penfever commited on
Commit
8004c82
·
verified ·
1 Parent(s): e3d5e5c

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 sha256:465492e897435008fe9d946d7fcb6be162a81d81383c9fd66d227a5fc291b4c7
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc66186266aa89ff9395f976b698fd37a05f691841d529eef93845d7cf9e07f
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:df41219bbbd77ec6fda385ba95dbdb45909908ffe889785c7f0288e88ef5efe4
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8465dfb22a9267bf14b5ddce04f85e089de9272c50cfd9ff796533b262c628
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17e2e0982439b8b107949011c89bbdfbd087b64571a84b15fc04f9edac0ae674
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b296109c52862b2ab98f94007d41894971e958ab278fa8b281c09ab92edbe964
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0630173216a7bff51202d16b6690c6a99653e86e1ecda54594d411076fbcd3d5
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dafbfaacd54db2d4d28d91ff95d4577c47cf6cff5df510d121fdf55d30627bd
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -359,3 +359,42 @@
359
  {"current_steps": 1795, "total_steps": 3850, "loss": 0.2297, "lr": 2.5782371850423627e-05, "epoch": 3.2638762511373978, "percentage": 46.62, "elapsed_time": "12:00:10", "remaining_time": "13:44:29"}
360
  {"current_steps": 1800, "total_steps": 3850, "loss": 0.2287, "lr": 2.5695518342513047e-05, "epoch": 3.272975432211101, "percentage": 46.75, "elapsed_time": "12:02:08", "remaining_time": "13:42:26"}
361
  {"current_steps": 1805, "total_steps": 3850, "loss": 0.235, "lr": 2.5608547786120056e-05, "epoch": 3.2820746132848044, "percentage": 46.88, "elapsed_time": "12:05:11", "remaining_time": "13:41:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
359
  {"current_steps": 1795, "total_steps": 3850, "loss": 0.2297, "lr": 2.5782371850423627e-05, "epoch": 3.2638762511373978, "percentage": 46.62, "elapsed_time": "12:00:10", "remaining_time": "13:44:29"}
360
  {"current_steps": 1800, "total_steps": 3850, "loss": 0.2287, "lr": 2.5695518342513047e-05, "epoch": 3.272975432211101, "percentage": 46.75, "elapsed_time": "12:02:08", "remaining_time": "13:42:26"}
361
  {"current_steps": 1805, "total_steps": 3850, "loss": 0.235, "lr": 2.5608547786120056e-05, "epoch": 3.2820746132848044, "percentage": 46.88, "elapsed_time": "12:05:11", "remaining_time": "13:41:36"}
362
+ {"current_steps": 1810, "total_steps": 3850, "loss": 0.2385, "lr": 2.55214619685748e-05, "epoch": 3.2911737943585075, "percentage": 47.01, "elapsed_time": "12:07:17", "remaining_time": "13:39:42"}
363
+ {"current_steps": 1815, "total_steps": 3850, "loss": 0.226, "lr": 2.5434262679576157e-05, "epoch": 3.300272975432211, "percentage": 47.14, "elapsed_time": "12:09:17", "remaining_time": "13:37:41"}
364
+ {"current_steps": 1820, "total_steps": 3850, "loss": 0.2506, "lr": 2.5346951711154946e-05, "epoch": 3.3093721565059147, "percentage": 47.27, "elapsed_time": "12:11:16", "remaining_time": "13:35:38"}
365
+ {"current_steps": 1825, "total_steps": 3850, "loss": 0.2351, "lr": 2.5259530857637125e-05, "epoch": 3.3184713375796178, "percentage": 47.4, "elapsed_time": "12:13:05", "remaining_time": "13:33:26"}
366
+ {"current_steps": 1830, "total_steps": 3850, "loss": 0.2305, "lr": 2.5172001915606883e-05, "epoch": 3.3275705186533213, "percentage": 47.53, "elapsed_time": "12:14:59", "remaining_time": "13:31:18"}
367
