Training in progress, step 200, 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:ebdc2a23fcaef49fa0a83fe2f1a0ac1cc1d5009d8b5ea5628b5a068a25413239
|
| 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 sha256:4e15062ba361330a6f4e31bc3620c10515f66c6e2b9a65eb473461da5704f025
|
| 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 sha256:8060d090b5d773f37886cd22ef5c28ea787abedb1269e9c60004f740842cf68a
|
| 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,
|
|
@@ -350,6 +350,24 @@
|
|
| 350 |
"mean_token_accuracy": 0.6561032950878143,
|
| 351 |
"num_tokens": 692477.0,
|
| 352 |
"step": 190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 353 |
}
|
| 354 |
],
|
| 355 |
"logging_steps": 5,
|
|
@@ -369,7 +387,7 @@
|
|
| 369 |
"attributes": {}
|
| 370 |
}
|
| 371 |
},
|
| 372 |
-
"total_flos": 3.
|
| 373 |
"train_batch_size": 4,
|
| 374 |
"trial_name": null,
|
| 375 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.5384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 350 |
"mean_token_accuracy": 0.6561032950878143,
|
| 351 |
"num_tokens": 692477.0,
|
| 352 |
"step": 190
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.5,
|
| 356 |
+
"grad_norm": 0.0,
|
| 357 |
+
"learning_rate": 4.903e-05,
|
| 358 |
+
"loss": 1.6869,
|
| 359 |
+
"mean_token_accuracy": 0.6576298862695694,
|
| 360 |
+
"num_tokens": 711509.0,
|
| 361 |
+
"step": 195
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5384615384615383,
|
| 365 |
+
"grad_norm": 0.0,
|
| 366 |
+
"learning_rate": 4.9005e-05,
|
| 367 |
+
"loss": 1.8134,
|
| 368 |
+
"mean_token_accuracy": 0.6296403974294662,
|
| 369 |
+
"num_tokens": 728738.0,
|
| 370 |
+
"step": 200
|
| 371 |
}
|
| 372 |
],
|
| 373 |
"logging_steps": 5,
|
|
|
|
| 387 |
"attributes": {}
|
| 388 |
}
|
| 389 |
},
|
| 390 |
+
"total_flos": 3.695171802955776e+16,
|
| 391 |
"train_batch_size": 4,
|
| 392 |
"trial_name": null,
|
| 393 |
"trial_params": null
|