Training in progress, step 400, 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 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6b5c8ae3ce3b75a3efb3cea4f0f22e522106b7a7a11f76b184da7ea8f0464cc
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abe10937b2346f32a25ef8a726c3a45c358a8eb207991431dcbb7ddc785c611f
|
| 3 |
size 469516363
|
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:ba03b8c06ab7ab86dfbcbefe7ba1358ea78b1ce004b09a6a9e08759669880b0f
|
| 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:b1c37070e6eb9d511a4f7c71d2c3f18ff0f2b091f4acb310e39c4f3f39019ddf
|
| 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": 50,
|
| 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": 5.514,
|
| 321 |
"eval_steps_per_second": 2.832,
|
| 322 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 323 |
}
|
| 324 |
],
|
| 325 |
"logging_steps": 5,
|
|
@@ -339,7 +651,7 @@
|
|
| 339 |
"attributes": {}
|
| 340 |
}
|
| 341 |
},
|
| 342 |
-
"total_flos":
|
| 343 |
"train_batch_size": 2,
|
| 344 |
"trial_name": null,
|
| 345 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4,
|
| 6 |
"eval_steps": 50,
|
| 7 |
+
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 320 |
"eval_samples_per_second": 5.514,
|
| 321 |
"eval_steps_per_second": 2.832,
|
| 322 |
"step": 200
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.205,
|
| 326 |
+
"grad_norm": 9.0625,
|
| 327 |
+
"learning_rate": 5e-05,
|
| 328 |
+
"loss": 3.09683895111084,
|
| 329 |
+
"step": 205
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.21,
|
| 333 |
+
"grad_norm": 43.25,
|
| 334 |
+
"learning_rate": 5e-05,
|
| 335 |
+
"loss": 3.141134834289551,
|
| 336 |
+
"step": 210
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.215,
|
| 340 |
+
"grad_norm": 2.4375,
|
| 341 |
+
"learning_rate": 5e-05,
|
| 342 |
+
"loss": 3.100748825073242,
|
| 343 |
+
"step": 215
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.22,
|
| 347 |
+
"grad_norm": 12.5625,
|
| 348 |
+
"learning_rate": 5e-05,
|
| 349 |
+
"loss": 3.0931968688964844,
|
| 350 |
+
"step": 220
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.225,
|
| 354 |
+
"grad_norm": 4.53125,
|
| 355 |
+
"learning_rate": 5e-05,
|
| 356 |
+
"loss": 3.0807849884033205,
|
| 357 |
+
"step": 225
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.23,
|
| 361 |
+
"grad_norm": 5.03125,
|
| 362 |
+
"learning_rate": 5e-05,
|
| 363 |
+
"loss": 3.1373645782470705,
|
| 364 |
+
"step": 230
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.235,
|
| 368 |
+
"grad_norm": 482.0,
|
| 369 |
+
"learning_rate": 5e-05,
|
| 370 |
+
"loss": 3.086713409423828,
|
| 371 |
+
"step": 235
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.24,
|
| 375 |
+
"grad_norm": 8.8125,
|
| 376 |
+
"learning_rate": 5e-05,
|
| 377 |
+
"loss": 3.107415199279785,
|
| 378 |
+
"step": 240
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.245,
|
| 382 |
+
"grad_norm": 35.25,
|
| 383 |
+
"learning_rate": 5e-05,
|
| 384 |
+
"loss": 3.1350580215454102,
|
| 385 |
+
"step": 245
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.25,
|
| 389 |
+
"grad_norm": 10.8125,
|
| 390 |
+
"learning_rate": 5e-05,
|
| 391 |
+
"loss": 3.085038757324219,
|
| 392 |
+
"step": 250
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.25,
|
| 396 |
+
"eval_loss": 3.35124135017395,
|
| 397 |
+
"eval_runtime": 6.7488,
|
| 398 |
+
"eval_samples_per_second": 5.482,
