mikhail-panzo
commited on
Commit
•
04af035
1
Parent(s):
f2ca9c2
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:e89ff2481874bf269cba7ac84ce957b44c8fa49e2c675e9e6b16008fdb7a55c7
|
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 sha256:2b314243ca4b21fc0b329b39dc658d58545fdaa26b0dc513de3ccf6b20a972ec
|
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 sha256:8f4e204979057d17355f455adeaa53e6157f86fff91322a4565250d75055d836
|
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/zlm_b128_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": 33.831,
|
710 |
"eval_steps_per_second": 4.232,
|
711 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
712 |
}
|
713 |
],
|
714 |
"logging_steps": 50,
|
@@ -728,7 +806,7 @@
|
|
728 |
"attributes": {}
|
729 |
}
|
730 |
},
|
731 |
-
"total_flos": 8.
|
732 |
"train_batch_size": 16,
|
733 |
"trial_name": null,
|
734 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.37838345766067505,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_s8000/checkpoint-5000",
|
4 |
+
"epoch": 8.37696335078534,
|
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": 33.831,
|
710 |
"eval_steps_per_second": 4.232,
|
711 |
"step": 4500
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 7.62303664921466,
|
715 |
+
"grad_norm": 1.3911954164505005,
|
716 |
+
"learning_rate": 5.755000000000001e-06,
|
717 |
+
"loss": 0.42,
|
718 |
+
"step": 4550
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 7.706806282722513,
|
722 |
+
"grad_norm": 1.3781930208206177,
|
723 |
+
"learning_rate": 5.671666666666668e-06,
|
724 |
+
"loss": 0.4234,
|
725 |
+
"step": 4600
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 7.790575916230367,
|
729 |
+
"grad_norm": 1.5225090980529785,
|
730 |
+
"learning_rate": 5.588333333333334e-06,
|
731 |
+
"loss": 0.4242,
|
732 |
+
"step": 4650
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 7.87434554973822,
|
736 |
+
"grad_norm": 1.4195870161056519,
|
737 |
+
"learning_rate": 5.505000000000001e-06,
|
738 |
+
"loss": 0.4243,
|
739 |
+
"step": 4700
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 7.958115183246074,
|
743 |
+
"grad_norm": 1.9713116884231567,
|
744 |
+
"learning_rate": 5.4216666666666676e-06,
|
745 |
+
"loss": 0.4158,
|
746 |
+
"step": 4750
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 8.041884816753926,
|
750 |
+
"grad_norm": 1.3215075731277466,
|
751 |
+
"learning_rate": 5.3383333333333345e-06,
|
752 |
+
"loss": 0.4141,
|
753 |
+
"step": 4800
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 8.12565445026178,
|
757 |
+
"grad_norm": 4.483395576477051,
|
758 |
+
"learning_rate": 5.2550000000000005e-06,
|
759 |
+
"loss": 0.4165,
|
760 |
+
"step": 4850
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 8.209424083769633,
|
764 |
+
"grad_norm": 1.4759974479675293,
|
765 |
+
"learning_rate": 5.171666666666667e-06,
|
766 |
+
"loss": 0.4291,
|
767 |
+
"step": 4900
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 8.293193717277488,
|
771 |
+
"grad_norm": 1.3336604833602905,
|
772 |
+
"learning_rate": 5.088333333333334e-06,
|
773 |
+
"loss": 0.4134,
|
774 |
+
"step": 4950
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 8.37696335078534,
|
778 |
+
"grad_norm": 1.5618665218353271,
|
779 |
+
"learning_rate": 5.0049999999999995e-06,
|
780 |
+
"loss": 0.4222,
|
781 |
+
"step": 5000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 8.37696335078534,
|
785 |
+
"eval_loss": 0.37838345766067505,
|
786 |
+
"eval_runtime": 256.1892,
|
787 |
+
"eval_samples_per_second": 33.136,
|
788 |
+
"eval_steps_per_second": 4.145,
|
789 |
+
"step": 5000
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 50,
|
|
|
806 |
"attributes": {}
|
807 |
}
|
808 |
},
|
809 |
+
"total_flos": 8.958474220139136e+16,
|
810 |
"train_batch_size": 16,
|
811 |
"trial_name": null,
|
812 |
"trial_params": null
|