Training in progress, step 100, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9632e1bff5f17086ad1def3c234561955e256311bd9f2a969b68fe2f4ddf2998
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671466706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f439b78259c1c2fc57babea1b73c33d1273fe60dbc47df07b0b26b74a24f20
|
| 3 |
size 671466706
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3a4ac9a9f9986597647c8a0e867c4f72eeab3c3d1e43c8f960b44a326903986
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9497c8a8d24f41cf5c0069eb540cebc255b08ff9535263160a28759922eb3e3
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a425f1c819a05abc0c03ce33851974f4dbcd20cfb9efd9dad629120a2b5f92
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81cc0f4203a4456d3477f2e743f020a5c58989c2a1cd33891ca202c49ac579ac
|
| 3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25aa2f483294991f80a6c969eac63941b33052740b29e7eb2c606cbf255fbb72
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7638214826583862,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -381,6 +381,372 @@
|
|
| 381 |
"eval_samples_per_second": 15.294,
|
| 382 |
"eval_steps_per_second": 3.976,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -395,7 +761,7 @@
|
|
| 395 |
"early_stopping_threshold": 0.0
|
| 396 |
},
|
| 397 |
"attributes": {
|
| 398 |
-
"early_stopping_patience_counter":
|
| 399 |
}
|
| 400 |
},
|
| 401 |
"TrainerControl": {
|
|
@@ -404,12 +770,12 @@
|
|
| 404 |
"should_evaluate": false,
|
| 405 |
"should_log": false,
|
| 406 |
"should_save": true,
|
| 407 |
-
"should_training_stop":
|
| 408 |
},
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 1,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7638214826583862,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 3.67816091954023,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 381 |
"eval_samples_per_second": 15.294,
|
| 382 |
"eval_steps_per_second": 3.976,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.8758620689655172,
|
| 387 |
+
"grad_norm": 0.21353751420974731,
|
| 388 |
+
"learning_rate": 6.311147670162576e-05,
|
| 389 |
+
"loss": 0.663,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.9126436781609195,
|
| 394 |
+
"grad_norm": 0.2514137327671051,
|
| 395 |
+
"learning_rate": 6.177090264736525e-05,
|
| 396 |
+
"loss": 0.7005,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.9494252873563218,
|
| 401 |
+
"grad_norm": 0.222330704331398,
|
| 402 |
+
"learning_rate": 6.042415061148954e-05,
|
| 403 |
+
"loss": 0.7893,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.986206896551724,
|
| 408 |
+
"grad_norm": 0.2652716040611267,
|
| 409 |
+
"learning_rate": 5.907244941233371e-05,
|
| 410 |
+
"loss": 0.7701,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.0229885057471266,
|
| 415 |
+
"grad_norm": 0.20406022667884827,
|
| 416 |
+
"learning_rate": 5.771703238400288e-05,
|
| 417 |
+
"loss": 0.557,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.0597701149425287,
|
| 422 |
+
"grad_norm": 0.1386067122220993,
|
| 423 |
+
"learning_rate": 5.635913625104e-05,
|
| 424 |
+
"loss": 0.5773,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.0965517241379312,
|
| 429 |
+
"grad_norm": 0.18351519107818604,
|
| 430 |
+
"learning_rate": 5.500000000000001e-05,
|
| 431 |
+
"loss": 0.6024,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.1333333333333333,
|
| 436 |
+
"grad_norm": 0.19990648329257965,
|
| 437 |
+
"learning_rate": 5.364086374896001e-05,
|
| 438 |
+
"loss": 0.6177,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.170114942528736,
|
| 443 |
+
"grad_norm": 0.19572705030441284,
|
| 444 |
+
"learning_rate": 5.2282967615997125e-05,
|
| 445 |
+
"loss": 0.6475,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.206896551724138,
|
| 450 |
+
"grad_norm": 0.23045289516448975,
|
| 451 |
+
"learning_rate": 5.092755058766631e-05,
|
| 452 |
+
"loss": 0.7089,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.2436781609195404,
|
| 457 |
+
"grad_norm": 0.2674247622489929,
|
| 458 |
+
"learning_rate": 4.9575849388510473e-05,
|
| 459 |
+
"loss": 0.6667,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.2804597701149425,
|
| 464 |
+
"grad_norm": 0.2119389772415161,
|
| 465 |
+
"learning_rate": 4.8229097352634765e-05,
