TachyHealthResearch
commited on
Commit
•
082d985
1
Parent(s):
a76dd58
Training in progress, step 95, 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:c6654ec142bf8709363917f4fb46f9b18031ac28b9333e5cb8f38f43e33e50b9
|
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 sha256:04b0c8b7e52ff85dcbc2f0b99687ed697c2985a726fdce31fd350a84b1969431
|
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 sha256:889d0cc867cbfb43ba68c124df826b0b034aee4977d4e2bcbed5aec2b804c16c
|
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 sha256:6108f4faef547664ffc49f24479d791d4a8a5a6cda6f7c8b0f62fd8408e62a4f
|
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,
|
@@ -547,13 +547,43 @@
|
|
547 |
"learning_rate": 8.163265306122449e-05,
|
548 |
"loss": 2.2407,
|
549 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
550 |
}
|
551 |
],
|
552 |
"logging_steps": 1,
|
553 |
"max_steps": 150,
|
554 |
"num_train_epochs": 1,
|
555 |
"save_steps": 5,
|
556 |
-
"total_flos":
|
557 |
"trial_name": null,
|
558 |
"trial_params": null
|
559 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.038,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 95,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
547 |
"learning_rate": 8.163265306122449e-05,
|
548 |
"loss": 2.2407,
|
549 |
"step": 90
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.04,
|
553 |
+
"learning_rate": 8.027210884353742e-05,
|
554 |
+
"loss": 1.8978,
|
555 |
+
"step": 91
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.04,
|
559 |
+
"learning_rate": 7.891156462585034e-05,
|
560 |
+
"loss": 1.2992,
|
561 |
+
"step": 92
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.04,
|
565 |
+
"learning_rate": 7.755102040816327e-05,
|
566 |
+
"loss": 1.9454,
|
567 |
+
"step": 93
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.04,
|
571 |
+
"learning_rate": 7.619047619047618e-05,
|
572 |
+
"loss": 2.5311,
|
573 |
+
"step": 94
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.04,
|
577 |
+
"learning_rate": 7.482993197278913e-05,
|
578 |
+
"loss": 1.753,
|
579 |
+
"step": 95
|
580 |
}
|
581 |
],
|
582 |
"logging_steps": 1,
|
583 |
"max_steps": 150,
|
584 |
"num_train_epochs": 1,
|
585 |
"save_steps": 5,
|
586 |
+
"total_flos": 5026926877999104.0,
|
587 |
"trial_name": null,
|
588 |
"trial_params": null
|
589 |
}
|