Training in progress, step 42200, 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:f693484def2b2a6313d116c6f4c54dafa51df3b9cbbafe6194f4aebf6a1037f4
|
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 sha256:111113eeb7f0cfb250b86c2d9112db0d080532efaab2b65ce354d94770c0163a
|
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 sha256:761caed2751672ced9080aac4251531b7fdea3daeaed6abed0a76b368594d8e0
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cad0da5e21b95095501337deb354a217aa91e17d351f9de3d09b404d08ce3095
|
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:b0634da82e984807c433cb6f91a27dc4d3830ec402aae54effd98d0a8ab70cc0
|
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": 17.
|
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,
|
@@ -6727,6 +6727,38 @@
|
|
6727 |
"eval_samples_per_second": 24.963,
|
6728 |
"eval_steps_per_second": 3.121,
|
6729 |
"step": 42000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6730 |
}
|
6731 |
],
|
6732 |
"logging_steps": 100,
|
@@ -6734,7 +6766,7 @@
|
|
6734 |
"num_input_tokens_seen": 0,
|
6735 |
"num_train_epochs": 30,
|
6736 |
"save_steps": 100,
|
6737 |
-
"total_flos": 4.
|
6738 |
"train_batch_size": 8,
|
6739 |
"trial_name": null,
|
6740 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.76468111976426,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 42200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
6727 |
"eval_samples_per_second": 24.963,
|
6728 |
"eval_steps_per_second": 3.121,
|
6729 |
"step": 42000
|
6730 |
+
},
|
6731 |
+
{
|
6732 |
+
"epoch": 17.72,
|
6733 |
+
"grad_norm": 3.275186777114868,
|
6734 |
+
"learning_rate": 2.0614134275618374e-05,
|
6735 |
+
"loss": 0.641,
|
6736 |
+
"step": 42100
|
6737 |
+
},
|
6738 |
+
{
|
6739 |
+
"epoch": 17.72,
|
6740 |
+
"eval_cer": 0.36079689883070665,
|
6741 |
+
"eval_loss": 1.8855453729629517,
|
6742 |
+
"eval_runtime": 405.5391,
|
6743 |
+
"eval_samples_per_second": 23.371,
|
6744 |
+
"eval_steps_per_second": 2.922,
|
6745 |
+
"step": 42100
|
6746 |
+
},
|
6747 |
+
{
|
6748 |
+
"epoch": 17.76,
|
6749 |
+
"grad_norm": 3.293827533721924,
|
6750 |
+
"learning_rate": 2.054416961130742e-05,
|
6751 |
+
"loss": 0.755,
|
6752 |
+
"step": 42200
|
6753 |
+
},
|
6754 |
+
{
|
6755 |
+
"epoch": 17.76,
|
6756 |
+
"eval_cer": 0.3628133432403895,
|
6757 |
+
"eval_loss": 2.0661118030548096,
|
6758 |
+
"eval_runtime": 378.6947,
|
6759 |
+
"eval_samples_per_second": 25.028,
|
6760 |
+
"eval_steps_per_second": 3.129,
|
6761 |
+
"step": 42200
|
6762 |
}
|
6763 |
],
|
6764 |
"logging_steps": 100,
|
|
|
6766 |
"num_input_tokens_seen": 0,
|
6767 |
"num_train_epochs": 30,
|
6768 |
"save_steps": 100,
|
6769 |
+
"total_flos": 4.624647649840507e+20,
|
6770 |
"train_batch_size": 8,
|
6771 |
"trial_name": null,
|
6772 |
"trial_params": null
|