|
| 466 |
+
"loss": 0.5402,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.317241379310345,
|
| 471 |
+
"grad_norm": 0.19508974254131317,
|
| 472 |
+
"learning_rate": 4.688852329837424e-05,
|
| 473 |
+
"loss": 0.6063,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.354022988505747,
|
| 478 |
+
"grad_norm": 0.19634996354579926,
|
| 479 |
+
"learning_rate": 4.5555350407081863e-05,
|
| 480 |
+
"loss": 0.6404,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.3908045977011496,
|
| 485 |
+
"grad_norm": 0.21487970650196075,
|
| 486 |
+
"learning_rate": 4.423079510705992e-05,
|
| 487 |
+
"loss": 0.6663,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.4275862068965517,
|
| 492 |
+
"grad_norm": 0.2401036024093628,
|
| 493 |
+
"learning_rate": 4.291606596365304e-05,
|
| 494 |
+
"loss": 0.6801,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.464367816091954,
|
| 499 |
+
"grad_norm": 0.2552790343761444,
|
| 500 |
+
"learning_rate": 4.161236257651587e-05,
|
| 501 |
+
"loss": 0.7218,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.5011494252873563,
|
| 506 |
+
"grad_norm": 0.4108894467353821,
|
| 507 |
+
"learning_rate": 4.032087448506089e-05,
|
| 508 |
+
"loss": 0.6251,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.5379310344827584,
|
| 513 |
+
"grad_norm": 0.1864066869020462,
|
| 514 |
+
"learning_rate": 3.904278008308589e-05,
|
| 515 |
+
"loss": 0.5174,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.574712643678161,
|
| 520 |
+
"grad_norm": 0.20834487676620483,
|
| 521 |
+
"learning_rate": 3.777924554357096e-05,
|
| 522 |
+
"loss": 0.5929,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.6114942528735634,
|
| 527 |
+
"grad_norm": 0.2088489681482315,
|
| 528 |
+
"learning_rate": 3.653142375462596e-05,
|
| 529 |
+
"loss": 0.6374,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.6482758620689655,
|
| 534 |
+
"grad_norm": 0.25101637840270996,
|
| 535 |
+
"learning_rate": 3.530045326755967e-05,
|
| 536 |
+
"loss": 0.6594,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.6850574712643676,
|
| 541 |
+
"grad_norm": 0.27176716923713684,
|
| 542 |
+
"learning_rate": 3.408745725803042e-05,
|
| 543 |
+
"loss": 0.6788,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.72183908045977,
|
| 548 |
+
"grad_norm": 0.3027721047401428,
|
| 549 |
+
"learning_rate": 3.2893542501225534e-05,
|
| 550 |
+
"loss": 0.7124,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.7586206896551726,
|
| 555 |
+
"grad_norm": 0.27195319533348083,
|
| 556 |
+
"learning_rate": 3.1719798362005444e-05,
|
| 557 |
+
"loss": 0.5897,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.7586206896551726,
|
| 562 |
+
"eval_loss": 0.7599511742591858,
|
| 563 |
+
"eval_runtime": 3.275,
|
| 564 |
+
"eval_samples_per_second": 15.267,
|
| 565 |
+
"eval_steps_per_second": 3.969,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.7954022988505747,
|
| 570 |
+
"grad_norm": 0.17247594892978668,
|
| 571 |
+
"learning_rate": 3.056729580093346e-05,
|
| 572 |
+
"loss": 0.5506,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.8321839080459768,
|
| 577 |
+
"grad_norm": 0.2535310685634613,
|
| 578 |
+
"learning_rate": 2.9437086397097995e-05,
|
| 579 |
+
"loss": 0.6236,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.8689655172413793,
|
| 584 |
+
"grad_norm": 0.2153378278017044,
|
| 585 |
+
"learning_rate": 2.8330201388619253e-05,
|
| 586 |
+
"loss": 0.6671,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.905747126436782,
|
| 591 |
+
"grad_norm": 0.23758837580680847,
|
| 592 |
+
"learning_rate": 2.7247650731715564e-05,
|
| 593 |
+
"loss": 0.6473,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.942528735632184,
|
| 598 |
+
"grad_norm": 0.25426074862480164,
|
| 599 |
+
"learning_rate": 2.6190422179188044e-05,
|
| 600 |
+
"loss": 0.6725,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.979310344827586,
|
| 605 |
+
"grad_norm": 0.3190159499645233,
|
| 606 |
+
"learning_rate": 2.515948037916423e-05,
|
| 607 |
+
"loss": 0.6748,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.0160919540229885,
|
| 612 |
+
"grad_norm": 0.26219987869262695,
|
| 613 |
+
"learning_rate": 2.415576599492321e-05,
|
| 614 |
+
"loss": 0.5995,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.052873563218391,
