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 78480072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6ea0d357987c22e19d62bc693ad25f9f75e8c29705927966891984bcfa15006
|
| 3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157104826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:360c92066fe24030b748d3e1a4a79cdad39167ce2d86a5cde6185f78d0be2afd
|
| 3 |
size 157104826
|
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 sha256:72e4f40153d720af5a9bc2d43b6e8c0264d4a78ff7944cbfcd5eae1a40c99950
|
| 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 sha256:48e5a60fd5a260f9c83e80fb175afa680e039a9594b460e7b3c282c848321c17
|
| 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 sha256:375a1f39f77328881cc4dff15556f86b1cf1c19b312aabc309ef42062f9242cc
|
| 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:b0a8e7093cfc46d661e82fccdbf1eaa9abd9a2f1dda8b3d0a97ab63067e39050
|
| 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 sha256:910cff932a69f6abbc99df6b748a086af6efc7922d876a1390fb1cf725edb026
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 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": 72.139,
|
| 382 |
"eval_steps_per_second": 18.756,
|
| 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": 0.12606343626976013,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 1.6891000263921878,
|
| 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": 72.139,
|
| 382 |
"eval_steps_per_second": 18.756,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.8614410134600158,
|
| 387 |
+
"grad_norm": 11.373549461364746,
|
| 388 |
+
"learning_rate": 0.000172161483570762,
|
| 389 |
+
"loss": 0.8296,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.8783320137239378,
|
| 394 |
+
"grad_norm": 8.694587707519531,
|
| 395 |
+
"learning_rate": 0.0001709553414463167,
|
| 396 |
+
"loss": 0.7572,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.8952230139878596,
|
| 401 |
+
"grad_norm": 10.283465385437012,
|
| 402 |
+
"learning_rate": 0.00016972862587414592,
|
| 403 |
+
"loss": 0.575,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.9121140142517815,
|
| 408 |
+
"grad_norm": 10.08366870880127,
|
| 409 |
+
"learning_rate": 0.0001684817508912824,
|
| 410 |
+
"loss": 0.3361,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.9290050145157034,
|
| 415 |
+
"grad_norm": 4.075512886047363,
|
| 416 |
+
"learning_rate": 0.00016721513733889716,
|
| 417 |
+
"loss": 0.2184,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.9458960147796253,
|
| 422 |
+
"grad_norm": 4.301791191101074,
|
| 423 |
+
"learning_rate": 0.00016592921272025882,
|
| 424 |
+
"loss": 0.2137,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.9627870150435471,
|
| 429 |
+
"grad_norm": 6.267927646636963,
|
| 430 |
+
"learning_rate": 0.0001646244110564441,
|
| 431 |
+
"loss": 0.3192,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.979678015307469,
|
| 436 |
+
"grad_norm": 4.850979804992676,
|
| 437 |
+
"learning_rate": 0.00016330117273984822,
|
| 438 |
+
"loss": 0.2671,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.9965690155713909,
|
| 443 |
+
"grad_norm": 7.005282402038574,
|
| 444 |
+
"learning_rate": 0.0001619599443855452,
|
| 445 |
+
"loss": 0.1437,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.0134600158353126,
|
| 450 |
+
"grad_norm": 28.618061065673828,
|
| 451 |
+
"learning_rate": 0.00016060117868054789,
|
| 452 |
+
"loss": 0.4224,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.0303510160992346,
|
| 457 |
+
"grad_norm": 4.588587284088135,
|
| 458 |
+
"learning_rate": 0.00015922533423101844,
|
| 459 |
+
"loss": 0.2437,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.0472420163631564,
|
| 464 |
+
"grad_norm": 5.091424942016602,
|
| 465 |
+
"learning_rate": 0.00015783287540748105,
|
| 466 |
+
"loss": 0.2079,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.0641330166270784,
|
| 471 |
+
"grad_norm": 4.7382025718688965,
|
| 472 |
+
