penfever commited on
Commit
882ae4c
·
verified ·
1 Parent(s): 87343be

Training in progress, step 4200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bab24cbb9d9eae73b2043d933f52fdf69e9526f9d1c9fdfcaa92bb3dbe1eeb5c
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f982df45c06070469defab9f2a3abfdd4874309948e74ef6f77789dd57434aae
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:eece067c9959f6276ac74033b3f84d652ff32cfc63aa3f02808846d3de862065
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b48e1289fa2642f50b4da37e66914d4829783e22e72896a47c327c1bf680119
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:d04b81701e6825dc891ac4786b5da8fb4277a96b8d524a66024edb7973bbcebe
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaff26d1e2298fa0422e02899648a7273ed274a760324e495e09d329aa1de86
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6578e9d4320da95fcc152a9bd9b052a769558d9c2b86c072ecf659f01a28281c
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f88c132ee7988b5cb85733ab01092aeed682ea1175f35c57efe6ecde177b0a1
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -821,3 +821,43 @@
821
  {"current_steps": 3990, "total_steps": 6713, "loss": 0.1621, "lr": 1.6928337970906406e-05, "epoch": 4.161711006781429, "percentage": 59.44, "elapsed_time": "7:32:20", "remaining_time": "5:08:42"}
822
  {"current_steps": 3995, "total_steps": 6713, "loss": 0.1723, "lr": 1.687696089476585e-05, "epoch": 4.166927490871153, "percentage": 59.51, "elapsed_time": "7:35:25", "remaining_time": "5:09:51"}
823
  {"current_steps": 4000, "total_steps": 6713, "loss": 0.1664, "lr": 1.6825604934022734e-05, "epoch": 4.172143974960877, "percentage": 59.59, "elapsed_time": "7:38:27", "remaining_time": "5:10:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
821
  {"current_steps": 3990, "total_steps": 6713, "loss": 0.1621, "lr": 1.6928337970906406e-05, "epoch": 4.161711006781429, "percentage": 59.44, "elapsed_time": "7:32:20", "remaining_time": "5:08:42"}
822
  {"current_steps": 3995, "total_steps": 6713, "loss": 0.1723, "lr": 1.687696089476585e-05, "epoch": 4.166927490871153, "percentage": 59.51, "elapsed_time": "7:35:25", "remaining_time": "5:09:51"}
823
  {"current_steps": 4000, "total_steps": 6713, "loss": 0.1664, "lr": 1.6825604934022734e-05, "epoch": 4.172143974960877, "percentage": 59.59, "elapsed_time": "7:38:27", "remaining_time": "5:10:56"}
824
+ {"current_steps": 4005, "total_steps": 6713, "loss": 0.1565, "lr": 1.6774270435903423e-05, "epoch": 4.1773604590505995, "percentage": 59.66, "elapsed_time": "7:42:37", "remaining_time": "5:12:48"}
825
+ {"current_steps": 4010, "total_steps": 6713, "loss": 0.1424, "lr": 1.6722957747489172e-05, "epoch": 4.182576943140323, "percentage": 59.73, "elapsed_time": "7:45:44", "remaining_time": "5:13:56"}
826
+ {"current_steps": 4015, "total_steps": 6713, "loss": 0.1672, "lr": 1.6671667215713784e-05, "epoch": 4.187793427230047, "percentage": 59.81, "elapsed_time": "7:48:48", "remaining_time": "5:15:01"}
827
+ {"current_steps": 4020, "total_steps": 6713, "loss": 0.1685, "lr": 1.6620399187361226e-05, "epoch": 4.193009911319771, "percentage": 59.88, "elapsed_time": "7:51:47", "remaining_time": "5:16:03"}
828
+ {"current_steps": 4025, "total_steps": 6713, "loss": 0.1653, "lr": 1.656915400906336e-05, "epoch": 4.198226395409494, "percentage": 59.96, "elapsed_time": "7:54:43", "remaining_time": "5:17:02"}
829
