penfever commited on
Commit
a6edd1c
·
verified ·
1 Parent(s): d72fdb4

Training in progress, step 5000

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be7f3d2f8d384c0d660fbb543a28b9c91984de1ef75d94e8eff5c58d5ef9a06f
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f295043e862bfc43941b52818ed957acadb915a5b77b1f242b5b9cfba576a963
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ba6c4b46758365285f10242153d40e33cecff6b9084525fcd20d7b516774c0a
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f198a7013444abd027674a0fa3316dd45bdecc853249dd43fd90f7126232dd9c
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:f6c6cccc1551ef32e2defb82b76cab7216fa2b319151b61ce14a90679ef16e52
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef60c579a98ae7b1c2a662ae65d7b064e89ae41226043766fdf4ff225913da88
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b6dd8211aec9d23f26329a57bb11423ad8559f5f1ed07201c5c1cea20944f3
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044d403b950c44e6a0e078ffb7217b9a6db825ce1cd485d56c9040b4ad533f93
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -961,3 +961,43 @@
961
  {"current_steps": 4795, "total_steps": 6188, "loss": 0.127, "lr": 5.871832560305573e-06, "epoch": 5.425580079230334, "percentage": 77.49, "elapsed_time": "13:42:20", "remaining_time": "3:58:53"}
962
  {"current_steps": 4800, "total_steps": 6188, "loss": 0.0822, "lr": 5.831960039888533e-06, "epoch": 5.431239388794567, "percentage": 77.57, "elapsed_time": "13:43:57", "remaining_time": "3:58:15"}
963
  {"current_steps": 4805, "total_steps": 6188, "loss": 0.0748, "lr": 5.792200237868361e-06, "epoch": 5.4368986983588, "percentage": 77.65, "elapsed_time": "13:46:48", "remaining_time": "3:57:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
961
  {"current_steps": 4795, "total_steps": 6188, "loss": 0.127, "lr": 5.871832560305573e-06, "epoch": 5.425580079230334, "percentage": 77.49, "elapsed_time": "13:42:20", "remaining_time": "3:58:53"}
962
  {"current_steps": 4800, "total_steps": 6188, "loss": 0.0822, "lr": 5.831960039888533e-06, "epoch": 5.431239388794567, "percentage": 77.57, "elapsed_time": "13:43:57", "remaining_time": "3:58:15"}
963
  {"current_steps": 4805, "total_steps": 6188, "loss": 0.0748, "lr": 5.792200237868361e-06, "epoch": 5.4368986983588, "percentage": 77.65, "elapsed_time": "13:46:48", "remaining_time": "3:57:58"}
964
+ {"current_steps": 4810, "total_steps": 6188, "loss": 0.0804, "lr": 5.752553470566957e-06, "epoch": 5.442558007923034, "percentage": 77.73, "elapsed_time": "13:48:21", "remaining_time": "3:57:18"}
965
+ {"current_steps": 4815, "total_steps": 6188, "loss": 0.0738, "lr": 5.713020053406917e-06, "epoch": 5.448217317487266, "percentage": 77.81, "elapsed_time": "13:49:55", "remaining_time": "3:56:39"}
966
+ {"current_steps": 4820, "total_steps": 6188, "loss": 0.0787, "lr": 5.673600300909053e-06, "epoch": 5.4538766270515, "percentage": 77.89, "elapsed_time": "13:51:39", "remaining_time": "3:56:02"}
967
+ {"current_steps": 4825, "total_steps": 6188, "loss": 0.1177, "lr": 5.634294526689872e-06, "epoch": 5.459535936615733, "percentage": 77.97, "elapsed_time": "13:53:18", "remaining_time": "3:55:24"}
968
+ {"current_steps": 4830, "total_steps": 6188, "loss": 0.0868, "lr": 5.595103043459109e-06, "epoch": 5.465195246179966, "percentage": 78.05, "elapsed_time": "13:54:59", "remaining_time": "3:54:45"}
969
