Training in progress, step 9670, 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:d8bb2e3b14b99924cf3972ecc39c5cf52a5d15965c339d517a33a83b4693a9dc
|
| 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:b7ecae1c300f20ad580f0c1b88b22cf71a2b96d50c89306f3c5af24184ac138d
|
| 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 sha256:7e9286444dd9239f86a922634e89fd083e482e6b3c22d98c3439923b2e16bf0f
|
| 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": 74.
|
| 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,
|
|
@@ -17396,6 +17396,24 @@
|
|
| 17396 |
"mean_token_accuracy": 0.6594295680522919,
|
| 17397 |
"num_tokens": 35227948.0,
|
| 17398 |
"step": 9660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17399 |
}
|
| 17400 |
],
|
| 17401 |
"logging_steps": 5,
|
|
@@ -17415,7 +17433,7 @@
|
|
| 17415 |
"attributes": {}
|
| 17416 |
}
|
| 17417 |
},
|
| 17418 |
-
"total_flos": 1.
|
| 17419 |
"train_batch_size": 4,
|
| 17420 |
"trial_name": null,
|
| 17421 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17396 |
"mean_token_accuracy": 0.6594295680522919,
|
| 17397 |
"num_tokens": 35227948.0,
|
| 17398 |
"step": 9660
|
| 17399 |
+
},
|
| 17400 |
+
{
|
| 17401 |
+
"epoch": 74.34615384615384,
|
| 17402 |
+
"grad_norm": 0.0,
|
| 17403 |
+
"learning_rate": 1.68e-06,
|
| 17404 |
+
"loss": 1.7291,
|
| 17405 |
+
"mean_token_accuracy": 0.6519060641527176,
|
| 17406 |
+
"num_tokens": 35246383.0,
|
| 17407 |
+
"step": 9665
|
| 17408 |
+
},
|
| 17409 |
+
{
|
| 17410 |
+
"epoch": 74.38461538461539,
|
| 17411 |
+
"grad_norm": 0.0,
|
| 17412 |
+
"learning_rate": 1.655e-06,
|
| 17413 |
+
"loss": 1.7533,
|
| 17414 |
+
"mean_token_accuracy": 0.6488317787647248,
|
| 17415 |
+
"num_tokens": 35264529.0,
|
| 17416 |
+
"step": 9670
|
| 17417 |
}
|
| 17418 |
],
|
| 17419 |
"logging_steps": 5,
|
|
|
|
| 17433 |
"attributes": {}
|
| 17434 |
}
|
| 17435 |
},
|
| 17436 |
+
"total_flos": 1.788311740836741e+18,
|
| 17437 |
"train_batch_size": 4,
|
| 17438 |
"trial_name": null,
|
| 17439 |
"trial_params": null
|