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 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2088566eadc56a5c8309a9531bb6fcf5a287cf6aed01561219646680e775bc7c
|
| 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 sha256:0afc49d3ba801d7bb515f6132b53e0e8d83661fee7451b4f10d12f29700de203
|
| 3 |
size 320194002
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec74150783c2cc872e2529bbd0d2e014450ca2c2d41574b73ae43e04a4e186f6
|
| 3 |
size 15024
|
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:b450beb98468102f678848fd7b1c9ac170795ba31d2520dca8e02930e5c50342
|
| 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 sha256:89d66feb0ea8a54d11448a4600eb4704984427b5101713ae09a68f2ee18ad14b
|
| 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 sha256:9a063ce9295766fdd4ede689a08b3bb1669d43ea325c566a6b0df29b077083b7
|
| 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:c160342f903ff44fe4f09c12524bb2ea4c4fd5ceb523de4433c70f0855514c14
|
| 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": 0.
|
| 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": 32.832,
|
| 382 |
"eval_steps_per_second": 8.536,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 1,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.106641411781311,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.025178412658446964,
|
| 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": 32.832,
|
| 382 |
"eval_steps_per_second": 8.536,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.012840990455807952,
|
| 387 |
+
"grad_norm": 0.10851637274026871,
|
| 388 |
+
"learning_rate": 9.207653525908994e-05,
|
| 389 |
+
"loss": 1.1919,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.01309277458239242,
|
| 394 |
+
"grad_norm": 0.12280933558940887,
|
| 395 |
+
"learning_rate": 9.170690845727655e-05,
|
| 396 |
+
"loss": 1.2008,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.01334455870897689,
|
| 401 |
+
"grad_norm": 0.11200592666864395,
|
| 402 |
+
"learning_rate": 9.132972809209626e-05,
|
| 403 |
+
"loss": 1.1743,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.01359634283556136,
|
| 408 |
+
"grad_norm": 0.10003667324781418,
|
| 409 |
+
"learning_rate": 9.094507177988643e-05,
|
| 410 |
+
"loss": 1.1631,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.01384812696214583,
|
| 415 |
+
"grad_norm": 0.09316058456897736,
|
| 416 |
+
"learning_rate": 9.055301867538794e-05,
|
| 417 |
+
"loss": 1.2185,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.0140999110887303,
|
| 422 |
+
"grad_norm": 0.07689037919044495,
|
| 423 |
+
"learning_rate": 9.01536494554568e-05,
|
| 424 |
+
"loss": 1.1249,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.014351695215314769,
|
| 429 |
+
"grad_norm": 0.0907893106341362,
|
| 430 |
+
"learning_rate": 8.974704630246239e-05,
|
| 431 |
+
"loss": 1.1772,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.014603479341899239,
|
| 436 |
+
"grad_norm": 0.09316601604223251,
|
| 437 |
+
"learning_rate": 8.933329288737597e-05,
|
| 438 |
+
"loss": 1.1482,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.014855263468483709,
|
| 443 |
+
"grad_norm": 0.09033600986003876,
|
| 444 |
+
"learning_rate": 8.89124743525527e-05,
|
| 445 |
+
"loss": 1.1258,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.015107047595068179,
|
| 450 |
+
"grad_norm": 0.10970163345336914,
|
| 451 |
+
"learning_rate": 8.848467729421124e-05,
|
| 452 |
+
"loss": 1.1349,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.015358831721652647,
|
| 457 |
+
"grad_norm": 0.10259843617677689,
|
| 458 |
+
"learning_rate": 8.804998974461371e-05,
|
| 459 |
+
"loss": 1.1576,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.015610615848237117,
|
| 464 |
+
"grad_norm": 0.11174706369638443,
|
| 465 |
+
"learning_rate": 8.760850115395054e-05,
|
| 466 |
+
"loss": 1.1705,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.015862399974821587,
|
| 471 |
+
"grad_norm": 0.08973610401153564,
|
| 472 |
+
"learning_rate": 8.716030237193325e-05,
