penfever commited on
Commit
de7c3f3
·
verified ·
1 Parent(s): ef577a9

Training in progress, step 3200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b6e05e1f5dfdffe008574a2332a84c8985f386b34a1e6155155aaf2ed610205
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06bdbb4bdde9a7c9c13e2d2faad6eec6f3b84da845f4ed3b8e68c2ea7127cd5
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:c2da7e8a6e9cef01ed0577dd39f1704365e3019abc6821d28a5d5247cebdfcfa
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6a21371bf4118ae91ecd6c1bf537cefb9ede5c088aa2d7c469707e123e6d69
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cc20ccbda2fb63b1840d0f08a59e818f1c96616345a23352fbd6306ae8aebf5
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba08d449e116e0c7969e16938839268d8a51b13a1f0f9c201d194733a4da8fe
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:111f18077843ea7c9758b195cbf45b408fab927d2b85a029b90ff558a84e3e72
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475a6a3e4e280e9060d99cb88190d3ebabba2e1a7984671892adb4cde8fc5aee
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -598,3 +598,45 @@
598
  {"current_steps": 2990, "total_steps": 3850, "loss": 0.2182, "lr": 5.790708434692627e-06, "epoch": 5.436760691537762, "percentage": 77.66, "elapsed_time": "19:59:14", "remaining_time": "5:44:56"}
599
  {"current_steps": 2995, "total_steps": 3850, "loss": 0.1952, "lr": 5.727049687904076e-06, "epoch": 5.445859872611465, "percentage": 77.79, "elapsed_time": "20:01:15", "remaining_time": "5:42:55"}
600
  {"current_steps": 3000, "total_steps": 3850, "loss": 0.1847, "lr": 5.66368426422909e-06, "epoch": 5.454959053685168, "percentage": 77.92, "elapsed_time": "20:03:20", "remaining_time": "5:40:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
598
  {"current_steps": 2990, "total_steps": 3850, "loss": 0.2182, "lr": 5.790708434692627e-06, "epoch": 5.436760691537762, "percentage": 77.66, "elapsed_time": "19:59:14", "remaining_time": "5:44:56"}
599
  {"current_steps": 2995, "total_steps": 3850, "loss": 0.1952, "lr": 5.727049687904076e-06, "epoch": 5.445859872611465, "percentage": 77.79, "elapsed_time": "20:01:15", "remaining_time": "5:42:55"}
600
  {"current_steps": 3000, "total_steps": 3850, "loss": 0.1847, "lr": 5.66368426422909e-06, "epoch": 5.454959053685168, "percentage": 77.92, "elapsed_time": "20:03:20", "remaining_time": "5:40:56"}
601
+ {"current_steps": 3005, "total_steps": 3850, "loss": 0.1837, "lr": 5.60061346588922e-06, "epoch": 5.4640582347588715, "percentage": 78.05, "elapsed_time": "20:06:55", "remaining_time": "5:39:22"}
602
+ {"current_steps": 3010, "total_steps": 3850, "loss": 0.1961, "lr": 5.537838589051155e-06, "epoch": 5.473157415832575, "percentage": 78.18, "elapsed_time": "20:08:54", "remaining_time": "5:37:22"}
603
+ {"current_steps": 3015, "total_steps": 3850, "loss": 0.2027, "lr": 5.475360923800141e-06, "epoch": 5.482256596906279, "percentage": 78.31, "elapsed_time": "20:10:49", "remaining_time": "5:35:20"}
604
+ {"current_steps": 3020, "total_steps": 3850, "loss": 0.1934, "lr": 5.413181754113392e-06, "epoch": 5.491355777979982, "percentage": 78.44, "elapsed_time": "20:12:54", "remaining_time": "5:33:20"}
605
+ {"current_steps": 3025, "total_steps": 3850, "loss": 0.2038, "lr": 5.351302357833785e-06, "epoch": 5.500454959053685, "percentage": 78.57, "elapsed_time": "20:14:40", "remaining_time": "5:31:16"}
606
+ {"current_steps": 3030, "total_steps": 3850, "loss": 0.1845, "lr": 5.289724006643529e-06, "epoch": 5.509554140127388, "percentage": 78.7, "elapsed_time": "20:16:50", "remaining_time": "5:29:18"}
607