|
| 619 |
+
"grad_norm": 0.16341930627822876,
|
| 620 |
+
"learning_rate": 2.3180194846605367e-05,
|
| 621 |
+
"loss": 0.5468,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.089655172413793,
|
| 626 |
+
"grad_norm": 0.18180637061595917,
|
| 627 |
+
"learning_rate": 2.223365707558953e-05,
|
| 628 |
+
"loss": 0.5735,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.1264367816091956,
|
| 633 |
+
"grad_norm": 0.21310141682624817,
|
| 634 |
+
"learning_rate": 2.1317016332300447e-05,
|
| 635 |
+
"loss": 0.636,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 3.1632183908045977,
|
| 640 |
+
"grad_norm": 0.2241068184375763,
|
| 641 |
+
"learning_rate": 2.043110898818738e-05,
|
| 642 |
+
"loss": 0.6183,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 3.2,
|
| 647 |
+
"grad_norm": 0.2601270079612732,
|
| 648 |
+
"learning_rate": 1.9576743372592747e-05,
|
| 649 |
+
"loss": 0.6213,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 3.2367816091954023,
|
| 654 |
+
"grad_norm": 0.3257927894592285,
|
| 655 |
+
"learning_rate": 1.875469903520743e-05,
|
| 656 |
+
"loss": 0.6393,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 3.2735632183908048,
|
| 661 |
+
"grad_norm": 0.24459469318389893,
|
| 662 |
+
"learning_rate": 1.7965726034785466e-05,
|
| 663 |
+
"loss": 0.5094,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 3.310344827586207,
|
| 668 |
+
"grad_norm": 0.19675396382808685,
|
| 669 |
+
"learning_rate": 1.7210544254767098e-05,
|
| 670 |
+
"loss": 0.5474,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.3471264367816094,
|
| 675 |
+
"grad_norm": 0.2235768735408783,
|
| 676 |
+
"learning_rate": 1.648984274643487e-05,
|
| 677 |
+
"loss": 0.5492,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 3.3839080459770114,
|
| 682 |
+
"grad_norm": 0.24168157577514648,
|
| 683 |
+
"learning_rate": 1.58042791002018e-05,
|
| 684 |
+
"loss": 0.6109,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 3.420689655172414,
|
| 689 |
+
"grad_norm": 0.2579849064350128,
|
| 690 |
+
"learning_rate": 1.515447884560556e-05,
|
| 691 |
+
"loss": 0.6455,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.457471264367816,
|
| 696 |
+
"grad_norm": 0.3024696111679077,
|
| 697 |
+
"learning_rate": 1.4541034880555838e-05,
|
| 698 |
+
"loss": 0.6716,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.4942528735632186,
|
| 703 |
+
"grad_norm": 0.3916833698749542,
|
| 704 |
+
"learning_rate": 1.3964506930355947e-05,
|
| 705 |
+
"loss": 0.6166,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 3.5310344827586206,
|
| 710 |
+
"grad_norm": 0.23013140261173248,
|
| 711 |
+
"learning_rate": 1.3425421036992098e-05,
|
| 712 |
+
"loss": 0.5145,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.5678160919540227,
|
| 717 |
+
"grad_norm": 0.2350182831287384,
|
| 718 |
+
"learning_rate": 1.292426907915634e-05,
|
| 719 |
+
"loss": 0.5648,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.6045977011494252,
|
| 724 |
+
"grad_norm": 0.24683219194412231,
|
| 725 |
+
"learning_rate": 1.2461508323441185e-05,
|
| 726 |
+
"loss": 0.6,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 3.6413793103448278,
|
| 731 |
+
"grad_norm": 0.2576511800289154,
|
| 732 |
+
"learning_rate": 1.203756100711545e-05,
|
| 733 |
+
"loss": 0.6375,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.67816091954023,
|
| 738 |
+
"grad_norm": 0.31485050916671753,
|
| 739 |
+
"learning_rate": 1.1652813952861769e-05,
|
| 740 |
+
"loss": 0.6974,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.67816091954023,
|
| 745 |
+
"eval_loss": 0.764268159866333,
|
| 746 |
+
"eval_runtime": 3.2754,
|
| 747 |
+
"eval_samples_per_second": 15.265,
|
| 748 |
+
"eval_steps_per_second": 3.969,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 761 |
"early_stopping_threshold": 0.0
|
| 762 |
},
|
| 763 |
"attributes": {
|
| 764 |
+
"early_stopping_patience_counter": 1
|
| 765 |
}
|
| 766 |
},
|
| 767 |
"TrainerControl": {
|
|
|
|
| 770 |
"should_evaluate": false,
|
| 771 |
"should_log": false,
|
| 772 |
"should_save": true,
|
| 773 |
+
"should_training_stop": true
|
| 774 |
},
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 1.1966940149176074e+18,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|