": 4260992} +{"current_steps": 7650, "total_steps": 179570, "loss": 0.1622, "lr": 2.1298101019101187e-05, "epoch": 0.42601770897143176, "percentage": 4.26, "elapsed_time": "1:40:21", "remaining_time": "1 day, 13:35:20", "throughput": 708.08, "total_tokens": 4263632} +{"current_steps": 7655, "total_steps": 179570, "loss": 0.0477, "lr": 2.1312023166453197e-05, "epoch": 0.4262961519184719, "percentage": 4.26, "elapsed_time": "1:40:25", "remaining_time": "1 day, 13:35:25", "throughput": 708.06, "total_tokens": 4266592} +{"current_steps": 7660, "total_steps": 179570, "loss": 0.3777, "lr": 2.13259453138052e-05, "epoch": 0.4265745948655121, "percentage": 4.27, "elapsed_time": "1:40:29", "remaining_time": "1 day, 13:35:26", "throughput": 708.08, "total_tokens": 4269632} +{"current_steps": 7665, "total_steps": 179570, "loss": 0.3476, "lr": 2.133986746115721e-05, "epoch": 0.4268530378125522, "percentage": 4.27, "elapsed_time": "1:40:33", "remaining_time": "1 day, 13:35:20", "throughput": 708.07, "total_tokens": 4272304} +{"current_steps": 7670, "total_steps": 179570, "loss": 0.2251, "lr": 2.1353789608509217e-05, "epoch": 0.42713148075959234, "percentage": 4.27, "elapsed_time": "1:40:37", "remaining_time": "1 day, 13:35:19", "throughput": 708.08, "total_tokens": 4275232} +{"current_steps": 7675, "total_steps": 179570, "loss": 0.0689, "lr": 2.1367711755861227e-05, "epoch": 0.4274099237066325, "percentage": 4.27, "elapsed_time": "1:40:41", "remaining_time": "1 day, 13:35:10", "throughput": 708.09, "total_tokens": 4277952} +{"current_steps": 7680, "total_steps": 179570, "loss": 0.1747, "lr": 2.1381633903213233e-05, "epoch": 0.42768836665367266, "percentage": 4.28, "elapsed_time": "1:40:45", "remaining_time": "1 day, 13:35:14", "throughput": 708.1, "total_tokens": 4281040} +{"current_steps": 7685, "total_steps": 179570, "loss": 0.2818, "lr": 2.139555605056524e-05, "epoch": 0.4279668096007128, "percentage": 4.28, "elapsed_time": "1:40:50", "remaining_time": "1 day, 13:35:17", "throughput": 708.11, "total_tokens": 4284080} +{"current_steps": 7690, "total_steps": 179570, "loss": 0.1961, "lr": 2.140947819791725e-05, "epoch": 0.428245252547753, "percentage": 4.28, "elapsed_time": "1:40:54", "remaining_time": "1 day, 13:35:15", "throughput": 708.12, "total_tokens": 4287056} +{"current_steps": 7695, "total_steps": 179570, "loss": 0.0011, "lr": 2.1423400345269256e-05, "epoch": 0.42852369549479313, "percentage": 4.29, "elapsed_time": "1:40:57", "remaining_time": "1 day, 13:35:08", "throughput": 708.13, "total_tokens": 4289792} +{"current_steps": 7700, "total_steps": 179570, "loss": 0.0012, "lr": 2.1437322492621263e-05, "epoch": 0.4288021384418333, "percentage": 4.29, "elapsed_time": "1:41:01", "remaining_time": "1 day, 13:35:00", "throughput": 708.13, "total_tokens": 4292416} +{"current_steps": 7705, "total_steps": 179570, "loss": 0.0081, "lr": 2.145124463997327e-05, "epoch": 0.4290805813888734, "percentage": 4.29, "elapsed_time": "1:41:05", "remaining_time": "1 day, 13:34:57", "throughput": 708.13, "total_tokens": 4295280} +{"current_steps": 7710, "total_steps": 179570, "loss": 0.1179, "lr": 2.146516678732528e-05, "epoch": 0.42935902433591355, "percentage": 4.29, "elapsed_time": "1:41:09", "remaining_time": "1 day, 13:34:44", "throughput": 708.13, "total_tokens": 4297728} +{"current_steps": 7715, "total_steps": 179570, "loss": 0.1975, "lr": 2.1479088934677286e-05, "epoch": 0.4296374672829537, "percentage": 4.3, "elapsed_time": "1:41:13", "remaining_time": "1 day, 13:34:48", "throughput": 708.13, "total_tokens": 4300752} +{"current_steps": 7720, "total_steps": 179570, "loss": 0.1516, "lr": 2.1493011082029292e-05, "epoch": 0.42991591022999387, "percentage": 4.3, "elapsed_time": "1:41:16", "remaining_time": "1 day, 13:34:32", "throughput": 708.1, "total_tokens": 4302992} +{"current_steps": 7725, "total_steps": 179570, "loss": 0.2893, "lr": 2.1506933229381302e-05, "epoch": 0.43019435317703403, "percentage": 4.3, "elapsed_time": "1:41:20", "remaining_time": "1 day, 13:34:31", "throughput": 708.13, "total_tokens": 4306064} +{"current_steps": 7730, "total_steps": 179570, "loss": 0.0452, "lr": 2.152085537673331e-05, "epoch": 0.4304727961240742, "percentage": 4.3, "elapsed_time": "1:41:24", "remaining_time": "1 day, 13:34:19", "throughput": 708.11, "total_tokens": 4308496} +{"current_steps": 7735, "total_steps": 179570, "loss": 0.2789, "lr": 2.153477752408532e-05, "epoch": 0.43075123907111434, "percentage": 4.31, "elapsed_time": "1:41:28", "remaining_time": "1 day, 13:34:25", "throughput": 708.12, "total_tokens": 4311616} +{"current_steps": 7740, "total_steps": 179570, "loss": 0.1841, "lr": 2.154869967143732e-05, "epoch": 0.4310296820181545, "percentage": 4.31, "elapsed_time": "1:41:32", "remaining_time": "1 day, 13:34:10", "throughput": 708.08, "total_tokens": 4313856} +{"current_steps": 7745, "total_steps": 179570, "loss": 0.4943, "lr": 2.156262181878933e-05, "epoch": 0.4313081249651946, "percentage": 4.31, "elapsed_time": "1:41:36", "remaining_time": "1 day, 13:34:05", "throughput": 708.08, "total_tokens": 4316592} +{"current_steps": 7750, "total_steps": 179570, "loss": 0.0006, "lr": 2.1576543966141338e-05, "epoch": 0.43158656791223476, "percentage": 4.32, "elapsed_time": "1:41:40", "remaining_time": "1 day, 13:34:06", "throughput": 708.07, "total_tokens": 4319456} +{"current_steps": 7755, "total_steps": 179570, "loss": 0.1963, "lr": 2.1590466113493345e-05, "epoch": 0.4318650108592749, "percentage": 4.32, "elapsed_time": "1:41:44", "remaining_time": "1 day, 13:34:00", "throughput": 708.05, "total_tokens": 4322080} +{"current_steps": 7760, "total_steps": 179570, "loss": 0.0113, "lr": 2.1604388260845355e-05, "epoch": 0.4321434538063151, "percentage": 4.32, "elapsed_time": "1:41:47", "remaining_time": "1 day, 13:33:52", "throughput": 708.06, "total_tokens": 4324784} +{"current_steps": 7765, "total_steps": 179570, "loss": 0.0056, "lr": 2.161831040819736e-05, "epoch": 0.43242189675335524, "percentage": 4.32, "elapsed_time": "1:41:52", "remaining_time": "1 day, 13:33:52", "throughput": 708.05, "total_tokens": 4327632} +{"current_steps": 7770, "total_steps": 179570, "loss": 0.1067, "lr": 2.163223255554937e-05, "epoch": 0.4327003397003954, "percentage": 4.33, "elapsed_time": "1:41:55", "remaining_time": "1 day, 13:33:42", "throughput": 708.03, "total_tokens": 4330096} +{"current_steps": 7775, "total_steps": 179570, "loss": 0.1014, "lr": 2.1646154702901377e-05, "epoch": 0.43297878264743556, "percentage": 4.33, "elapsed_time": "1:41:59", "remaining_time": "1 day, 13:33:34", "throughput": 708.03, "total_tokens": 4332784} +{"current_steps": 7780, "total_steps": 179570, "loss": 0.242, "lr": 2.1660076850253384e-05, "epoch": 0.4332572255944757, "percentage": 4.33, "elapsed_time": "1:42:03", "remaining_time": "1 day, 13:33:43", "throughput": 708.02, "total_tokens": 4335920} +{"current_steps": 7785, "total_steps": 179570, "loss": 0.285, "lr": 2.167399899760539e-05, "epoch": 0.4335356685415158, "percentage": 4.34, "elapsed_time": "1:42:07", "remaining_time": "1 day, 13:33:35", "throughput": 708.01, "total_tokens": 4338496} +{"current_steps": 7790, "total_steps": 179570, "loss": 0.2781, "lr": 2.16879211449574e-05, "epoch": 0.433814111488556, "percentage": 4.34, "elapsed_time": "1:42:11", "remaining_time": "1 day, 13:33:34", "throughput": 708.02, "total_tokens": 4341456} +{"current_steps": 7795, "total_steps": 179570, "loss": 0.2187, "lr": 2.1701843292309407e-05, "epoch": 0.43409255443559613, "percentage": 4.34, "elapsed_time": "1:42:15", "remaining_time": "1 day, 13:33:26", "throughput": 708.03, "total_tokens": 4344144} +{"current_steps": 7800, "total_steps": 179570, "loss": 0.0526, "lr": 2.1715765439661413e-05, "epoch": 0.4343709973826363, "percentage": 4.34, "elapsed_time": "1:42:19", "remaining_time": "1 day, 13:33:29", "throughput": 708.04, "total_tokens": 4347216} +{"current_steps": 7805, "total_steps": 179570, "loss": 0.2404, "lr": 2.1729687587013423e-05, "epoch": 0.43464944032967645, "percentage": 4.35, "elapsed_time": "1:42:23", "remaining_time": "1 day, 13:33:24", "throughput": 708.03, "total_tokens": 4349952} +{"current_steps": 7810, "total_steps": 179570, "loss": 0.5338, "lr": 2.174360973436543e-05, "epoch": 0.4349278832767166, "percentage": 4.35, "elapsed_time": "1:42:27", "remaining_time": "1 day, 13:33:17", "throughput": 708.03, "total_tokens": 4352608} +{"current_steps": 7815, "total_steps": 179570, "loss": 0.004, "lr": 2.175753188171744e-05, "epoch": 0.43520632622375677, "percentage": 4.35, "elapsed_time": "1:42:31", "remaining_time": "1 day, 13:33:15", "throughput": 708.04, "total_tokens": 