|
| 473 |
+
"loss": 1.1515,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.016114184101406057,
|
| 478 |
+
"grad_norm": 0.08280681818723679,
|
| 479 |
+
"learning_rate": 8.670548562909947e-05,
|
| 480 |
+
"loss": 1.1607,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.016365968227990527,
|
| 485 |
+
"grad_norm": 0.09221348911523819,
|
| 486 |
+
"learning_rate": 8.624414451783364e-05,
|
| 487 |
+
"loss": 1.1482,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.016617752354574997,
|
| 492 |
+
"grad_norm": 0.09574998915195465,
|
| 493 |
+
"learning_rate": 8.577637397310749e-05,
|
| 494 |
+
"loss": 1.241,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.016869536481159467,
|
| 499 |
+
"grad_norm": 0.09795909374952316,
|
| 500 |
+
"learning_rate": 8.530227025294435e-05,
|
| 501 |
+
"loss": 1.1739,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.017121320607743934,
|
| 506 |
+
"grad_norm": 0.09504640102386475,
|
| 507 |
+
"learning_rate": 8.482193091861112e-05,
|
| 508 |
+
"loss": 1.1334,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.017373104734328404,
|
| 513 |
+
"grad_norm": 0.08822384476661682,
|
| 514 |
+
"learning_rate": 8.433545481454206e-05,
|
| 515 |
+
"loss": 1.137,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.017624888860912874,
|
| 520 |
+
"grad_norm": 0.0878458246588707,
|
| 521 |
+
"learning_rate": 8.384294204799853e-05,
|
| 522 |
+
"loss": 1.1719,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.017876672987497344,
|
| 527 |
+
"grad_norm": 0.08970195800065994,
|
| 528 |
+
"learning_rate": 8.334449396846886e-05,
|
| 529 |
+
"loss": 1.1298,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.018128457114081814,
|
| 534 |
+
"grad_norm": 0.0950387567281723,
|
| 535 |
+
"learning_rate": 8.284021314681265e-05,
|
| 536 |
+
"loss": 1.1556,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.018380241240666284,
|
| 541 |
+
"grad_norm": 0.09765107929706573,
|
| 542 |
+
"learning_rate": 8.233020335415371e-05,
|
| 543 |
+
"loss": 1.1732,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.018632025367250754,
|
| 548 |
+
"grad_norm": 0.11165706068277359,
|
| 549 |
+
"learning_rate": 8.18145695405259e-05,
|
| 550 |
+
"loss": 1.1746,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.018883809493835224,
|
| 555 |
+
"grad_norm": 0.15581081807613373,
|
| 556 |
+
"learning_rate": 8.129341781327658e-05,
|
| 557 |
+
"loss": 1.0963,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.018883809493835224,
|
| 562 |
+
"eval_loss": 1.122991681098938,
|
| 563 |
+
"eval_runtime": 1.5233,
|
| 564 |
+
"eval_samples_per_second": 32.822,
|
| 565 |
+
"eval_steps_per_second": 8.534,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.019135593620419694,
|
| 570 |
+
"grad_norm": 0.08741319179534912,
|
| 571 |
+
"learning_rate": 8.07668554152317e-05,
|
| 572 |
+
"loss": 1.1688,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.01938737774700416,
|
| 577 |
+
"grad_norm": 0.08875293284654617,
|
| 578 |
+
"learning_rate": 8.02349907026274e-05,
|
| 579 |
+
"loss": 1.1829,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.01963916187358863,
|
| 584 |
+
"grad_norm": 0.08861377090215683,
|
| 585 |
+
"learning_rate": 7.969793312281237e-05,
|
| 586 |
+
"loss": 1.1803,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.0198909460001731,
|
| 591 |
+
"grad_norm": 0.09791383892297745,
|
| 592 |
+
"learning_rate": 7.915579319172573e-05,
|
| 593 |
+
"loss": 1.2001,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.02014273012675757,
|
| 598 |
+
"grad_norm": 0.0991906151175499,
|
| 599 |
+
"learning_rate": 7.860868247115505e-05,
|
| 600 |
+
"loss": 1.1669,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.02039451425334204,
|
| 605 |
+
"grad_norm": 0.09529578685760498,
|
| 606 |
+
"learning_rate": 7.805671354577908e-05,
|
| 607 |
+
"loss": 1.1522,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.02064629837992651,
|
| 612 |
+
"grad_norm": 0.09793104231357574,
|
| 613 |
+