|
| 399 |
+
"eval_steps_per_second": 2.815,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.255,
|
| 404 |
+
"grad_norm": 7.78125,
|
| 405 |
+
"learning_rate": 5e-05,
|
| 406 |
+
"loss": 3.0779041290283202,
|
| 407 |
+
"step": 255
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.26,
|
| 411 |
+
"grad_norm": 8.9375,
|
| 412 |
+
"learning_rate": 5e-05,
|
| 413 |
+
"loss": 3.0426475524902346,
|
| 414 |
+
"step": 260
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.265,
|
| 418 |
+
"grad_norm": 1.9765625,
|
| 419 |
+
"learning_rate": 5e-05,
|
| 420 |
+
"loss": 3.108402442932129,
|
| 421 |
+
"step": 265
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.27,
|
| 425 |
+
"grad_norm": 10.125,
|
| 426 |
+
"learning_rate": 5e-05,
|
| 427 |
+
"loss": 3.068155288696289,
|
| 428 |
+
"step": 270
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.275,
|
| 432 |
+
"grad_norm": 25.625,
|
| 433 |
+
"learning_rate": 5e-05,
|
| 434 |
+
"loss": 3.0750944137573244,
|
| 435 |
+
"step": 275
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.28,
|
| 439 |
+
"grad_norm": 1.609375,
|
| 440 |
+
"learning_rate": 5e-05,
|
| 441 |
+
"loss": 3.0479175567626955,
|
| 442 |
+
"step": 280
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.285,
|
| 446 |
+
"grad_norm": 50.75,
|
| 447 |
+
"learning_rate": 5e-05,
|
| 448 |
+
"loss": 3.088734817504883,
|
| 449 |
+
"step": 285
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.29,
|
| 453 |
+
"grad_norm": 8.8125,
|
| 454 |
+
"learning_rate": 5e-05,
|
| 455 |
+
"loss": 3.0425872802734375,
|
| 456 |
+
"step": 290
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.295,
|
| 460 |
+
"grad_norm": 18.5,
|
| 461 |
+
"learning_rate": 5e-05,
|
| 462 |
+
"loss": 3.0785484313964844,
|
| 463 |
+
"step": 295
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.3,
|
| 467 |
+
"grad_norm": 7.3125,
|
| 468 |
+
"learning_rate": 5e-05,
|
| 469 |
+
"loss": 3.067402648925781,
|
| 470 |
+
"step": 300
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.3,
|
| 474 |
+
"eval_loss": 3.339944839477539,
|
| 475 |
+
"eval_runtime": 6.7462,
|
| 476 |
+
"eval_samples_per_second": 5.485,
|
| 477 |
+
"eval_steps_per_second": 2.816,
|
| 478 |
+
"step": 300
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.305,
|
| 482 |
+
"grad_norm": 7.25,
|
| 483 |
+
"learning_rate": 5e-05,
|
| 484 |
+
"loss": 3.063138961791992,
|
| 485 |
+
"step": 305
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.31,
|
| 489 |
+
"grad_norm": 22.5,
|
| 490 |
+
"learning_rate": 5e-05,
|
| 491 |
+
"loss": 3.0437475204467774,
|
| 492 |
+
"step": 310
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.315,
|
| 496 |
+
"grad_norm": 9.75,
|
| 497 |
+
"learning_rate": 5e-05,
|
| 498 |
+
"loss": 3.0719404220581055,
|
| 499 |
+
"step": 315
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.32,
|
| 503 |
+
"grad_norm": 8.75,
|
| 504 |
+
"learning_rate": 5e-05,
|
| 505 |
+
"loss": 3.0688711166381837,
|
| 506 |
+
"step": 320
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.325,
|
| 510 |
+
"grad_norm": 2.671875,
|
| 511 |
+
"learning_rate": 5e-05,
|
| 512 |
+
"loss": 3.0548662185668944,
|
| 513 |
+
"step": 325
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.33,
|
| 517 |
+
"grad_norm": 12.6875,
|
| 518 |
+
"learning_rate": 5e-05,
|
| 519 |
+
"loss": 3.057333564758301,
|
| 520 |
+
"step": 330
