Training in progress, step 20000, 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 1262135480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8815656f39bb31a27997a0b4985228221e357c0c54a99006d4f5c2dab0368d2
|
3 |
size 1262135480
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490815798
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1bc25a2e77b3cb67994f8b8ed9943ee4caad68cba1eae5f0dab4aaa607f87db
|
3 |
size 2490815798
|
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 sha256:9ae3e06391b56f7d5d884accce0258dfa3afdca721551b70c01b265975815b61
|
3 |
+
size 14308
|
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 sha256:0385e4a12dd5228a18991bc2f050826728def0ff0eed46203f29e5046dc0c739
|
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": 13.
|
5 |
"eval_steps": 400,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -791,6 +791,22 @@
|
|
791 |
"eval_steps_per_second": 0.831,
|
792 |
"eval_wer": 0.06208596518256047,
|
793 |
"step": 19600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
794 |
}
|
795 |
],
|
796 |
"logging_steps": 400,
|
@@ -798,7 +814,7 @@
|
|
798 |
"num_input_tokens_seen": 0,
|
799 |
"num_train_epochs": 30,
|
800 |
"save_steps": 400,
|
801 |
-
"total_flos":
|
802 |
"train_batch_size": 8,
|
803 |
"trial_name": null,
|
804 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.568521031207599,
|
5 |
"eval_steps": 400,
|
6 |
+
"global_step": 20000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
791 |
"eval_steps_per_second": 0.831,
|
792 |
"eval_wer": 0.06208596518256047,
|
793 |
"step": 19600
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 13.57,
|
797 |
+
"grad_norm": 0.8884561657905579,
|
798 |
+
"learning_rate": 0.00016619396157365048,
|
799 |
+
"loss": 0.0773,
|
800 |
+
"step": 20000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 13.57,
|
804 |
+
"eval_loss": 0.032973628491163254,
|
805 |
+
"eval_runtime": 210.0131,
|
806 |
+
"eval_samples_per_second": 6.661,
|
807 |
+
"eval_steps_per_second": 0.833,
|
808 |
+
"eval_wer": 0.05646279463873055,
|
809 |
+
"step": 20000
|
810 |
}
|
811 |
],
|
812 |
"logging_steps": 400,
|
|
|
814 |
"num_input_tokens_seen": 0,
|
815 |
"num_train_epochs": 30,
|
816 |
"save_steps": 400,
|
817 |
+
"total_flos": 6.100475557233166e+19,
|
818 |
"train_batch_size": 8,
|
819 |
"trial_name": null,
|
820 |
"trial_params": null
|