TachyHealthResearch
commited on
Commit
·
93accf8
1
Parent(s):
e1ee9db
Training in progress, step 105, 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:a1a8485baffd4ccd87e49f0cc204b7132e6855e9c887531d30e8568099ec14e8
|
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 sha256:08f3181fb02820176b6253acf7ac9d567410dc54bd05e6078be7f052a3be504f
|
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:a8f61387f66c53bbe2e89961f3144d563083860b3648a351be094db0e238f002
|
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:cb1788e6a1bc90172eb379091d3d6012641cdbceff45f62df18ceefa4d2ee278
|
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,
|
@@ -607,13 +607,43 @@
|
|
607 |
"learning_rate": 6.802721088435374e-05,
|
608 |
"loss": 1.4834,
|
609 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
610 |
}
|
611 |
],
|
612 |
"logging_steps": 1,
|
613 |
"max_steps": 150,
|
614 |
"num_train_epochs": 1,
|
615 |
"save_steps": 5,
|
616 |
-
"total_flos": 1.
|
617 |
"trial_name": null,
|
618 |
"trial_params": null
|
619 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.042,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 105,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
607 |
"learning_rate": 6.802721088435374e-05,
|
608 |
"loss": 1.4834,
|
609 |
"step": 100
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.04,
|
613 |
+
"learning_rate": 6.666666666666667e-05,
|
614 |
+
"loss": 1.4514,
|
615 |
+
"step": 101
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.04,
|
619 |
+
"learning_rate": 6.530612244897959e-05,
|
620 |
+
"loss": 1.5484,
|
621 |
+
"step": 102
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.04,
|
625 |
+
"learning_rate": 6.394557823129253e-05,
|
626 |
+
"loss": 1.6164,
|
627 |
+
"step": 103
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.04,
|
631 |
+
"learning_rate": 6.258503401360545e-05,
|
632 |
+
"loss": 1.6819,
|
633 |
+
"step": 104
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.04,
|
637 |
+
"learning_rate": 6.122448979591838e-05,
|
638 |
+
"loss": 1.8219,
|
639 |
+
"step": 105
|
640 |
}
|
641 |
],
|
642 |
"logging_steps": 1,
|
643 |
"max_steps": 150,
|
644 |
"num_train_epochs": 1,
|
645 |
"save_steps": 5,
|
646 |
+
"total_flos": 1.299196538486784e+16,
|
647 |
"trial_name": null,
|
648 |
"trial_params": null
|
649 |
}
|