4355536} +{"current_steps": 7820, "total_steps": 179570, "loss": 0.2487, "lr": 2.1771454029069443e-05, "epoch": 0.4354847691707969, "percentage": 4.35, "elapsed_time": "1:42:34", "remaining_time": "1 day, 13:32:55", "throughput": 708.02, "total_tokens": 4357648} +{"current_steps": 7825, "total_steps": 179570, "loss": 0.1644, "lr": 2.1785376176421453e-05, "epoch": 0.43576321211783703, "percentage": 4.36, "elapsed_time": "1:42:38", "remaining_time": "1 day, 13:32:56", "throughput": 708.02, "total_tokens": 4360624} +{"current_steps": 7830, "total_steps": 179570, "loss": 0.3427, "lr": 2.179929832377346e-05, "epoch": 0.4360416550648772, "percentage": 4.36, "elapsed_time": "1:42:43", "remaining_time": "1 day, 13:32:58", "throughput": 708.03, "total_tokens": 4363632} +{"current_steps": 7835, "total_steps": 179570, "loss": 0.2571, "lr": 2.1813220471125466e-05, "epoch": 0.43632009801191735, "percentage": 4.36, "elapsed_time": "1:42:47", "remaining_time": "1 day, 13:32:55", "throughput": 708.03, "total_tokens": 4366464} +{"current_steps": 7840, "total_steps": 179570, "loss": 0.1118, "lr": 2.1827142618477476e-05, "epoch": 0.4365985409589575, "percentage": 4.37, "elapsed_time": "1:42:51", "remaining_time": "1 day, 13:32:51", "throughput": 708.04, "total_tokens": 4369296} +{"current_steps": 7845, "total_steps": 179570, "loss": 0.2959, "lr": 2.1841064765829482e-05, "epoch": 0.43687698390599766, "percentage": 4.37, "elapsed_time": "1:42:55", "remaining_time": "1 day, 13:32:52", "throughput": 708.04, "total_tokens": 4372272} +{"current_steps": 7850, "total_steps": 179570, "loss": 0.0515, "lr": 2.1854986913181492e-05, "epoch": 0.4371554268530378, "percentage": 4.37, "elapsed_time": "1:42:59", "remaining_time": "1 day, 13:32:53", "throughput": 708.04, "total_tokens": 4375200} +{"current_steps": 7855, "total_steps": 179570, "loss": 0.0016, "lr": 2.18689090605335e-05, "epoch": 0.437433869800078, "percentage": 4.37, "elapsed_time": "1:43:03", "remaining_time": "1 day, 13:33:01", "throughput": 708.03, "total_tokens": 4378336} +{"current_steps": 7860, "total_steps": 179570, "loss": 0.3382, "lr": 2.1882831207885505e-05, "epoch": 0.43771231274711814, "percentage": 4.38, "elapsed_time": "1:43:07", "remaining_time": "1 day, 13:32:52", "throughput": 708.02, "total_tokens": 4380880} +{"current_steps": 7865, "total_steps": 179570, "loss": 0.1879, "lr": 2.1896753355237512e-05, "epoch": 0.43799075569415824, "percentage": 4.38, "elapsed_time": "1:43:11", "remaining_time": "1 day, 13:32:54", "throughput": 708.04, "total_tokens": 4383984} +{"current_steps": 7870, "total_steps": 179570, "loss": 0.1126, "lr": 2.191067550258952e-05, "epoch": 0.4382691986411984, "percentage": 4.38, "elapsed_time": "1:43:15", "remaining_time": "1 day, 13:32:55", "throughput": 708.05, "total_tokens": 4386992} +{"current_steps": 7875, "total_steps": 179570, "loss": 0.135, "lr": 2.192459764994153e-05, "epoch": 0.43854764158823856, "percentage": 4.39, "elapsed_time": "1:43:19", "remaining_time": "1 day, 13:32:50", "throughput": 708.04, "total_tokens": 4389696} +{"current_steps": 7880, "total_steps": 179570, "loss": 0.0478, "lr": 2.1938519797293535e-05, "epoch": 0.4388260845352787, "percentage": 4.39, "elapsed_time": "1:43:23", "remaining_time": "1 day, 13:32:47", "throughput": 708.05, "total_tokens": 4392560} +{"current_steps": 7885, "total_steps": 179570, "loss": 0.2689, "lr": 2.1952441944645545e-05, "epoch": 0.4391045274823189, "percentage": 4.39, "elapsed_time": "1:43:27", "remaining_time": "1 day, 13:32:39", "throughput": 708.06, "total_tokens": 4395264} +{"current_steps": 7890, "total_steps": 179570, "loss": 0.0297, "lr": 2.196636409199755e-05, "epoch": 0.43938297042935903, "percentage": 4.39, "elapsed_time": "1:43:31", "remaining_time": "1 day, 13:32:38", "throughput": 708.06, "total_tokens": 4398128} +{"current_steps": 7895, "total_steps": 179570, "loss": 0.123, "lr": 2.198028623934956e-05, "epoch": 0.4396614133763992, "percentage": 4.4, "elapsed_time": "1:43:35", "remaining_time": "1 day, 13:32:24", "throughput": 708.06, "total_tokens": 4400624} +{"current_steps": 7900, "total_steps": 179570, "loss": 0.2598, "lr": 2.1994208386701564e-05, "epoch": 0.43993985632343935, "percentage": 4.4, "elapsed_time": "1:43:38", "remaining_time": "1 day, 13:32:11", "throughput": 708.05, "total_tokens": 4403072} +{"current_steps": 7905, "total_steps": 179570, "loss": 0.056, "lr": 2.2008130534053574e-05, "epoch": 0.44021829927047945, "percentage": 4.4, "elapsed_time": "1:43:42", "remaining_time": "1 day, 13:32:09", "throughput": 708.05, "total_tokens": 4405888} +{"current_steps": 7910, "total_steps": 179570, "loss": 0.223, "lr": 2.202205268140558e-05, "epoch": 0.4404967422175196, "percentage": 4.4, "elapsed_time": "1:43:46", "remaining_time": "1 day, 13:31:58", "throughput": 708.04, "total_tokens": 4408416} +{"current_steps": 7915, "total_steps": 179570, "loss": 0.2259, "lr": 2.2035974828757587e-05, "epoch": 0.44077518516455977, "percentage": 4.41, "elapsed_time": "1:43:50", "remaining_time": "1 day, 13:31:55", "throughput": 708.04, "total_tokens": 4411184} +{"current_steps": 7920, "total_steps": 179570, "loss": 0.0778, "lr": 2.2049896976109597e-05, "epoch": 0.4410536281115999, "percentage": 4.41, "elapsed_time": "1:43:54", "remaining_time": "1 day, 13:31:54", "throughput": 708.06, "total_tokens": 4414240} +{"current_steps": 7925, "total_steps": 179570, "loss": 0.1919, "lr": 2.2063819123461604e-05, "epoch": 0.4413320710586401, "percentage": 4.41, "elapsed_time": "1:43:58", "remaining_time": "1 day, 13:31:51", "throughput": 708.07, "total_tokens": 4417072} +{"current_steps": 7930, "total_steps": 179570, "loss": 0.6776, "lr": 2.2077741270813614e-05, "epoch": 0.44161051400568024, "percentage": 4.42, "elapsed_time": "1:44:02", "remaining_time": "1 day, 13:31:50", "throughput": 708.06, "total_tokens": 4419920} +{"current_steps": 7935, "total_steps": 179570, "loss": 0.0788, "lr": 2.209166341816562e-05, "epoch": 0.4418889569527204, "percentage": 4.42, "elapsed_time": "1:44:06", "remaining_time": "1 day, 13:31:48", "throughput": 708.07, "total_tokens": 4422832} +{"current_steps": 7940, "total_steps": 179570, "loss": 0.1986, "lr": 2.2105585565517627e-05, "epoch": 0.44216739989976056, "percentage": 4.42, "elapsed_time": "1:44:10", "remaining_time": "1 day, 13:31:47", "throughput": 708.08, "total_tokens": 4425808} +{"current_steps": 7945, "total_steps": 179570, "loss": 0.1077, "lr": 2.2119507712869633e-05, "epoch": 0.44244584284680066, "percentage": 4.42, "elapsed_time": "1:44:14", "remaining_time": "1 day, 13:31:38", "throughput": 708.08, "total_tokens": 4428368} +{"current_steps": 7950, "total_steps": 179570, "loss": 0.1301, "lr": 2.213342986022164e-05, "epoch": 0.4427242857938408, "percentage": 4.43, "elapsed_time": "1:44:18", "remaining_time": "1 day, 13:31:44", "throughput": 708.09, "total_tokens": 4431552} +{"current_steps": 7955, "total_steps": 179570, "loss": 0.3679, "lr": 2.214735200757365e-05, "epoch": 0.443002728740881, "percentage": 4.43, "elapsed_time": "1:44:21", "remaining_time": "1 day, 13:31:30", "throughput": 708.08, "total_tokens": 4434000} +{"current_steps": 7960, "total_steps": 179570, "loss": 0.1802, "lr": 2.2161274154925656e-05, "epoch": 0.44328117168792114, "percentage": 4.43, "elapsed_time": "1:44:26", "remaining_time": "1 day, 13:31:32", "throughput": 708.09, "total_tokens": 4437008} +{"current_steps": 7965, "total_steps": 179570, "loss": 0.0654, "lr": 2.2175196302277666e-05, "epoch": 0.4435596146349613, "percentage": 4.44, "elapsed_time": "1:44:30", "remaining_time": "1 day, 13:31:33", "throughput": 708.08, "total_tokens": 4439904} +{"current_steps": 7970, "total_steps": 179570, "loss": 0.0637, "lr": 2.2189118449629673e-05, "epoch": 0.44383805758200146, "percentage": 4.44, "elapsed_time": "1:44:34", "remaining_time": "1 day, 13:31:27", "throughput": 708.06, "total_tokens": 4442480} +{"current_steps": 7975, "total_steps": 179570, "loss": 0.0184, "lr": 2.220304059698168e-05, "epoch": 0.4441165005290416, "percentage": 4.44, "elapsed_time": "1:44:38", "remaining_time": "1 day, 13:31:33", "throughput": 708.08, "total_tokens": 4445712} +{"current_steps": 7980, "total_steps": 179570, "loss": 0.0333, "lr": 2.2216962744333686e-05, "epoch": 0.44439494347608177, "percentage": 4.44, "elapsed_time": "1:44:42", "remaining_time": "1 day, 13:31:25", "throughput": 708.07, "total_tokens": 4448336} +{"current_steps": 7985, "total_steps": 179570, "loss": 0.2445, "lr": 2.2230884891685692e-05, "epoch": 0.4446733864231219, "percentage": 4.45, "elapsed_time": "1:44:45", "remaining_time": "1 day, 13:31:11", "throughput": 708.05, "total_tokens": 