Training in progress, step 4200, checkpoint
Browse files
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4978139416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dbdd6f80dc79a8405e31ae7786528edc85a46546c81b10d835d82e28f972d7e
|
3 |
size 4978139416
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3659223436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42b57c72afc83f80ebcb3ac2c3025ecf0061be5a4ba0dbe9fff2daed822328cc
|
3 |
size 3659223436
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17241500333
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38852f16d1dc1f5bbcbc93dc34aea8227dab25604d05cca96d84347321f03d6f
|
3 |
size 17241500333
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b1aec0a96b3ecb58cc9d8ef8a09a92cddd9227edd51fc5e1fd3970354bfc8e6
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e234c273d80c40346bcc08d22e92500d903e21d8697287e8453c0f063d1a8ee1
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -647,6 +647,38 @@
|
|
647 |
"eval_samples_per_second": 27.203,
|
648 |
"eval_steps_per_second": 3.401,
|
649 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
650 |
}
|
651 |
],
|
652 |
"logging_steps": 100,
|
@@ -654,7 +686,7 @@
|
|
654 |
"num_input_tokens_seen": 0,
|
655 |
"num_train_epochs": 30,
|
656 |
"save_steps": 100,
|
657 |
-
"total_flos": 4.
|
658 |
"train_batch_size": 8,
|
659 |
"trial_name": null,
|
660 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.768048831824879,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 4200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
647 |
"eval_samples_per_second": 27.203,
|
648 |
"eval_steps_per_second": 3.401,
|
649 |
"step": 4000
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 1.73,
|
653 |
+
"grad_norm": 2.8654837608337402,
|
654 |
+
"learning_rate": 4.746077738515901e-05,
|
655 |
+
"loss": 2.226,
|
656 |
+
"step": 4100
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 1.73,
|
660 |
+
"eval_cer": 0.5324904188338352,
|
661 |
+
"eval_loss": 3.042088031768799,
|
662 |
+
"eval_runtime": 354.1261,
|
663 |
+
"eval_samples_per_second": 26.764,
|
664 |
+
"eval_steps_per_second": 3.346,
|
665 |
+
"step": 4100
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.77,
|
669 |
+
"grad_norm": 7.595367908477783,
|
670 |
+
"learning_rate": 4.7390106007067143e-05,
|
671 |
+
"loss": 2.7925,
|
672 |
+
"step": 4200
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 1.77,
|
676 |
+
"eval_cer": 0.5470479253842243,
|
677 |
+
"eval_loss": 3.0831844806671143,
|
678 |
+
"eval_runtime": 344.2619,
|
679 |
+
"eval_samples_per_second": 27.531,
|
680 |
+
"eval_steps_per_second": 3.442,
|
681 |
+
"step": 4200
|
682 |
}
|
683 |
],
|
684 |
"logging_steps": 100,
|
|
|
686 |
"num_input_tokens_seen": 0,
|
687 |
"num_train_epochs": 30,
|
688 |
"save_steps": 100,
|
689 |
+
"total_flos": 4.61125002150313e+19,
|
690 |
"train_batch_size": 8,
|
691 |
"trial_name": null,
|
692 |
"trial_params": null
|