Training in progress, step 2400
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c6afc12279a2e42b04f908d42daeadceace92e7a16313473ec7fdd3fd61a7e
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b2793bbe3188fc34d215df3e1d1addc4ac96365d6650491504715ccf2a83599
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1236533de187c96b290f44a4ec38e5dc082a9228898b73d8432aecd35c4cd5a
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9664f97a09b0f312e7a8385eb1a2cbe29da6b98042707f5fa1542b6b4777971e
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -439,3 +439,43 @@
|
|
| 439 |
{"current_steps": 2195, "total_steps": 9128, "loss": 0.301, "lr": 3.764776823132891e-05, "epoch": 1.6835443037974684, "percentage": 24.05, "elapsed_time": "13:47:42", "remaining_time": "1 day, 19:34:21"}
|
| 440 |
{"current_steps": 2200, "total_steps": 9128, "loss": 0.2993, "lr": 3.762974221835433e-05, "epoch": 1.687380130418105, "percentage": 24.1, "elapsed_time": "13:49:19", "remaining_time": "1 day, 19:31:36"}
|
| 441 |
{"current_steps": 2205, "total_steps": 9128, "loss": 0.2959, "lr": 3.761165174832634e-05, "epoch": 1.6912159570387417, "percentage": 24.16, "elapsed_time": "13:52:18", "remaining_time": "1 day, 19:33:12"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 439 |
{"current_steps": 2195, "total_steps": 9128, "loss": 0.301, "lr": 3.764776823132891e-05, "epoch": 1.6835443037974684, "percentage": 24.05, "elapsed_time": "13:47:42", "remaining_time": "1 day, 19:34:21"}
|
| 440 |
{"current_steps": 2200, "total_steps": 9128, "loss": 0.2993, "lr": 3.762974221835433e-05, "epoch": 1.687380130418105, "percentage": 24.1, "elapsed_time": "13:49:19", "remaining_time": "1 day, 19:31:36"}
|
| 441 |
{"current_steps": 2205, "total_steps": 9128, "loss": 0.2959, "lr": 3.761165174832634e-05, "epoch": 1.6912159570387417, "percentage": 24.16, "elapsed_time": "13:52:18", "remaining_time": "1 day, 19:33:12"}
|
| 442 |
+
{"current_steps": 2210, "total_steps": 9128, "loss": 0.2871, "lr": 3.7593496887386485e-05, "epoch": 1.6950517836593786, "percentage": 24.21, "elapsed_time": "13:54:01", "remaining_time": "1 day, 19:30:45"}
|
| 443 |
+
{"current_steps": 2215, "total_steps": 9128, "loss": 0.2957, "lr": 3.757527770191173e-05, "epoch": 1.6988876102800154, "percentage": 24.27, "elapsed_time": "13:55:41", "remaining_time": "1 day, 19:28:12"}
|
| 444 |
+
{"current_steps": 2220, "total_steps": 9128, "loss": 0.2973, "lr": 3.7556994258514235e-05, "epoch": 1.702723436900652, "percentage": 24.32, "elapsed_time": "13:57:28", "remaining_time": "1 day, 19:25:59"}
|
| 445 |
+
{"current_steps": 2225, "total_steps": 9128, "loss": 0.2887, "lr": 3.753864662404107e-05, "epoch": 1.7065592635212887, "percentage": 24.38, "elapsed_time": "13:59:04", "remaining_time": "1 day, 19:23:11"}
|
| 446 |
+
{"current_steps": 2230, "total_steps": 9128, "loss": 0.2988, "lr": 3.752023486557401e-05, "epoch": 1.7103950901419256, "percentage": 24.43, "elapsed_time": "14:00:42", "remaining_time": "1 day, 19:20:33"}
|
| 447 |
+
{"current_steps": 2235, "total_steps": 9128, "loss": 0.2929, "lr": 3.75017590504293e-05, "epoch": 1.7142309167625625, "percentage": 24.49, "elapsed_time": "14:02:26", "remaining_time": "1 day, 19:18:10"}
|
| 448 |
+
{"current_steps": 2240, "total_steps": 9128, "loss": 0.2848, "lr": 3.748321924615736e-05, "epoch": 1.718066743383199, "percentage": 24.54, "elapsed_time": "14:04:09", "remaining_time": "1 day, 19:15:47"}
|
| 449 |
+