4450688} +{"current_steps": 7990, "total_steps": 179570, "loss": 0.0105, "lr": 2.2244807039037702e-05, "epoch": 0.44495182937016203, "percentage": 4.45, "elapsed_time": "1:44:49", "remaining_time": "1 day, 13:31:08", "throughput": 708.03, "total_tokens": 4453360} +{"current_steps": 7995, "total_steps": 179570, "loss": 0.0194, "lr": 2.225872918638971e-05, "epoch": 0.4452302723172022, "percentage": 4.45, "elapsed_time": "1:44:53", "remaining_time": "1 day, 13:31:06", "throughput": 708.05, "total_tokens": 4456320} +{"current_steps": 8000, "total_steps": 179570, "loss": 0.7339, "lr": 2.227265133374172e-05, "epoch": 0.44550871526424235, "percentage": 4.46, "elapsed_time": "1:44:57", "remaining_time": "1 day, 13:30:59", "throughput": 708.04, "total_tokens": 4458928} +{"current_steps": 8005, "total_steps": 179570, "loss": 0.7416, "lr": 2.2286573481093725e-05, "epoch": 0.4457871582112825, "percentage": 4.46, "elapsed_time": "1:45:01", "remaining_time": "1 day, 13:30:56", "throughput": 708.03, "total_tokens": 4461680} +{"current_steps": 8010, "total_steps": 179570, "loss": 0.1884, "lr": 2.2300495628445735e-05, "epoch": 0.44606560115832267, "percentage": 4.46, "elapsed_time": "1:45:05", "remaining_time": "1 day, 13:30:49", "throughput": 708.02, "total_tokens": 4464320} +{"current_steps": 8015, "total_steps": 179570, "loss": 0.0764, "lr": 2.231441777579774e-05, "epoch": 0.4463440441053628, "percentage": 4.46, "elapsed_time": "1:45:09", "remaining_time": "1 day, 13:30:41", "throughput": 708.01, "total_tokens": 4466880} +{"current_steps": 8020, "total_steps": 179570, "loss": 0.0046, "lr": 2.2328339923149748e-05, "epoch": 0.446622487052403, "percentage": 4.47, "elapsed_time": "1:45:13", "remaining_time": "1 day, 13:30:42", "throughput": 708.03, "total_tokens": 4469952} +{"current_steps": 8025, "total_steps": 179570, "loss": 0.133, "lr": 2.2342262070501755e-05, "epoch": 0.44690092999944314, "percentage": 4.47, "elapsed_time": "1:45:17", "remaining_time": "1 day, 13:30:39", "throughput": 708.05, "total_tokens": 4472928} +{"current_steps": 8030, "total_steps": 179570, "loss": 0.1116, "lr": 2.235618421785376e-05, "epoch": 0.44717937294648324, "percentage": 4.47, "elapsed_time": "1:45:21", "remaining_time": "1 day, 13:30:35", "throughput": 708.04, "total_tokens": 4475664} +{"current_steps": 8035, "total_steps": 179570, "loss": 0.0535, "lr": 2.237010636520577e-05, "epoch": 0.4474578158935234, "percentage": 4.47, "elapsed_time": "1:45:25", "remaining_time": "1 day, 13:30:31", "throughput": 708.04, "total_tokens": 4478432} +{"current_steps": 8040, "total_steps": 179570, "loss": 0.0318, "lr": 2.2384028512557778e-05, "epoch": 0.44773625884056356, "percentage": 4.48, "elapsed_time": "1:45:29", "remaining_time": "1 day, 13:30:26", "throughput": 708.04, "total_tokens": 4481184} +{"current_steps": 8045, "total_steps": 179570, "loss": 0.2388, "lr": 2.2397950659909787e-05, "epoch": 0.4480147017876037, "percentage": 4.48, "elapsed_time": "1:45:32", "remaining_time": "1 day, 13:30:22", "throughput": 708.04, "total_tokens": 4483952} +{"current_steps": 8050, "total_steps": 179570, "loss": 0.0039, "lr": 2.2411872807261794e-05, "epoch": 0.4482931447346439, "percentage": 4.48, "elapsed_time": "1:45:36", "remaining_time": "1 day, 13:30:18", "throughput": 708.02, "total_tokens": 4486592} +{"current_steps": 8055, "total_steps": 179570, "loss": 0.1506, "lr": 2.24257949546138e-05, "epoch": 0.44857158768168404, "percentage": 4.49, "elapsed_time": "1:45:40", "remaining_time": "1 day, 13:30:16", "throughput": 708.03, "total_tokens": 4489568} +{"current_steps": 8060, "total_steps": 179570, "loss": 0.3764, "lr": 2.2439717101965807e-05, "epoch": 0.4488500306287242, "percentage": 4.49, "elapsed_time": "1:45:45", "remaining_time": "1 day, 13:30:17", "throughput": 708.03, "total_tokens": 4492464} +{"current_steps": 8065, "total_steps": 179570, "loss": 0.0228, "lr": 2.2453639249317814e-05, "epoch": 0.44912847357576435, "percentage": 4.49, "elapsed_time": "1:45:48", "remaining_time": "1 day, 13:30:09", "throughput": 708.02, "total_tokens": 4495088} +{"current_steps": 8070, "total_steps": 179570, "loss": 0.3832, "lr": 2.2467561396669823e-05, "epoch": 0.44940691652280446, "percentage": 4.49, "elapsed_time": "1:45:52", "remaining_time": "1 day, 13:30:06", "throughput": 708.02, "total_tokens": 4497888} +{"current_steps": 8075, "total_steps": 179570, "loss": 0.1363, "lr": 2.248148354402183e-05, "epoch": 0.4496853594698446, "percentage": 4.5, "elapsed_time": "1:45:56", "remaining_time": "1 day, 13:30:08", "throughput": 708.03, "total_tokens": 4500944} +{"current_steps": 8080, "total_steps": 179570, "loss": 0.0027, "lr": 2.249540569137384e-05, "epoch": 0.4499638024168848, "percentage": 4.5, "elapsed_time": "1:46:01", "remaining_time": "1 day, 13:30:07", "throughput": 708.05, "total_tokens": 4503952} +{"current_steps": 8085, "total_steps": 179570, "loss": 0.1845, "lr": 2.2509327838725846e-05, "epoch": 0.45024224536392493, "percentage": 4.5, "elapsed_time": "1:46:04", "remaining_time": "1 day, 13:29:58", "throughput": 708.05, "total_tokens": 4506544} +{"current_steps": 8090, "total_steps": 179570, "loss": 0.898, "lr": 2.2523249986077853e-05, "epoch": 0.4505206883109651, "percentage": 4.51, "elapsed_time": "1:46:08", "remaining_time": "1 day, 13:29:50", "throughput": 708.05, "total_tokens": 4509216} +{"current_steps": 8095, "total_steps": 179570, "loss": 0.0338, "lr": 2.2537172133429863e-05, "epoch": 0.45079913125800525, "percentage": 4.51, "elapsed_time": "1:46:12", "remaining_time": "1 day, 13:29:49", "throughput": 708.06, "total_tokens": 4512176} +{"current_steps": 8100, "total_steps": 179570, "loss": 0.0198, "lr": 2.2551094280781866e-05, "epoch": 0.4510775742050454, "percentage": 4.51, "elapsed_time": "1:46:16", "remaining_time": "1 day, 13:29:45", "throughput": 708.06, "total_tokens": 4514944} +{"current_steps": 8105, "total_steps": 179570, "loss": 0.1725, "lr": 2.2565016428133876e-05, "epoch": 0.45135601715208556, "percentage": 4.51, "elapsed_time": "1:46:20", "remaining_time": "1 day, 13:29:38", "throughput": 708.06, "total_tokens": 4517648} +{"current_steps": 8110, "total_steps": 179570, "loss": 0.0336, "lr": 2.2578938575485882e-05, "epoch": 0.45163446009912567, "percentage": 4.52, "elapsed_time": "1:46:24", "remaining_time": "1 day, 13:29:40", "throughput": 708.08, "total_tokens": 4520752} +{"current_steps": 8115, "total_steps": 179570, "loss": 0.2006, "lr": 2.2592860722837892e-05, "epoch": 0.4519129030461658, "percentage": 4.52, "elapsed_time": "1:46:28", "remaining_time": "1 day, 13:29:39", "throughput": 708.07, "total_tokens": 4523600} +{"current_steps": 8120, "total_steps": 179570, "loss": 0.0515, "lr": 2.26067828701899e-05, "epoch": 0.452191345993206, "percentage": 4.52, "elapsed_time": "1:46:32", "remaining_time": "1 day, 13:29:26", "throughput": 708.06, "total_tokens": 4525984} +{"current_steps": 8125, "total_steps": 179570, "loss": 0.2153, "lr": 2.262070501754191e-05, "epoch": 0.45246978894024614, "percentage": 4.52, "elapsed_time": "1:46:36", "remaining_time": "1 day, 13:29:22", "throughput": 708.05, "total_tokens": 4528720} +{"current_steps": 8130, "total_steps": 179570, "loss": 0.2949, "lr": 2.2634627164893915e-05, "epoch": 0.4527482318872863, "percentage": 4.53, "elapsed_time": "1:46:40", "remaining_time": "1 day, 13:29:23", "throughput": 708.05, "total_tokens": 4531648} +{"current_steps": 8135, "total_steps": 179570, "loss": 0.0011, "lr": 2.2648549312245922e-05, "epoch": 0.45302667483432646, "percentage": 4.53, "elapsed_time": "1:46:43", "remaining_time": "1 day, 13:29:15", "throughput": 708.04, "total_tokens": 4534240} +{"current_steps": 8140, "total_steps": 179570, "loss": 0.2033, "lr": 2.266247145959793e-05, "epoch": 0.4533051177813666, "percentage": 4.53, "elapsed_time": "1:46:48", "remaining_time": "1 day, 13:29:17", "throughput": 708.04, "total_tokens": 4537232} +{"current_steps": 8145, "total_steps": 179570, "loss": 0.0252, "lr": 2.2676393606949935e-05, "epoch": 0.4535835607284068, "percentage": 4.54, "elapsed_time": "1:46:51", "remaining_time": "1 day, 13:29:10", "throughput": 708.06, "total_tokens": 4540032} +{"current_steps": 8150, "total_steps": 179570, "loss": 0.0737, "lr": 2.2690315754301945e-05, "epoch": 0.4538620036754469, "percentage": 4.54, "elapsed_time": "1:46:56", "remaining_time": "1 day, 13:29:08", "throughput": 708.06, "total_tokens": 4542912} +{"current_steps": 8155, "total_steps": 179570, "loss": 0.1729, "lr": 2.270423790165395e-05, "epoch": 0.45414044662248704, "percentage": 4.54, "elapsed_time": "1:47:00", "remaining_time": "1 day, 13:29:11", "throughput": 708.08, "total_tokens": 