Training in progress, step 8000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d40820fb221ed5ab5ca4d9701da2049c6d1761cfc543431f711239f4c0a14f
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5169ba6435acf0ba6f9c584893daa0bc9782c7d8adc4d46b177c96492031e90b
|
| 3 |
size 1082379659
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abbae167a9f0ed409523b108568bee9d935380e25b792884224d262a0c2c795
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -320,6 +320,318 @@
|
|
| 320 |
"eval_samples_per_second": 34.081,
|
| 321 |
"eval_steps_per_second": 8.52,
|
| 322 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 323 |
}
|
| 324 |
],
|
| 325 |
"logging_steps": 100,
|
|
@@ -339,7 +651,7 @@
|
|
| 339 |
"attributes": {}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
-
"total_flos":
|
| 343 |
"train_batch_size": 22,
|
| 344 |
"trial_name": null,
|
| 345 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.1038961038961039,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 8000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 320 |
"eval_samples_per_second": 34.081,
|
| 321 |
"eval_steps_per_second": 8.52,
|
| 322 |
"step": 4000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.053246753246753244,
|
| 326 |
+
"grad_norm": 0.24371765553951263,
|
| 327 |
+
"learning_rate": 0.0009980688306054227,
|
| 328 |
+
"loss": 3.2775,
|
| 329 |
+
"step": 4100
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.05454545454545454,
|
| 333 |
+
"grad_norm": 0.20401820540428162,
|
| 334 |
+
"learning_rate": 0.0009979401661574985,
|
| 335 |
+
"loss": 3.2952,
|
| 336 |
+
"step": 4200
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.05584415584415584,
|
| 340 |
+
"grad_norm": 0.2212119996547699,
|
| 341 |
+
"learning_rate": 0.0009978073615018127,
|
| 342 |
+
"loss": 3.257,
|
| 343 |
+
"step": 4300
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.05714285714285714,
|
| 347 |
+
"grad_norm": 0.2384602129459381,
|
| 348 |
+
"learning_rate": 0.000997670417742592,
|
| 349 |
+
"loss": 3.2859,
|
| 350 |
+
"step": 4400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.05844155844155844,
|
| 354 |
+
"grad_norm": 0.21143975853919983,
|
| 355 |
+
"learning_rate": 0.0009975293360184785,
|
| 356 |
+
"loss": 3.2475,
|
| 357 |
+
"step": 4500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.05974025974025974,
|
| 361 |
+
"grad_norm": 0.20411203801631927,
|
| 362 |
+
"learning_rate": 0.00099738411750252,
|
| 363 |
+
"loss": 3.2443,
|
| 364 |
+
"step": 4600
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.06103896103896104,
|
| 368 |
+
"grad_norm": 0.2097695916891098,
|
| 369 |
+
"learning_rate": 0.0009972347634021606,
|
| 370 |
+
"loss": 3.2703,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.06233766233766234,
|
| 375 |
+
"grad_norm": 0.2140115350484848,
|
| 376 |
+
"learning_rate": 0.00099708127495923,
|
| 377 |
+
"loss": 3.2569,
|
| 378 |
+
"step": 4800
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.06363636363636363,
|
| 382 |
+
"grad_norm": 0.2163541465997696,
|
| 383 |
+
"learning_rate": 0.000996923653449934,
|
| 384 |
+
"loss": 3.2646,
|
| 385 |
+
"step": 4900
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.06493506493506493,
|
| 389 |
+
"grad_norm": 0.1931372582912445,
|
| 390 |
+
"learning_rate": 0.0009967619001848434,
|
| 391 |
+
"loss": 3.2224,
|
| 392 |
+
"step": 5000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.06493506493506493,
|
| 396 |
+
"eval_loss": 3.59517240524292,
|
| 397 |
+
"eval_runtime": 15.382,
|
| 398 |
+
"eval_samples_per_second": 37.446,
|
| 399 |
+
"eval_steps_per_second": 9.362,
|
| 400 |
+
"step": 5000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.06623376623376623,
|
| 404 |
+
"grad_norm": 0.2017965465784073,
|
| 405 |
+