+ {"current_steps": 1835, "total_steps": 3850, "loss": 0.2321, "lr": 2.5084366683869746e-05, "epoch": 3.3366696997270244, "percentage": 47.66, "elapsed_time": "12:16:53", "remaining_time": "13:29:10"}
368
+ {"current_steps": 1840, "total_steps": 3850, "loss": 0.2267, "lr": 2.4996626963415577e-05, "epoch": 3.345768880800728, "percentage": 47.79, "elapsed_time": "12:18:49", "remaining_time": "13:27:04"}
369
+ {"current_steps": 1845, "total_steps": 3850, "loss": 0.2341, "lr": 2.4908784557381616e-05, "epoch": 3.3548680618744315, "percentage": 47.92, "elapsed_time": "12:21:11", "remaining_time": "13:25:28"}
370
+ {"current_steps": 1850, "total_steps": 3850, "loss": 0.2301, "lr": 2.4820841271015364e-05, "epoch": 3.3639672429481347, "percentage": 48.05, "elapsed_time": "12:23:20", "remaining_time": "13:23:36"}
371
+ {"current_steps": 1855, "total_steps": 3850, "loss": 0.2271, "lr": 2.4732798911637525e-05, "epoch": 3.373066424021838, "percentage": 48.18, "elapsed_time": "12:25:18", "remaining_time": "13:21:33"}
372
+ {"current_steps": 1860, "total_steps": 3850, "loss": 0.2433, "lr": 2.4644659288604853e-05, "epoch": 3.3821656050955413, "percentage": 48.31, "elapsed_time": "12:27:00", "remaining_time": "13:19:13"}
373
+ {"current_steps": 1865, "total_steps": 3850, "loss": 0.2149, "lr": 2.4556424213272955e-05, "epoch": 3.391264786169245, "percentage": 48.44, "elapsed_time": "12:28:56", "remaining_time": "13:17:07"}
374
+ {"current_steps": 1870, "total_steps": 3850, "loss": 0.2248, "lr": 2.4468095498959086e-05, "epoch": 3.400363967242948, "percentage": 48.57, "elapsed_time": "12:30:52", "remaining_time": "13:15:02"}
375
+ {"current_steps": 1875, "total_steps": 3850, "loss": 0.2412, "lr": 2.4379674960904867e-05, "epoch": 3.4094631483166515, "percentage": 48.7, "elapsed_time": "12:32:53", "remaining_time": "13:13:02"}
376
+ {"current_steps": 1880, "total_steps": 3850, "loss": 0.2342, "lr": 2.4291164416238994e-05, "epoch": 3.4185623293903546, "percentage": 48.83, "elapsed_time": "12:34:46", "remaining_time": "13:10:54"}
377
+ {"current_steps": 1885, "total_steps": 3850, "loss": 0.2423, "lr": 2.4202565683939872e-05, "epoch": 3.427661510464058, "percentage": 48.96, "elapsed_time": "12:36:37", "remaining_time": "13:08:44"}
378
+ {"current_steps": 1890, "total_steps": 3850, "loss": 0.2253, "lr": 2.411388058479827e-05, "epoch": 3.4367606915377618, "percentage": 49.09, "elapsed_time": "12:38:38", "remaining_time": "13:06:43"}
379
+ {"current_steps": 1895, "total_steps": 3850, "loss": 0.2139, "lr": 2.402511094137987e-05, "epoch": 3.445859872611465, "percentage": 49.22, "elapsed_time": "12:40:53", "remaining_time": "13:04:58"}
380
+ {"current_steps": 1900, "total_steps": 3850, "loss": 0.2317, "lr": 2.3936258577987807e-05, "epoch": 3.4549590536851684, "percentage": 49.35, "elapsed_time": "12:42:52", "remaining_time": "13:02:57"}
381
+ {"current_steps": 1905, "total_steps": 3850, "loss": 0.2384, "lr": 2.3847325320625223e-05, "epoch": 3.4640582347588715, "percentage": 49.48, "elapsed_time": "12:44:47", "remaining_time": "13:00:51"}
382
+ {"current_steps": 1910, "total_steps": 3850, "loss": 0.231, "lr": 2.3758312996957676e-05, "epoch": 3.473157415832575, "percentage": 49.61, "elapsed_time": "12:46:52", "remaining_time": "12:58:55"}
383
+ {"current_steps": 1915, "total_steps": 3850, "loss": 0.2201, "lr": 2.366922343627565e-05, "epoch": 3.4822565969062786, "percentage": 49.74, "elapsed_time": "12:48:57", "remaining_time": "12:56:58"}
384
