Training in progress, step 2000
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 sha256:38316f9f44cb674400f46d3ef1b8e1cbf47079b927be637c3708a48c33f9b5eb
|
| 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:aff7994492f5b6ceb077c69049150d1ff5e40ea2427fca1fa7f5d0fcea11b7c5
|
| 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:fc799f05181676bc1bb5481d10a9dcdbb66b31697235c39d34ede0903334ffd6
|
| 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 sha256:3f9f1f922e39e4370ce5cc3a0b7bd0be9242ca68e0bf7a146852f241c2c954d5
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -359,3 +359,42 @@
|
|
| 359 |
{"current_steps": 1795, "total_steps": 9128, "loss": 0.2142, "lr": 3.887559065067551e-05, "epoch": 1.3766781741465286, "percentage": 19.66, "elapsed_time": "11:41:40", "remaining_time": "1 day, 23:46:28"}
|
| 360 |
{"current_steps": 1800, "total_steps": 9128, "loss": 0.2287, "lr": 3.886291423246746e-05, "epoch": 1.3805140007671652, "percentage": 19.72, "elapsed_time": "11:42:56", "remaining_time": "1 day, 23:41:46"}
|
| 361 |
{"current_steps": 1805, "total_steps": 9128, "loss": 0.2034, "lr": 3.885016884853915e-05, "epoch": 1.384349827387802, "percentage": 19.77, "elapsed_time": "11:45:33", "remaining_time": "1 day, 23:42:30"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 359 |
{"current_steps": 1795, "total_steps": 9128, "loss": 0.2142, "lr": 3.887559065067551e-05, "epoch": 1.3766781741465286, "percentage": 19.66, "elapsed_time": "11:41:40", "remaining_time": "1 day, 23:46:28"}
|
| 360 |
{"current_steps": 1800, "total_steps": 9128, "loss": 0.2287, "lr": 3.886291423246746e-05, "epoch": 1.3805140007671652, "percentage": 19.72, "elapsed_time": "11:42:56", "remaining_time": "1 day, 23:41:46"}
|
| 361 |
{"current_steps": 1805, "total_steps": 9128, "loss": 0.2034, "lr": 3.885016884853915e-05, "epoch": 1.384349827387802, "percentage": 19.77, "elapsed_time": "11:45:33", "remaining_time": "1 day, 23:42:30"}
|
| 362 |
+
{"current_steps": 1810, "total_steps": 9128, "loss": 0.2118, "lr": 3.883735454548967e-05, "epoch": 1.3881856540084387, "percentage": 19.83, "elapsed_time": "11:46:49", "remaining_time": "1 day, 23:37:47"}
|
| 363 |
+
{"current_steps": 1815, "total_steps": 9128, "loss": 0.2134, "lr": 3.882447137017007e-05, "epoch": 1.3920214806290756, "percentage": 19.88, "elapsed_time": "11:48:04", "remaining_time": "1 day, 23:32:58"}
|
| 364 |
+
{"current_steps": 1820, "total_steps": 9128, "loss": 0.2004, "lr": 3.8811519369683225e-05, "epoch": 1.3958573072497122, "percentage": 19.94, "elapsed_time": "11:49:18", "remaining_time": "1 day, 23:28:09"}
|
| 365 |
+
{"current_steps": 1825, "total_steps": 9128, "loss": 0.2053, "lr": 3.8798498591383665e-05, "epoch": 1.399693133870349, "percentage": 19.99, "elapsed_time": "11:50:33", "remaining_time": "1 day, 23:23:23"}
|
| 366 |
+
{"current_steps": 1830, "total_steps": 9128, "loss": 0.2108, "lr": 3.878540908287734e-05, "epoch": 1.4035289604909857, "percentage": 20.05, "elapsed_time": "11:51:50", "remaining_time": "1 day, 23:18:48"}
|
| 367 |
+
{"current_steps": 1835, "total_steps": 9128, "loss": 0.211, "lr": 3.877225089202151e-05, "epoch": 1.4073647871116226, "percentage": 20.1, "elapsed_time": "11:53:05", "remaining_time": "1 day, 23:14:04"}
|
| 368 |
+
{"current_steps": 1840, "total_steps": 9128, "loss": 0.2145, "lr": 3.875902406692456e-05, "epoch": 1.4112006137322592, "percentage": 20.16, "elapsed_time": "11:54:20", "remaining_time": "1 day, 23:09:25"}
|