"learning_rate": 0.0009965960165088828,
|
| 406 |
+
"loss": 3.2159,
|
| 407 |
+
"step": 5100
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.06753246753246753,
|
| 411 |
+
"grad_norm": 0.2096720039844513,
|
| 412 |
+
"learning_rate": 0.0009964260038013203,
|
| 413 |
+
"loss": 3.1967,
|
| 414 |
+
"step": 5200
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.06883116883116883,
|
| 418 |
+
"grad_norm": 0.2119290977716446,
|
| 419 |
+
"learning_rate": 0.000996251863475755,
|
| 420 |
+
"loss": 3.1962,
|
| 421 |
+
"step": 5300
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.07012987012987013,
|
| 425 |
+
"grad_norm": 0.27017727494239807,
|
| 426 |
+
"learning_rate": 0.0009960735969801067,
|
| 427 |
+
"loss": 3.1672,
|
| 428 |
+
"step": 5400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.07142857142857142,
|
| 432 |
+
"grad_norm": 0.21126972138881683,
|
| 433 |
+
"learning_rate": 0.0009958912057966018,
|
| 434 |
+
"loss": 3.2301,
|
| 435 |
+
"step": 5500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.07272727272727272,
|
| 439 |
+
"grad_norm": 0.238760307431221,
|
| 440 |
+
"learning_rate": 0.0009957046914417628,
|
| 441 |
+
"loss": 3.2367,
|
| 442 |
+
"step": 5600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.07402597402597402,
|
| 446 |
+
"grad_norm": 0.19038313627243042,
|
| 447 |
+
"learning_rate": 0.000995514055466395,
|
| 448 |
+
"loss": 3.2026,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.07532467532467532,
|
| 453 |
+
"grad_norm": 0.20789292454719543,
|
| 454 |
+
"learning_rate": 0.0009953192994555736,
|
| 455 |
+
"loss": 3.1718,
|
| 456 |
+
"step": 5800
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.07662337662337662,
|
| 460 |
+
"grad_norm": 0.18676762282848358,
|
| 461 |
+
"learning_rate": 0.00099512042502863,
|
| 462 |
+
"loss": 3.167,
|
| 463 |
+
"step": 5900
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.07792207792207792,
|
| 467 |
+
"grad_norm": 0.19430765509605408,
|
| 468 |
+
"learning_rate": 0.0009949174338391394,
|
| 469 |
+
"loss": 3.1721,
|
| 470 |
+
"step": 6000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.07792207792207792,
|
| 474 |
+
"eval_loss": 3.5258212089538574,
|
| 475 |
+
"eval_runtime": 15.3635,
|
| 476 |
+
"eval_samples_per_second": 37.491,
|
| 477 |
+
"eval_steps_per_second": 9.373,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.07922077922077922,
|
| 482 |
+
"grad_norm": 0.20157617330551147,
|
| 483 |
+
"learning_rate": 0.0009947103275749064,
|
| 484 |
+
"loss": 3.1696,
|
| 485 |
+
"step": 6100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.08051948051948052,
|
| 489 |
+
"grad_norm": 0.18047969043254852,
|
| 490 |
+
"learning_rate": 0.0009944991079579514,
|
| 491 |
+
"loss": 3.1601,
|
| 492 |
+
"step": 6200
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.08181818181818182,
|
| 496 |
+
"grad_norm": 0.2030571699142456,
|
| 497 |
+
"learning_rate": 0.0009942837767444952,
|
| 498 |
+
"loss": 3.1709,
|
| 499 |
+
"step": 6300
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.08311688311688312,
|
| 503 |
+
"grad_norm": 0.18791615962982178,
|
| 504 |
+
"learning_rate": 0.000994064335724946,
|
| 505 |
+
"loss": 3.1808,
|
| 506 |
+
"step": 6400
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.08441558441558442,
|
| 510 |
+
"grad_norm": 0.1927482783794403,
|
| 511 |
+
"learning_rate": 0.0009938407867238828,
|
| 512 |
+
"loss": 3.1272,
|
| 513 |
+
"step": 6500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.08571428571428572,
|
| 517 |
+
"grad_norm": 0.1764034628868103,
|
| 518 |
+
"learning_rate": 0.0009936131316000418,
|
| 519 |
+
"loss": 3.1407,
|
| 520 |
+
"step": 6600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.08701298701298701,
|
| 524 |
+
"grad_norm": 0.1786874383687973,