+ {"current_steps": 4030, "total_steps": 6713, "loss": 0.1582, "lr": 1.6517932027297525e-05, "epoch": 4.203442879499217, "percentage": 60.03, "elapsed_time": "7:57:26", "remaining_time": "5:17:51"}
830
+ {"current_steps": 4035, "total_steps": 6713, "loss": 0.1506, "lr": 1.6466733588384233e-05, "epoch": 4.208659363588941, "percentage": 60.11, "elapsed_time": "8:00:23", "remaining_time": "5:18:50"}
831
+ {"current_steps": 4040, "total_steps": 6713, "loss": 0.1635, "lr": 1.6415559038484827e-05, "epoch": 4.213875847678665, "percentage": 60.18, "elapsed_time": "8:03:20", "remaining_time": "5:19:47"}
832
+ {"current_steps": 4045, "total_steps": 6713, "loss": 0.1666, "lr": 1.6364408723599116e-05, "epoch": 4.219092331768388, "percentage": 60.26, "elapsed_time": "8:06:09", "remaining_time": "5:20:39"}
833
+ {"current_steps": 4050, "total_steps": 6713, "loss": 0.1566, "lr": 1.6313282989563062e-05, "epoch": 4.2243088158581115, "percentage": 60.33, "elapsed_time": "8:08:59", "remaining_time": "5:21:31"}
834
+ {"current_steps": 4055, "total_steps": 6713, "loss": 0.1664, "lr": 1.626218218204643e-05, "epoch": 4.229525299947835, "percentage": 60.41, "elapsed_time": "8:11:51", "remaining_time": "5:22:24"}
835
+ {"current_steps": 4060, "total_steps": 6713, "loss": 0.1605, "lr": 1.6211106646550455e-05, "epoch": 4.234741784037559, "percentage": 60.48, "elapsed_time": "8:14:38", "remaining_time": "5:23:13"}
836
+ {"current_steps": 4065, "total_steps": 6713, "loss": 0.1373, "lr": 1.616005672840551e-05, "epoch": 4.239958268127282, "percentage": 60.55, "elapsed_time": "8:17:38", "remaining_time": "5:24:10"}
837
+ {"current_steps": 4070, "total_steps": 6713, "loss": 0.1414, "lr": 1.6109032772768736e-05, "epoch": 4.245174752217006, "percentage": 60.63, "elapsed_time": "8:20:42", "remaining_time": "5:25:08"}
838
+ {"current_steps": 4075, "total_steps": 6713, "loss": 0.1466, "lr": 1.6058035124621766e-05, "epoch": 4.250391236306729, "percentage": 60.7, "elapsed_time": "8:23:46", "remaining_time": "5:26:07"}
839
+ {"current_steps": 4080, "total_steps": 6713, "loss": 0.1578, "lr": 1.6007064128768354e-05, "epoch": 4.255607720396453, "percentage": 60.78, "elapsed_time": "8:26:43", "remaining_time": "5:27:00"}
840
+ {"current_steps": 4085, "total_steps": 6713, "loss": 0.1801, "lr": 1.5956120129832054e-05, "epoch": 4.260824204486176, "percentage": 60.85, "elapsed_time": "8:29:33", "remaining_time": "5:27:49"}
841
+ {"current_steps": 4090, "total_steps": 6713, "loss": 0.1877, "lr": 1.5905203472253892e-05, "epoch": 4.2660406885759, "percentage": 60.93, "elapsed_time": "8:32:20", "remaining_time": "5:28:34"}
842
+ {"current_steps": 4095, "total_steps": 6713, "loss": 0.1538, "lr": 1.5854314500290025e-05, "epoch": 4.271257172665623, "percentage": 61.0, "elapsed_time": "8:35:17", "remaining_time": "5:29:25"}
843
+ {"current_steps": 4100, "total_steps": 6713, "loss": 0.1621, "lr": 1.580345355800944e-05, "epoch": 4.276473656755347, "percentage": 61.08, "elapsed_time": "8:38:19", "remaining_time": "5:30:20"}
844
+ {"current_steps": 4105, "total_steps": 6713, "loss": 0.1648, "lr": 1.5752620989291592e-05, "epoch": 4.28169014084507, "percentage": 61.15, "elapsed_time": "8:41:23", "remaining_time": "5:31:15"}
845
+ {"current_steps": 4110, "total_steps": 6713, "loss": 0.1747, "lr": 1.5701817137824108e-05, "epoch": 4.286906624934794, "percentage": 61.22, "elapsed_time": "8:44:30", "remaining_time": "5:32:11"}
846
+ {"current_steps": 4115, "total_steps": 6713, "loss": 0.1588, "lr": 1.5651042347100452e-05, "epoch": 4.2921231090245175, "percentage": 61.3, "elapsed_time": "8:47:36", "remaining_time": "5:33:05"}
