Training in progress, step 91, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bd955ac6403e2c46118e3030e9ccbc4e0794de73024af378377a9bbaa39e0f6
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bfb2bd91d0cb45ae57b8f396ba69f92b82a8a118970d0147730b6570dc9407e
|
3 |
size 37430836
|
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 sha256:514a1033fbdd80980bd26435e44ca89b19af0dbd08dbc451c61ffcb64e978087
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -637,6 +637,13 @@
|
|
637 |
"learning_rate": 0.00018,
|
638 |
"loss": 1.303,
|
639 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
640 |
}
|
641 |
],
|
642 |
"logging_steps": 1,
|
@@ -656,7 +663,7 @@
|
|
656 |
"attributes": {}
|
657 |
}
|
658 |
},
|
659 |
-
"total_flos": 1.
|
660 |
"train_batch_size": 4,
|
661 |
"trial_name": null,
|
662 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2496570644718793,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 91,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
637 |
"learning_rate": 0.00018,
|
638 |
"loss": 1.303,
|
639 |
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.2496570644718793,
|
643 |
+
"grad_norm": 0.09918926656246185,
|
644 |
+
"learning_rate": 0.000182,
|
645 |
+
"loss": 1.2377,
|
646 |
+
"step": 91
|
647 |
}
|
648 |
],
|
649 |
"logging_steps": 1,
|
|
|
663 |
"attributes": {}
|
664 |
}
|
665 |
},
|
666 |
+
"total_flos": 1.1299211233937818e+17,
|
667 |
"train_batch_size": 4,
|
668 |
"trial_name": null,
|
669 |
"trial_params": null
|