Training in progress, step 240, 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 sha256:83920dd8f3ee22c3c310936f79316e323e7ac1207184e836ee0a43b2c912b268
|
| 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 sha256:81111bba7fcb44be8f8d3adf18ca0b69c5dd07c13eea088731d5a1486e060910
|
| 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 sha256:0aca53917bb866af45a787894c26bccdc5ff511b84514674a7d7fe57ca88c9bb
|
| 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,
|
|
@@ -422,6 +422,24 @@
|
|
| 422 |
"mean_token_accuracy": 0.6462311297655106,
|
| 423 |
"num_tokens": 838437.0,
|
| 424 |
"step": 230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 425 |
}
|
| 426 |
],
|
| 427 |
"logging_steps": 5,
|
|
@@ -441,7 +459,7 @@
|
|
| 441 |
"attributes": {}
|
| 442 |
}
|
| 443 |
},
|
| 444 |
-
"total_flos": 4.
|
| 445 |
"train_batch_size": 4,
|
| 446 |
"trial_name": null,
|
| 447 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.8461538461538463,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 422 |
"mean_token_accuracy": 0.6462311297655106,
|
| 423 |
"num_tokens": 838437.0,
|
| 424 |
"step": 230
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.8076923076923077,
|
| 428 |
+
"grad_norm": 0.0,
|
| 429 |
+
"learning_rate": 4.8830000000000005e-05,
|
| 430 |
+
"loss": 1.753,
|
| 431 |
+
"mean_token_accuracy": 0.6491482555866241,
|
| 432 |
+
"num_tokens": 856808.0,
|
| 433 |
+
"step": 235
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.8461538461538463,
|
| 437 |
+
"grad_norm": 0.0,
|
| 438 |
+
"learning_rate": 4.8805e-05,
|
| 439 |
+
"loss": 1.756,
|
| 440 |
+
"mean_token_accuracy": 0.6505926042795181,
|
| 441 |
+
"num_tokens": 874848.0,
|
| 442 |
+
"step": 240
|
| 443 |
}
|
| 444 |
],
|
| 445 |
"logging_steps": 5,
|
|
|
|
| 459 |
"attributes": {}
|
| 460 |
}
|
| 461 |
},
|
| 462 |
+
"total_flos": 4.436400491347968e+16,
|
| 463 |
"train_batch_size": 4,
|
| 464 |
"trial_name": null,
|
| 465 |
"trial_params": null
|