+ {"current_steps": 4835, "total_steps": 6188, "loss": 0.0849, "lr": 5.556026163017205e-06, "epoch": 5.470854555744199, "percentage": 78.14, "elapsed_time": "13:56:32", "remaining_time": "3:54:05"}
970
+ {"current_steps": 4840, "total_steps": 6188, "loss": 0.1077, "lr": 5.517064196252837e-06, "epoch": 5.476513865308433, "percentage": 78.22, "elapsed_time": "13:59:03", "remaining_time": "3:53:41"}
971
+ {"current_steps": 4845, "total_steps": 6188, "loss": 0.0683, "lr": 5.478217453140471e-06, "epoch": 5.482173174872665, "percentage": 78.3, "elapsed_time": "14:00:51", "remaining_time": "3:53:04"}
972
+ {"current_steps": 4850, "total_steps": 6188, "loss": 0.0734, "lr": 5.439486242737855e-06, "epoch": 5.487832484436899, "percentage": 78.38, "elapsed_time": "14:02:43", "remaining_time": "3:52:29"}
973
+ {"current_steps": 4855, "total_steps": 6188, "loss": 0.071, "lr": 5.400870873183583e-06, "epoch": 5.493491794001132, "percentage": 78.46, "elapsed_time": "14:04:32", "remaining_time": "3:51:52"}
974
+ {"current_steps": 4860, "total_steps": 6188, "loss": 0.1167, "lr": 5.362371651694647e-06, "epoch": 5.499151103565365, "percentage": 78.54, "elapsed_time": "14:06:21", "remaining_time": "3:51:16"}
975
+ {"current_steps": 4865, "total_steps": 6188, "loss": 0.0659, "lr": 5.323988884563975e-06, "epoch": 5.504810413129598, "percentage": 78.62, "elapsed_time": "14:07:54", "remaining_time": "3:50:34"}
976
+ {"current_steps": 4870, "total_steps": 6188, "loss": 0.0794, "lr": 5.2857228771580105e-06, "epoch": 5.5104697226938315, "percentage": 78.7, "elapsed_time": "14:09:45", "remaining_time": "3:49:58"}
977
+ {"current_steps": 4875, "total_steps": 6188, "loss": 0.0604, "lr": 5.247573933914285e-06, "epoch": 5.516129032258064, "percentage": 78.78, "elapsed_time": "14:11:17", "remaining_time": "3:49:16"}
978
+ {"current_steps": 4880, "total_steps": 6188, "loss": 0.08, "lr": 5.20954235833898e-06, "epoch": 5.5217883418222975, "percentage": 78.86, "elapsed_time": "14:12:51", "remaining_time": "3:48:35"}
979
+ {"current_steps": 4885, "total_steps": 6188, "loss": 0.0823, "lr": 5.171628453004512e-06, "epoch": 5.527447651386531, "percentage": 78.94, "elapsed_time": "14:14:28", "remaining_time": "3:47:55"}
980
+ {"current_steps": 4890, "total_steps": 6188, "loss": 0.0849, "lr": 5.133832519547155e-06, "epoch": 5.533106960950764, "percentage": 79.02, "elapsed_time": "14:16:14", "remaining_time": "3:47:16"}
981
+ {"current_steps": 4895, "total_steps": 6188, "loss": 0.0832, "lr": 5.096154858664608e-06, "epoch": 5.538766270514997, "percentage": 79.1, "elapsed_time": "14:17:45", "remaining_time": "3:46:34"}
982
+ {"current_steps": 4900, "total_steps": 6188, "loss": 0.121, "lr": 5.058595770113606e-06, "epoch": 5.54442558007923, "percentage": 79.19, "elapsed_time": "14:19:44", "remaining_time": "3:45:59"}
983
+ {"current_steps": 4905, "total_steps": 6188, "loss": 0.07, "lr": 5.0211555527075664e-06, "epoch": 5.550084889643464, "percentage": 79.27, "elapsed_time": "14:21:15", "remaining_time": "3:45:16"}
984
+ {"current_steps": 4910, "total_steps": 6188, "loss": 0.0851, "lr": 4.9838345043141665e-06, "epoch": 5.555744199207696, "percentage": 79.35, "elapsed_time": "14:22:45", "remaining_time": "3:44:33"}
985
+ {"current_steps": 4915, "total_steps": 6188, "loss": 0.0935, "lr": 4.946632921853009e-06, "epoch": 5.56140350877193, "percentage": 79.43, "elapsed_time": "14:24:18", "remaining_time": "3:43:51"}
986
+ {"current_steps": 4920, "total_steps": 6188, "loss": 0.0862, "lr": 4.909551101293238e-06, "epoch": 5.567062818336163, "percentage": 79.51, "elapsed_time": "14:26:16", "remaining_time": "3:43:15"}