"learning_rate": 7.75e-05,
|
| 614 |
+
"loss": 1.1407,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.02089808250651098,
|
| 619 |
+
"grad_norm": 0.09607716649770737,
|
| 620 |
+
"learning_rate": 7.693865639457011e-05,
|
| 621 |
+
"loss": 1.1291,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.02114986663309545,
|
| 626 |
+
"grad_norm": 0.10056506842374802,
|
| 627 |
+
"learning_rate": 7.637279824301728e-05,
|
| 628 |
+
"loss": 1.1124,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.02140165075967992,
|
| 633 |
+
"grad_norm": 0.10144215822219849,
|
| 634 |
+
"learning_rate": 7.580254198787463e-05,
|
| 635 |
+
"loss": 1.1022,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.021653434886264387,
|
| 640 |
+
"grad_norm": 0.10326708108186722,
|
| 641 |
+
"learning_rate": 7.522800497671897e-05,
|
| 642 |
+
"loss": 1.073,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.021905219012848857,
|
| 647 |
+
"grad_norm": 0.1260983794927597,
|
| 648 |
+
"learning_rate": 7.464930543802289e-05,
|
| 649 |
+
"loss": 1.1218,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.022157003139433327,
|
| 654 |
+
"grad_norm": 0.10883725434541702,
|
| 655 |
+
"learning_rate": 7.406656245682565e-05,
|
| 656 |
+
"loss": 1.1167,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.022408787266017798,
|
| 661 |
+
"grad_norm": 0.09835278987884521,
|
| 662 |
+
"learning_rate": 7.34798959502279e-05,
|
| 663 |
+
"loss": 1.1506,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.022660571392602268,
|
| 668 |
+
"grad_norm": 0.10083261877298355,
|
| 669 |
+
"learning_rate": 7.288942664271503e-05,
|
| 670 |
+
"loss": 1.1792,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.022912355519186738,
|
| 675 |
+
"grad_norm": 0.10250851511955261,
|
| 676 |
+
"learning_rate": 7.229527604131436e-05,
|
| 677 |
+
"loss": 1.1897,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.023164139645771208,
|
| 682 |
+
"grad_norm": 0.1085507944226265,
|
| 683 |
+
"learning_rate": 7.16975664105915e-05,
|
| 684 |
+
"loss": 1.1402,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.023415923772355678,
|
| 689 |
+
"grad_norm": 0.10734712332487106,
|
| 690 |
+
"learning_rate": 7.109642074749067e-05,
|
| 691 |
+
"loss": 1.0878,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.023667707898940148,
|
| 696 |
+
"grad_norm": 0.10455948859453201,
|
| 697 |
+
"learning_rate": 7.049196275602421e-05,
|
| 698 |
+
"loss": 1.116,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.023919492025524614,
|
| 703 |
+
"grad_norm": 0.10420308262109756,
|
| 704 |
+
"learning_rate": 6.988431682181693e-05,
|
| 705 |
+
"loss": 1.1243,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.024171276152109084,
|
| 710 |
+
"grad_norm": 0.10482881218194962,
|
| 711 |
+
"learning_rate": 6.927360798650978e-05,
|
| 712 |
+
"loss": 1.1198,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.024423060278693554,
|
| 717 |
+
"grad_norm": 0.11121159791946411,
|
| 718 |
+
"learning_rate": 6.865996192202884e-05,
|
| 719 |
+
"loss": 1.1097,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.024674844405278024,
|
| 724 |
+
"grad_norm": 0.11902576684951782,
|
| 725 |
+
"learning_rate": 6.804350490472446e-05,
|
| 726 |
+
"loss": 1.1056,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.024926628531862494,
|
| 731 |
+
"grad_norm": 0.12510505318641663,
|
| 732 |
+
"learning_rate": 6.742436378938612e-05,
|
| 733 |
+
"loss": 1.109,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.025178412658446964,
|
| 738 |
+
"grad_norm": 0.1589539796113968,
|
| 739 |
+
"learning_rate": 6.680266598313802e-05,
|
| 740 |
+
"loss": 1.065,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.025178412658446964,
|
| 745 |
+
"eval_loss": 1.106641411781311,
|
| 746 |
+
"eval_runtime": 1.5233,
|
| 747 |
+
"eval_samples_per_second": 32.824,
|
| 748 |
+
"eval_steps_per_second": 8.534,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 1.0782060130074624e+18,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|