Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50899792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca426d6b70c198d2c2f812ce353ad21b626d9231fb8a2e3bbcc002aa97759df9
|
| 3 |
size 50899792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102009558
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b51e19732313b26832a0bfe2f37292bf5d70e151c09e013fd40dd87a17084d9b
|
| 3 |
size 102009558
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab42bf7c0b1143745cac6be25d185daecba57306b31d237ccd6b1214b290f97
|
| 3 |
size 14244
|
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:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,364 @@
|
|
| 373 |
"eval_samples_per_second": 14.061,
|
| 374 |
"eval_steps_per_second": 1.759,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9471560716629028,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.006386511687316388,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 14.061,
|
| 374 |
"eval_steps_per_second": 1.759,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0032571209605313576,
|
| 379 |
+
"grad_norm": 0.35466328263282776,
|
| 380 |
+
"learning_rate": 3.969463130731183e-06,
|
| 381 |
+
"loss": 1.0494,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0033209860774045218,
|
| 386 |
+
"grad_norm": 0.4603920578956604,
|
| 387 |
+
"learning_rate": 3.8772424536302565e-06,
|
| 388 |
+
"loss": 0.8436,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0033848511942776854,
|
| 393 |
+
"grad_norm": 0.4390234351158142,
|
| 394 |
+
"learning_rate": 3.782248193514766e-06,
|
| 395 |
+
"loss": 0.8673,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.0034487163111508496,
|
| 400 |
+
"grad_norm": 0.43319058418273926,
|
| 401 |
+
"learning_rate": 3.684671656182497e-06,
|
| 402 |
+
"loss": 1.0298,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.0035125814280240132,
|
| 407 |
+
"grad_norm": 0.46855083107948303,
|
| 408 |
+
"learning_rate": 3.5847093477938955e-06,
|
| 409 |
+
"loss": 0.7543,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.0035764465448971773,
|
| 414 |
+
"grad_norm": 0.48883286118507385,
|
| 415 |
+
"learning_rate": 3.4825625791348093e-06,
|
| 416 |
+
"loss": 0.7879,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.003640311661770341,
|
| 421 |
+
"grad_norm": 0.4997875392436981,
|
| 422 |
+
"learning_rate": 3.3784370602033572e-06,
|
| 423 |
+
"loss": 0.8255,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0037041767786435047,
|
| 428 |
+
"grad_norm": 0.48925676941871643,
|
| 429 |
+
"learning_rate": 3.272542485937369e-06,
|
| 430 |
+
"loss": 0.8007,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.003768041895516669,
|
| 435 |
+
"grad_norm": 0.5267242193222046,
|
| 436 |
+
"learning_rate": 3.165092113916688e-06,
|
| 437 |
+
"loss": 0.7858,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0038319070123898325,
|
| 442 |
+
"grad_norm": 0.5722787380218506,
|
| 443 |
+
"learning_rate": 3.056302334890786e-06,
|
| 444 |
+
"loss": 0.832,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0038957721292629966,
|
| 449 |
+
"grad_norm": 0.5531828999519348,
|
| 450 |
+
"learning_rate": 2.946392236996592e-06,
|
| 451 |
+
"loss": 0.8113,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.00395963724613616,
|
| 456 |
+
"grad_norm": 0.5620059370994568,
|
| 457 |
+
"learning_rate": 2.835583164544139e-06,
|
| 458 |
+
"loss": 0.8526,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.004023502363009324,
|
| 463 |
+
"grad_norm": 0.5260962247848511,
|
| 464 |
+
"learning_rate": 2.724098272258584e-06,
|
| 465 |
+
"loss": 0.8254,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0040873674798824885,
|
| 470 |
+
"grad_norm": 0.5846118927001953,
|
| 471 |
+
"learning_rate": 2.6121620758762877e-06,
|
| 472 |
