Training in progress, step 5950, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0286408cc438768bfd5ef094ed53e8c56bbdd5cb2bf128226e4a31f05abde5e7
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b93bd52b3610e7058ccfa0f69d5253acdd2edac442b534f2a46de1c85ffe56a9
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa6e084655cfa40426416f3a4129801d59904046a3941476cf6775dc56420c3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 45.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -10700,6 +10700,24 @@
|
|
| 10700 |
"mean_token_accuracy": 0.6421581089496613,
|
| 10701 |
"num_tokens": 21661822.0,
|
| 10702 |
"step": 5940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10703 |
}
|
| 10704 |
],
|
| 10705 |
"logging_steps": 5,
|
|
@@ -10719,7 +10737,7 @@
|
|
| 10719 |
"attributes": {}
|
| 10720 |
}
|
| 10721 |
},
|
| 10722 |
-
"total_flos": 1.
|
| 10723 |
"train_batch_size": 4,
|
| 10724 |
"trial_name": null,
|
| 10725 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10700 |
"mean_token_accuracy": 0.6421581089496613,
|
| 10701 |
"num_tokens": 21661822.0,
|
| 10702 |
"step": 5940
|
| 10703 |
+
},
|
| 10704 |
+
{
|
| 10705 |
+
"epoch": 45.73076923076923,
|
| 10706 |
+
"grad_norm": 0.0,
|
| 10707 |
+
"learning_rate": 2.0280000000000002e-05,
|
| 10708 |
+
"loss": 1.6908,
|
| 10709 |
+
"mean_token_accuracy": 0.6561397314071655,
|
| 10710 |
+
"num_tokens": 21681068.0,
|
| 10711 |
+
"step": 5945
|
| 10712 |
+
},
|
| 10713 |
+
{
|
| 10714 |
+
"epoch": 45.76923076923077,
|
| 10715 |
+
"grad_norm": 0.0,
|
| 10716 |
+
"learning_rate": 2.0255000000000002e-05,
|
| 10717 |
+
"loss": 1.7477,
|
| 10718 |
+
"mean_token_accuracy": 0.6448839485645295,
|
| 10719 |
+
"num_tokens": 21699251.0,
|
| 10720 |
+
"step": 5950
|
| 10721 |
}
|
| 10722 |
],
|
| 10723 |
"logging_steps": 5,
|
|
|
|
| 10737 |
"attributes": {}
|
| 10738 |
}
|
| 10739 |
},
|
| 10740 |
+
"total_flos": 1.0996518109608346e+18,
|
| 10741 |
"train_batch_size": 4,
|
| 10742 |
"trial_name": null,
|
| 10743 |
"trial_params": null
|