{"current_steps": 2245, "total_steps": 9128, "loss": 0.2797, "lr": 3.746461552054256e-05, "epoch": 1.7219025700038357, "percentage": 24.59, "elapsed_time": "14:05:46", "remaining_time": "1 day, 19:13:03"}
|
| 450 |
+
{"current_steps": 2250, "total_steps": 9128, "loss": 0.3008, "lr": 3.7445947941603e-05, "epoch": 1.7257383966244726, "percentage": 24.65, "elapsed_time": "14:07:25", "remaining_time": "1 day, 19:10:28"}
|
| 451 |
+
{"current_steps": 2255, "total_steps": 9128, "loss": 0.2866, "lr": 3.742721657759021e-05, "epoch": 1.7295742232451095, "percentage": 24.7, "elapsed_time": "14:09:08", "remaining_time": "1 day, 19:08:06"}
|
| 452 |
+
{"current_steps": 2260, "total_steps": 9128, "loss": 0.2942, "lr": 3.740842149698896e-05, "epoch": 1.733410049865746, "percentage": 24.76, "elapsed_time": "14:10:44", "remaining_time": "1 day, 19:05:22"}
|
| 453 |
+
{"current_steps": 2265, "total_steps": 9128, "loss": 0.2985, "lr": 3.7389562768516945e-05, "epoch": 1.7372458764863827, "percentage": 24.81, "elapsed_time": "14:12:25", "remaining_time": "1 day, 19:02:51"}
|
| 454 |
+
{"current_steps": 2270, "total_steps": 9128, "loss": 0.2962, "lr": 3.737064046112458e-05, "epoch": 1.7410817031070196, "percentage": 24.87, "elapsed_time": "14:14:06", "remaining_time": "1 day, 19:00:24"}
|
| 455 |
+
{"current_steps": 2275, "total_steps": 9128, "loss": 0.2901, "lr": 3.735165464399475e-05, "epoch": 1.7449175297276565, "percentage": 24.92, "elapsed_time": "14:15:49", "remaining_time": "1 day, 18:58:01"}
|
| 456 |
+
{"current_steps": 2280, "total_steps": 9128, "loss": 0.302, "lr": 3.733260538654252e-05, "epoch": 1.748753356348293, "percentage": 24.98, "elapsed_time": "14:17:26", "remaining_time": "1 day, 18:55:19"}
|
| 457 |
+
{"current_steps": 2285, "total_steps": 9128, "loss": 0.2794, "lr": 3.731349275841491e-05, "epoch": 1.7525891829689297, "percentage": 25.03, "elapsed_time": "14:19:08", "remaining_time": "1 day, 18:52:56"}
|
| 458 |
+
{"current_steps": 2290, "total_steps": 9128, "loss": 0.2798, "lr": 3.729431682949063e-05, "epoch": 1.7564250095895666, "percentage": 25.09, "elapsed_time": "14:20:48", "remaining_time": "1 day, 18:50:25"}
|
| 459 |
+
{"current_steps": 2295, "total_steps": 9128, "loss": 0.2789, "lr": 3.727507766987983e-05, "epoch": 1.7602608362102035, "percentage": 25.14, "elapsed_time": "14:22:26", "remaining_time": "1 day, 18:47:47"}
|
| 460 |
+
{"current_steps": 2300, "total_steps": 9128, "loss": 0.2884, "lr": 3.725577534992385e-05, "epoch": 1.76409666283084, "percentage": 25.2, "elapsed_time": "14:24:10", "remaining_time": "1 day, 18:45:28"}
|
| 461 |
+
{"current_steps": 2305, "total_steps": 9128, "loss": 0.2917, "lr": 3.7236409940194936e-05, "epoch": 1.7679324894514767, "percentage": 25.25, "elapsed_time": "14:25:51", "remaining_time": "1 day, 18:43:00"}
|
| 462 |
+
{"current_steps": 2310, "total_steps": 9128, "loss": 0.292, "lr": 3.721698151149601e-05, "epoch": 1.7717683160721136, "percentage": 25.31, "elapsed_time": "14:27:40", "remaining_time": "1 day, 18:40:57"}
|
| 463 |
+
{"current_steps": 2315, "total_steps": 9128, "loss": 0.2856, "lr": 3.719749013486041e-05, "epoch": 1.7756041426927502, "percentage": 25.36, "elapsed_time": "14:29:25", "remaining_time": "1 day, 18:38:42"}
|
| 464 |
+
{"current_steps": 2320, "total_steps": 9128, "loss": 0.2977, "lr": 3.71779358815516e-05, "epoch": 1.7794399693133869, "percentage": 25.42, "elapsed_time": "14:31:08", "remaining_time": "1 day, 18:36:22"}
|
| 465 |
+
{"current_steps": 2325, "total_steps": 9128, "loss": 0.2959, "lr": 3.715831882306294e-05, "epoch": 1.7832757959340237, "percentage": 25.47, "elapsed_time": "14:32:49", "remaining_time": "1 day, 18:33:53"}
