mikhail-panzo
commited on
Commit
•
7f53844
1
Parent(s):
0986eb7
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 sha256:3fb634d25a31951e441158f54ae0db2c273aaeb251169c41f8467cecc648bf56
|
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 sha256:4cc68ae6c7c867a9ae1fe921933744282f9631aa37051c6ca0a82c81119ae62e
|
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 sha256:404094f43137b5b2180fadcde3d1168585bcd71ff155f508576088e11be9d3e1
|
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_le4_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": 30.95,
|
710 |
"eval_steps_per_second": 3.872,
|
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": 0.3284249007701874,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_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": 30.95,
|
710 |
"eval_steps_per_second": 3.872,
|
711 |
"step": 4500
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 7.62303664921466,
|
715 |
+
"grad_norm": 1.3059043884277344,
|
716 |
+
"learning_rate": 5.753333333333334e-05,
|
717 |
+
"loss": 0.3603,
|
718 |
+
"step": 4550
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 7.706806282722513,
|
722 |
+
"grad_norm": 1.6313170194625854,
|
723 |
+
"learning_rate": 5.6699999999999996e-05,
|
724 |
+
"loss": 0.3622,
|
725 |
+
"step": 4600
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 7.790575916230367,
|
729 |
+
"grad_norm": 1.7790875434875488,
|
730 |
+
"learning_rate": 5.5866666666666665e-05,
|
731 |
+
"loss": 0.3635,
|
732 |
+
"step": 4650
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 7.87434554973822,
|
736 |
+
"grad_norm": 1.1874761581420898,
|
737 |
+
"learning_rate": 5.5033333333333334e-05,
|
738 |
+
"loss": 0.3635,
|
739 |
+
"step": 4700
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 7.958115183246074,
|
743 |
+
"grad_norm": 0.9745219349861145,
|
744 |
+
"learning_rate": 5.420000000000001e-05,
|
745 |
+
"loss": 0.357,
|
746 |
+
"step": 4750
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 8.041884816753926,
|
750 |
+
"grad_norm": 1.3074321746826172,
|
751 |
+
"learning_rate": 5.3366666666666665e-05,
|
752 |
+
"loss": 0.3543,
|
753 |
+
"step": 4800
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 8.12565445026178,
|
757 |
+
"grad_norm": 1.3384989500045776,
|
758 |
+
"learning_rate": 5.2533333333333334e-05,
|
759 |
+
"loss": 0.3556,
|
760 |
+
"step": 4850
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 8.209424083769633,
|
764 |
+
"grad_norm": 1.0133076906204224,
|
765 |
+
"learning_rate": 5.17e-05,
|
766 |
+
"loss": 0.3654,
|
767 |
+
"step": 4900
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 8.293193717277488,
|
771 |
+
"grad_norm": 1.194360375404358,
|
772 |
+
"learning_rate": 5.086666666666667e-05,
|
773 |
+
"loss": 0.3547,
|
774 |
+
"step": 4950
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 8.37696335078534,
|
778 |
+
"grad_norm": 1.049672245979309,
|
779 |
+
"learning_rate": 5.0033333333333334e-05,
|
780 |
+
"loss": 0.3607,
|
781 |
+
"step": 5000
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 8.37696335078534,
|
785 |
+
"eval_loss": 0.3284249007701874,
|
786 |
+
"eval_runtime": 274.7134,
|
787 |
+
"eval_samples_per_second": 30.901,
|
788 |
+
"eval_steps_per_second": 3.866,
|
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
|