| 369 |
+
{"current_steps": 1845, "total_steps": 9128, "loss": 0.2023, "lr": 3.87457286559458e-05, "epoch": 1.415036440352896, "percentage": 20.21, "elapsed_time": "11:55:37", "remaining_time": "1 day, 23:04:52"}
|
| 370 |
+
{"current_steps": 1850, "total_steps": 9128, "loss": 0.2092, "lr": 3.873236470769529e-05, "epoch": 1.4188722669735327, "percentage": 20.27, "elapsed_time": "11:56:53", "remaining_time": "1 day, 23:00:17"}
|
| 371 |
+
{"current_steps": 1855, "total_steps": 9128, "loss": 0.2098, "lr": 3.8718932271033684e-05, "epoch": 1.4227080935941696, "percentage": 20.32, "elapsed_time": "11:58:10", "remaining_time": "1 day, 22:55:45"}
|
| 372 |
+
{"current_steps": 1860, "total_steps": 9128, "loss": 0.2032, "lr": 3.8705431395072045e-05, "epoch": 1.4265439202148062, "percentage": 20.38, "elapsed_time": "11:59:25", "remaining_time": "1 day, 22:51:10"}
|
| 373 |
+
{"current_steps": 1865, "total_steps": 9128, "loss": 0.2107, "lr": 3.869186212917166e-05, "epoch": 1.4303797468354431, "percentage": 20.43, "elapsed_time": "12:00:43", "remaining_time": "1 day, 22:46:44"}
|
| 374 |
+
{"current_steps": 1870, "total_steps": 9128, "loss": 0.1886, "lr": 3.867822452294385e-05, "epoch": 1.4342155734560798, "percentage": 20.49, "elapsed_time": "12:01:55", "remaining_time": "1 day, 22:42:00"}
|
| 375 |
+
{"current_steps": 1875, "total_steps": 9128, "loss": 0.2028, "lr": 3.86645186262498e-05, "epoch": 1.4380514000767166, "percentage": 20.54, "elapsed_time": "12:03:11", "remaining_time": "1 day, 22:37:28"}
|
| 376 |
+
{"current_steps": 1880, "total_steps": 9128, "loss": 0.2094, "lr": 3.865074448920039e-05, "epoch": 1.4418872266973533, "percentage": 20.6, "elapsed_time": "12:04:28", "remaining_time": "1 day, 22:33:03"}
|
| 377 |
+
{"current_steps": 1885, "total_steps": 9128, "loss": 0.1961, "lr": 3.8636902162155975e-05, "epoch": 1.4457230533179901, "percentage": 20.65, "elapsed_time": "12:05:41", "remaining_time": "1 day, 22:28:24"}
|
| 378 |
+
{"current_steps": 1890, "total_steps": 9128, "loss": 0.2099, "lr": 3.862299169572624e-05, "epoch": 1.4495588799386268, "percentage": 20.71, "elapsed_time": "12:06:54", "remaining_time": "1 day, 22:23:45"}
|
| 379 |
+
{"current_steps": 1895, "total_steps": 9128, "loss": 0.205, "lr": 3.860901314077e-05, "epoch": 1.4533947065592634, "percentage": 20.76, "elapsed_time": "12:08:08", "remaining_time": "1 day, 22:19:12"}
|
| 380 |
+
{"current_steps": 1900, "total_steps": 9128, "loss": 0.21, "lr": 3.8594966548394994e-05, "epoch": 1.4572305331799003, "percentage": 20.82, "elapsed_time": "12:09:23", "remaining_time": "1 day, 22:14:45"}
|
| 381 |
+
{"current_steps": 1905, "total_steps": 9128, "loss": 0.2063, "lr": 3.858085196995774e-05, "epoch": 1.4610663598005371, "percentage": 20.87, "elapsed_time": "12:10:38", "remaining_time": "1 day, 22:10:17"}
|
| 382 |
+
{"current_steps": 1910, "total_steps": 9128, "loss": 0.2028, "lr": 3.8566669457063295e-05, "epoch": 1.4649021864211738, "percentage": 20.92, "elapsed_time": "12:11:51", "remaining_time": "1 day, 22:05:44"}
|
| 383 |
+
{"current_steps": 1915, "total_steps": 9128, "loss": 0.2144, "lr": 3.855241906156513e-05, "epoch": 1.4687380130418104, "percentage": 20.98, "elapsed_time": "12:13:06", "remaining_time": "1 day, 22:01:19"}
|
| 384 |
+
{"current_steps": 1920, "total_steps": 9128, "loss": 0.2095, "lr": 3.853810083556487e-05, "epoch": 1.4725738396624473, "percentage": 21.03, "elapsed_time": "12:14:20", "remaining_time": "1 day, 21:56:50"}
|
