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 138995824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54a1f1609bb5f58b2468698ff4bce26523666945476e36625d3ec3f09864b471
|
| 3 |
size 138995824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 71077780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965bae697fcc66b08293e0be1ba9c9b66b2220d74b6dec48500ff3fbec1b9053
|
| 3 |
size 71077780
|
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 sha256:99789e0b3553bcbb83c8a3b67f24949aaea5fe69f7d19ba0f836e5dce8a78f2b
|
| 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 sha256:12eb45274142bc6bee73da891a0b4fb75fbeb223d2c8699bd3dc5134ec0878cf
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch":
|
| 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": 56.991,
|
| 374 |
"eval_steps_per_second": 14.867,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.8051786422729492,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 2.4691358024691357,
|
| 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": 56.991,
|
| 374 |
"eval_steps_per_second": 14.867,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.2592592592592593,
|
| 379 |
+
"grad_norm": 0.35165345668792725,
|
| 380 |
+
"learning_rate": 7.042221284679982e-05,
|
| 381 |
+
"loss": 1.7912,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.2839506172839505,
|
| 386 |
+
"grad_norm": 0.1966906636953354,
|
| 387 |
+
"learning_rate": 6.91341716182545e-05,
|
| 388 |
+
"loss": 1.8102,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.308641975308642,
|
| 393 |
+
"grad_norm": 0.24283820390701294,
|
| 394 |
+
"learning_rate": 6.783107663311565e-05,
|
| 395 |
+
"loss": 2.0686,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.3333333333333333,
|
| 400 |
+
"grad_norm": 0.21965524554252625,
|
| 401 |
+
"learning_rate": 6.651395309775837e-05,
|
| 402 |
+
"loss": 1.6701,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.3580246913580247,
|
| 407 |
+
"grad_norm": 0.25558704137802124,
|
| 408 |
+
"learning_rate": 6.518383725548074e-05,
|
| 409 |
+
"loss": 1.9965,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.382716049382716,
|
| 414 |
+
"grad_norm": 0.24983792006969452,
|
| 415 |
+
"learning_rate": 6.384177557124247e-05,
|
| 416 |
+
"loss": 1.6517,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.4074074074074074,
|
| 421 |
+
"grad_norm": 0.27970802783966064,
|
| 422 |
+
"learning_rate": 6.248882390836135e-05,
|
| 423 |
+
"loss": 1.7792,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.4320987654320987,
|
| 428 |
+
"grad_norm": 0.3209986686706543,
|
| 429 |
+
"learning_rate": 6.112604669781572e-05,
|
| 430 |
+
"loss": 1.9831,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.4567901234567902,
|
| 435 |
+
"grad_norm": 0.3848767876625061,
|
| 436 |
+
"learning_rate": 5.9754516100806423e-05,
|
| 437 |
+
"loss": 1.8107,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.4814814814814814,
|
| 442 |
+
"grad_norm": 0.5168919563293457,
|
| 443 |
+
"learning_rate": 5.837531116523682e-05,
|
| 444 |
+
"loss": 1.6918,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.5061728395061729,
|
| 449 |
+
"grad_norm": 0.45516857504844666,
|
| 450 |
+
"learning_rate": 5.698951697677498e-05,
|
| 451 |
+
"loss": 1.3992,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.5308641975308643,
|
| 456 |
+
"grad_norm": 0.2247449904680252,
|
| 457 |
+
"learning_rate": 5.559822380516539e-05,
|
| 458 |
+
"loss": 2.0824,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.5555555555555556,
|
| 463 |
+
"grad_norm": 0.23172587156295776,
|
| 464 |
+
"learning_rate": 5.420252624646238e-05,
|
| 465 |
+
"loss": 1.8623,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.5802469135802468,
|
| 470 |
+
"grad_norm": 0.23838010430335999,
