Training in progress, step 220, 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:e7284ff6993176e5c2cce8f3204becd35194620070a89d258968ea4b7016897b
|
| 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 sha256:528fc92511141c1c16ea6a1d7f747580ca0c167789a0bbf01633b64661ef0ff0
|
| 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 sha256:4afaaa6ef87f5a075f6af75f3517185bee4e1aad08d25d647ed4bfec9e9e8bfd
|
| 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": 1.
|
| 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,
|
|
@@ -386,6 +386,24 @@
|
|
| 386 |
"mean_token_accuracy": 0.6415642440319062,
|
| 387 |
"num_tokens": 765489.0,
|
| 388 |
"step": 210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 389 |
}
|
| 390 |
],
|
| 391 |
"logging_steps": 5,
|
|
@@ -405,7 +423,7 @@
|
|
| 405 |
"attributes": {}
|
| 406 |
}
|
| 407 |
},
|
| 408 |
-
"total_flos":
|
| 409 |
"train_batch_size": 4,
|
| 410 |
"trial_name": null,
|
| 411 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 386 |
"mean_token_accuracy": 0.6415642440319062,
|
| 387 |
"num_tokens": 765489.0,
|
| 388 |
"step": 210
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6538461538461537,
|
| 392 |
+
"grad_norm": 0.0,
|
| 393 |
+
"learning_rate": 4.893e-05,
|
| 394 |
+
"loss": 1.6952,
|
| 395 |
+
"mean_token_accuracy": 0.6612388670444489,
|
| 396 |
+
"num_tokens": 783973.0,
|
| 397 |
+
"step": 215
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.6923076923076923,
|
| 401 |
+
"grad_norm": 0.0,
|
| 402 |
+
"learning_rate": 4.8905e-05,
|
| 403 |
+
"loss": 1.7186,
|
| 404 |
+
"mean_token_accuracy": 0.6559958964586258,
|
| 405 |
+
"num_tokens": 802295.0,
|
| 406 |
+
"step": 220
|
| 407 |
}
|
| 408 |
],
|
| 409 |
"logging_steps": 5,
|
|
|
|
| 423 |
"attributes": {}
|
| 424 |
}
|
| 425 |
},
|
| 426 |
+
"total_flos": 4.069128448180224e+16,
|
| 427 |
"train_batch_size": 4,
|
| 428 |
"trial_name": null,
|
| 429 |
"trial_params": null
|