TachyHealthResearch
commited on
Commit
•
a497110
1
Parent(s):
f9854cb
Training in progress, step 125, 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 75012288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d31a15a30587c8cb41fd070ea0adfbad493a3aa54f96f5306d87734c4857a712
|
3 |
size 75012288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 38034724
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5bd5f0b7fa09551ebc281b6f3c17d8ad8c38545284ecbbb67ebbe9c7f8b48d0
|
3 |
size 38034724
|
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 sha256:57e2991ea9fcf19b1ca7581a8de4820419ce73b6a8a974227e04c239b386ffe7
|
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 sha256:5c5810ebf48e1cd08b1da484cd43f42f5cd1b4a4451e8333eb82845cd321c500
|
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,
|
@@ -727,13 +727,43 @@
|
|
727 |
"learning_rate": 4.0816326530612245e-05,
|
728 |
"loss": 1.6725,
|
729 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
730 |
}
|
731 |
],
|
732 |
"logging_steps": 1,
|
733 |
"max_steps": 150,
|
734 |
"num_train_epochs": 1,
|
735 |
"save_steps": 5,
|
736 |
-
"total_flos":
|
737 |
"trial_name": null,
|
738 |
"trial_params": null
|
739 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 125,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
727 |
"learning_rate": 4.0816326530612245e-05,
|
728 |
"loss": 1.6725,
|
729 |
"step": 120
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.05,
|
733 |
+
"learning_rate": 3.945578231292517e-05,
|
734 |
+
"loss": 1.6443,
|
735 |
+
"step": 121
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.05,
|
739 |
+
"learning_rate": 3.809523809523809e-05,
|
740 |
+
"loss": 2.0864,
|
741 |
+
"step": 122
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.05,
|
745 |
+
"learning_rate": 3.673469387755102e-05,
|
746 |
+
"loss": 1.7234,
|
747 |
+
"step": 123
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.05,
|
751 |
+
"learning_rate": 3.5374149659863946e-05,
|
752 |
+
"loss": 1.8916,
|
753 |
+
"step": 124
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.05,
|
757 |
+
"learning_rate": 3.401360544217687e-05,
|
758 |
+
"loss": 2.2922,
|
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": 6725170760515584.0,
|
767 |
"trial_name": null,
|
768 |
"trial_params": null
|
769 |
}
|