Training in progress, step 94, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd8e8ea727a553a672823874809873f890a2f801464cffe42914f5c2ad4108b7
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675156
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ac036fe2d7d8803936314b87cb8eec10f6ead9619f3dbd596a8b052e42a682
|
3 |
size 50675156
|
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 sha256:880474794efefa84f5a3a228baae3dec1f301dca9a3d5a599be6d457021aa061
|
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,
|
@@ -644,6 +644,27 @@
|
|
644 |
"learning_rate": 0.000182,
|
645 |
"loss": 1.1481,
|
646 |
"step": 91
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
647 |
}
|
648 |
],
|
649 |
"logging_steps": 1,
|
@@ -663,7 +684,7 @@
|
|
663 |
"attributes": {}
|
664 |
}
|
665 |
},
|
666 |
-
"total_flos": 2.
|
667 |
"train_batch_size": 16,
|
668 |
"trial_name": null,
|
669 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2578875171467764,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 94,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
644 |
"learning_rate": 0.000182,
|
645 |
"loss": 1.1481,
|
646 |
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.252400548696845,
|
650 |
+
"grad_norm": 0.06837109476327896,
|
651 |
+
"learning_rate": 0.00018400000000000003,
|
652 |
+
"loss": 1.2352,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.2551440329218107,
|
657 |
+
"grad_norm": 0.06343371421098709,
|
658 |
+
"learning_rate": 0.00018600000000000002,
|
659 |
+
"loss": 1.1362,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.2578875171467764,
|
664 |
+
"grad_norm": 0.06184321269392967,
|
665 |
+
"learning_rate": 0.000188,
|
666 |
+
"loss": 1.1256,
|
667 |
+
"step": 94
|
668 |
}
|
669 |
],
|
670 |
"logging_steps": 1,
|
|
|
684 |
"attributes": {}
|
685 |
}
|
686 |
},
|
687 |
+
"total_flos": 2.6971271019115315e+17,
|
688 |
"train_batch_size": 16,
|
689 |
"trial_name": null,
|
690 |
"trial_params": null
|