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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:052a390e625610a7e9eaa7423d1c31c35602d2615d5245b32002114116020de5
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d82aee273e77605d0f5c6624f80e753f1fd61c733b21927f56600da1789fdb6
|
| 3 |
size 938825803
|
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 sha256:3482ff4d448b35418681eb31100e133b6dd964f5bb4c2c9eca6680b10bd0977e
|
| 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 sha256:11829097af6776cbee61b048d98aace8148b1dc770060a280833ccf8b49be52d
|
| 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": 84.704,
|
| 321 |
"eval_steps_per_second": 21.176,
|
| 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": 0.07272727272727272,
|
| 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": 84.704,
|
| 321 |
"eval_steps_per_second": 21.176,
|
| 322 |
"step": 4000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.03727272727272727,
|
| 326 |
+
"grad_norm": 0.2137739211320877,
|
| 327 |
+
"learning_rate": 0.000996814686090343,
|
| 328 |
+
"loss": 3.288787841796875,
|
| 329 |
+
"step": 4100
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.038181818181818185,
|
| 333 |
+
"grad_norm": 0.20396745204925537,
|
| 334 |
+
"learning_rate": 0.0009966515035386867,
|
| 335 |
+
"loss": 3.277693786621094,
|
| 336 |
+
"step": 4200
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.03909090909090909,
|
| 340 |
+
"grad_norm": 0.20048071444034576,
|
| 341 |
+
"learning_rate": 0.0009964842588826267,
|
| 342 |
+
"loss": 3.2614068603515625,
|
| 343 |
+
"step": 4300
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.04,
|
| 347 |
+
"grad_norm": 0.2545357346534729,
|
| 348 |
+
"learning_rate": 0.0009963129534900535,
|
| 349 |
+
"loss": 3.241942138671875,
|
| 350 |
+
"step": 4400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.04090909090909091,
|
| 354 |
+
"grad_norm": 0.21150407195091248,
|
| 355 |
+
"learning_rate": 0.0009961375887620715,
|
| 356 |
+
"loss": 3.254181213378906,
|
| 357 |
+
"step": 4500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.04181818181818182,
|
| 361 |
+
"grad_norm": 0.25913697481155396,
|
| 362 |
+
"learning_rate": 0.0009959581661329855,
|
| 363 |
+
"loss": 3.256631164550781,
|
| 364 |
+
"step": 4600
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.042727272727272725,
|
| 368 |
+
"grad_norm": 0.21662315726280212,
|
| 369 |
+
"learning_rate": 0.000995774687070291,
|
| 370 |
+
"loss": 3.246457214355469,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.04363636363636364,
|
| 375 |
+
"grad_norm": 0.21578437089920044,
|
| 376 |
+
"learning_rate": 0.0009955871530746593,
|
| 377 |
+
"loss": 3.2591009521484375,
|
| 378 |
+
"step": 4800
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.04454545454545455,
|
| 382 |
+
"grad_norm": 0.2277086228132248,
|
| 383 |
+
"learning_rate": 0.0009953955656799285,
|
| 384 |
+
"loss": 3.2139767456054686,
|
| 385 |
+
"step": 4900
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.045454545454545456,
|
| 389 |
+
"grad_norm": 0.21145710349082947,
|
| 390 |
+
"learning_rate": 0.0009951999264530885,
|
| 391 |
+
"loss": 3.217757263183594,
|
| 392 |
+
"step": 5000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.045454545454545456,
|
| 396 |
+
"eval_loss": 3.559657573699951,
|
| 397 |
+
"eval_runtime": 6.8094,
|
| 398 |
+
"eval_samples_per_second": 84.589,
|
| 399 |
+
"eval_steps_per_second": 21.147,
|
| 400 |
+
"step": 5000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.046363636363636364,
|
| 404 |
+
"grad_norm": 0.2059008628129959,
|
| 405 |
+
"learning_rate": 0.0009950002369942693,
|
| 406 |
+
"loss": 3.2310595703125,
|
| 407 |
+
"step": 5100
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.04727272727272727,
|
| 411 |
+
"grad_norm": 0.31273841857910156,
|