987
+ {"current_steps": 4925, "total_steps": 6188, "loss": 0.1131, "lr": 4.872589337651208e-06, "epoch": 5.572722127900396, "percentage": 79.59, "elapsed_time": "14:28:02", "remaining_time": "3:42:36"}
988
+ {"current_steps": 4930, "total_steps": 6188, "loss": 0.2371, "lr": 4.835747924988105e-06, "epoch": 5.578381437464629, "percentage": 79.67, "elapsed_time": "14:30:10", "remaining_time": "3:42:02"}
989
+ {"current_steps": 4935, "total_steps": 6188, "loss": 0.0831, "lr": 4.799027156407632e-06, "epoch": 5.584040747028863, "percentage": 79.75, "elapsed_time": "14:31:59", "remaining_time": "3:41:23"}
990
+ {"current_steps": 4940, "total_steps": 6188, "loss": 0.0857, "lr": 4.7624273240536756e-06, "epoch": 5.589700056593095, "percentage": 79.83, "elapsed_time": "14:33:36", "remaining_time": "3:40:42"}
991
+ {"current_steps": 4945, "total_steps": 6188, "loss": 0.1742, "lr": 4.725948719107965e-06, "epoch": 5.595359366157329, "percentage": 79.91, "elapsed_time": "14:35:49", "remaining_time": "3:40:09"}
992
+ {"current_steps": 4950, "total_steps": 6188, "loss": 0.0666, "lr": 4.6895916317877624e-06, "epoch": 5.601018675721562, "percentage": 79.99, "elapsed_time": "14:37:36", "remaining_time": "3:39:29"}
993
+ {"current_steps": 4955, "total_steps": 6188, "loss": 0.0804, "lr": 4.653356351343577e-06, "epoch": 5.6066779852857955, "percentage": 80.07, "elapsed_time": "14:39:26", "remaining_time": "3:38:50"}
994
+ {"current_steps": 4960, "total_steps": 6188, "loss": 0.0831, "lr": 4.617243166056826e-06, "epoch": 5.612337294850028, "percentage": 80.16, "elapsed_time": "14:41:06", "remaining_time": "3:38:08"}
995
+ {"current_steps": 4965, "total_steps": 6188, "loss": 0.069, "lr": 4.581252363237567e-06, "epoch": 5.6179966044142615, "percentage": 80.24, "elapsed_time": "14:42:52", "remaining_time": "3:37:28"}
996
+ {"current_steps": 4970, "total_steps": 6188, "loss": 0.0679, "lr": 4.545384229222196e-06, "epoch": 5.623655913978495, "percentage": 80.32, "elapsed_time": "14:44:25", "remaining_time": "3:36:44"}
997
+ {"current_steps": 4975, "total_steps": 6188, "loss": 0.0722, "lr": 4.509639049371193e-06, "epoch": 5.6293152235427275, "percentage": 80.4, "elapsed_time": "14:45:54", "remaining_time": "3:36:00"}
998
+ {"current_steps": 4980, "total_steps": 6188, "loss": 0.0668, "lr": 4.474017108066828e-06, "epoch": 5.634974533106961, "percentage": 80.48, "elapsed_time": "14:47:26", "remaining_time": "3:35:16"}
999
+ {"current_steps": 4985, "total_steps": 6188, "loss": 0.1108, "lr": 4.438518688710898e-06, "epoch": 5.640633842671194, "percentage": 80.56, "elapsed_time": "14:49:18", "remaining_time": "3:34:36"}
1000
+ {"current_steps": 4990, "total_steps": 6188, "loss": 0.0626, "lr": 4.403144073722501e-06, "epoch": 5.646293152235427, "percentage": 80.64, "elapsed_time": "14:51:04", "remaining_time": "3:33:55"}
1001
+ {"current_steps": 4995, "total_steps": 6188, "loss": 0.0625, "lr": 4.367893544535757e-06, "epoch": 5.65195246179966, "percentage": 80.72, "elapsed_time": "14:52:40", "remaining_time": "3:33:12"}
1002
+ {"current_steps": 5000, "total_steps": 6188, "loss": 0.0615, "lr": 4.332767381597575e-06, "epoch": 5.657611771363894, "percentage": 80.8, "elapsed_time": "14:54:11", "remaining_time": "3:32:27"}
1003
+ {"current_steps": 5005, "total_steps": 6188, "loss": 0.0647, "lr": 4.297765864365453e-06, "epoch": 5.663271080928126, "percentage": 80.88, "elapsed_time": "14:57:02", "remaining_time": "3:32:01"}