Training in progress, step 9660, 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:c7e1bc55d0f45e575b4f5280b3739bfbe279cafdaf45c1a53c8bb2b7af52fc2e
|
| 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:e215ba009b58c94b56107d2e8ddb3075117a05decc885c089f1a70fd35691917
|
| 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 sha256:7262b14e8fc56c29f19ac5b909bcf6fdec1736407a46d6c286a8e99d7758fe87
|
| 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,
|
|
@@ -17378,6 +17378,24 @@
|
|
| 17378 |
"mean_token_accuracy": 0.6455636918544769,
|
| 17379 |
"num_tokens": 35191312.0,
|
| 17380 |
"step": 9650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17381 |
}
|
| 17382 |
],
|
| 17383 |
"logging_steps": 5,
|
|
@@ -17397,7 +17415,7 @@
|
|
| 17397 |
"attributes": {}
|
| 17398 |
}
|
| 17399 |
},
|
| 17400 |
-
"total_flos": 1.
|
| 17401 |
"train_batch_size": 4,
|
| 17402 |
"trial_name": null,
|
| 17403 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17378 |
"mean_token_accuracy": 0.6455636918544769,
|
| 17379 |
"num_tokens": 35191312.0,
|
| 17380 |
"step": 9650
|
| 17381 |
+
},
|
| 17382 |
+
{
|
| 17383 |
+
"epoch": 74.26923076923077,
|
| 17384 |
+
"grad_norm": 0.0,
|
| 17385 |
+
"learning_rate": 1.73e-06,
|
| 17386 |
+
"loss": 1.7323,
|
| 17387 |
+
"mean_token_accuracy": 0.656083607673645,
|
| 17388 |
+
"num_tokens": 35209464.0,
|
| 17389 |
+
"step": 9655
|
| 17390 |
+
},
|
| 17391 |
+
{
|
| 17392 |
+
"epoch": 74.3076923076923,
|
| 17393 |
+
"grad_norm": 0.0,
|
| 17394 |
+
"learning_rate": 1.705e-06,
|
| 17395 |
+
"loss": 1.6952,
|
| 17396 |
+
"mean_token_accuracy": 0.6594295680522919,
|
| 17397 |
+
"num_tokens": 35227948.0,
|
| 17398 |
+
"step": 9660
|
| 17399 |
}
|
| 17400 |
],
|
| 17401 |
"logging_steps": 5,
|
|
|
|
| 17415 |
"attributes": {}
|
| 17416 |
}
|
| 17417 |
},
|
| 17418 |
+
"total_flos": 1.7864384644694016e+18,
|
| 17419 |
"train_batch_size": 4,
|
| 17420 |
"trial_name": null,
|
| 17421 |
"trial_params": null
|