| 412 |
+
"learning_rate": 0.0009947964989367275,
|
| 413 |
+
"loss": 3.236092529296875,
|
| 414 |
+
"step": 5200
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.04818181818181818,
|
| 418 |
+
"grad_norm": 0.20427817106246948,
|
| 419 |
+
"learning_rate": 0.0009945887139468335,
|
| 420 |
+
"loss": 3.20990966796875,
|
| 421 |
+
"step": 5300
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.04909090909090909,
|
| 425 |
+
"grad_norm": 0.21813584864139557,
|
| 426 |
+
"learning_rate": 0.0009943768837240572,
|
| 427 |
+
"loss": 3.23782470703125,
|
| 428 |
+
"step": 5400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.05,
|
| 432 |
+
"grad_norm": 0.21357640624046326,
|
| 433 |
+
"learning_rate": 0.0009941610100009546,
|
| 434 |
+
"loss": 3.2014178466796874,
|
| 435 |
+
"step": 5500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.05090909090909091,
|
| 439 |
+
"grad_norm": 0.19788503646850586,
|
| 440 |
+
"learning_rate": 0.0009939410945431532,
|
| 441 |
+
"loss": 3.201743469238281,
|
| 442 |
+
"step": 5600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.05181818181818182,
|
| 446 |
+
"grad_norm": 0.2109798789024353,
|
| 447 |
+
"learning_rate": 0.0009937171391493375,
|
| 448 |
+
"loss": 3.1780130004882814,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.05272727272727273,
|
| 453 |
+
"grad_norm": 0.1952320784330368,
|
| 454 |
+
"learning_rate": 0.0009934891456512356,
|
| 455 |
+
"loss": 3.1811758422851564,
|
| 456 |
+
"step": 5800
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.053636363636363635,
|
| 460 |
+
"grad_norm": 0.19197046756744385,
|
| 461 |
+
"learning_rate": 0.0009932571159136023,
|
| 462 |
+
"loss": 3.1767172241210937,
|
| 463 |
+
"step": 5900
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.05454545454545454,
|
| 467 |
+
"grad_norm": 0.20798423886299133,
|
| 468 |
+
"learning_rate": 0.0009930210518342049,
|
| 469 |
+
"loss": 3.1700228881835937,
|
| 470 |
+
"step": 6000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.05454545454545454,
|
| 474 |
+
"eval_loss": 3.494601249694824,
|
| 475 |
+
"eval_runtime": 6.8416,
|
| 476 |
+
"eval_samples_per_second": 84.191,
|
| 477 |
+
"eval_steps_per_second": 21.048,
|
| 478 |
+
"step": 6000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.05545454545454546,
|
| 482 |
+
"grad_norm": 0.18669773638248444,
|
| 483 |
+
"learning_rate": 0.0009927809553438077,
|
| 484 |
+
"loss": 3.1545779418945314,
|
| 485 |
+
"step": 6100
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.056363636363636366,
|
| 489 |
+
"grad_norm": 0.2077275514602661,
|
| 490 |
+
"learning_rate": 0.0009925368284061555,
|
| 491 |
+
"loss": 3.160372619628906,
|
| 492 |
+
"step": 6200
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.057272727272727274,
|
| 496 |
+
"grad_norm": 0.18006086349487305,
|
| 497 |
+
"learning_rate": 0.000992288673017959,
|
| 498 |
+
"loss": 3.1383782958984376,
|
| 499 |
+
"step": 6300
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.05818181818181818,
|
| 503 |
+
"grad_norm": 0.19835108518600464,
|
| 504 |
+
"learning_rate": 0.000992036491208877,
|
| 505 |
+
"loss": 3.15177001953125,
|
| 506 |
+
"step": 6400
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.05909090909090909,
|
| 510 |
+
"grad_norm": 0.19680027663707733,
|
| 511 |
+
"learning_rate": 0.0009917802850414998,
|
| 512 |
+
"loss": 3.16474365234375,
|
| 513 |
+
"step": 6500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.06,
|
| 517 |
+
"grad_norm": 0.28204840421676636,
|
| 518 |
+
"learning_rate": 0.0009915200566113338,
|
| 519 |
+
"loss": 3.1483929443359373,
|
| 520 |
+
"step": 6600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.060909090909090906,
|
| 524 |
+
"grad_norm": 0.18320120871067047,
|
| 525 |
+
"learning_rate": 0.000991255808046783,
|
| 526 |
+
"loss": 3.150434875488281,
|
| 527 |