|
| 471 |
+
"learning_rate": 5.2803522361859594e-05,
|
| 472 |
+
"loss": 1.9431,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.6049382716049383,
|
| 477 |
+
"grad_norm": 0.25559642910957336,
|
| 478 |
+
"learning_rate": 5.140231281379345e-05,
|
| 479 |
+
"loss": 1.8672,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.6296296296296298,
|
| 484 |
+
"grad_norm": 0.2604578733444214,
|
| 485 |
+
"learning_rate": 5e-05,
|
| 486 |
+
"loss": 1.9074,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.654320987654321,
|
| 491 |
+
"grad_norm": 0.30712196230888367,
|
| 492 |
+
"learning_rate": 4.859768718620656e-05,
|
| 493 |
+
"loss": 1.8103,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.6790123456790123,
|
| 498 |
+
"grad_norm": 0.3221416175365448,
|
| 499 |
+
"learning_rate": 4.7196477638140404e-05,
|
| 500 |
+
"loss": 1.7468,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.7037037037037037,
|
| 505 |
+
"grad_norm": 0.3665846586227417,
|
| 506 |
+
"learning_rate": 4.579747375353763e-05,
|
| 507 |
+
"loss": 1.6083,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.7283950617283952,
|
| 512 |
+
"grad_norm": 0.47580888867378235,
|
| 513 |
+
"learning_rate": 4.4401776194834613e-05,
|
| 514 |
+
"loss": 1.7429,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.7530864197530864,
|
| 519 |
+
"grad_norm": 0.39478451013565063,
|
| 520 |
+
"learning_rate": 4.3010483023225045e-05,
|
| 521 |
+
"loss": 1.6895,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.7777777777777777,
|
| 526 |
+
"grad_norm": 0.19653937220573425,
|
| 527 |
+
"learning_rate": 4.162468883476319e-05,
|
| 528 |
+
"loss": 1.8156,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.8024691358024691,
|
| 533 |
+
"grad_norm": 0.26667800545692444,
|
| 534 |
+
"learning_rate": 4.0245483899193595e-05,
|
| 535 |
+
"loss": 2.1007,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.8271604938271606,
|
| 540 |
+
"grad_norm": 0.22694823145866394,
|
| 541 |
+
"learning_rate": 3.887395330218429e-05,
|
| 542 |
+
"loss": 1.6717,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.8518518518518519,
|
| 547 |
+
"grad_norm": 0.27870312333106995,
|
| 548 |
+
"learning_rate": 3.7511176091638653e-05,
|
| 549 |
+
"loss": 1.9098,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.876543209876543,
|
| 554 |
+
"grad_norm": 0.24723252654075623,
|
| 555 |
+
"learning_rate": 3.6158224428757535e-05,
|
| 556 |
+
"loss": 1.75,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.9012345679012346,
|
| 561 |
+
"grad_norm": 0.27670368552207947,
|
| 562 |
+
"learning_rate": 3.4816162744519263e-05,
|
| 563 |
+
"loss": 1.8367,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.925925925925926,
|
| 568 |
+
"grad_norm": 0.33188384771347046,
|
| 569 |
+
"learning_rate": 3.3486046902241664e-05,
|
| 570 |
+
"loss": 1.7393,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.9506172839506173,
|
| 575 |
+
"grad_norm": 0.3645884692668915,
|
| 576 |
+
"learning_rate": 3.216892336688435e-05,
|
| 577 |
+
"loss": 1.7558,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.9753086419753085,
|
| 582 |
+
"grad_norm": 0.5310534834861755,
|
| 583 |
+
"learning_rate": 3.086582838174551e-05,
|
| 584 |
+
"loss": 1.7483,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.0,
|
| 589 |
+
"grad_norm": 0.5409613847732544,
|
| 590 |
+
"learning_rate": 2.9577787153200197e-05,
|
| 591 |
+
"loss": 2.4523,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.0246913580246915,
|
| 596 |
+
"grad_norm": 0.1562846601009369,
|
| 597 |
+
"learning_rate": 2.8305813044122097e-05,
|
| 598 |
+
"loss": 1.9007,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.049382716049383,
|
| 603 |
+
"grad_norm": 0.2033800333738327,
|
| 604 |
+
"learning_rate": 2.705090677662311e-05,