4546048} +{"current_steps": 8160, "total_steps": 179570, "loss": 0.2624, "lr": 2.271816004900596e-05, "epoch": 0.4544188895695272, "percentage": 4.54, "elapsed_time": "1:47:03", "remaining_time": "1 day, 13:28:56", "throughput": 708.07, "total_tokens": 4548432} +{"current_steps": 8165, "total_steps": 179570, "loss": 0.1177, "lr": 2.2732082196357968e-05, "epoch": 0.45469733251656735, "percentage": 4.55, "elapsed_time": "1:47:07", "remaining_time": "1 day, 13:28:47", "throughput": 708.05, "total_tokens": 4550880} +{"current_steps": 8170, "total_steps": 179570, "loss": 0.251, "lr": 2.2746004343709974e-05, "epoch": 0.4549757754636075, "percentage": 4.55, "elapsed_time": "1:47:11", "remaining_time": "1 day, 13:28:42", "throughput": 708.03, "total_tokens": 4553536} +{"current_steps": 8175, "total_steps": 179570, "loss": 0.0285, "lr": 2.2759926491061984e-05, "epoch": 0.45525421841064767, "percentage": 4.55, "elapsed_time": "1:47:15", "remaining_time": "1 day, 13:28:43", "throughput": 708.03, "total_tokens": 4556464} +{"current_steps": 8180, "total_steps": 179570, "loss": 0.3851, "lr": 2.2773848638413987e-05, "epoch": 0.45553266135768783, "percentage": 4.56, "elapsed_time": "1:47:19", "remaining_time": "1 day, 13:28:37", "throughput": 708.02, "total_tokens": 4559088} +{"current_steps": 8185, "total_steps": 179570, "loss": 0.0208, "lr": 2.2787770785765997e-05, "epoch": 0.455811104304728, "percentage": 4.56, "elapsed_time": "1:47:23", "remaining_time": "1 day, 13:28:33", "throughput": 708.02, "total_tokens": 4561904} +{"current_steps": 8190, "total_steps": 179570, "loss": 0.2183, "lr": 2.2801692933118004e-05, "epoch": 0.4560895472517681, "percentage": 4.56, "elapsed_time": "1:47:26", "remaining_time": "1 day, 13:28:26", "throughput": 708.03, "total_tokens": 4564672} +{"current_steps": 8195, "total_steps": 179570, "loss": 0.2978, "lr": 2.2815615080470014e-05, "epoch": 0.45636799019880825, "percentage": 4.56, "elapsed_time": "1:47:30", "remaining_time": "1 day, 13:28:22", "throughput": 708.03, "total_tokens": 4567440} +{"current_steps": 8200, "total_steps": 179570, "loss": 0.4077, "lr": 2.282953722782202e-05, "epoch": 0.4566464331458484, "percentage": 4.57, "elapsed_time": "1:47:34", "remaining_time": "1 day, 13:28:11", "throughput": 708.01, "total_tokens": 4569872} +{"current_steps": 8205, "total_steps": 179570, "loss": 0.2071, "lr": 2.2843459375174027e-05, "epoch": 0.45692487609288857, "percentage": 4.57, "elapsed_time": "1:47:38", "remaining_time": "1 day, 13:28:09", "throughput": 708.02, "total_tokens": 4572784} +{"current_steps": 8210, "total_steps": 179570, "loss": 0.2416, "lr": 2.2857381522526037e-05, "epoch": 0.4572033190399287, "percentage": 4.57, "elapsed_time": "1:47:42", "remaining_time": "1 day, 13:27:56", "throughput": 708.01, "total_tokens": 4575232} +{"current_steps": 8215, "total_steps": 179570, "loss": 0.2505, "lr": 2.2871303669878043e-05, "epoch": 0.4574817619869689, "percentage": 4.57, "elapsed_time": "1:47:46", "remaining_time": "1 day, 13:28:01", "throughput": 708.02, "total_tokens": 4578368} +{"current_steps": 8220, "total_steps": 179570, "loss": 0.0118, "lr": 2.288522581723005e-05, "epoch": 0.45776020493400904, "percentage": 4.58, "elapsed_time": "1:47:50", "remaining_time": "1 day, 13:28:01", "throughput": 708.02, "total_tokens": 4581280} +{"current_steps": 8225, "total_steps": 179570, "loss": 0.0025, "lr": 2.2899147964582056e-05, "epoch": 0.4580386478810492, "percentage": 4.58, "elapsed_time": "1:47:54", "remaining_time": "1 day, 13:27:58", "throughput": 708.03, "total_tokens": 4584160} +{"current_steps": 8230, "total_steps": 179570, "loss": 0.0019, "lr": 2.2913070111934066e-05, "epoch": 0.4583170908280893, "percentage": 4.58, "elapsed_time": "1:47:58", "remaining_time": "1 day, 13:27:59", "throughput": 708.04, "total_tokens": 4587152} +{"current_steps": 8235, "total_steps": 179570, "loss": 0.0613, "lr": 2.2926992259286073e-05, "epoch": 0.45859553377512946, "percentage": 4.59, "elapsed_time": "1:48:02", "remaining_time": "1 day, 13:27:51", "throughput": 708.03, "total_tokens": 4589760} +{"current_steps": 8240, "total_steps": 179570, "loss": 0.1327, "lr": 2.2940914406638083e-05, "epoch": 0.4588739767221696, "percentage": 4.59, "elapsed_time": "1:48:06", "remaining_time": "1 day, 13:27:53", "throughput": 708.05, "total_tokens": 4592832} +{"current_steps": 8245, "total_steps": 179570, "loss": 0.0697, "lr": 2.295483655399009e-05, "epoch": 0.4591524196692098, "percentage": 4.59, "elapsed_time": "1:48:10", "remaining_time": "1 day, 13:27:57", "throughput": 708.04, "total_tokens": 4595904} +{"current_steps": 8250, "total_steps": 179570, "loss": 0.0012, "lr": 2.2968758701342096e-05, "epoch": 0.45943086261624994, "percentage": 4.59, "elapsed_time": "1:48:14", "remaining_time": "1 day, 13:27:54", "throughput": 708.05, "total_tokens": 4598768} +{"current_steps": 8255, "total_steps": 179570, "loss": 0.1197, "lr": 2.2982680848694106e-05, "epoch": 0.4597093055632901, "percentage": 4.6, "elapsed_time": "1:48:18", "remaining_time": "1 day, 13:27:46", "throughput": 708.03, "total_tokens": 4601280} +{"current_steps": 8260, "total_steps": 179570, "loss": 0.1387, "lr": 2.299660299604611e-05, "epoch": 0.45998774851033025, "percentage": 4.6, "elapsed_time": "1:48:22", "remaining_time": "1 day, 13:27:41", "throughput": 708.02, "total_tokens": 4603952} +{"current_steps": 8265, "total_steps": 179570, "loss": 0.116, "lr": 2.301052514339812e-05, "epoch": 0.4602661914573704, "percentage": 4.6, "elapsed_time": "1:48:26", "remaining_time": "1 day, 13:27:37", "throughput": 708.01, "total_tokens": 4606640} +{"current_steps": 8270, "total_steps": 179570, "loss": 0.2988, "lr": 2.3024447290750125e-05, "epoch": 0.4605446344044105, "percentage": 4.61, "elapsed_time": "1:48:30", "remaining_time": "1 day, 13:27:32", "throughput": 708.0, "total_tokens": 4609376} +{"current_steps": 8275, "total_steps": 179570, "loss": 0.1144, "lr": 2.3038369438102135e-05, "epoch": 0.46082307735145067, "percentage": 4.61, "elapsed_time": "1:48:34", "remaining_time": "1 day, 13:27:23", "throughput": 708.0, "total_tokens": 4611952} +{"current_steps": 8280, "total_steps": 179570, "loss": 0.153, "lr": 2.305229158545414e-05, "epoch": 0.46110152029849083, "percentage": 4.61, "elapsed_time": "1:48:38", "remaining_time": "1 day, 13:27:19", "throughput": 707.99, "total_tokens": 4614672} +{"current_steps": 8285, "total_steps": 179570, "loss": 0.4934, "lr": 2.3066213732806148e-05, "epoch": 0.461379963245531, "percentage": 4.61, "elapsed_time": "1:48:41", "remaining_time": "1 day, 13:27:05", "throughput": 707.96, "total_tokens": 4616960} +{"current_steps": 8290, "total_steps": 179570, "loss": 0.023, "lr": 2.3080135880158158e-05, "epoch": 0.46165840619257115, "percentage": 4.62, "elapsed_time": "1:48:45", "remaining_time": "1 day, 13:26:58", "throughput": 707.97, "total_tokens": 4619728} +{"current_steps": 8295, "total_steps": 179570, "loss": 0.306, "lr": 2.3094058027510165e-05, "epoch": 0.4619368491396113, "percentage": 4.62, "elapsed_time": "1:48:48", "remaining_time": "1 day, 13:26:43", "throughput": 707.95, "total_tokens": 4621968} +{"current_steps": 8300, "total_steps": 179570, "loss": 0.2603, "lr": 2.310798017486217e-05, "epoch": 0.46221529208665146, "percentage": 4.62, "elapsed_time": "1:48:52", "remaining_time": "1 day, 13:26:41", "throughput": 707.95, "total_tokens": 4624816} +{"current_steps": 8305, "total_steps": 179570, "loss": 0.0005, "lr": 2.3121902322214178e-05, "epoch": 0.4624937350336916, "percentage": 4.62, "elapsed_time": "1:48:56", "remaining_time": "1 day, 13:26:43", "throughput": 707.93, "total_tokens": 4627696} +{"current_steps": 8310, "total_steps": 179570, "loss": 0.21, "lr": 2.3135824469566188e-05, "epoch": 0.4627721779807317, "percentage": 4.63, "elapsed_time": "1:49:00", "remaining_time": "1 day, 13:26:39", "throughput": 707.93, "total_tokens": 4630464} +{"current_steps": 8315, "total_steps": 179570, "loss": 0.2361, "lr": 2.3149746616918194e-05, "epoch": 0.4630506209277719, "percentage": 4.63, "elapsed_time": "1:49:04", "remaining_time": "1 day, 13:26:37", "throughput": 707.92, "total_tokens": 4633200} +{"current_steps": 8320, "total_steps": 179570, "loss": 0.0597, "lr": 2.31636687642702e-05, "epoch": 0.46332906387481204, "percentage": 4.63, "elapsed_time": "1:49:08", "remaining_time": "1 day, 13:26:32", "throughput": 707.9, "total_tokens": 4635856} +{"current_steps": 8325, "total_steps": 179570, "loss": 0.2205, "lr": 2.317759091162221e-05, "epoch": 0.4636075068218522, "percentage": 4.64, "elapsed_time": "1:49:12", "remaining_time": "1 day, 13:26:28", "throughput": 707.9, "total_tokens": 