Training in progress, step 250, 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 sha256:0f68270209d0eaa47326bd072c3b05ef3ca20508d08728adc43ed5afca12d8b7
|
| 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 sha256:2d60141e82f3920359a4ddcb3e83837404115cc64e87c49de4f2285e92191b0a
|
| 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:c7bba56bb39bee3e3a9155e82f365a0e53bce3c5c46d304d3b1aa431bf300109
|
| 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,
|
|
@@ -440,6 +440,24 @@
|
|
| 440 |
"mean_token_accuracy": 0.6505926042795181,
|
| 441 |
"num_tokens": 874848.0,
|
| 442 |
"step": 240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 443 |
}
|
| 444 |
],
|
| 445 |
"logging_steps": 5,
|
|
@@ -459,7 +477,7 @@
|
|
| 459 |
"attributes": {}
|
| 460 |
}
|
| 461 |
},
|
| 462 |
-
"total_flos": 4.
|
| 463 |
"train_batch_size": 4,
|
| 464 |
"trial_name": null,
|
| 465 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 440 |
"mean_token_accuracy": 0.6505926042795181,
|
| 441 |
"num_tokens": 874848.0,
|
| 442 |
"step": 240
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.8846153846153846,
|
| 446 |
+
"grad_norm": 0.0,
|
| 447 |
+
"learning_rate": 4.8780000000000004e-05,
|
| 448 |
+
"loss": 1.7598,
|
| 449 |
+
"mean_token_accuracy": 0.6512235313653946,
|
| 450 |
+
"num_tokens": 893014.0,
|
| 451 |
+
"step": 245
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9230769230769231,
|
| 455 |
+
"grad_norm": 0.0,
|
| 456 |
+
"learning_rate": 4.8755e-05,
|
| 457 |
+
"loss": 1.748,
|
| 458 |
+
"mean_token_accuracy": 0.6448923200368881,
|
| 459 |
+
"num_tokens": 911604.0,
|
| 460 |
+
"step": 250
|
| 461 |
}
|
| 462 |
],
|
| 463 |
"logging_steps": 5,
|
|
|
|
| 477 |
"attributes": {}
|
| 478 |
}
|
| 479 |
},
|
| 480 |
+
"total_flos": 4.623347058130944e+16,
|
| 481 |
"train_batch_size": 4,
|
| 482 |
"trial_name": null,
|
| 483 |
"trial_params": null
|