Training in progress, step 47000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891644712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dded3ce5b3f4ec86c1659a422eefea27e21f4bf53d4c0e5a2b48119f3d4182b
|
3 |
size 891644712
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783444357
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6672624875535e946663af5b1a359fd25b5540443bcb208aef146daadd1a8cc4
|
3 |
size 1783444357
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:614dc170c377123eff61387041314b6fd377aab7f7b532611b80b4afc31f488a
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e84764852580c5946c4e5a7fe468c9a184e8d636981b7bfc9bfe05aa325b501
|
3 |
size 627
|
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,
|
@@ -658,6 +658,13 @@
|
|
658 |
"learning_rate": 4.256272e-05,
|
659 |
"loss": 0.3445,
|
660 |
"step": 46500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
661 |
}
|
662 |
],
|
663 |
"logging_steps": 500,
|
@@ -677,7 +684,7 @@
|
|
677 |
"attributes": {}
|
678 |
}
|
679 |
},
|
680 |
-
"total_flos": 2.
|
681 |
"train_batch_size": 64,
|
682 |
"trial_name": null,
|
683 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3008,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 47000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
658 |
"learning_rate": 4.256272e-05,
|
659 |
"loss": 0.3445,
|
660 |
"step": 46500
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.3008,
|
664 |
+
"grad_norm": 0.7245766520500183,
|
665 |
+
"learning_rate": 4.248272e-05,
|
666 |
+
"loss": 0.3462,
|
667 |
+
"step": 47000
|
668 |
}
|
669 |
],
|
670 |
"logging_steps": 500,
|
|
|
684 |
"attributes": {}
|
685 |
}
|
686 |
},
|
687 |
+
"total_flos": 2.2896816685056e+17,
|
688 |
"train_batch_size": 64,
|
689 |
"trial_name": null,
|
690 |
"trial_params": null
|