847
+ {"current_steps": 4120, "total_steps": 6713, "loss": 0.1659, "lr": 1.5600296960417597e-05, "epoch": 4.297339593114241, "percentage": 61.37, "elapsed_time": "8:50:37", "remaining_time": "5:33:57"}
848
+ {"current_steps": 4125, "total_steps": 6713, "loss": 0.1623, "lr": 1.5549581320873715e-05, "epoch": 4.302556077203964, "percentage": 61.45, "elapsed_time": "8:53:39", "remaining_time": "5:34:48"}
849
+ {"current_steps": 4130, "total_steps": 6713, "loss": 0.1474, "lr": 1.549889577136586e-05, "epoch": 4.307772561293688, "percentage": 61.52, "elapsed_time": "8:56:40", "remaining_time": "5:35:38"}
850
+ {"current_steps": 4135, "total_steps": 6713, "loss": 0.1572, "lr": 1.5448240654587622e-05, "epoch": 4.312989045383412, "percentage": 61.6, "elapsed_time": "8:59:45", "remaining_time": "5:36:30"}
851
+ {"current_steps": 4140, "total_steps": 6713, "loss": 0.2034, "lr": 1.5397616313026853e-05, "epoch": 4.318205529473135, "percentage": 61.67, "elapsed_time": "9:02:49", "remaining_time": "5:37:21"}
852
+ {"current_steps": 4145, "total_steps": 6713, "loss": 0.1507, "lr": 1.5347023088963315e-05, "epoch": 4.323422013562858, "percentage": 61.75, "elapsed_time": "9:05:54", "remaining_time": "5:38:12"}
853
+ {"current_steps": 4150, "total_steps": 6713, "loss": 0.1633, "lr": 1.5296461324466384e-05, "epoch": 4.328638497652582, "percentage": 61.82, "elapsed_time": "9:08:48", "remaining_time": "5:38:56"}
854
+ {"current_steps": 4155, "total_steps": 6713, "loss": 0.1684, "lr": 1.5245931361392727e-05, "epoch": 4.333854981742306, "percentage": 61.89, "elapsed_time": "9:11:52", "remaining_time": "5:39:45"}
855
+ {"current_steps": 4160, "total_steps": 6713, "loss": 0.1472, "lr": 1.5195433541384009e-05, "epoch": 4.3390714658320295, "percentage": 61.97, "elapsed_time": "9:14:57", "remaining_time": "5:40:34"}
856
+ {"current_steps": 4165, "total_steps": 6713, "loss": 0.1499, "lr": 1.514496820586456e-05, "epoch": 4.344287949921752, "percentage": 62.04, "elapsed_time": "9:18:00", "remaining_time": "5:41:22"}
857
+ {"current_steps": 4170, "total_steps": 6713, "loss": 0.1404, "lr": 1.5094535696039067e-05, "epoch": 4.349504434011476, "percentage": 62.12, "elapsed_time": "9:21:05", "remaining_time": "5:42:10"}
858
+ {"current_steps": 4175, "total_steps": 6713, "loss": 0.1603, "lr": 1.50441363528903e-05, "epoch": 4.3547209181012, "percentage": 62.19, "elapsed_time": "9:24:06", "remaining_time": "5:42:55"}
859
+ {"current_steps": 4180, "total_steps": 6713, "loss": 0.1497, "lr": 1.4993770517176764e-05, "epoch": 4.359937402190924, "percentage": 62.27, "elapsed_time": "9:27:04", "remaining_time": "5:43:37"}
860
+ {"current_steps": 4185, "total_steps": 6713, "loss": 0.1525, "lr": 1.4943438529430428e-05, "epoch": 4.3651538862806465, "percentage": 62.34, "elapsed_time": "9:30:08", "remaining_time": "5:44:24"}
861
+ {"current_steps": 4190, "total_steps": 6713, "loss": 0.1605, "lr": 1.4893140729954402e-05, "epoch": 4.37037037037037, "percentage": 62.42, "elapsed_time": "9:33:08", "remaining_time": "5:45:07"}
862
+ {"current_steps": 4195, "total_steps": 6713, "loss": 0.1423, "lr": 1.4842877458820644e-05, "epoch": 4.375586854460094, "percentage": 62.49, "elapsed_time": "9:36:13", "remaining_time": "5:45:52"}
863
+ {"current_steps": 4200, "total_steps": 6713, "loss": 0.1617, "lr": 1.4792649055867668e-05, "epoch": 4.380803338549818, "percentage": 62.57, "elapsed_time": "9:39:20", "remaining_time": "5:46:38"}