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 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e4f3b58c24f87f6560869f0a57471a3fb26df7400ca06792c4e17e1c1a36ec2
|
| 3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 320194002
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:802142b852ce2beb520e38beb1cb34c6dfe69c4fb8af1c7c85369dfafcf706e7
|
| 3 |
size 320194002
|
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:bc8afd77857ea80d425b1c16cfed4cb483ac5a5abd07b72260c215d556e738be
|
| 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 sha256:52e7e615ef85192a77dfa418d0a1415bde484c32aceb04c8295b02411d9b9920
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7010467052459717,
|
| 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": 9.509,
|
| 382 |
"eval_steps_per_second": 1.331,
|
| 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": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7010467052459717,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 1.3840830449826989,
|
| 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": 9.509,
|
| 382 |
"eval_steps_per_second": 1.331,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.7058823529411765,
|
| 387 |
+
"grad_norm": 9.266826629638672,
|
| 388 |
+
"learning_rate": 0.00023674985042519795,
|
| 389 |
+
"loss": 3.4074,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.7197231833910035,
|
| 394 |
+
"grad_norm": 2.7682924270629883,
|
| 395 |
+
"learning_rate": 0.00023387893552061199,
|
| 396 |
+
"loss": 2.6934,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.7335640138408305,
|
| 401 |
+
"grad_norm": 1.135008454322815,
|
| 402 |
+
"learning_rate": 0.00023096259869272693,
|
| 403 |
+
"loss": 2.7218,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.7474048442906575,
|
| 408 |
+
"grad_norm": 3.1696879863739014,
|
| 409 |
+
"learning_rate": 0.00022800241918938228,
|
| 410 |
+
"loss": 2.8763,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.7612456747404844,
|
| 415 |
+
"grad_norm": 3.2597336769104004,
|
| 416 |
+
"learning_rate": 0.000225,
|
| 417 |
+
"loss": 2.794,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.7750865051903114,
|
| 422 |
+
"grad_norm": 2.9772768020629883,
|
| 423 |
+
"learning_rate": 0.00022195696698753693,
|
| 424 |
+
"loss": 2.9002,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.7889273356401384,
|
| 429 |
+
"grad_norm": 2.6768057346343994,
|
| 430 |
+
"learning_rate": 0.00021887496800805173,
|
| 431 |
+
"loss": 2.8117,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.8027681660899654,
|
| 436 |
+
"grad_norm": 1.5049817562103271,
|
| 437 |
+
"learning_rate": 0.0002157556720183616,
|
| 438 |
+
"loss": 2.8173,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.8166089965397924,
|
| 443 |
+
"grad_norm": 1.5916688442230225,
|
| 444 |
+
"learning_rate": 0.00021260076817227266,
|
| 445 |
+
"loss": 2.7637,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.8304498269896193,
|
| 450 |
+
"grad_norm": 2.124816656112671,
|
| 451 |
+
"learning_rate": 0.0002094119649058735,
|
| 452 |
+
"loss": 2.7946,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.8442906574394463,
|
| 457 |
+
"grad_norm": 1.6769332885742188,
|
| 458 |
+
"learning_rate": 0.0002061909890123868,
|
| 459 |
+
"loss": 2.7702,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8581314878892734,
|
| 464 |
+
"grad_norm": 3.2984721660614014,
|
| 465 |
+
"learning_rate": 0.0002029395847070803,
|
| 466 |
+
"loss": 2.7117,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8719723183391004,
|
| 471 |
+
"grad_norm": 1.5877281427383423,
|
| 472 |
+
"learning_rate": 0.0001996595126827437,
|
| 473 |
+
"loss": 2.705,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8858131487889274,
|
| 478 |
+
"grad_norm": 3.0824265480041504,
|
| 479 |
+
"learning_rate": 0.0001963525491562421,
|
| 480 |