4638624} +{"current_steps": 8330, "total_steps": 179570, "loss": 0.1562, "lr": 2.3191513058974217e-05, "epoch": 0.46388594976889236, "percentage": 4.64, "elapsed_time": "1:49:16", "remaining_time": "1 day, 13:26:26", "throughput": 707.9, "total_tokens": 4641504} +{"current_steps": 8335, "total_steps": 179570, "loss": 0.0742, "lr": 2.3205435206326227e-05, "epoch": 0.4641643927159325, "percentage": 4.64, "elapsed_time": "1:49:20", "remaining_time": "1 day, 13:26:22", "throughput": 707.9, "total_tokens": 4644240} +{"current_steps": 8340, "total_steps": 179570, "loss": 0.3617, "lr": 2.321935735367823e-05, "epoch": 0.4644428356629727, "percentage": 4.64, "elapsed_time": "1:49:24", "remaining_time": "1 day, 13:26:13", "throughput": 707.9, "total_tokens": 4646880} +{"current_steps": 8345, "total_steps": 179570, "loss": 0.2587, "lr": 2.323327950103024e-05, "epoch": 0.46472127861001283, "percentage": 4.65, "elapsed_time": "1:49:28", "remaining_time": "1 day, 13:26:12", "throughput": 707.92, "total_tokens": 4649920} +{"current_steps": 8350, "total_steps": 179570, "loss": 0.0229, "lr": 2.3247201648382246e-05, "epoch": 0.46499972155705294, "percentage": 4.65, "elapsed_time": "1:49:32", "remaining_time": "1 day, 13:26:09", "throughput": 707.93, "total_tokens": 4652784} +{"current_steps": 8355, "total_steps": 179570, "loss": 0.2015, "lr": 2.3261123795734256e-05, "epoch": 0.4652781645040931, "percentage": 4.65, "elapsed_time": "1:49:36", "remaining_time": "1 day, 13:26:02", "throughput": 707.94, "total_tokens": 4655520} +{"current_steps": 8360, "total_steps": 179570, "loss": 0.0677, "lr": 2.3275045943086263e-05, "epoch": 0.46555660745113325, "percentage": 4.66, "elapsed_time": "1:49:40", "remaining_time": "1 day, 13:25:58", "throughput": 707.93, "total_tokens": 4658272} +{"current_steps": 8365, "total_steps": 179570, "loss": 0.1062, "lr": 2.328896809043827e-05, "epoch": 0.4658350503981734, "percentage": 4.66, "elapsed_time": "1:49:44", "remaining_time": "1 day, 13:25:58", "throughput": 707.96, "total_tokens": 4661376} +{"current_steps": 8370, "total_steps": 179570, "loss": 0.5066, "lr": 2.330289023779028e-05, "epoch": 0.46611349334521357, "percentage": 4.66, "elapsed_time": "1:49:48", "remaining_time": "1 day, 13:25:54", "throughput": 707.96, "total_tokens": 4664176} +{"current_steps": 8375, "total_steps": 179570, "loss": 0.2978, "lr": 2.3316812385142286e-05, "epoch": 0.46639193629225373, "percentage": 4.66, "elapsed_time": "1:49:52", "remaining_time": "1 day, 13:25:55", "throughput": 707.96, "total_tokens": 4667120} +{"current_steps": 8380, "total_steps": 179570, "loss": 0.2727, "lr": 2.3330734532494296e-05, "epoch": 0.4666703792392939, "percentage": 4.67, "elapsed_time": "1:49:56", "remaining_time": "1 day, 13:25:53", "throughput": 707.97, "total_tokens": 4670048} +{"current_steps": 8385, "total_steps": 179570, "loss": 0.0518, "lr": 2.33446566798463e-05, "epoch": 0.46694882218633404, "percentage": 4.67, "elapsed_time": "1:50:00", "remaining_time": "1 day, 13:25:51", "throughput": 707.99, "total_tokens": 4672992} +{"current_steps": 8390, "total_steps": 179570, "loss": 0.0225, "lr": 2.335857882719831e-05, "epoch": 0.46722726513337415, "percentage": 4.67, "elapsed_time": "1:50:04", "remaining_time": "1 day, 13:25:47", "throughput": 707.98, "total_tokens": 4675728} +{"current_steps": 8395, "total_steps": 179570, "loss": 0.0048, "lr": 2.3372500974550315e-05, "epoch": 0.4675057080804143, "percentage": 4.68, "elapsed_time": "1:50:08", "remaining_time": "1 day, 13:25:57", "throughput": 707.98, "total_tokens": 4679008} +{"current_steps": 8400, "total_steps": 179570, "loss": 0.0307, "lr": 2.3386423121902322e-05, "epoch": 0.46778415102745446, "percentage": 4.68, "elapsed_time": "1:50:12", "remaining_time": "1 day, 13:25:50", "throughput": 707.98, "total_tokens": 4681712} +{"current_steps": 8405, "total_steps": 179570, "loss": 0.2904, "lr": 2.3400345269254332e-05, "epoch": 0.4680625939744946, "percentage": 4.68, "elapsed_time": "1:50:16", "remaining_time": "1 day, 13:25:49", "throughput": 707.99, "total_tokens": 4684608} +{"current_steps": 8410, "total_steps": 179570, "loss": 0.1025, "lr": 2.341426741660634e-05, "epoch": 0.4683410369215348, "percentage": 4.68, "elapsed_time": "1:50:20", "remaining_time": "1 day, 13:25:38", "throughput": 707.97, "total_tokens": 4687072} +{"current_steps": 8415, "total_steps": 179570, "loss": 0.2391, "lr": 2.3428189563958348e-05, "epoch": 0.46861947986857494, "percentage": 4.69, "elapsed_time": "1:50:24", "remaining_time": "1 day, 13:25:42", "throughput": 707.98, "total_tokens": 4690144} +{"current_steps": 8420, "total_steps": 179570, "loss": 0.3477, "lr": 2.3442111711310355e-05, "epoch": 0.4688979228156151, "percentage": 4.69, "elapsed_time": "1:50:28", "remaining_time": "1 day, 13:25:40", "throughput": 707.97, "total_tokens": 4692992} +{"current_steps": 8425, "total_steps": 179570, "loss": 0.0004, "lr": 2.345603385866236e-05, "epoch": 0.46917636576265526, "percentage": 4.69, "elapsed_time": "1:50:32", "remaining_time": "1 day, 13:25:40", "throughput": 707.98, "total_tokens": 4695920} +{"current_steps": 8430, "total_steps": 179570, "loss": 0.0461, "lr": 2.3469956006014368e-05, "epoch": 0.46945480870969536, "percentage": 4.69, "elapsed_time": "1:50:36", "remaining_time": "1 day, 13:25:32", "throughput": 707.98, "total_tokens": 4698608} +{"current_steps": 8435, "total_steps": 179570, "loss": 0.1991, "lr": 2.3483878153366374e-05, "epoch": 0.4697332516567355, "percentage": 4.7, "elapsed_time": "1:50:40", "remaining_time": "1 day, 13:25:31", "throughput": 708.0, "total_tokens": 4701632} +{"current_steps": 8440, "total_steps": 179570, "loss": 0.1486, "lr": 2.3497800300718384e-05, "epoch": 0.4700116946037757, "percentage": 4.7, "elapsed_time": "1:50:44", "remaining_time": "1 day, 13:25:30", "throughput": 708.02, "total_tokens": 4704656} +{"current_steps": 8445, "total_steps": 179570, "loss": 0.2234, "lr": 2.351172244807039e-05, "epoch": 0.47029013755081583, "percentage": 4.7, "elapsed_time": "1:50:48", "remaining_time": "1 day, 13:25:27", "throughput": 708.02, "total_tokens": 4707456} +{"current_steps": 8450, "total_steps": 179570, "loss": 0.2712, "lr": 2.35256445954224e-05, "epoch": 0.470568580497856, "percentage": 4.71, "elapsed_time": "1:50:52", "remaining_time": "1 day, 13:25:27", "throughput": 708.02, "total_tokens": 4710416} +{"current_steps": 8455, "total_steps": 179570, "loss": 0.1835, "lr": 2.3539566742774407e-05, "epoch": 0.47084702344489615, "percentage": 4.71, "elapsed_time": "1:50:56", "remaining_time": "1 day, 13:25:25", "throughput": 708.03, "total_tokens": 4713312} +{"current_steps": 8460, "total_steps": 179570, "loss": 0.0966, "lr": 2.3553488890126417e-05, "epoch": 0.4711254663919363, "percentage": 4.71, "elapsed_time": "1:51:00", "remaining_time": "1 day, 13:25:18", "throughput": 708.02, "total_tokens": 4715968} +{"current_steps": 8465, "total_steps": 179570, "loss": 0.2785, "lr": 2.356741103747842e-05, "epoch": 0.47140390933897647, "percentage": 4.71, "elapsed_time": "1:51:04", "remaining_time": "1 day, 13:25:04", "throughput": 708.0, "total_tokens": 4718240} +{"current_steps": 8470, "total_steps": 179570, "loss": 0.0533, "lr": 2.358133318483043e-05, "epoch": 0.47168235228601657, "percentage": 4.72, "elapsed_time": "1:51:08", "remaining_time": "1 day, 13:25:09", "throughput": 708.0, "total_tokens": 4721344} +{"current_steps": 8475, "total_steps": 179570, "loss": 0.1006, "lr": 2.3595255332182437e-05, "epoch": 0.47196079523305673, "percentage": 4.72, "elapsed_time": "1:51:12", "remaining_time": "1 day, 13:25:06", "throughput": 708.02, "total_tokens": 4724304} +{"current_steps": 8480, "total_steps": 179570, "loss": 0.2841, "lr": 2.3609177479534443e-05, "epoch": 0.4722392381800969, "percentage": 4.72, "elapsed_time": "1:51:16", "remaining_time": "1 day, 13:25:08", "throughput": 708.02, "total_tokens": 4727280} +{"current_steps": 8485, "total_steps": 179570, "loss": 0.392, "lr": 2.3623099626886453e-05, "epoch": 0.47251768112713705, "percentage": 4.73, "elapsed_time": "1:51:20", "remaining_time": "1 day, 13:25:08", "throughput": 708.01, "total_tokens": 4730160} +{"current_steps": 8490, "total_steps": 179570, "loss": 0.2343, "lr": 2.363702177423846e-05, "epoch": 0.4727961240741772, "percentage": 4.73, "elapsed_time": "1:51:24", "remaining_time": "1 day, 13:25:01", "throughput": 708.0, "total_tokens": 4732768} +{"current_steps": 8495, "total_steps": 179570, "loss": 0.1966, "lr": 2.365094392159047e-05, "epoch": 0.47307456702121736, "percentage": 4.73, "elapsed_time": "1:51:28", "remaining_time": "1 day, 13:25:02", "throughput": 708.01, "total_tokens": 