Training in progress, step 2980, 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 sha256:6089f6b2d3b6a280d26789a304fcfde27ddb5ff002ba8855aca22705c536d37e
|
| 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 sha256:6f95de6db78f2a80c80212513cb636935b979f404f078755f93942cd2460052d
|
| 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 sha256:8a76a2933dc00ec7ae197b81fca3da9c2907aadc732447bddad1c46392450afa
|
| 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": 22.
|
| 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,
|
|
@@ -5354,6 +5354,24 @@
|
|
| 5354 |
"mean_token_accuracy": 0.6510158330202103,
|
| 5355 |
"num_tokens": 10831125.0,
|
| 5356 |
"step": 2970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5357 |
}
|
| 5358 |
],
|
| 5359 |
"logging_steps": 5,
|
|
@@ -5373,7 +5391,7 @@
|
|
| 5373 |
"attributes": {}
|
| 5374 |
}
|
| 5375 |
},
|
| 5376 |
-
"total_flos": 5.
|
| 5377 |
"train_batch_size": 4,
|
| 5378 |
"trial_name": null,
|
| 5379 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5354 |
"mean_token_accuracy": 0.6510158330202103,
|
| 5355 |
"num_tokens": 10831125.0,
|
| 5356 |
"step": 2970
|
| 5357 |
+
},
|
| 5358 |
+
{
|
| 5359 |
+
"epoch": 22.884615384615383,
|
| 5360 |
+
"grad_norm": 0.0,
|
| 5361 |
+
"learning_rate": 3.5130000000000004e-05,
|
| 5362 |
+
"loss": 1.7005,
|
| 5363 |
+
"mean_token_accuracy": 0.662487056851387,
|
| 5364 |
+
"num_tokens": 10849387.0,
|
| 5365 |
+
"step": 2975
|
| 5366 |
+
},
|
| 5367 |
+
{
|
| 5368 |
+
"epoch": 22.923076923076923,
|
| 5369 |
+
"grad_norm": 0.0,
|
| 5370 |
+
"learning_rate": 3.5105e-05,
|
| 5371 |
+
"loss": 1.7911,
|
| 5372 |
+
"mean_token_accuracy": 0.6427533149719238,
|
| 5373 |
+
"num_tokens": 10867773.0,
|
| 5374 |
+
"step": 2980
|
| 5375 |
}
|
| 5376 |
],
|
| 5377 |
"logging_steps": 5,
|
|
|
|
| 5391 |
"attributes": {}
|
| 5392 |
}
|
| 5393 |
},
|
| 5394 |
+
"total_flos": 5.507445222309888e+17,
|
| 5395 |
"train_batch_size": 4,
|
| 5396 |
"trial_name": null,
|
| 5397 |
"trial_params": null
|