+
"loss": 0.8756,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.004151232596755652,
|
| 477 |
+
"grad_norm": 0.591052770614624,
|
| 478 |
+
"learning_rate": 2.5e-06,
|
| 479 |
+
"loss": 0.8552,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.004215097713628816,
|
| 484 |
+
"grad_norm": 0.5996527671813965,
|
| 485 |
+
"learning_rate": 2.3878379241237136e-06,
|
| 486 |
+
"loss": 0.7867,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0042789628305019796,
|
| 491 |
+
"grad_norm": 0.6025989055633545,
|
| 492 |
+
"learning_rate": 2.2759017277414165e-06,
|
| 493 |
+
"loss": 0.8736,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.004342827947375144,
|
| 498 |
+
"grad_norm": 0.6134032011032104,
|
| 499 |
+
"learning_rate": 2.1644168354558623e-06,
|
| 500 |
+
"loss": 0.8842,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.004406693064248308,
|
| 505 |
+
"grad_norm": 0.6772037744522095,
|
| 506 |
+
"learning_rate": 2.053607763003409e-06,
|
| 507 |
+
"loss": 0.8653,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.0044705581811214715,
|
| 512 |
+
"grad_norm": 0.554199755191803,
|
| 513 |
+
"learning_rate": 1.9436976651092143e-06,
|
| 514 |
+
"loss": 0.8358,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.004534423297994635,
|
| 519 |
+
"grad_norm": 0.6779680252075195,
|
| 520 |
+
"learning_rate": 1.8349078860833125e-06,
|
| 521 |
+
"loss": 0.9094,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.004598288414867799,
|
| 526 |
+
"grad_norm": 0.6369734406471252,
|
| 527 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 528 |
+
"loss": 0.8661,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.004662153531740963,
|
| 533 |
+
"grad_norm": 0.6391808390617371,
|
| 534 |
+
"learning_rate": 1.6215629397966432e-06,
|
| 535 |
+
"loss": 0.9004,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.004726018648614127,
|
| 540 |
+
"grad_norm": 0.6250472068786621,
|
| 541 |
+
"learning_rate": 1.5174374208651913e-06,
|
| 542 |
+
"loss": 0.8611,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.004789883765487291,
|
| 547 |
+
"grad_norm": 0.7451426386833191,
|
| 548 |
+
"learning_rate": 1.415290652206105e-06,
|
| 549 |
+
"loss": 0.9557,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.004853748882360454,
|
| 554 |
+
"grad_norm": 0.6133967041969299,
|
| 555 |
+
"learning_rate": 1.3153283438175036e-06,
|
| 556 |
+
"loss": 0.9089,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.004917613999233619,
|
| 561 |
+
"grad_norm": 0.7205358743667603,
|
| 562 |
+
"learning_rate": 1.217751806485235e-06,
|
| 563 |
+
"loss": 0.9354,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.004981479116106783,
|
| 568 |
+
"grad_norm": 0.7420779466629028,
|
| 569 |
+
"learning_rate": 1.122757546369744e-06,
|
| 570 |
+
"loss": 1.0057,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.005045344232979946,
|
| 575 |
+
"grad_norm": 0.7057881951332092,
|
| 576 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 577 |
+
"loss": 0.9137,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.00510920934985311,
|
| 582 |
+
"grad_norm": 0.7535944581031799,
|
| 583 |
+
"learning_rate": 9.412754953531664e-07,
|
| 584 |
+
"loss": 0.9348,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.005173074466726274,
|
| 589 |
+
"grad_norm": 0.6707415580749512,
|
| 590 |
+
"learning_rate": 8.551531851507186e-07,
|
| 591 |
+
"loss": 0.8909,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.005236939583599438,
|
| 596 |
+
"grad_norm": 0.7699809074401855,
|
| 597 |
+
"learning_rate": 7.723433775328385e-07,
|
| 598 |
+
"loss": 1.0632,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.005300804700472602,
|
| 603 |
+
"grad_norm": 0.7439144849777222,
|
| 604 |
+
"learning_rate": 6.930128404315214e-07,