"learning_rate": 0.00015642427218808918,
|
| 473 |
+
"loss": 0.1574,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.0810240168910004,
|
| 478 |
+
"grad_norm": 4.417683124542236,
|
| 479 |
+
"learning_rate": 0.000155,
|
| 480 |
+
"loss": 0.1475,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.0979150171549221,
|
| 485 |
+
"grad_norm": 1.9370671510696411,
|
| 486 |
+
"learning_rate": 0.00015356053955890993,
|
| 487 |
+
"loss": 0.1239,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.114806017418844,
|
| 492 |
+
"grad_norm": 4.699803829193115,
|
| 493 |
+
"learning_rate": 0.00015210637670680472,
|
| 494 |
+
"loss": 0.357,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.1316970176827659,
|
| 499 |
+
"grad_norm": 4.869682788848877,
|
| 500 |
+
"learning_rate": 0.00015063800224798007,
|
| 501 |
+
"loss": 0.3851,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.1485880179466879,
|
| 506 |
+
"grad_norm": 3.7498834133148193,
|
| 507 |
+
"learning_rate": 0.0001491559117833866,
|
| 508 |
+
"loss": 0.334,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.1654790182106096,
|
| 513 |
+
"grad_norm": 4.540921211242676,
|
| 514 |
+
"learning_rate": 0.0001476606055433565,
|
| 515 |
+
"loss": 0.3964,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1823700184745316,
|
| 520 |
+
"grad_norm": 4.821572303771973,
|
| 521 |
+
"learning_rate": 0.00014615258821876727,
|
| 522 |
+
"loss": 0.3421,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.1992610187384534,
|
| 527 |
+
"grad_norm": 6.549943923950195,
|
| 528 |
+
"learning_rate": 0.00014463236879070013,
|
| 529 |
+
"loss": 0.4211,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.2161520190023754,
|
| 534 |
+
"grad_norm": 5.620640277862549,
|
| 535 |
+
"learning_rate": 0.0001431004603586504,
|
| 536 |
+
"loss": 0.4023,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.2330430192662971,
|
| 541 |
+
"grad_norm": 6.463934421539307,
|
| 542 |
+
"learning_rate": 0.0001415573799673479,
|
| 543 |
+
"loss": 0.4277,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.249934019530219,
|
| 548 |
+
"grad_norm": 3.2470703125,
|
| 549 |
+
"learning_rate": 0.00014000364843224562,
|
| 550 |
+
"loss": 0.3017,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.2668250197941409,
|
| 555 |
+
"grad_norm": 3.9443600177764893,
|
| 556 |
+
"learning_rate": 0.00013843979016373573,
|
| 557 |
+
"loss": 0.3262,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.2668250197941409,
|
| 562 |
+
"eval_loss": 0.19759434461593628,
|
| 563 |
+
"eval_runtime": 0.6939,
|
| 564 |
+
"eval_samples_per_second": 72.058,
|
| 565 |
+
"eval_steps_per_second": 18.735,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.2837160200580628,
|
| 570 |
+
"grad_norm": 4.828883647918701,
|
| 571 |
+
"learning_rate": 0.00013686633299015251,
|
| 572 |
+
"loss": 0.3834,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.3006070203219848,
|
| 577 |
+
"grad_norm": 5.459804534912109,
|
| 578 |
+
"learning_rate": 0.00013528380797962126,
|
| 579 |
+
"loss": 0.3427,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.3174980205859066,
|
| 584 |
+
"grad_norm": 4.264815330505371,
|
| 585 |
+
"learning_rate": 0.00013369274926081394,
|
| 586 |
+
"loss": 0.2111,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.3343890208498284,
|
| 591 |
+
"grad_norm": 3.133007526397705,
|
| 592 |
+
"learning_rate": 0.00013209369384267194,
|
| 593 |
+
"loss": 0.177,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.3512800211137503,
|
| 598 |
+
"grad_norm": 2.766847848892212,
|
| 599 |
+
"learning_rate": 0.00013048718143315643,
|
| 600 |
+
"loss": 0.1618,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.3681710213776723,
|
| 605 |
+
"grad_norm": 3.8833649158477783,
|
| 606 |
+
"learning_rate": 0.00012887375425708794,
|
| 607 |
+
"loss": 0.2155,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.385062021641594,
|
| 612 |
+
"grad_norm": 3.8597495555877686,
|
| 613 |
+
