mikhail-panzo
commited on
Commit
•
e3c02bc
1
Parent(s):
e999607
Training in progress, step 5000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f669e1edaf809ee0b127b9819fd1f231d281115cbf44cb10938e4e60a2d53f62
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:943f2614f294b9345e99d0909b80fc9febf29a6705251ef48ff3aef917e58d2e
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab3632b412639e7ce8b5588ff8a7239c0f85ee0022719040327317447154761e
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ae9e871201b5140a75803631a3b447a66295ef984c1c9cd1719a8febdf7390
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -709,6 +709,84 @@
|
|
709 |
"eval_samples_per_second": 24.148,
|
710 |
"eval_steps_per_second": 3.037,
|
711 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
712 |
}
|
713 |
],
|
714 |
"logging_steps": 50,
|
@@ -728,7 +806,7 @@
|
|
728 |
"attributes": {}
|
729 |
}
|
730 |
},
|
731 |
-
"total_flos":
|
732 |
"train_batch_size": 64,
|
733 |
"trial_name": null,
|
734 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.41126948595046997,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5000",
|
4 |
+
"epoch": 217.3913043478261,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
709 |
"eval_samples_per_second": 24.148,
|
710 |
"eval_steps_per_second": 3.037,
|
711 |
"step": 4500
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 197.82608695652175,
|
715 |
+
"grad_norm": 1.1709681749343872,
|
716 |
+
"learning_rate": 5.755000000000001e-06,
|
717 |
+
"loss": 0.4178,
|
718 |
+
"step": 4550
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 200.0,
|
722 |
+
"grad_norm": 3.5350754261016846,
|
723 |
+
"learning_rate": 5.671666666666668e-06,
|
724 |
+
"loss": 0.4211,
|
725 |
+
"step": 4600
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 202.17391304347825,
|
729 |
+
"grad_norm": 2.050933361053467,
|
730 |
+
"learning_rate": 5.588333333333334e-06,
|
731 |
+
"loss": 0.4266,
|
732 |
+
"step": 4650
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 204.34782608695653,
|
736 |
+
"grad_norm": 1.973078966140747,
|
737 |
+
"learning_rate": 5.505000000000001e-06,
|
738 |
+
"loss": 0.4187,
|
739 |
+
"step": 4700
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 206.52173913043478,
|
743 |
+
"grad_norm": 1.4094629287719727,
|
744 |
+
"learning_rate": 5.4216666666666676e-06,
|
745 |
+
"loss": 0.4294,
|
746 |
+
"step": 4750
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 208.69565217391303,
|
750 |
+
"grad_norm": 0.9872909188270569,
|
751 |
+
"learning_rate": 5.3383333333333345e-06,
|
752 |
+
"loss": 0.4239,
|
753 |
+
"step": 4800
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 210.8695652173913,
|
757 |
+
"grad_norm": 1.4357950687408447,
|
758 |
+
"learning_rate": 5.2550000000000005e-06,
|
759 |
+
"loss": 0.4117,
|
760 |
+
"step": 4850
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 213.04347826086956,
|
764 |
+
"grad_norm": 1.4760295152664185,
|
765 |
+
"learning_rate": 5.171666666666667e-06,
|
766 |
+
"loss": 0.4239,
|
767 |
+
"step": 4900
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 215.2173913043478,
|
771 |
+
"grad_norm": 0.9877930879592896,
|
772 |
+
"learning_rate": 5.088333333333334e-06,
|
773 |
+
"loss": 0.4151,
|
774 |
+
"step": 4950
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 217.3913043478261,
|
778 |
+
"grad_norm": 1.3829108476638794,
|
779 |
+
"learning_rate": 5.0049999999999995e-06,
|
780 |
+
"loss": 0.4223,
|
781 |
+
"step": 5000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 217.3913043478261,
|
785 |
+
"eval_loss": 0.41126948595046997,
|
786 |
+
"eval_runtime": 6.7795,
|
787 |
+
"eval_samples_per_second": 23.453,
|
788 |
+
"eval_steps_per_second": 2.95,
|
789 |
+
"step": 5000
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 50,
|
|
|
806 |
"attributes": {}
|
807 |
}
|
808 |
},
|
809 |
+
"total_flos": 7.422809573607754e+16,
|
810 |
"train_batch_size": 64,
|
811 |
"trial_name": null,
|
812 |
"trial_params": null
|