4735792} +{"current_steps": 8500, "total_steps": 179570, "loss": 0.4953, "lr": 2.3664866068942476e-05, "epoch": 0.4733530099682575, "percentage": 4.73, "elapsed_time": "1:51:32", "remaining_time": "1 day, 13:24:58", "throughput": 708.0, "total_tokens": 4738528} +{"current_steps": 8505, "total_steps": 179570, "loss": 0.4146, "lr": 2.3678788216294483e-05, "epoch": 0.4736314529152977, "percentage": 4.74, "elapsed_time": "1:51:36", "remaining_time": "1 day, 13:24:51", "throughput": 708.01, "total_tokens": 4741264} +{"current_steps": 8510, "total_steps": 179570, "loss": 0.0851, "lr": 2.369271036364649e-05, "epoch": 0.4739098958623378, "percentage": 4.74, "elapsed_time": "1:51:40", "remaining_time": "1 day, 13:24:42", "throughput": 708.0, "total_tokens": 4743808} +{"current_steps": 8515, "total_steps": 179570, "loss": 0.0939, "lr": 2.3706632510998496e-05, "epoch": 0.47418833880937794, "percentage": 4.74, "elapsed_time": "1:51:44", "remaining_time": "1 day, 13:24:38", "throughput": 708.0, "total_tokens": 4746608} +{"current_steps": 8520, "total_steps": 179570, "loss": 0.373, "lr": 2.3720554658350506e-05, "epoch": 0.4744667817564181, "percentage": 4.74, "elapsed_time": "1:51:48", "remaining_time": "1 day, 13:24:33", "throughput": 708.0, "total_tokens": 4749312} +{"current_steps": 8525, "total_steps": 179570, "loss": 0.0956, "lr": 2.3734476805702512e-05, "epoch": 0.47474522470345826, "percentage": 4.75, "elapsed_time": "1:51:51", "remaining_time": "1 day, 13:24:27", "throughput": 708.0, "total_tokens": 4752032} +{"current_steps": 8530, "total_steps": 179570, "loss": 0.0218, "lr": 2.3748398953054522e-05, "epoch": 0.4750236676504984, "percentage": 4.75, "elapsed_time": "1:51:55", "remaining_time": "1 day, 13:24:24", "throughput": 708.0, "total_tokens": 4754880} +{"current_steps": 8535, "total_steps": 179570, "loss": 0.2052, "lr": 2.376232110040653e-05, "epoch": 0.4753021105975386, "percentage": 4.75, "elapsed_time": "1:51:59", "remaining_time": "1 day, 13:24:21", "throughput": 708.0, "total_tokens": 4757696} +{"current_steps": 8540, "total_steps": 179570, "loss": 0.0268, "lr": 2.3776243247758535e-05, "epoch": 0.47558055354457873, "percentage": 4.76, "elapsed_time": "1:52:03", "remaining_time": "1 day, 13:24:08", "throughput": 708.0, "total_tokens": 4760128} +{"current_steps": 8545, "total_steps": 179570, "loss": 0.1113, "lr": 2.379016539511054e-05, "epoch": 0.4758589964916189, "percentage": 4.76, "elapsed_time": "1:52:07", "remaining_time": "1 day, 13:24:04", "throughput": 708.01, "total_tokens": 4762992} +{"current_steps": 8550, "total_steps": 179570, "loss": 0.3227, "lr": 2.3804087542462548e-05, "epoch": 0.476137439438659, "percentage": 4.76, "elapsed_time": "1:52:11", "remaining_time": "1 day, 13:24:05", "throughput": 708.01, "total_tokens": 4765968} +{"current_steps": 8555, "total_steps": 179570, "loss": 0.2163, "lr": 2.3818009689814558e-05, "epoch": 0.47641588238569915, "percentage": 4.76, "elapsed_time": "1:52:14", "remaining_time": "1 day, 13:23:47", "throughput": 707.99, "total_tokens": 4768128} +{"current_steps": 8560, "total_steps": 179570, "loss": 0.002, "lr": 2.3831931837166565e-05, "epoch": 0.4766943253327393, "percentage": 4.77, "elapsed_time": "1:52:18", "remaining_time": "1 day, 13:23:45", "throughput": 707.99, "total_tokens": 4771008} +{"current_steps": 8565, "total_steps": 179570, "loss": 0.0539, "lr": 2.3845853984518575e-05, "epoch": 0.47697276827977947, "percentage": 4.77, "elapsed_time": "1:52:22", "remaining_time": "1 day, 13:23:40", "throughput": 707.97, "total_tokens": 4773584} +{"current_steps": 8570, "total_steps": 179570, "loss": 0.0018, "lr": 2.385977613187058e-05, "epoch": 0.4772512112268196, "percentage": 4.77, "elapsed_time": "1:52:26", "remaining_time": "1 day, 13:23:41", "throughput": 707.98, "total_tokens": 4776608} +{"current_steps": 8575, "total_steps": 179570, "loss": 0.0046, "lr": 2.387369827922259e-05, "epoch": 0.4775296541738598, "percentage": 4.78, "elapsed_time": "1:52:31", "remaining_time": "1 day, 13:23:43", "throughput": 707.98, "total_tokens": 4779568} +{"current_steps": 8580, "total_steps": 179570, "loss": 0.13, "lr": 2.3887620426574597e-05, "epoch": 0.47780809712089994, "percentage": 4.78, "elapsed_time": "1:52:34", "remaining_time": "1 day, 13:23:33", "throughput": 707.95, "total_tokens": 4782000} +{"current_steps": 8585, "total_steps": 179570, "loss": 0.2294, "lr": 2.3901542573926604e-05, "epoch": 0.4780865400679401, "percentage": 4.78, "elapsed_time": "1:52:38", "remaining_time": "1 day, 13:23:26", "throughput": 707.96, "total_tokens": 4784768} +{"current_steps": 8590, "total_steps": 179570, "loss": 0.1925, "lr": 2.391546472127861e-05, "epoch": 0.4783649830149802, "percentage": 4.78, "elapsed_time": "1:52:42", "remaining_time": "1 day, 13:23:22", "throughput": 707.96, "total_tokens": 4787520} +{"current_steps": 8595, "total_steps": 179570, "loss": 0.3092, "lr": 2.3929386868630617e-05, "epoch": 0.47864342596202036, "percentage": 4.79, "elapsed_time": "1:52:46", "remaining_time": "1 day, 13:23:14", "throughput": 707.95, "total_tokens": 4790096} +{"current_steps": 8600, "total_steps": 179570, "loss": 0.2748, "lr": 2.3943309015982627e-05, "epoch": 0.4789218689090605, "percentage": 4.79, "elapsed_time": "1:52:50", "remaining_time": "1 day, 13:23:10", "throughput": 707.94, "total_tokens": 4792800} +{"current_steps": 8605, "total_steps": 179570, "loss": 0.5881, "lr": 2.3957231163334633e-05, "epoch": 0.4792003118561007, "percentage": 4.79, "elapsed_time": "1:52:53", "remaining_time": "1 day, 13:23:00", "throughput": 707.93, "total_tokens": 4795296} +{"current_steps": 8610, "total_steps": 179570, "loss": 0.1814, "lr": 2.3971153310686643e-05, "epoch": 0.47947875480314084, "percentage": 4.79, "elapsed_time": "1:52:57", "remaining_time": "1 day, 13:22:56", "throughput": 707.95, "total_tokens": 4798192} +{"current_steps": 8615, "total_steps": 179570, "loss": 0.0322, "lr": 2.398507545803865e-05, "epoch": 0.479757197750181, "percentage": 4.8, "elapsed_time": "1:53:01", "remaining_time": "1 day, 13:22:57", "throughput": 707.96, "total_tokens": 4801264} +{"current_steps": 8620, "total_steps": 179570, "loss": 0.0372, "lr": 2.3998997605390656e-05, "epoch": 0.48003564069722116, "percentage": 4.8, "elapsed_time": "1:53:06", "remaining_time": "1 day, 13:23:01", "throughput": 707.95, "total_tokens": 4804304} +{"current_steps": 8625, "total_steps": 179570, "loss": 0.0048, "lr": 2.4012919752742663e-05, "epoch": 0.4803140836442613, "percentage": 4.8, "elapsed_time": "1:53:10", "remaining_time": "1 day, 13:23:06", "throughput": 707.97, "total_tokens": 4807536} +{"current_steps": 8630, "total_steps": 179570, "loss": 0.5029, "lr": 2.402684190009467e-05, "epoch": 0.4805925265913014, "percentage": 4.81, "elapsed_time": "1:53:14", "remaining_time": "1 day, 13:23:08", "throughput": 707.98, "total_tokens": 4810528} +{"current_steps": 8635, "total_steps": 179570, "loss": 0.1937, "lr": 2.404076404744668e-05, "epoch": 0.4808709695383416, "percentage": 4.81, "elapsed_time": "1:53:18", "remaining_time": "1 day, 13:22:59", "throughput": 707.96, "total_tokens": 4813024} +{"current_steps": 8640, "total_steps": 179570, "loss": 0.1263, "lr": 2.4054686194798686e-05, "epoch": 0.48114941248538173, "percentage": 4.81, "elapsed_time": "1:53:22", "remaining_time": "1 day, 13:22:54", "throughput": 707.95, "total_tokens": 4815696} +{"current_steps": 8645, "total_steps": 179570, "loss": 0.288, "lr": 2.4068608342150696e-05, "epoch": 0.4814278554324219, "percentage": 4.81, "elapsed_time": "1:53:26", "remaining_time": "1 day, 13:22:56", "throughput": 707.96, "total_tokens": 4818768} +{"current_steps": 8650, "total_steps": 179570, "loss": 0.2858, "lr": 2.4082530489502702e-05, "epoch": 0.48170629837946205, "percentage": 4.82, "elapsed_time": "1:53:30", "remaining_time": "1 day, 13:22:51", "throughput": 707.95, "total_tokens": 4821488} +{"current_steps": 8655, "total_steps": 179570, "loss": 0.0029, "lr": 2.409645263685471e-05, "epoch": 0.4819847413265022, "percentage": 4.82, "elapsed_time": "1:53:33", "remaining_time": "1 day, 13:22:38", "throughput": 707.93, "total_tokens": 4823824} +{"current_steps": 8660, "total_steps": 179570, "loss": 0.0102, "lr": 2.411037478420672e-05, "epoch": 0.48226318427354237, "percentage": 4.82, "elapsed_time": "1:53:37", "remaining_time": "1 day, 13:22:31", "throughput": 707.91, "total_tokens": 4826320} +{"current_steps": 8665, "total_steps": 179570, "loss": 0.0033, "lr": 2.4124296931558722e-05, "epoch": 0.4825416272205825, "percentage": 4.83, "elapsed_time": "1:53:41", "remaining_time": "1 day, 13:22:33", "throughput": 707.93, "total_tokens": 