+
"step": 6700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.06181818181818182,
|
| 531 |
+
"grad_norm": 0.19188480079174042,
|
| 532 |
+
"learning_rate": 0.000990987541509132,
|
| 533 |
+
"loss": 3.118103332519531,
|
| 534 |
+
"step": 6800
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.06272727272727273,
|
| 538 |
+
"grad_norm": 0.1749107539653778,
|
| 539 |
+
"learning_rate": 0.0009907152591925282,
|
| 540 |
+
"loss": 3.1161154174804686,
|
| 541 |
+
"step": 6900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.06363636363636363,
|
| 545 |
+
"grad_norm": 0.17627771198749542,
|
| 546 |
+
"learning_rate": 0.0009904389633239644,
|
| 547 |
+
"loss": 3.140033874511719,
|
| 548 |
+
"step": 7000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.06363636363636363,
|
| 552 |
+
"eval_loss": 3.460543632507324,
|
| 553 |
+
"eval_runtime": 6.8262,
|
| 554 |
+
"eval_samples_per_second": 84.381,
|
| 555 |
+
"eval_steps_per_second": 21.095,
|
| 556 |
+
"step": 7000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.06454545454545454,
|
| 560 |
+
"grad_norm": 0.19298093020915985,
|
| 561 |
+
"learning_rate": 0.0009901586561632597,
|
| 562 |
+
"loss": 3.1127783203125,
|
| 563 |
+
"step": 7100
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.06545454545454546,
|
| 567 |
+
"grad_norm": 0.2005312442779541,
|
| 568 |
+
"learning_rate": 0.0009898743400030417,
|
| 569 |
+
"loss": 3.131772155761719,
|
| 570 |
+
"step": 7200
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.06636363636363636,
|
| 574 |
+
"grad_norm": 0.20932316780090332,
|
| 575 |
+
"learning_rate": 0.0009895860171687276,
|
| 576 |
+
"loss": 3.1065127563476564,
|
| 577 |
+
"step": 7300
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.06727272727272728,
|
| 581 |
+
"grad_norm": 0.1870882213115692,
|
| 582 |
+
"learning_rate": 0.0009892936900185053,
|
| 583 |
+
"loss": 3.1155380249023437,
|
| 584 |
+
"step": 7400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.06818181818181818,
|
| 588 |
+
"grad_norm": 0.18347717821598053,
|
| 589 |
+
"learning_rate": 0.0009889973609433136,
|
| 590 |
+
"loss": 3.094842529296875,
|
| 591 |
+
"step": 7500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.06909090909090909,
|
| 595 |
+
"grad_norm": 0.20144793391227722,
|
| 596 |
+
"learning_rate": 0.000988697032366823,
|
| 597 |
+
"loss": 3.1140432739257813,
|
| 598 |
+
"step": 7600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.07,
|
| 602 |
+
"grad_norm": 0.17255835235118866,
|
| 603 |
+
"learning_rate": 0.0009883927067454157,
|
| 604 |
+
"loss": 3.0936923217773438,
|
| 605 |
+
"step": 7700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.07090909090909091,
|
| 609 |
+
"grad_norm": 0.19149735569953918,
|
| 610 |
+
"learning_rate": 0.0009880843865681666,
|
| 611 |
+
"loss": 3.0889437866210936,
|
| 612 |
+
"step": 7800
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.07181818181818182,
|
| 616 |
+
"grad_norm": 0.18358978629112244,
|
| 617 |
+
"learning_rate": 0.0009877720743568204,
|
| 618 |
+
"loss": 3.0625601196289063,
|
| 619 |
+
"step": 7900
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.07272727272727272,
|
| 623 |
+
"grad_norm": 0.16700264811515808,
|
| 624 |
+
"learning_rate": 0.0009874557726657744,
|
| 625 |
+
"loss": 3.0754776000976562,
|
| 626 |
+
"step": 8000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.07272727272727272,
|
| 630 |
+
"eval_loss": 3.418283700942993,
|
| 631 |
+
"eval_runtime": 6.8139,
|
| 632 |
+
"eval_samples_per_second": 84.533,
|
| 633 |
+
"eval_steps_per_second": 21.133,
|
| 634 |
+
"step": 8000
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 100,
|
|
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
+
"total_flos": 1.99316647968768e+17,
|
| 655 |
"train_batch_size": 22,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|