"learning_rate": 0.00012725395687313647,
|
| 614 |
+
"loss": 0.1842,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.4019530219055159,
|
| 619 |
+
"grad_norm": 6.810535907745361,
|
| 620 |
+
"learning_rate": 0.00012562833599002375,
|
| 621 |
+
"loss": 0.2377,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.4188440221694378,
|
| 626 |
+
"grad_norm": 12.93388843536377,
|
| 627 |
+
"learning_rate": 0.0001239974402819999,
|
| 628 |
+
"loss": 0.2895,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.4357350224333598,
|
| 633 |
+
"grad_norm": 3.9634480476379395,
|
| 634 |
+
"learning_rate": 0.00012236182020365673,
|
| 635 |
+
"loss": 0.2547,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.4526260226972816,
|
| 640 |
+
"grad_norm": 4.790787220001221,
|
| 641 |
+
"learning_rate": 0.00012072202780414012,
|
| 642 |
+
"loss": 0.2652,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.4695170229612033,
|
| 647 |
+
"grad_norm": 3.763577699661255,
|
| 648 |
+
"learning_rate": 0.00011907861654082417,
|
| 649 |
+
"loss": 0.1602,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.4864080232251253,
|
| 654 |
+
"grad_norm": 3.399597644805908,
|
| 655 |
+
"learning_rate": 0.00011743214109250993,
|
| 656 |
+
"loss": 0.1438,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.5032990234890473,
|
| 661 |
+
"grad_norm": 2.587632417678833,
|
| 662 |
+
"learning_rate": 0.00011578315717221234,
|
| 663 |
+
"loss": 0.1121,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.520190023752969,
|
| 668 |
+
"grad_norm": 1.242765188217163,
|
| 669 |
+
"learning_rate": 0.00011413222133959747,
|
| 670 |
+
"loss": 0.0997,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.5370810240168908,
|
| 675 |
+
"grad_norm": 3.1180193424224854,
|
| 676 |
+
"learning_rate": 0.0001124798908131346,
|
| 677 |
+
"loss": 0.2238,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.5539720242808128,
|
| 682 |
+
"grad_norm": 3.6643130779266357,
|
| 683 |
+
"learning_rate": 0.00011082672328202539,
|
| 684 |
+
"loss": 0.312,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.5708630245447348,
|
| 689 |
+
"grad_norm": 3.1813502311706543,
|
| 690 |
+
"learning_rate": 0.00010917327671797463,
|
| 691 |
+
"loss": 0.31,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.5877540248086568,
|
| 696 |
+
"grad_norm": 2.9217069149017334,
|
| 697 |
+
"learning_rate": 0.00010752010918686544,
|
| 698 |
+
"loss": 0.2821,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.6046450250725786,
|
| 703 |
+
"grad_norm": 3.552128314971924,
|
| 704 |
+
"learning_rate": 0.00010586777866040254,
|
| 705 |
+
"loss": 0.2903,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.6215360253365003,
|
| 710 |
+
"grad_norm": 5.272158622741699,
|
| 711 |
+
"learning_rate": 0.0001042168428277877,
|
| 712 |
+
"loss": 0.3607,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.6384270256004223,
|
| 717 |
+
"grad_norm": 3.992403507232666,
|
| 718 |
+
"learning_rate": 0.0001025678589074901,
|
| 719 |
+
"loss": 0.2743,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.6553180258643443,
|
| 724 |
+
"grad_norm": 3.073756217956543,
|
| 725 |
+
"learning_rate": 0.00010092138345917588,
|
| 726 |
+
"loss": 0.2355,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.672209026128266,
|
| 731 |
+
"grad_norm": 2.897674083709717,
|
| 732 |
+
"learning_rate": 9.927797219585989e-05,
|
| 733 |
+
"loss": 0.206,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.6891000263921878,
|
| 738 |
+
"grad_norm": 3.1351470947265625,
|
| 739 |
+
"learning_rate": 9.763817979634326e-05,
|
| 740 |
+
"loss": 0.1611,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.6891000263921878,
|
| 745 |
+
"eval_loss": 0.12606343626976013,
|
| 746 |
+
"eval_runtime": 0.6938,
|
| 747 |
+
"eval_samples_per_second": 72.064,
|
| 748 |
+
"eval_steps_per_second": 18.737,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 6.296162210414592e+17,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|