+
"loss": 2.8567,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.8996539792387543,
|
| 485 |
+
"grad_norm": 3.194683313369751,
|
| 486 |
+
"learning_rate": 0.00019302048490666353,
|
| 487 |
+
"loss": 2.8681,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.9134948096885813,
|
| 492 |
+
"grad_norm": 2.6802637577056885,
|
| 493 |
+
"learning_rate": 0.00018966512430558034,
|
| 494 |
+
"loss": 2.8496,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.9273356401384083,
|
| 499 |
+
"grad_norm": 3.094783067703247,
|
| 500 |
+
"learning_rate": 0.00018628828433995013,
|
| 501 |
+
"loss": 2.8264,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.9411764705882353,
|
| 506 |
+
"grad_norm": 1.2324931621551514,
|
| 507 |
+
"learning_rate": 0.00018289179362818546,
|
| 508 |
+
"loss": 2.7473,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.9550173010380623,
|
| 513 |
+
"grad_norm": 2.415250778198242,
|
| 514 |
+
"learning_rate": 0.0001794774914299245,
|
| 515 |
+
"loss": 2.835,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.9688581314878892,
|
| 520 |
+
"grad_norm": 2.9529473781585693,
|
| 521 |
+
"learning_rate": 0.00017604722665003956,
|
| 522 |
+
"loss": 2.958,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.9826989619377162,
|
| 527 |
+
"grad_norm": 1.7587758302688599,
|
| 528 |
+
"learning_rate": 0.00017260285683742246,
|
| 529 |
+
"loss": 2.8396,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.9965397923875432,
|
| 534 |
+
"grad_norm": 1.809816598892212,
|
| 535 |
+
"learning_rate": 0.00016914624717908922,
|
| 536 |
+
"loss": 2.8112,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.0103806228373702,
|
| 541 |
+
"grad_norm": 1.430889368057251,
|
| 542 |
+
"learning_rate": 0.000165679269490148,
|
| 543 |
+
"loss": 2.7052,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.0242214532871972,
|
| 548 |
+
"grad_norm": 2.520479440689087,
|
| 549 |
+
"learning_rate": 0.00016220380120017872,
|
| 550 |
+
"loss": 2.7617,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.0380622837370241,
|
| 555 |
+
"grad_norm": 1.8224382400512695,
|
| 556 |
+
"learning_rate": 0.00015872172433657134,
|
| 557 |
+
"loss": 2.7747,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.0380622837370241,
|
| 562 |
+
"eval_loss": 0.6992730498313904,
|
| 563 |
+
"eval_runtime": 5.2527,
|
| 564 |
+
"eval_samples_per_second": 9.519,
|
| 565 |
+
"eval_steps_per_second": 1.333,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.0519031141868511,
|
| 570 |
+
"grad_norm": 1.3448646068572998,
|
| 571 |
+
"learning_rate": 0.00015523492450537517,
|
| 572 |
+
"loss": 2.763,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.065743944636678,
|
| 577 |
+
"grad_norm": 1.085045576095581,
|
| 578 |
+
"learning_rate": 0.00015174528987020957,
|
| 579 |
+
"loss": 2.7388,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.0795847750865053,
|
| 584 |
+
"grad_norm": 1.328552007675171,
|
| 585 |
+
"learning_rate": 0.00014825471012979045,
|
| 586 |
+
"loss": 2.7668,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.0934256055363323,
|
| 591 |
+
"grad_norm": 1.4537187814712524,
|
| 592 |
+
"learning_rate": 0.0001447650754946249,
|
| 593 |
+
"loss": 2.7073,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.1072664359861593,
|
| 598 |
+
"grad_norm": 1.3335843086242676,
|
| 599 |
+
"learning_rate": 0.00014127827566342863,
|
| 600 |
+
"loss": 2.796,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.1211072664359862,
|
| 605 |
+
"grad_norm": 2.351191997528076,
|
| 606 |
+
"learning_rate": 0.00013779619879982126,
|
| 607 |
+
"loss": 2.8494,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.1349480968858132,
|
| 612 |
+
"grad_norm": 2.260059118270874,
|
| 613 |
+
"learning_rate": 0.000134320730509852,
|
| 614 |
+
"loss": 2.7993,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.1487889273356402,