+ {"current_steps": 1920, "total_steps": 3850, "loss": 0.2336, "lr": 2.358005846945689e-05, "epoch": 3.4913557779799818, "percentage": 49.87, "elapsed_time": "12:51:01", "remaining_time": "12:55:02"}
385
+ {"current_steps": 1925, "total_steps": 3850, "loss": 0.2365, "lr": 2.349081992892885e-05, "epoch": 3.5004549590536853, "percentage": 50.0, "elapsed_time": "12:52:59", "remaining_time": "12:52:59"}
386
+ {"current_steps": 1930, "total_steps": 3850, "loss": 0.2385, "lr": 2.3401509648630954e-05, "epoch": 3.5095541401273884, "percentage": 50.13, "elapsed_time": "12:54:56", "remaining_time": "12:50:55"}
387
+ {"current_steps": 1935, "total_steps": 3850, "loss": 0.2434, "lr": 2.331212946397698e-05, "epoch": 3.518653321201092, "percentage": 50.26, "elapsed_time": "12:57:00", "remaining_time": "12:48:58"}
388
+ {"current_steps": 1940, "total_steps": 3850, "loss": 0.2386, "lr": 2.3222681211817287e-05, "epoch": 3.5277525022747955, "percentage": 50.39, "elapsed_time": "12:58:42", "remaining_time": "12:46:40"}
389
+ {"current_steps": 1945, "total_steps": 3850, "loss": 0.2433, "lr": 2.31331667304011e-05, "epoch": 3.5368516833484986, "percentage": 50.52, "elapsed_time": "13:00:48", "remaining_time": "12:44:44"}
390
+ {"current_steps": 1950, "total_steps": 3850, "loss": 0.2238, "lr": 2.3043587859338735e-05, "epoch": 3.5459508644222018, "percentage": 50.65, "elapsed_time": "13:02:34", "remaining_time": "12:42:30"}
391
+ {"current_steps": 1955, "total_steps": 3850, "loss": 0.2392, "lr": 2.2953946439563736e-05, "epoch": 3.5550500454959053, "percentage": 50.78, "elapsed_time": "13:04:25", "remaining_time": "12:40:21"}
392
+ {"current_steps": 1960, "total_steps": 3850, "loss": 0.2445, "lr": 2.286424431329513e-05, "epoch": 3.564149226569609, "percentage": 50.91, "elapsed_time": "13:06:39", "remaining_time": "12:38:34"}
393
+ {"current_steps": 1965, "total_steps": 3850, "loss": 0.2228, "lr": 2.277448332399949e-05, "epoch": 3.573248407643312, "percentage": 51.04, "elapsed_time": "13:08:31", "remaining_time": "12:36:25"}
394
+ {"current_steps": 1970, "total_steps": 3850, "loss": 0.2414, "lr": 2.2684665316353112e-05, "epoch": 3.5823475887170155, "percentage": 51.17, "elapsed_time": "13:10:23", "remaining_time": "12:34:17"}
395
+ {"current_steps": 1975, "total_steps": 3850, "loss": 0.2388, "lr": 2.2594792136204037e-05, "epoch": 3.5914467697907186, "percentage": 51.3, "elapsed_time": "13:12:16", "remaining_time": "12:32:09"}
396
+ {"current_steps": 1980, "total_steps": 3850, "loss": 0.2411, "lr": 2.250486563053419e-05, "epoch": 3.600545950864422, "percentage": 51.43, "elapsed_time": "13:14:14", "remaining_time": "12:30:06"}
397
+ {"current_steps": 1985, "total_steps": 3850, "loss": 0.242, "lr": 2.241488764742135e-05, "epoch": 3.6096451319381258, "percentage": 51.56, "elapsed_time": "13:16:22", "remaining_time": "12:28:13"}
398
+ {"current_steps": 1990, "total_steps": 3850, "loss": 0.2209, "lr": 2.232486003600126e-05, "epoch": 3.618744313011829, "percentage": 51.69, "elapsed_time": "13:18:19", "remaining_time": "12:26:10"}
399
+ {"current_steps": 1995, "total_steps": 3850, "loss": 0.2267, "lr": 2.223478464642952e-05, "epoch": 3.6278434940855324, "percentage": 51.82, "elapsed_time": "13:20:27", "remaining_time": "12:24:16"}
400
+ {"current_steps": 2000, "total_steps": 3850, "loss": 0.2339, "lr": 2.2144663329843653e-05, "epoch": 3.6369426751592355, "percentage": 51.95, "elapsed_time": "13:22:21", "remaining_time": "12:22:10"}