training state at step 30
Browse files- trainer_state.json +78 -3
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -367,6 +367,81 @@
|
|
| 367 |
"eval_samples_per_second": 1.138,
|
| 368 |
"eval_steps_per_second": 0.569,
|
| 369 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 370 |
}
|
| 371 |
],
|
| 372 |
"logging_steps": 1,
|
|
@@ -386,7 +461,7 @@
|
|
| 386 |
"attributes": {}
|
| 387 |
}
|
| 388 |
},
|
| 389 |
-
"total_flos": 3.
|
| 390 |
"train_batch_size": 2,
|
| 391 |
"trial_name": null,
|
| 392 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.41379310344827586,
|
| 5 |
"eval_steps": 1,
|
| 6 |
+
"global_step": 30,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 367 |
"eval_samples_per_second": 1.138,
|
| 368 |
"eval_steps_per_second": 0.569,
|
| 369 |
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.3448275862068966,
|
| 373 |
+
"grad_norm": 2.2879106998443604,
|
| 374 |
+
"learning_rate": 4.997050398198977e-05,
|
| 375 |
+
"loss": 1.5164,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.3448275862068966,
|
| 380 |
+
"eval_loss": 1.0196115970611572,
|
| 381 |
+
"eval_runtime": 17.9439,
|
| 382 |
+
"eval_samples_per_second": 1.115,
|
| 383 |
+
"eval_steps_per_second": 0.557,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.3586206896551724,
|
| 388 |
+
"grad_norm": 2.319134473800659,
|
| 389 |
+
"learning_rate": 4.9947570655942796e-05,
|
| 390 |
+
"loss": 1.5282,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.3586206896551724,
|
| 395 |
+
"eval_loss": 1.013381004333496,
|
| 396 |
+
"eval_runtime": 17.7628,
|
| 397 |
+
"eval_samples_per_second": 1.126,
|
| 398 |
+
"eval_steps_per_second": 0.563,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.3724137931034483,
|
| 403 |
+
"grad_norm": 2.259608745574951,
|
| 404 |
+
"learning_rate": 4.991809526186424e-05,
|
| 405 |
+
"loss": 1.4901,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.3724137931034483,
|
| 410 |
+
"eval_loss": 1.0091207027435303,
|
| 411 |
+
"eval_runtime": 17.619,
|
| 412 |
+
"eval_samples_per_second": 1.135,
|
| 413 |
+
"eval_steps_per_second": 0.568,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.38620689655172413,
|
| 418 |
+
"grad_norm": 2.2252631187438965,
|
| 419 |
+
"learning_rate": 4.988208552916535e-05,
|
| 420 |
+
"loss": 1.5518,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.38620689655172413,
|
| 425 |
+
"eval_loss": 1.0063353776931763,
|
| 426 |
+
"eval_runtime": 17.4778,
|
| 427 |
+
"eval_samples_per_second": 1.144,
|
| 428 |
+
"eval_steps_per_second": 0.572,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4,
|
| 433 |
+
"grad_norm": 2.2154901027679443,
|
| 434 |
+
"learning_rate": 4.983955090077444e-05,
|
| 435 |
+
"loss": 1.4682,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.4,
|
| 440 |
+
"eval_loss": 0.99261075258255,
|
| 441 |
+
"eval_runtime": 17.4894,
|
| 442 |
+
"eval_samples_per_second": 1.144,
|
| 443 |
+
"eval_steps_per_second": 0.572,
|
| 444 |
+
"step": 29
|
| 445 |
}
|
| 446 |
],
|
| 447 |
"logging_steps": 1,
|
|
|
|
| 461 |
"attributes": {}
|
| 462 |
}
|
| 463 |
},
|
| 464 |
+
"total_flos": 3.786199396619059e+16,
|
| 465 |
"train_batch_size": 2,
|
| 466 |
"trial_name": null,
|
| 467 |
"trial_params": null
|