+ {"current_steps": 3035, "total_steps": 3850, "loss": 0.1991, "lr": 5.2284479660380906e-06, "epoch": 5.518653321201092, "percentage": 78.83, "elapsed_time": "20:18:45", "remaining_time": "5:27:16"}
608
+ {"current_steps": 3040, "total_steps": 3850, "loss": 0.1872, "lr": 5.167475495300134e-06, "epoch": 5.5277525022747955, "percentage": 78.96, "elapsed_time": "20:20:45", "remaining_time": "5:25:16"}
609
+ {"current_steps": 3045, "total_steps": 3850, "loss": 0.1934, "lr": 5.1068078474736695e-06, "epoch": 5.536851683348498, "percentage": 79.09, "elapsed_time": "20:22:38", "remaining_time": "5:23:13"}
610
+ {"current_steps": 3050, "total_steps": 3850, "loss": 0.1881, "lr": 5.046446269338314e-06, "epoch": 5.545950864422202, "percentage": 79.22, "elapsed_time": "20:24:47", "remaining_time": "5:21:15"}
611
+ {"current_steps": 3055, "total_steps": 3850, "loss": 0.2015, "lr": 4.986392001383633e-06, "epoch": 5.555050045495905, "percentage": 79.35, "elapsed_time": "20:26:43", "remaining_time": "5:19:13"}
612
+ {"current_steps": 3060, "total_steps": 3850, "loss": 0.2002, "lr": 4.926646277783675e-06, "epoch": 5.564149226569609, "percentage": 79.48, "elapsed_time": "20:28:43", "remaining_time": "5:17:13"}
613
+ {"current_steps": 3065, "total_steps": 3850, "loss": 0.1987, "lr": 4.867210326371596e-06, "epoch": 5.573248407643312, "percentage": 79.61, "elapsed_time": "20:30:37", "remaining_time": "5:15:11"}
614
+ {"current_steps": 3070, "total_steps": 3850, "loss": 0.1917, "lr": 4.808085368614441e-06, "epoch": 5.582347588717015, "percentage": 79.74, "elapsed_time": "20:32:55", "remaining_time": "5:13:14"}
615
+ {"current_steps": 3075, "total_steps": 3850, "loss": 0.1853, "lr": 4.74927261958801e-06, "epoch": 5.591446769790719, "percentage": 79.87, "elapsed_time": "20:35:01", "remaining_time": "5:11:15"}
616
+ {"current_steps": 3080, "total_steps": 3850, "loss": 0.1875, "lr": 4.690773287951942e-06, "epoch": 5.600545950864422, "percentage": 80.0, "elapsed_time": "20:37:11", "remaining_time": "5:09:17"}
617
+ {"current_steps": 3085, "total_steps": 3850, "loss": 0.1929, "lr": 4.632588575924795e-06, "epoch": 5.609645131938126, "percentage": 80.13, "elapsed_time": "20:38:54", "remaining_time": "5:07:13"}
618
+ {"current_steps": 3090, "total_steps": 3850, "loss": 0.1948, "lr": 4.574719679259425e-06, "epoch": 5.618744313011829, "percentage": 80.26, "elapsed_time": "20:40:41", "remaining_time": "5:05:09"}
619
+ {"current_steps": 3095, "total_steps": 3850, "loss": 0.182, "lr": 4.5171677872183506e-06, "epoch": 5.627843494085532, "percentage": 80.39, "elapsed_time": "20:42:41", "remaining_time": "5:03:08"}
620
+ {"current_steps": 3100, "total_steps": 3850, "loss": 0.1807, "lr": 4.459934082549353e-06, "epoch": 5.6369426751592355, "percentage": 80.52, "elapsed_time": "20:44:38", "remaining_time": "5:01:07"}
621
+ {"current_steps": 3105, "total_steps": 3850, "loss": 0.1861, "lr": 4.4030197414611344e-06, "epoch": 5.646041856232939, "percentage": 80.65, "elapsed_time": "20:46:41", "remaining_time": "4:59:07"}
622
+ {"current_steps": 3110, "total_steps": 3850, "loss": 0.1932, "lr": 4.346425933599165e-06, "epoch": 5.655141037306643, "percentage": 80.78, "elapsed_time": "20:48:48", "remaining_time": "4:57:08"}
623
+ {"current_steps": 3115, "total_steps": 3850, "loss": 0.1861, "lr": 4.2901538220216565e-06, "epoch": 5.664240218380346, "percentage": 80.91, "elapsed_time": "20:50:43", "remaining_time": "4:55:06"}
624
+ {"current_steps": 3120, "total_steps": 3850, "loss": 0.1964, "lr": 4.234204563175625e-06, "epoch": 5.673339399454049, "percentage": 81.04, "elapsed_time": "20:52:35", "remaining_time": "4:53:04"}
625