|
| 525 |
+
"learning_rate": 0.0009933813722463004,
|
| 526 |
+
"loss": 3.107,
|
| 527 |
+
"step": 6700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.08831168831168831,
|
| 531 |
+
"grad_norm": 0.2685558497905731,
|
| 532 |
+
"learning_rate": 0.0009931455105896606,
|
| 533 |
+
"loss": 3.1609,
|
| 534 |
+
"step": 6800
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.08961038961038961,
|
| 538 |
+
"grad_norm": 0.19291436672210693,
|
| 539 |
+
"learning_rate": 0.000992905548591234,
|
| 540 |
+
"loss": 3.1444,
|
| 541 |
+
"step": 6900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.09090909090909091,
|
| 545 |
+
"grad_norm": 0.1896260678768158,
|
| 546 |
+
"learning_rate": 0.0009926614882462253,
|
| 547 |
+
"loss": 3.1329,
|
| 548 |
+
"step": 7000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.09090909090909091,
|
| 552 |
+
"eval_loss": 3.4966745376586914,
|
| 553 |
+
"eval_runtime": 14.4834,
|
| 554 |
+
"eval_samples_per_second": 39.77,
|
| 555 |
+
"eval_steps_per_second": 9.942,
|
| 556 |
+
"step": 7000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.09220779220779221,
|
| 560 |
+
"grad_norm": 0.17750093340873718,
|
| 561 |
+
"learning_rate": 0.0009924133315839156,
|
| 562 |
+
"loss": 3.1602,
|
| 563 |
+
"step": 7100
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.09350649350649351,
|
| 567 |
+
"grad_norm": 0.18574649095535278,
|
| 568 |
+
"learning_rate": 0.0009921610806676456,
|
| 569 |
+
"loss": 3.1451,
|
| 570 |
+
"step": 7200
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09480519480519481,
|
| 574 |
+
"grad_norm": 0.18256109952926636,
|
| 575 |
+
"learning_rate": 0.000991904737594798,
|
| 576 |
+
"loss": 3.1305,
|
| 577 |
+
"step": 7300
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.09610389610389611,
|
| 581 |
+
"grad_norm": 0.17488889396190643,
|
| 582 |
+
"learning_rate": 0.0009916443044967807,
|
| 583 |
+
"loss": 3.1211,
|
| 584 |
+
"step": 7400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.09740259740259741,
|
| 588 |
+
"grad_norm": 0.205893412232399,
|
| 589 |
+
"learning_rate": 0.0009913797835390088,
|
| 590 |
+
"loss": 3.1039,
|
| 591 |
+
"step": 7500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0987012987012987,
|
| 595 |
+
"grad_norm": 0.20423896610736847,
|
| 596 |
+
"learning_rate": 0.0009911111769208864,
|
| 597 |
+
"loss": 3.1159,
|
| 598 |
+
"step": 7600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.1,
|
| 602 |
+
"grad_norm": 0.18055465817451477,
|
| 603 |
+
"learning_rate": 0.000990838486875789,
|
| 604 |
+
"loss": 3.0872,
|
| 605 |
+
"step": 7700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.1012987012987013,
|
| 609 |
+
"grad_norm": 0.18993014097213745,
|
| 610 |
+
"learning_rate": 0.0009905617156710437,
|
| 611 |
+
"loss": 3.0976,
|
| 612 |
+
"step": 7800
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.1025974025974026,
|
| 616 |
+
"grad_norm": 0.1896851807832718,
|
| 617 |
+
"learning_rate": 0.000990280865607912,
|
| 618 |
+
"loss": 3.0932,
|
| 619 |
+
"step": 7900
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.1038961038961039,
|
| 623 |
+
"grad_norm": 0.18168048560619354,
|
| 624 |
+
"learning_rate": 0.0009899959390215689,
|
| 625 |
+
"loss": 3.0862,
|
| 626 |
+
"step": 8000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.1038961038961039,
|
| 630 |
+
"eval_loss": 3.4424216747283936,
|
| 631 |
+
"eval_runtime": 12.6555,
|
| 632 |
+
"eval_samples_per_second": 45.514,
|
| 633 |
+
"eval_steps_per_second": 11.378,
|
| 634 |
+
"step": 8000
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 100,
|
|
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
+
"total_flos": 2.3815451049984e+17,
|
| 655 |
"train_batch_size": 22,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|