Training in progress, step 5980, 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 sha256:5109ffb1f9c269c8a4bfe03aa31903c41519f9a9751a9c6cb2eb730ba4a07dbc
|
| 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 sha256:32e803b8c088ef49343ada162097c30e307da6e9b627ab65b25d7a41aa4ef756
|
| 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 sha256:2ab32727bf946d972dc2971c5e3d0d72685dfab0ab98222e0246eb944c4e0466
|
| 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":
|
| 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,
|
|
@@ -10754,6 +10754,24 @@
|
|
| 10754 |
"mean_token_accuracy": 0.663582494854927,
|
| 10755 |
"num_tokens": 21771809.0,
|
| 10756 |
"step": 5970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10757 |
}
|
| 10758 |
],
|
| 10759 |
"logging_steps": 5,
|
|
@@ -10773,7 +10791,7 @@
|
|
| 10773 |
"attributes": {}
|
| 10774 |
}
|
| 10775 |
},
|
| 10776 |
-
"total_flos": 1.
|
| 10777 |
"train_batch_size": 4,
|
| 10778 |
"trial_name": null,
|
| 10779 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10754 |
"mean_token_accuracy": 0.663582494854927,
|
| 10755 |
"num_tokens": 21771809.0,
|
| 10756 |
"step": 5970
|
| 10757 |
+
},
|
| 10758 |
+
{
|
| 10759 |
+
"epoch": 45.96153846153846,
|
| 10760 |
+
"grad_norm": 0.0,
|
| 10761 |
+
"learning_rate": 2.0130000000000002e-05,
|
| 10762 |
+
"loss": 1.7161,
|
| 10763 |
+
"mean_token_accuracy": 0.6539533823728562,
|
| 10764 |
+
"num_tokens": 21790432.0,
|
| 10765 |
+
"step": 5975
|
| 10766 |
+
},
|
| 10767 |
+
{
|
| 10768 |
+
"epoch": 46.0,
|
| 10769 |
+
"grad_norm": 0.0,
|
| 10770 |
+
"learning_rate": 2.0105e-05,
|
| 10771 |
+
"loss": 1.7338,
|
| 10772 |
+
"mean_token_accuracy": 0.6510831654071808,
|
| 10773 |
+
"num_tokens": 21808830.0,
|
| 10774 |
+
"step": 5980
|
| 10775 |
}
|
| 10776 |
],
|
| 10777 |
"logging_steps": 5,
|
|
|
|
| 10791 |
"attributes": {}
|
| 10792 |
}
|
| 10793 |
},
|
| 10794 |
+
"total_flos": 1.1052189253863014e+18,
|
| 10795 |
"train_batch_size": 4,
|
| 10796 |
"trial_name": null,
|
| 10797 |
"trial_params": null
|