|
| 619 |
+
"grad_norm": 2.7046008110046387,
|
| 620 |
+
"learning_rate": 0.00013085375282091078,
|
| 621 |
+
"loss": 2.837,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.1626297577854672,
|
| 626 |
+
"grad_norm": 1.4147647619247437,
|
| 627 |
+
"learning_rate": 0.0001273971431625775,
|
| 628 |
+
"loss": 2.7192,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.1764705882352942,
|
| 633 |
+
"grad_norm": 2.916611909866333,
|
| 634 |
+
"learning_rate": 0.00012395277334996044,
|
| 635 |
+
"loss": 2.8989,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.1903114186851211,
|
| 640 |
+
"grad_norm": 3.9687960147857666,
|
| 641 |
+
"learning_rate": 0.00012052250857007545,
|
| 642 |
+
"loss": 2.728,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.2041522491349481,
|
| 647 |
+
"grad_norm": 1.5941438674926758,
|
| 648 |
+
"learning_rate": 0.00011710820637181447,
|
| 649 |
+
"loss": 2.7109,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.217993079584775,
|
| 654 |
+
"grad_norm": 1.5909277200698853,
|
| 655 |
+
"learning_rate": 0.00011371171566004985,
|
| 656 |
+
"loss": 2.78,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.231833910034602,
|
| 661 |
+
"grad_norm": 3.141655206680298,
|
| 662 |
+
"learning_rate": 0.0001103348756944197,
|
| 663 |
+
"loss": 2.7588,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.245674740484429,
|
| 668 |
+
"grad_norm": 2.018080234527588,
|
| 669 |
+
"learning_rate": 0.0001069795150933365,
|
| 670 |
+
"loss": 2.7771,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.259515570934256,
|
| 675 |
+
"grad_norm": 1.5090923309326172,
|
| 676 |
+
"learning_rate": 0.0001036474508437579,
|
| 677 |
+
"loss": 2.7333,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.273356401384083,
|
| 682 |
+
"grad_norm": 1.451968789100647,
|
| 683 |
+
"learning_rate": 0.0001003404873172563,
|
| 684 |
+
"loss": 2.7345,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.28719723183391,
|
| 689 |
+
"grad_norm": 2.1932549476623535,
|
| 690 |
+
"learning_rate": 9.706041529291968e-05,
|
| 691 |
+
"loss": 2.7071,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.301038062283737,
|
| 696 |
+
"grad_norm": 2.9638872146606445,
|
| 697 |
+
"learning_rate": 9.380901098761319e-05,
|
| 698 |
+
"loss": 2.8978,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.314878892733564,
|
| 703 |
+
"grad_norm": 2.9430599212646484,
|
| 704 |
+
"learning_rate": 9.058803509412646e-05,
|
| 705 |
+
"loss": 2.8598,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.328719723183391,
|
| 710 |
+
"grad_norm": 2.1553397178649902,
|
| 711 |
+
"learning_rate": 8.739923182772731e-05,
|
| 712 |
+
"loss": 2.6598,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.342560553633218,
|
| 717 |
+
"grad_norm": 1.4002549648284912,
|
| 718 |
+
"learning_rate": 8.424432798163836e-05,
|
| 719 |
+
"loss": 2.7373,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.356401384083045,
|
| 724 |
+
"grad_norm": 2.587266206741333,
|
| 725 |
+
"learning_rate": 8.112503199194821e-05,
|
| 726 |
+
"loss": 2.785,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.370242214532872,
|
| 731 |
+
"grad_norm": 1.669758915901184,
|
| 732 |
+
"learning_rate": 7.804303301246311e-05,
|
| 733 |
+
"loss": 2.6785,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.3840830449826989,
|
| 738 |
+
"grad_norm": 3.042837381362915,
|
| 739 |
+
"learning_rate": 7.500000000000002e-05,
|
| 740 |
+
"loss": 2.858,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.3840830449826989,
|
| 745 |
+
"eval_loss": 0.7048866748809814,
|
| 746 |
+
"eval_runtime": 5.2514,
|
| 747 |
+
"eval_samples_per_second": 9.521,
|
| 748 |
+
"eval_steps_per_second": 1.333,
|
| 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": 1.3877308048696934e+17,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|