Training in progress, step 8060, 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:a20b5695852a4a6aea19ae82de0b88a43cc2dabee75659040cfeac42868387a3
|
| 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:cca8fb039635a6cb9aa3d355b92265c18ce4dcca5a970a240bd0bbd2c1744abf
|
| 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:d95f307bb1af2395b8b0132c7167419e052fe0ef823165c127fbfe84d914c375
|
| 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,
|
|
@@ -14498,6 +14498,24 @@
|
|
| 14498 |
"mean_token_accuracy": 0.6602411061525345,
|
| 14499 |
"num_tokens": 29357996.0,
|
| 14500 |
"step": 8050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14501 |
}
|
| 14502 |
],
|
| 14503 |
"logging_steps": 5,
|
|
@@ -14517,7 +14535,7 @@
|
|
| 14517 |
"attributes": {}
|
| 14518 |
}
|
| 14519 |
},
|
| 14520 |
-
"total_flos": 1.
|
| 14521 |
"train_batch_size": 4,
|
| 14522 |
"trial_name": null,
|
| 14523 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14498 |
"mean_token_accuracy": 0.6602411061525345,
|
| 14499 |
"num_tokens": 29357996.0,
|
| 14500 |
"step": 8050
|
| 14501 |
+
},
|
| 14502 |
+
{
|
| 14503 |
+
"epoch": 61.96153846153846,
|
| 14504 |
+
"grad_norm": 0.0,
|
| 14505 |
+
"learning_rate": 9.73e-06,
|
| 14506 |
+
"loss": 1.6993,
|
| 14507 |
+
"mean_token_accuracy": 0.657492709159851,
|
| 14508 |
+
"num_tokens": 29376683.0,
|
| 14509 |
+
"step": 8055
|
| 14510 |
+
},
|
| 14511 |
+
{
|
| 14512 |
+
"epoch": 62.0,
|
| 14513 |
+
"grad_norm": 0.0,
|
| 14514 |
+
"learning_rate": 9.705e-06,
|
| 14515 |
+
"loss": 1.7704,
|
| 14516 |
+
"mean_token_accuracy": 0.6440939038991929,
|
| 14517 |
+
"num_tokens": 29394510.0,
|
| 14518 |
+
"step": 8060
|
| 14519 |
}
|
| 14520 |
],
|
| 14521 |
"logging_steps": 5,
|
|
|
|
| 14535 |
"attributes": {}
|
| 14536 |
}
|
| 14537 |
},
|
| 14538 |
+
"total_flos": 1.4902775672949965e+18,
|
| 14539 |
"train_batch_size": 4,
|
| 14540 |
"trial_name": null,
|
| 14541 |
"trial_params": null
|