+ {"current_steps": 3125, "total_steps": 3850, "loss": 0.1922, "lr": 4.17857930687318e-06, "epoch": 5.682438580527752, "percentage": 81.17, "elapsed_time": "20:54:35", "remaining_time": "4:51:03"}
626
+ {"current_steps": 3130, "total_steps": 3850, "loss": 0.1961, "lr": 4.123279196267815e-06, "epoch": 5.691537761601456, "percentage": 81.3, "elapsed_time": "20:56:30", "remaining_time": "4:49:02"}
627
+ {"current_steps": 3135, "total_steps": 3850, "loss": 0.199, "lr": 4.068305367831002e-06, "epoch": 5.7006369426751595, "percentage": 81.43, "elapsed_time": "20:58:48", "remaining_time": "4:47:05"}
628
+ {"current_steps": 3140, "total_steps": 3850, "loss": 0.1804, "lr": 4.013658951328769e-06, "epoch": 5.709736123748863, "percentage": 81.56, "elapsed_time": "21:00:53", "remaining_time": "4:45:06"}
629
+ {"current_steps": 3145, "total_steps": 3850, "loss": 0.1995, "lr": 3.95934106979853e-06, "epoch": 5.718835304822566, "percentage": 81.69, "elapsed_time": "21:02:54", "remaining_time": "4:43:06"}
630
+ {"current_steps": 3150, "total_steps": 3850, "loss": 0.1822, "lr": 3.905352839525962e-06, "epoch": 5.727934485896269, "percentage": 81.82, "elapsed_time": "21:05:13", "remaining_time": "4:41:09"}
631
+ {"current_steps": 3155, "total_steps": 3850, "loss": 0.2048, "lr": 3.851695370022093e-06, "epoch": 5.737033666969973, "percentage": 81.95, "elapsed_time": "21:07:22", "remaining_time": "4:39:11"}
632
+ {"current_steps": 3160, "total_steps": 3850, "loss": 0.1789, "lr": 3.7983697640005048e-06, "epoch": 5.746132848043676, "percentage": 82.08, "elapsed_time": "21:09:36", "remaining_time": "4:37:13"}
633
+ {"current_steps": 3165, "total_steps": 3850, "loss": 0.1868, "lr": 3.7453771173546426e-06, "epoch": 5.755232029117379, "percentage": 82.21, "elapsed_time": "21:11:32", "remaining_time": "4:35:12"}
634
+ {"current_steps": 3170, "total_steps": 3850, "loss": 0.1889, "lr": 3.6927185191353188e-06, "epoch": 5.764331210191083, "percentage": 82.34, "elapsed_time": "21:13:39", "remaining_time": "4:33:12"}
635
+ {"current_steps": 3175, "total_steps": 3850, "loss": 0.1992, "lr": 3.640395051528316e-06, "epoch": 5.773430391264786, "percentage": 82.47, "elapsed_time": "21:15:33", "remaining_time": "4:31:10"}
636
+ {"current_steps": 3180, "total_steps": 3850, "loss": 0.1808, "lr": 3.5884077898321713e-06, "epoch": 5.78252957233849, "percentage": 82.6, "elapsed_time": "21:17:27", "remaining_time": "4:29:09"}
637
+ {"current_steps": 3185, "total_steps": 3850, "loss": 0.1711, "lr": 3.536757802436039e-06, "epoch": 5.791628753412192, "percentage": 82.73, "elapsed_time": "21:19:26", "remaining_time": "4:27:08"}
638
+ {"current_steps": 3190, "total_steps": 3850, "loss": 0.1922, "lr": 3.4854461507977776e-06, "epoch": 5.800727934485896, "percentage": 82.86, "elapsed_time": "21:21:24", "remaining_time": "4:25:07"}
639
+ {"current_steps": 3195, "total_steps": 3850, "loss": 0.1927, "lr": 3.4344738894220964e-06, "epoch": 5.8098271155595995, "percentage": 82.99, "elapsed_time": "21:23:21", "remaining_time": "4:23:05"}
640
+ {"current_steps": 3200, "total_steps": 3850, "loss": 0.1952, "lr": 3.383842065838907e-06, "epoch": 5.818926296633303, "percentage": 83.12, "elapsed_time": "21:25:18", "remaining_time": "4:21:04"}
641
+ {"current_steps": 3205, "total_steps": 3850, "loss": 0.1918, "lr": 3.3335517205818e-06, "epoch": 5.828025477707007, "percentage": 83.25, "elapsed_time": "21:28:35", "remaining_time": "4:19:19"}
642
+ {"current_steps": 3210, "total_steps": 3850, "loss": 0.1941, "lr": 3.2836038871666444e-06, "epoch": 5.837124658780709, "percentage": 83.38, "elapsed_time": "21:30:28", "remaining_time": "4:17:17"}