|
| 605 |
+
"loss": 0.9034,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.005364669817345766,
|
| 610 |
+
"grad_norm": 0.7623469829559326,
|
| 611 |
+
"learning_rate": 6.17321334990973e-07,
|
| 612 |
+
"loss": 0.9428,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.005428534934218929,
|
| 617 |
+
"grad_norm": 0.7557162642478943,
|
| 618 |
+
"learning_rate": 5.454212938299256e-07,
|
| 619 |
+
"loss": 0.9681,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.005492400051092094,
|
| 624 |
+
"grad_norm": 0.8695307374000549,
|
| 625 |
+
"learning_rate": 4.774575140626317e-07,
|
| 626 |
+
"loss": 1.0252,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.0055562651679652575,
|
| 631 |
+
"grad_norm": 0.8959054946899414,
|
| 632 |
+
"learning_rate": 4.1356686569674344e-07,
|
| 633 |
+
"loss": 1.0098,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.005620130284838421,
|
| 638 |
+
"grad_norm": 0.8213502764701843,
|
| 639 |
+
"learning_rate": 3.538780159953348e-07,
|
| 640 |
+
"loss": 1.0395,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.005683995401711585,
|
| 645 |
+
"grad_norm": 0.8729150891304016,
|
| 646 |
+
"learning_rate": 2.98511170358155e-07,
|
| 647 |
+
"loss": 1.0537,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.005747860518584749,
|
| 652 |
+
"grad_norm": 0.8639337420463562,
|
| 653 |
+
"learning_rate": 2.4757783024395244e-07,
|
| 654 |
+
"loss": 1.1122,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.005811725635457913,
|
| 659 |
+
"grad_norm": 0.8852090239524841,
|
| 660 |
+
"learning_rate": 2.0118056862137358e-07,
|
| 661 |
+
"loss": 1.1326,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.005875590752331077,
|
| 666 |
+
"grad_norm": 1.0262387990951538,
|
| 667 |
+
"learning_rate": 1.59412823400657e-07,
|
| 668 |
+
"loss": 1.2442,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.0059394558692042404,
|
| 673 |
+
"grad_norm": 1.0481868982315063,
|
| 674 |
+
"learning_rate": 1.223587092621162e-07,
|
| 675 |
+
"loss": 1.1703,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.006003320986077404,
|
| 680 |
+
"grad_norm": 1.0297393798828125,
|
| 681 |
+
"learning_rate": 9.00928482603669e-08,
|
| 682 |
+
"loss": 1.0855,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.006067186102950569,
|
| 687 |
+
"grad_norm": 1.0903443098068237,
|
| 688 |
+
"learning_rate": 6.268021954544095e-08,
|
| 689 |
+
"loss": 1.1983,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.006131051219823732,
|
| 694 |
+
"grad_norm": 0.9865908026695251,
|
| 695 |
+
"learning_rate": 4.017602850342584e-08,
|
| 696 |
+
"loss": 1.0632,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.006194916336696896,
|
| 701 |
+
"grad_norm": 1.1608613729476929,
|
| 702 |
+
"learning_rate": 2.262559558016325e-08,
|
| 703 |
+
"loss": 1.2043,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.00625878145357006,
|
| 708 |
+
"grad_norm": 0.9920202493667603,
|
| 709 |
+
"learning_rate": 1.006426501190233e-08,
|
| 710 |
+
"loss": 1.073,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.006322646570443224,
|
| 715 |
+
"grad_norm": 1.018128514289856,
|
| 716 |
+
"learning_rate": 2.5173336467135266e-09,
|
| 717 |
+
"loss": 1.1236,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.006386511687316388,
|
| 722 |
+
"grad_norm": 1.1295783519744873,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 1.2105,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.006386511687316388,
|
| 729 |
+
"eval_loss": 0.9471560716629028,
|
| 730 |
+
"eval_runtime": 467.8522,
|
| 731 |
+
"eval_samples_per_second": 14.092,
|
| 732 |
+
"eval_steps_per_second": 1.763,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1.672899276570624e+16,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|