4829488} +{"current_steps": 8670, "total_steps": 179570, "loss": 0.0021, "lr": 2.4138219078910732e-05, "epoch": 0.48282007016762263, "percentage": 4.83, "elapsed_time": "1:53:46", "remaining_time": "1 day, 13:22:38", "throughput": 707.94, "total_tokens": 4832624} +{"current_steps": 8675, "total_steps": 179570, "loss": 0.496, "lr": 2.415214122626274e-05, "epoch": 0.4830985131146628, "percentage": 4.83, "elapsed_time": "1:53:50", "remaining_time": "1 day, 13:22:31", "throughput": 707.95, "total_tokens": 4835408} +{"current_steps": 8680, "total_steps": 179570, "loss": 0.0391, "lr": 2.416606337361475e-05, "epoch": 0.48337695606170294, "percentage": 4.83, "elapsed_time": "1:53:54", "remaining_time": "1 day, 13:22:27", "throughput": 707.96, "total_tokens": 4838240} +{"current_steps": 8685, "total_steps": 179570, "loss": 0.129, "lr": 2.4179985520966755e-05, "epoch": 0.4836553990087431, "percentage": 4.84, "elapsed_time": "1:53:57", "remaining_time": "1 day, 13:22:20", "throughput": 707.95, "total_tokens": 4840864} +{"current_steps": 8690, "total_steps": 179570, "loss": 0.0038, "lr": 2.4193907668318765e-05, "epoch": 0.48393384195578326, "percentage": 4.84, "elapsed_time": "1:54:01", "remaining_time": "1 day, 13:22:15", "throughput": 707.95, "total_tokens": 4843616} +{"current_steps": 8695, "total_steps": 179570, "loss": 0.018, "lr": 2.420782981567077e-05, "epoch": 0.4842122849028234, "percentage": 4.84, "elapsed_time": "1:54:05", "remaining_time": "1 day, 13:22:00", "throughput": 707.93, "total_tokens": 4845872} +{"current_steps": 8700, "total_steps": 179570, "loss": 0.1777, "lr": 2.4221751963022778e-05, "epoch": 0.4844907278498636, "percentage": 4.84, "elapsed_time": "1:54:09", "remaining_time": "1 day, 13:22:01", "throughput": 707.94, "total_tokens": 4848928} +{"current_steps": 8705, "total_steps": 179570, "loss": 0.0002, "lr": 2.4235674110374784e-05, "epoch": 0.48476917079690374, "percentage": 4.85, "elapsed_time": "1:54:13", "remaining_time": "1 day, 13:22:06", "throughput": 707.95, "total_tokens": 4852064} +{"current_steps": 8710, "total_steps": 179570, "loss": 0.2596, "lr": 2.424959625772679e-05, "epoch": 0.48504761374394384, "percentage": 4.85, "elapsed_time": "1:54:17", "remaining_time": "1 day, 13:22:02", "throughput": 707.96, "total_tokens": 4854880} +{"current_steps": 8715, "total_steps": 179570, "loss": 0.1836, "lr": 2.42635184050788e-05, "epoch": 0.485326056690984, "percentage": 4.85, "elapsed_time": "1:54:21", "remaining_time": "1 day, 13:22:02", "throughput": 707.95, "total_tokens": 4857760} +{"current_steps": 8720, "total_steps": 179570, "loss": 0.0192, "lr": 2.4277440552430807e-05, "epoch": 0.48560449963802416, "percentage": 4.86, "elapsed_time": "1:54:26", "remaining_time": "1 day, 13:22:07", "throughput": 707.94, "total_tokens": 4860832} +{"current_steps": 8725, "total_steps": 179570, "loss": 0.061, "lr": 2.4291362699782817e-05, "epoch": 0.4858829425850643, "percentage": 4.86, "elapsed_time": "1:54:30", "remaining_time": "1 day, 13:22:03", "throughput": 707.94, "total_tokens": 4863584} +{"current_steps": 8730, "total_steps": 179570, "loss": 0.0378, "lr": 2.4305284847134824e-05, "epoch": 0.4861613855321045, "percentage": 4.86, "elapsed_time": "1:54:34", "remaining_time": "1 day, 13:22:01", "throughput": 707.94, "total_tokens": 4866464} +{"current_steps": 8735, "total_steps": 179570, "loss": 0.0001, "lr": 2.431920699448683e-05, "epoch": 0.48643982847914463, "percentage": 4.86, "elapsed_time": "1:54:38", "remaining_time": "1 day, 13:22:02", "throughput": 707.94, "total_tokens": 4869472} +{"current_steps": 8740, "total_steps": 179570, "loss": 0.2803, "lr": 2.433312914183884e-05, "epoch": 0.4867182714261848, "percentage": 4.87, "elapsed_time": "1:54:42", "remaining_time": "1 day, 13:21:55", "throughput": 707.94, "total_tokens": 4872080} +{"current_steps": 8745, "total_steps": 179570, "loss": 0.0018, "lr": 2.4347051289190843e-05, "epoch": 0.48699671437322495, "percentage": 4.87, "elapsed_time": "1:54:46", "remaining_time": "1 day, 13:21:52", "throughput": 707.92, "total_tokens": 4874816} +{"current_steps": 8750, "total_steps": 179570, "loss": 0.0, "lr": 2.4360973436542853e-05, "epoch": 0.48727515732026505, "percentage": 4.87, "elapsed_time": "1:54:50", "remaining_time": "1 day, 13:21:52", "throughput": 707.93, "total_tokens": 4877808} +{"current_steps": 8755, "total_steps": 179570, "loss": 0.0269, "lr": 2.437489558389486e-05, "epoch": 0.4875536002673052, "percentage": 4.88, "elapsed_time": "1:54:54", "remaining_time": "1 day, 13:21:46", "throughput": 707.94, "total_tokens": 4880560} +{"current_steps": 8760, "total_steps": 179570, "loss": 0.2689, "lr": 2.438881773124687e-05, "epoch": 0.48783204321434537, "percentage": 4.88, "elapsed_time": "1:54:57", "remaining_time": "1 day, 13:21:42", "throughput": 707.94, "total_tokens": 4883392} +{"current_steps": 8765, "total_steps": 179570, "loss": 0.1498, "lr": 2.4402739878598876e-05, "epoch": 0.4881104861613855, "percentage": 4.88, "elapsed_time": "1:55:01", "remaining_time": "1 day, 13:21:32", "throughput": 707.91, "total_tokens": 4885728} +{"current_steps": 8770, "total_steps": 179570, "loss": 0.1429, "lr": 2.4416662025950883e-05, "epoch": 0.4883889291084257, "percentage": 4.88, "elapsed_time": "1:55:05", "remaining_time": "1 day, 13:21:25", "throughput": 707.91, "total_tokens": 4888384} +{"current_steps": 8775, "total_steps": 179570, "loss": 0.4223, "lr": 2.4430584173302893e-05, "epoch": 0.48866737205546584, "percentage": 4.89, "elapsed_time": "1:55:09", "remaining_time": "1 day, 13:21:19", "throughput": 707.91, "total_tokens": 4891088} +{"current_steps": 8780, "total_steps": 179570, "loss": 0.188, "lr": 2.44445063206549e-05, "epoch": 0.488945815002506, "percentage": 4.89, "elapsed_time": "1:55:13", "remaining_time": "1 day, 13:21:22", "throughput": 707.9, "total_tokens": 4894080} +{"current_steps": 8785, "total_steps": 179570, "loss": 0.0611, "lr": 2.4458428468006906e-05, "epoch": 0.48922425794954616, "percentage": 4.89, "elapsed_time": "1:55:17", "remaining_time": "1 day, 13:21:15", "throughput": 707.9, "total_tokens": 4896768} +{"current_steps": 8790, "total_steps": 179570, "loss": 0.1686, "lr": 2.4472350615358912e-05, "epoch": 0.48950270089658626, "percentage": 4.9, "elapsed_time": "1:55:20", "remaining_time": "1 day, 13:21:01", "throughput": 707.9, "total_tokens": 4899200} +{"current_steps": 8795, "total_steps": 179570, "loss": 0.2485, "lr": 2.4486272762710922e-05, "epoch": 0.4897811438436264, "percentage": 4.9, "elapsed_time": "1:55:24", "remaining_time": "1 day, 13:20:54", "throughput": 707.89, "total_tokens": 4901760} +{"current_steps": 8800, "total_steps": 179570, "loss": 0.0359, "lr": 2.450019491006293e-05, "epoch": 0.4900595867906666, "percentage": 4.9, "elapsed_time": "1:55:28", "remaining_time": "1 day, 13:20:55", "throughput": 707.9, "total_tokens": 4904816} +{"current_steps": 8805, "total_steps": 179570, "loss": 0.188, "lr": 2.451411705741494e-05, "epoch": 0.49033802973770674, "percentage": 4.9, "elapsed_time": "1:55:32", "remaining_time": "1 day, 13:20:47", "throughput": 707.91, "total_tokens": 4907504} +{"current_steps": 8810, "total_steps": 179570, "loss": 0.2497, "lr": 2.4528039204766945e-05, "epoch": 0.4906164726847469, "percentage": 4.91, "elapsed_time": "1:55:35", "remaining_time": "1 day, 13:20:35", "throughput": 707.91, "total_tokens": 4910016} +{"current_steps": 8815, "total_steps": 179570, "loss": 0.1454, "lr": 2.454196135211895e-05, "epoch": 0.49089491563178705, "percentage": 4.91, "elapsed_time": "1:55:39", "remaining_time": "1 day, 13:20:34", "throughput": 707.93, "total_tokens": 4913008} +{"current_steps": 8820, "total_steps": 179570, "loss": 0.2214, "lr": 2.455588349947096e-05, "epoch": 0.4911733585788272, "percentage": 4.91, "elapsed_time": "1:55:43", "remaining_time": "1 day, 13:20:27", "throughput": 707.93, "total_tokens": 4915712} +{"current_steps": 8825, "total_steps": 179570, "loss": 0.2208, "lr": 2.4569805646822965e-05, "epoch": 0.49145180152586737, "percentage": 4.91, "elapsed_time": "1:55:47", "remaining_time": "1 day, 13:20:25", "throughput": 707.93, "total_tokens": 4918560} +{"current_steps": 8830, "total_steps": 179570, "loss": 0.0138, "lr": 2.4583727794174975e-05, "epoch": 0.4917302444729075, "percentage": 4.92, "elapsed_time": "1:55:51", "remaining_time": "1 day, 13:20:22", "throughput": 707.95, "total_tokens": 4921504} +{"current_steps": 8835, "total_steps": 179570, "loss": 0.1058, "lr": 2.459764994152698e-05, "epoch": 0.49200868741994763, "percentage": 4.92, "elapsed_time": "1:55:55", "remaining_time": "1 day, 13:20:19", "throughput": 707.95, "total_tokens": 