Commit
·
e2819fe
1
Parent(s):
87b765e
Training in progress, step 100, 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 sha256:8e48fbfb9a27c93b319e9a84a87f1a886746f8657f7d1e2f5dfd64649dd342cd
|
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 sha256:95493ba0a3c1e394aab64991592db08e344b6ea9a442175c7442bab215ed3609
|
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 sha256:1ea9587f57d558858d9209d96d19ea2be1ea0213796d98d94e89cfd6c1b66c54
|
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:b994682a19542ea2d9b8a16c5c3be20af753056a6bf87ab6895aa9396ba8db1a
|
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,
|
@@ -577,13 +577,43 @@
|
|
577 |
"learning_rate": 7.482993197278913e-05,
|
578 |
"loss": 1.4248,
|
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": 1.
|
587 |
"trial_name": null,
|
588 |
"trial_params": null
|
589 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
577 |
"learning_rate": 7.482993197278913e-05,
|
578 |
"loss": 1.4248,
|
579 |
"step": 95
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.04,
|
583 |
+
"learning_rate": 7.346938775510205e-05,
|
584 |
+
"loss": 1.4999,
|
585 |
+
"step": 96
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.04,
|
589 |
+
"learning_rate": 7.210884353741498e-05,
|
590 |
+
"loss": 1.6352,
|
591 |
+
"step": 97
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.04,
|
595 |
+
"learning_rate": 7.074829931972789e-05,
|
596 |
+
"loss": 1.6345,
|
597 |
+
"step": 98
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.04,
|
601 |
+
"learning_rate": 6.938775510204082e-05,
|
602 |
+
"loss": 1.6019,
|
603 |
+
"step": 99
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.04,
|
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": 1.236815439519744e+16,
|
617 |
"trial_name": null,
|
618 |
"trial_params": null
|
619 |
}
|