|
| 466 |
+
{"current_steps": 2330, "total_steps": 9128, "loss": 0.291, "lr": 3.7138639031117426e-05, "epoch": 1.7871116225546606, "percentage": 25.53, "elapsed_time": "14:34:27", "remaining_time": "1 day, 18:31:18"}
|
| 467 |
+
{"current_steps": 2335, "total_steps": 9128, "loss": 0.2823, "lr": 3.7118896577667414e-05, "epoch": 1.7909474491752972, "percentage": 25.58, "elapsed_time": "14:36:09", "remaining_time": "1 day, 18:28:56"}
|
| 468 |
+
{"current_steps": 2340, "total_steps": 9128, "loss": 0.276, "lr": 3.709909153489435e-05, "epoch": 1.7947832757959339, "percentage": 25.64, "elapsed_time": "14:37:46", "remaining_time": "1 day, 18:26:18"}
|
| 469 |
+
{"current_steps": 2345, "total_steps": 9128, "loss": 0.284, "lr": 3.707922397520852e-05, "epoch": 1.7986191024165707, "percentage": 25.69, "elapsed_time": "14:39:23", "remaining_time": "1 day, 18:23:39"}
|
| 470 |
+
{"current_steps": 2350, "total_steps": 9128, "loss": 0.2748, "lr": 3.705929397124878e-05, "epoch": 1.8024549290372076, "percentage": 25.74, "elapsed_time": "14:41:04", "remaining_time": "1 day, 18:21:15"}
|
| 471 |
+
{"current_steps": 2355, "total_steps": 9128, "loss": 0.2749, "lr": 3.703930159588229e-05, "epoch": 1.8062907556578442, "percentage": 25.8, "elapsed_time": "14:42:44", "remaining_time": "1 day, 18:18:46"}
|
| 472 |
+
{"current_steps": 2360, "total_steps": 9128, "loss": 0.2756, "lr": 3.701924692220427e-05, "epoch": 1.810126582278481, "percentage": 25.85, "elapsed_time": "14:44:23", "remaining_time": "1 day, 18:16:15"}
|
| 473 |
+
{"current_steps": 2365, "total_steps": 9128, "loss": 0.2883, "lr": 3.699913002353769e-05, "epoch": 1.8139624088991178, "percentage": 25.91, "elapsed_time": "14:46:00", "remaining_time": "1 day, 18:13:39"}
|
| 474 |
+
{"current_steps": 2370, "total_steps": 9128, "loss": 0.3029, "lr": 3.6978950973433014e-05, "epoch": 1.8177982355197546, "percentage": 25.96, "elapsed_time": "14:47:40", "remaining_time": "1 day, 18:11:12"}
|
| 475 |
+
{"current_steps": 2375, "total_steps": 9128, "loss": 0.2852, "lr": 3.695870984566799e-05, "epoch": 1.8216340621403913, "percentage": 26.02, "elapsed_time": "14:49:15", "remaining_time": "1 day, 18:08:30"}
|
| 476 |
+
{"current_steps": 2380, "total_steps": 9128, "loss": 0.2886, "lr": 3.693840671424727e-05, "epoch": 1.825469888761028, "percentage": 26.07, "elapsed_time": "14:50:57", "remaining_time": "1 day, 18:06:06"}
|
| 477 |
+
{"current_steps": 2385, "total_steps": 9128, "loss": 0.282, "lr": 3.6918041653402246e-05, "epoch": 1.8293057153816648, "percentage": 26.13, "elapsed_time": "14:52:40", "remaining_time": "1 day, 18:03:49"}
|
| 478 |
+
{"current_steps": 2390, "total_steps": 9128, "loss": 0.2808, "lr": 3.6897614737590716e-05, "epoch": 1.8331415420023016, "percentage": 26.18, "elapsed_time": "14:54:23", "remaining_time": "1 day, 18:01:31"}
|
| 479 |
+
{"current_steps": 2395, "total_steps": 9128, "loss": 0.2857, "lr": 3.687712604149662e-05, "epoch": 1.8369773686229383, "percentage": 26.24, "elapsed_time": "14:56:06", "remaining_time": "1 day, 17:59:11"}
|
| 480 |
+
{"current_steps": 2400, "total_steps": 9128, "loss": 0.2768, "lr": 3.685657564002981e-05, "epoch": 1.840813195243575, "percentage": 26.29, "elapsed_time": "14:57:49", "remaining_time": "1 day, 17:56:54"}
|
| 481 |
+
{"current_steps": 2405, "total_steps": 9128, "loss": 0.2868, "lr": 3.68359636083257e-05, "epoch": 1.8446490218642118, "percentage": 26.35, "elapsed_time": "15:00:38", "remaining_time": "1 day, 17:57:40"}
|