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.335,
|
| 524 |
+
"grad_norm": 298.0,
|
| 525 |
+
"learning_rate": 5e-05,
|
| 526 |
+
"loss": 3.0870180130004883,
|
| 527 |
+
"step": 335
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.34,
|
| 531 |
+
"grad_norm": 18.375,
|
| 532 |
+
"learning_rate": 5e-05,
|
| 533 |
+
"loss": 3.051515579223633,
|
| 534 |
+
"step": 340
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.345,
|
| 538 |
+
"grad_norm": 44.0,
|
| 539 |
+
"learning_rate": 5e-05,
|
| 540 |
+
"loss": 3.0610748291015626,
|
| 541 |
+
"step": 345
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.35,
|
| 545 |
+
"grad_norm": 11.6875,
|
| 546 |
+
"learning_rate": 5e-05,
|
| 547 |
+
"loss": 3.02484016418457,
|
| 548 |
+
"step": 350
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.35,
|
| 552 |
+
"eval_loss": 3.328155755996704,
|
| 553 |
+
"eval_runtime": 6.6732,
|
| 554 |
+
"eval_samples_per_second": 5.545,
|
| 555 |
+
"eval_steps_per_second": 2.847,
|
| 556 |
+
"step": 350
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.355,
|
| 560 |
+
"grad_norm": 17.875,
|
| 561 |
+
"learning_rate": 5e-05,
|
| 562 |
+
"loss": 3.0564363479614256,
|
| 563 |
+
"step": 355
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.36,
|
| 567 |
+
"grad_norm": 2.6875,
|
| 568 |
+
"learning_rate": 5e-05,
|
| 569 |
+
"loss": 3.068992805480957,
|
| 570 |
+
"step": 360
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.365,
|
| 574 |
+
"grad_norm": 1.5078125,
|
| 575 |
+
"learning_rate": 5e-05,
|
| 576 |
+
"loss": 3.0664575576782225,
|
| 577 |
+
"step": 365
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.37,
|
| 581 |
+
"grad_norm": 204.0,
|
| 582 |
+
"learning_rate": 5e-05,
|
| 583 |
+
"loss": 3.015609931945801,
|
| 584 |
+
"step": 370
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.375,
|
| 588 |
+
"grad_norm": 296.0,
|
| 589 |
+
"learning_rate": 5e-05,
|
| 590 |
+
"loss": 3.0494104385375977,
|
| 591 |
+
"step": 375
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.38,
|
| 595 |
+
"grad_norm": 1024.0,
|
| 596 |
+
"learning_rate": 5e-05,
|
| 597 |
+
"loss": 3.0338293075561524,
|
| 598 |
+
"step": 380
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.385,
|
| 602 |
+
"grad_norm": 7.4375,
|
| 603 |
+
"learning_rate": 5e-05,
|
| 604 |
+
"loss": 3.037934684753418,
|
| 605 |
+
"step": 385
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.39,
|
| 609 |
+
"grad_norm": 3.28125,
|
| 610 |
+
"learning_rate": 5e-05,
|
| 611 |
+
"loss": 3.0603221893310546,
|
| 612 |
+
"step": 390
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.395,
|
| 616 |
+
"grad_norm": 17.125,
|
| 617 |
+
"learning_rate": 5e-05,
|
| 618 |
+
"loss": 3.0717981338500975,
|
| 619 |
+
"step": 395
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4,
|
| 623 |
+
"grad_norm": 44.75,
|
| 624 |
+
"learning_rate": 5e-05,
|
| 625 |
+
"loss": 3.0237457275390627,
|
| 626 |
+
"step": 400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4,
|
| 630 |
+
"eval_loss": 3.322870969772339,
|
| 631 |
+
"eval_runtime": 6.749,
|
| 632 |
+
"eval_samples_per_second": 5.482,
|
| 633 |
+
"eval_steps_per_second": 2.815,
|
| 634 |
+
"step": 400
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 5,
|
|
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
+
"total_flos": 1.159660497272832e+17,
|
| 655 |
"train_batch_size": 2,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|