| 385 |
+
{"current_steps": 1925, "total_steps": 9128, "loss": 0.2139, "lr": 3.8523714831412166e-05, "epoch": 1.4764096662830841, "percentage": 21.09, "elapsed_time": "12:15:36", "remaining_time": "1 day, 21:52:30"}
|
| 386 |
+
{"current_steps": 1930, "total_steps": 9128, "loss": 0.21, "lr": 3.850926110170446e-05, "epoch": 1.4802454929037208, "percentage": 21.14, "elapsed_time": "12:16:56", "remaining_time": "1 day, 21:48:27"}
|
| 387 |
+
{"current_steps": 1935, "total_steps": 9128, "loss": 0.2116, "lr": 3.849473969928681e-05, "epoch": 1.4840813195243574, "percentage": 21.2, "elapsed_time": "12:18:12", "remaining_time": "1 day, 21:44:08"}
|
| 388 |
+
{"current_steps": 1940, "total_steps": 9128, "loss": 0.1988, "lr": 3.8480150677251706e-05, "epoch": 1.4879171461449943, "percentage": 21.25, "elapsed_time": "12:19:25", "remaining_time": "1 day, 21:39:40"}
|
| 389 |
+
{"current_steps": 1945, "total_steps": 9128, "loss": 0.2072, "lr": 3.846549408893887e-05, "epoch": 1.4917529727656311, "percentage": 21.31, "elapsed_time": "12:20:40", "remaining_time": "1 day, 21:35:20"}
|
| 390 |
+
{"current_steps": 1950, "total_steps": 9128, "loss": 0.2069, "lr": 3.8450769987935024e-05, "epoch": 1.4955887993862678, "percentage": 21.36, "elapsed_time": "12:21:55", "remaining_time": "1 day, 21:31:01"}
|
| 391 |
+
{"current_steps": 1955, "total_steps": 9128, "loss": 0.2011, "lr": 3.8435978428073764e-05, "epoch": 1.4994246260069044, "percentage": 21.42, "elapsed_time": "12:23:09", "remaining_time": "1 day, 21:26:41"}
|
| 392 |
+
{"current_steps": 1960, "total_steps": 9128, "loss": 0.1997, "lr": 3.842111946343531e-05, "epoch": 1.5032604526275413, "percentage": 21.47, "elapsed_time": "12:24:24", "remaining_time": "1 day, 21:22:25"}
|
| 393 |
+
{"current_steps": 1965, "total_steps": 9128, "loss": 0.1946, "lr": 3.840619314834633e-05, "epoch": 1.5070962792481781, "percentage": 21.53, "elapsed_time": "12:25:40", "remaining_time": "1 day, 21:18:11"}
|
| 394 |
+
{"current_steps": 1970, "total_steps": 9128, "loss": 0.2129, "lr": 3.8391199537379714e-05, "epoch": 1.5109321058688148, "percentage": 21.58, "elapsed_time": "12:26:55", "remaining_time": "1 day, 21:13:58"}
|
| 395 |
+
{"current_steps": 1975, "total_steps": 9128, "loss": 0.2021, "lr": 3.837613868535444e-05, "epoch": 1.5147679324894514, "percentage": 21.64, "elapsed_time": "12:28:10", "remaining_time": "1 day, 21:09:43"}
|
| 396 |
+
{"current_steps": 1980, "total_steps": 9128, "loss": 0.1936, "lr": 3.836101064733528e-05, "epoch": 1.5186037591100883, "percentage": 21.69, "elapsed_time": "12:29:28", "remaining_time": "1 day, 21:05:42"}
|
| 397 |
+
{"current_steps": 1985, "total_steps": 9128, "loss": 0.1946, "lr": 3.834581547863268e-05, "epoch": 1.5224395857307251, "percentage": 21.75, "elapsed_time": "12:30:53", "remaining_time": "1 day, 21:02:03"}
|
| 398 |
+
{"current_steps": 1990, "total_steps": 9128, "loss": 0.1872, "lr": 3.833055323480253e-05, "epoch": 1.5262754123513618, "percentage": 21.8, "elapsed_time": "12:32:07", "remaining_time": "1 day, 20:57:49"}
|
| 399 |
+
{"current_steps": 1995, "total_steps": 9128, "loss": 0.2032, "lr": 3.831522397164592e-05, "epoch": 1.5301112389719984, "percentage": 21.86, "elapsed_time": "12:33:22", "remaining_time": "1 day, 20:53:38"}
|
| 400 |
+
{"current_steps": 2000, "total_steps": 9128, "loss": 0.2, "lr": 3.829982774520901e-05, "epoch": 1.5339470655926353, "percentage": 21.91, "elapsed_time": "12:34:36", "remaining_time": "1 day, 20:49:26"}
|