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 253577648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432cd4b3f20b2d6b60bb6abf5d4699a91e48537ef0ed052bfe0d334aff3b31bf
|
| 3 |
size 253577648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 37798173
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47dfb8bdf14d7cfe7ba9207ba749f2873b045289c0d4506db957b0945ea255b
|
| 3 |
size 37798173
|
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:a5efa17066b0a1d4b6e03d692b024a4c72e68b8316289796ae7ade09fa5d1efd
|
| 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:f927da8d60437265b92417ce9964e2748b26b27fe8a5e4da654d140885fdf9c1
|
| 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": 1.482,
|
| 321 |
"eval_steps_per_second": 0.298,
|
| 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": 1.482,
|
| 321 |
"eval_steps_per_second": 0.298,
|
| 322 |
"step": 200
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.205,
|
| 326 |
+
"grad_norm": 5811.900390625,
|
| 327 |
+
"learning_rate": 0.00018382315692263323,
|
| 328 |
+
"loss": 3.4652740478515627,
|
| 329 |
+
"step": 205
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.21,
|
| 333 |
+
"grad_norm": 1784.0272216796875,
|
| 334 |
+
"learning_rate": 0.00018293377532205968,
|
| 335 |
+
"loss": 3.136703681945801,
|
| 336 |
+
"step": 210
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.215,
|
| 340 |
+
"grad_norm": 8352.1416015625,
|
| 341 |
+
"learning_rate": 0.0001820228682553533,
|
| 342 |
+
"loss": 3.3410572052001952,
|
| 343 |
+
"step": 215
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.22,
|
| 347 |
+
"grad_norm": 9626.669921875,
|
| 348 |
+
"learning_rate": 0.00018109067214849538,
|
| 349 |
+
"loss": 3.3538772583007814,
|
| 350 |
+
"step": 220
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.225,
|
| 354 |
+
"grad_norm": 5929.7529296875,
|
| 355 |
+
"learning_rate": 0.00018013742895303883,
|
| 356 |
+
"loss": 3.598949432373047,
|
| 357 |
+
"step": 225
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.23,
|
| 361 |
+
"grad_norm": 280.86492919921875,
|
| 362 |
+
"learning_rate": 0.0001791633860833096,
|
| 363 |
+
"loss": 3.4480300903320313,
|
| 364 |
+
"step": 230
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.235,
|
| 368 |
+
"grad_norm": 19.305431365966797,
|
| 369 |
+
"learning_rate": 0.00017816879635219028,
|
| 370 |
+
"loss": 3.521527099609375,
|
| 371 |
+
"step": 235
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.24,
|
| 375 |
+
"grad_norm": 11.262675285339355,
|
| 376 |
+
"learning_rate": 0.00017715391790550252,
|
| 377 |
+
"loss": 3.543391799926758,
|
| 378 |
+
"step": 240
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.245,
|
| 382 |
+
"grad_norm": 107.26178741455078,
|
| 383 |
+
"learning_rate": 0.00017611901415500535,
|
| 384 |
+
"loss": 3.380891799926758,
|
| 385 |
+
"step": 245
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.25,
|
| 389 |
+
"grad_norm": 0.6105318069458008,
|
| 390 |
+
"learning_rate": 0.00017506435371002633,
|
| 391 |
+
"loss": 3.2983978271484373,
|
| 392 |
+
"step": 250
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.25,
|
| 396 |
+
"eval_loss": 3.6096248626708984,
|
| 397 |
+
"eval_runtime": 200.7485,
|
| 398 |
+
"eval_samples_per_second": 1.484,
|
| 399 |
+
"eval_steps_per_second": 0.299,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.255,
|
| 404 |
+
"grad_norm": 1.168889045715332,
|
| 405 |
+
"learning_rate": 0.00017399021030774442,
|
| 406 |
+
"loss": 3.5202346801757813,
|
| 407 |
+
"step": 255
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.26,
|
| 411 |
+
"grad_norm": 4.2245283126831055,
|
| 412 |
+
"learning_rate": 0.00017289686274214118,
|
| 413 |
+
"loss": 3.2942405700683595,
|
| 414 |
+
"step": 260
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.265,
|
| 418 |
+
"grad_norm": 0.3621503710746765,
|
| 419 |
+
"learning_rate": 0.00017178459479163976,
|
| 420 |
+
"loss": 3.4601863861083983,
|
| 421 |
+
"step": 265
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.27,
|
| 425 |
+
"grad_norm": 35.780120849609375,
|
| 426 |
+
"learning_rate": 0.00017065369514545053,
|
| 427 |
+
"loss": 3.2967288970947264,
|
| 428 |
+
"step": 270
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.275,
|
| 432 |
+
"grad_norm": 474.76861572265625,
|
| 433 |
+
"learning_rate": 0.00016950445732864127,
|
| 434 |
+
"loss": 3.4325428009033203,
|
| 435 |
+
"step": 275
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.28,
|
| 439 |
+
"grad_norm": 2.8445627689361572,
|
| 440 |
+
