TachyHealthResearch
commited on
Commit
·
aed8cb5
1
Parent(s):
8cb1cf0
Training in progress, step 130, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:279ff56643c1fd53edc2e1149b1713de9eb6ab18f853cb390ec873392ffcfd34
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:429bc6ac13dc437a695eb56f4b3bc6512c584c75bd0f49d6e799f8e9e99a4d07
|
3 |
size 63350356
|
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:acd9b06a21fcf82080ee1e3028a1d0da77d901214b51c999e4aef01ba794228c
|
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 sha256:5a9caa421f5edeb4c03822697934b69a6bb3503e7fa549e085d56c6e70b7d90a
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -757,13 +757,43 @@
|
|
757 |
"learning_rate": 3.401360544217687e-05,
|
758 |
"loss": 1.8325,
|
759 |
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
760 |
}
|
761 |
],
|
762 |
"logging_steps": 1,
|
763 |
"max_steps": 150,
|
764 |
"num_train_epochs": 1,
|
765 |
"save_steps": 5,
|
766 |
-
"total_flos": 1.
|
767 |
"trial_name": null,
|
768 |
"trial_params": null
|
769 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.052,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 130,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
757 |
"learning_rate": 3.401360544217687e-05,
|
758 |
"loss": 1.8325,
|
759 |
"step": 125
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.05,
|
763 |
+
"learning_rate": 3.265306122448979e-05,
|
764 |
+
"loss": 1.6309,
|
765 |
+
"step": 126
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.05,
|
769 |
+
"learning_rate": 3.1292517006802724e-05,
|
770 |
+
"loss": 1.6754,
|
771 |
+
"step": 127
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.05,
|
775 |
+
"learning_rate": 2.9931972789115647e-05,
|
776 |
+
"loss": 1.1972,
|
777 |
+
"step": 128
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.05,
|
781 |
+
"learning_rate": 2.857142857142857e-05,
|
782 |
+
"loss": 1.6411,
|
783 |
+
"step": 129
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.05,
|
787 |
+
"learning_rate": 2.72108843537415e-05,
|
788 |
+
"loss": 2.031,
|
789 |
+
"step": 130
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 1,
|
793 |
"max_steps": 150,
|
794 |
"num_train_epochs": 1,
|
795 |
"save_steps": 5,
|
796 |
+
"total_flos": 1.6062939734016e+16,
|
797 |
"trial_name": null,
|
798 |
"trial_params": null
|
799 |
}
|