|
| 605 |
+
"loss": 1.9369,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.074074074074074,
|
| 610 |
+
"grad_norm": 0.22452938556671143,
|
| 611 |
+
"learning_rate": 2.581405564473801e-05,
|
| 612 |
+
"loss": 1.962,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.0987654320987654,
|
| 617 |
+
"grad_norm": 0.2419237196445465,
|
| 618 |
+
"learning_rate": 2.459623273767354e-05,
|
| 619 |
+
"loss": 1.7808,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.123456790123457,
|
| 624 |
+
"grad_norm": 0.27632632851600647,
|
| 625 |
+
"learning_rate": 2.3398396174233178e-05,
|
| 626 |
+
"loss": 1.9695,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.148148148148148,
|
| 631 |
+
"grad_norm": 0.26683545112609863,
|
| 632 |
+
"learning_rate": 2.2221488349019903e-05,
|
| 633 |
+
"loss": 1.8651,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.1728395061728394,
|
| 638 |
+
"grad_norm": 0.2869678735733032,
|
| 639 |
+
"learning_rate": 2.1066435191009715e-05,
|
| 640 |
+
"loss": 1.7975,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.197530864197531,
|
| 645 |
+
"grad_norm": 0.31071460247039795,
|
| 646 |
+
"learning_rate": 1.9934145435079702e-05,
|
| 647 |
+
"loss": 1.7865,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.2222222222222223,
|
| 652 |
+
"grad_norm": 0.3720311224460602,
|
| 653 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 654 |
+
"loss": 1.5558,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.246913580246914,
|
| 659 |
+
"grad_norm": 0.4831774830818176,
|
| 660 |
+
"learning_rate": 1.774140082289563e-05,
|
| 661 |
+
"loss": 1.4962,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.271604938271605,
|
| 666 |
+
"grad_norm": 0.1712505966424942,
|
| 667 |
+
"learning_rate": 1.6682671102399805e-05,
|
| 668 |
+
"loss": 1.724,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.2962962962962963,
|
| 673 |
+
"grad_norm": 0.24379503726959229,
|
| 674 |
+
"learning_rate": 1.5650153698254916e-05,
|
| 675 |
+
"loss": 1.8886,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.3209876543209877,
|
| 680 |
+
"grad_norm": 0.22222569584846497,
|
| 681 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 682 |
+
"loss": 1.8285,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.3456790123456788,
|
| 687 |
+
"grad_norm": 0.2787880301475525,
|
| 688 |
+
"learning_rate": 1.3666983898298657e-05,
|
| 689 |
+
"loss": 1.6753,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.3703703703703702,
|
| 694 |
+
"grad_norm": 0.23695729672908783,
|
| 695 |
+
"learning_rate": 1.2717891755841722e-05,
|
| 696 |
+
"loss": 1.846,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.3950617283950617,
|
| 701 |
+
"grad_norm": 0.255487859249115,
|
| 702 |
+
"learning_rate": 1.1798131208919627e-05,
|
| 703 |
+
"loss": 1.7061,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.419753086419753,
|
| 708 |
+
"grad_norm": 0.32571518421173096,
|
| 709 |
+
"learning_rate": 1.090842587659851e-05,
|
| 710 |
+
"loss": 1.8259,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.4444444444444446,
|
| 715 |
+
"grad_norm": 0.3715745210647583,
|
| 716 |
+
"learning_rate": 1.004947573208756e-05,
|
| 717 |
+
"loss": 1.7244,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.4691358024691357,
|
| 722 |
+
"grad_norm": 0.43399521708488464,
|
| 723 |
+
"learning_rate": 9.221956552036992e-06,
|
| 724 |
+
"loss": 1.6352,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.4691358024691357,
|
| 729 |
+
"eval_loss": 1.8051786422729492,
|
| 730 |
+
"eval_runtime": 1.2101,
|
| 731 |
+
"eval_samples_per_second": 57.02,
|
| 732 |
+
"eval_steps_per_second": 14.875,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 6864586490511360.0,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|