4924352} +{"current_steps": 8840, "total_steps": 179570, "loss": 0.0212, "lr": 2.461157208887899e-05, "epoch": 0.4922871303669878, "percentage": 4.92, "elapsed_time": "1:55:59", "remaining_time": "1 day, 13:20:18", "throughput": 707.97, "total_tokens": 4927392} +{"current_steps": 8845, "total_steps": 179570, "loss": 0.0038, "lr": 2.4625494236230998e-05, "epoch": 0.49256557331402795, "percentage": 4.93, "elapsed_time": "1:56:03", "remaining_time": "1 day, 13:20:16", "throughput": 707.97, "total_tokens": 4930272} +{"current_steps": 8850, "total_steps": 179570, "loss": 0.4752, "lr": 2.4639416383583004e-05, "epoch": 0.4928440162610681, "percentage": 4.93, "elapsed_time": "1:56:07", "remaining_time": "1 day, 13:20:09", "throughput": 707.98, "total_tokens": 4933024} +{"current_steps": 8855, "total_steps": 179570, "loss": 0.0071, "lr": 2.4653338530935014e-05, "epoch": 0.49312245920810827, "percentage": 4.93, "elapsed_time": "1:56:11", "remaining_time": "1 day, 13:20:06", "throughput": 707.99, "total_tokens": 4935856} +{"current_steps": 8860, "total_steps": 179570, "loss": 0.5878, "lr": 2.466726067828702e-05, "epoch": 0.4934009021551484, "percentage": 4.93, "elapsed_time": "1:56:15", "remaining_time": "1 day, 13:19:58", "throughput": 707.98, "total_tokens": 4938400} +{"current_steps": 8865, "total_steps": 179570, "loss": 0.0932, "lr": 2.4681182825639027e-05, "epoch": 0.4936793451021886, "percentage": 4.94, "elapsed_time": "1:56:19", "remaining_time": "1 day, 13:19:48", "throughput": 707.97, "total_tokens": 4940896} +{"current_steps": 8870, "total_steps": 179570, "loss": 0.4166, "lr": 2.4695104972991034e-05, "epoch": 0.4939577880492287, "percentage": 4.94, "elapsed_time": "1:56:22", "remaining_time": "1 day, 13:19:40", "throughput": 707.96, "total_tokens": 4943552} +{"current_steps": 8875, "total_steps": 179570, "loss": 0.1017, "lr": 2.4709027120343043e-05, "epoch": 0.49423623099626884, "percentage": 4.94, "elapsed_time": "1:56:26", "remaining_time": "1 day, 13:19:37", "throughput": 707.97, "total_tokens": 4946384} +{"current_steps": 8880, "total_steps": 179570, "loss": 0.2035, "lr": 2.472294926769505e-05, "epoch": 0.494514673943309, "percentage": 4.95, "elapsed_time": "1:56:30", "remaining_time": "1 day, 13:19:25", "throughput": 707.94, "total_tokens": 4948720} +{"current_steps": 8885, "total_steps": 179570, "loss": 0.3014, "lr": 2.4736871415047057e-05, "epoch": 0.49479311689034916, "percentage": 4.95, "elapsed_time": "1:56:34", "remaining_time": "1 day, 13:19:25", "throughput": 707.95, "total_tokens": 4951696} +{"current_steps": 8890, "total_steps": 179570, "loss": 0.2588, "lr": 2.4750793562399066e-05, "epoch": 0.4950715598373893, "percentage": 4.95, "elapsed_time": "1:56:38", "remaining_time": "1 day, 13:19:20", "throughput": 707.94, "total_tokens": 4954400} +{"current_steps": 8895, "total_steps": 179570, "loss": 0.0256, "lr": 2.4764715709751073e-05, "epoch": 0.4953500027844295, "percentage": 4.95, "elapsed_time": "1:56:41", "remaining_time": "1 day, 13:19:08", "throughput": 707.93, "total_tokens": 4956752} +{"current_steps": 8900, "total_steps": 179570, "loss": 0.5601, "lr": 2.4778637857103083e-05, "epoch": 0.49562844573146964, "percentage": 4.96, "elapsed_time": "1:56:45", "remaining_time": "1 day, 13:18:58", "throughput": 707.92, "total_tokens": 4959264} +{"current_steps": 8905, "total_steps": 179570, "loss": 0.1412, "lr": 2.4792560004455086e-05, "epoch": 0.4959068886785098, "percentage": 4.96, "elapsed_time": "1:56:49", "remaining_time": "1 day, 13:18:54", "throughput": 707.93, "total_tokens": 4962128} +{"current_steps": 8910, "total_steps": 179570, "loss": 0.2039, "lr": 2.4806482151807096e-05, "epoch": 0.49618533162554995, "percentage": 4.96, "elapsed_time": "1:56:53", "remaining_time": "1 day, 13:18:50", "throughput": 707.93, "total_tokens": 4964944} +{"current_steps": 8915, "total_steps": 179570, "loss": 0.1999, "lr": 2.4820404299159102e-05, "epoch": 0.49646377457259006, "percentage": 4.96, "elapsed_time": "1:56:57", "remaining_time": "1 day, 13:18:43", "throughput": 707.94, "total_tokens": 4967648} +{"current_steps": 8920, "total_steps": 179570, "loss": 0.2577, "lr": 2.4834326446511112e-05, "epoch": 0.4967422175196302, "percentage": 4.97, "elapsed_time": "1:57:01", "remaining_time": "1 day, 13:18:48", "throughput": 707.95, "total_tokens": 4970816} +{"current_steps": 8925, "total_steps": 179570, "loss": 0.2494, "lr": 2.484824859386312e-05, "epoch": 0.49702066046667037, "percentage": 4.97, "elapsed_time": "1:57:05", "remaining_time": "1 day, 13:18:43", "throughput": 707.94, "total_tokens": 4973520} +{"current_steps": 8930, "total_steps": 179570, "loss": 0.1094, "lr": 2.4862170741215125e-05, "epoch": 0.49729910341371053, "percentage": 4.97, "elapsed_time": "1:57:09", "remaining_time": "1 day, 13:18:45", "throughput": 707.96, "total_tokens": 4976656} +{"current_steps": 8935, "total_steps": 179570, "loss": 0.0024, "lr": 2.4876092888567135e-05, "epoch": 0.4975775463607507, "percentage": 4.98, "elapsed_time": "1:57:13", "remaining_time": "1 day, 13:18:47", "throughput": 707.97, "total_tokens": 4979760} +{"current_steps": 8940, "total_steps": 179570, "loss": 0.0692, "lr": 2.4890015035919142e-05, "epoch": 0.49785598930779085, "percentage": 4.98, "elapsed_time": "1:57:17", "remaining_time": "1 day, 13:18:44", "throughput": 707.98, "total_tokens": 4982656} +{"current_steps": 8945, "total_steps": 179570, "loss": 0.1526, "lr": 2.490393718327115e-05, "epoch": 0.498134432254831, "percentage": 4.98, "elapsed_time": "1:57:21", "remaining_time": "1 day, 13:18:45", "throughput": 707.99, "total_tokens": 4985648} +{"current_steps": 8950, "total_steps": 179570, "loss": 0.1706, "lr": 2.4917859330623155e-05, "epoch": 0.49841287520187116, "percentage": 4.98, "elapsed_time": "1:57:25", "remaining_time": "1 day, 13:18:29", "throughput": 707.95, "total_tokens": 4987776} +{"current_steps": 8955, "total_steps": 179570, "loss": 0.1248, "lr": 2.4931781477975165e-05, "epoch": 0.49869131814891127, "percentage": 4.99, "elapsed_time": "1:57:29", "remaining_time": "1 day, 13:18:21", "throughput": 707.95, "total_tokens": 4990368} +{"current_steps": 8960, "total_steps": 179570, "loss": 0.2972, "lr": 2.494570362532717e-05, "epoch": 0.4989697610959514, "percentage": 4.99, "elapsed_time": "1:57:32", "remaining_time": "1 day, 13:18:17", "throughput": 707.94, "total_tokens": 4993088} +{"current_steps": 8965, "total_steps": 179570, "loss": 0.1058, "lr": 2.4959625772679178e-05, "epoch": 0.4992482040429916, "percentage": 4.99, "elapsed_time": "1:57:37", "remaining_time": "1 day, 13:18:15", "throughput": 707.97, "total_tokens": 4996128} +{"current_steps": 8970, "total_steps": 179570, "loss": 0.5803, "lr": 2.4973547920031188e-05, "epoch": 0.49952664699003174, "percentage": 5.0, "elapsed_time": "1:57:41", "remaining_time": "1 day, 13:18:17", "throughput": 707.98, "total_tokens": 4999232} +{"current_steps": 8975, "total_steps": 179570, "loss": 0.149, "lr": 2.4987470067383194e-05, "epoch": 0.4998050899370719, "percentage": 5.0, "elapsed_time": "1:57:45", "remaining_time": "1 day, 13:18:10", "throughput": 707.98, "total_tokens": 5001872} +{"current_steps": 8979, "total_steps": 179570, "eval_loss": 0.16585436463356018, "epoch": 0.500027844294704, "percentage": 5.0, "elapsed_time": "2:06:23", "remaining_time": "1 day, 16:01:25", "throughput": 659.81, "total_tokens": 5003904} +{"current_steps": 8980, "total_steps": 179570, "loss": 0.0021, "lr": 2.5001392214735204e-05, "epoch": 0.500083532884112, "percentage": 5.0, "elapsed_time": "2:06:34", "remaining_time": "1 day, 16:04:24", "throughput": 659.0, "total_tokens": 5004544} +{"current_steps": 8985, "total_steps": 179570, "loss": 0.0002, "lr": 2.501531436208721e-05, "epoch": 0.5003619758311522, "percentage": 5.0, "elapsed_time": "2:06:38", "remaining_time": "1 day, 16:04:18", "throughput": 659.02, "total_tokens": 5007456} +{"current_steps": 8990, "total_steps": 179570, "loss": 0.1617, "lr": 2.5029236509439217e-05, "epoch": 0.5006404187781923, "percentage": 5.01, "elapsed_time": "2:06:42", "remaining_time": "1 day, 16:04:03", "throughput": 659.01, "total_tokens": 5009824} +{"current_steps": 8995, "total_steps": 179570, "loss": 0.3569, "lr": 2.5043158656791227e-05, "epoch": 0.5009188617252325, "percentage": 5.01, "elapsed_time": "2:06:46", "remaining_time": "1 day, 16:04:07", "throughput": 659.03, "total_tokens": 5013056} +{"current_steps": 9000, "total_steps": 179570, "loss": 0.0366, "lr": 2.5057080804143234e-05, "epoch": 0.5011973046722726, "percentage": 5.01, "elapsed_time": "2:06:50", "remaining_time": "1 day, 16:04:05", "throughput": 659.03, "total_tokens": 5015856}