"learning_rate": 0.00016833717962595326,
|
| 441 |
+
"loss": 3.3004375457763673,
|
| 442 |
+
"step": 280
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.285,
|
| 446 |
+
"grad_norm": 19.516523361206055,
|
| 447 |
+
"learning_rate": 0.00016715216500438093,
|
| 448 |
+
"loss": 3.612904739379883,
|
| 449 |
+
"step": 285
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.29,
|
| 453 |
+
"grad_norm": 25.849435806274414,
|
| 454 |
+
"learning_rate": 0.00016594972103453726,
|
| 455 |
+
"loss": 3.567874526977539,
|
| 456 |
+
"step": 290
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.295,
|
| 460 |
+
"grad_norm": 58.06301498413086,
|
| 461 |
+
"learning_rate": 0.00016473015981082338,
|
| 462 |
+
"loss": 3.525835418701172,
|
| 463 |
+
"step": 295
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.3,
|
| 467 |
+
"grad_norm": 191.27548217773438,
|
| 468 |
+
"learning_rate": 0.00016349379787042477,
|
| 469 |
+
"loss": 3.3833484649658203,
|
| 470 |
+
"step": 300
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.3,
|
| 474 |
+
"eval_loss": 3.7416040897369385,
|
| 475 |
+
"eval_runtime": 200.7531,
|
| 476 |
+
"eval_samples_per_second": 1.484,
|
| 477 |
+
"eval_steps_per_second": 0.299,
|
| 478 |
+
"step": 300
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.305,
|
| 482 |
+
"grad_norm": 56.349708557128906,
|
| 483 |
+
"learning_rate": 0.00016224095611115384,
|
| 484 |
+
"loss": 3.6572975158691405,
|
| 485 |
+
"step": 305
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.31,
|
| 489 |
+
"grad_norm": 1745.9088134765625,
|
| 490 |
+
"learning_rate": 0.00016097195970816094,
|
| 491 |
+
"loss": 3.601942443847656,
|
| 492 |
+
"step": 310
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.315,
|
| 496 |
+
"grad_norm": 1165.1402587890625,
|
| 497 |
+
"learning_rate": 0.0001596871380295351,
|
| 498 |
+
"loss": 3.6535247802734374,
|
| 499 |
+
"step": 315
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.32,
|
| 503 |
+
"grad_norm": 46.510684967041016,
|
| 504 |
+
"learning_rate": 0.00015838682455081657,
|
| 505 |
+
"loss": 3.5322292327880858,
|
| 506 |
+
"step": 320
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.325,
|
| 510 |
+
"grad_norm": 147.2434539794922,
|
| 511 |
+
"learning_rate": 0.0001570713567684432,
|
| 512 |
+
"loss": 3.4837066650390627,
|
| 513 |
+
"step": 325
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.33,
|
| 517 |
+
"grad_norm": 7.8114013671875,
|
| 518 |
+
"learning_rate": 0.00015574107611215319,
|
| 519 |
+
"loss": 3.5842933654785156,
|
| 520 |
+
"step": 330
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.335,
|
| 524 |
+
"grad_norm": 40.32650375366211,
|
| 525 |
+
"learning_rate": 0.00015439632785636706,
|
| 526 |
+
"loss": 3.451204299926758,
|
| 527 |
+
"step": 335
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.34,
|
| 531 |
+
"grad_norm": 54.91672134399414,
|
| 532 |
+
"learning_rate": 0.00015303746103057162,
|
| 533 |
+
"loss": 3.6410243988037108,
|
| 534 |
+
"step": 340
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.345,
|
| 538 |
+
"grad_norm": 143.5968017578125,
|
| 539 |
+
"learning_rate": 0.00015166482832872923,
|
| 540 |
+
"loss": 3.567627716064453,
|
| 541 |
+
"step": 345
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.35,
|
| 545 |
+
"grad_norm": 66.56953430175781,
|
| 546 |
+
"learning_rate": 0.00015027878601773633,
|
| 547 |
+
"loss": 3.7443378448486326,
|
| 548 |
+
"step": 350
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.35,
|
| 552 |
+
"eval_loss": 3.8730692863464355,
|
| 553 |
+
"eval_runtime": 200.7554,
|
| 554 |
+
"eval_samples_per_second": 1.484,
|
| 555 |
+
"eval_steps_per_second": 0.299,
|
| 556 |
+
"step": 350
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.355,
|
| 560 |
+
"grad_norm": 109.56166076660156,
|
| 561 |
+
"learning_rate": 0.00014887969384495402,
|
| 562 |
+
"loss": 3.7462512969970705,
|
| 563 |
+
"step": 355
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.36,
|
| 567 |
+
"grad_norm": 403.760986328125,
|
| 568 |
+
"learning_rate": 0.00014746791494483583,
|
| 569 |
+
"loss": 3.4167720794677736,
|
| 570 |
+
"step": 360
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.365,
|
| 574 |
+
"grad_norm": 78.5467300415039,
|
| 575 |
+
"learning_rate": 0.00014604381574467615,
|
| 576 |
+
"loss": 3.653825378417969,
|
| 577 |
+
"step": 365
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.37,
|
| 581 |
+
"grad_norm": 7.657294273376465,
|
| 582 |
+
"learning_rate": 0.00014460776586950393,
|
| 583 |
+
"loss": 3.5837642669677736,
|
| 584 |
+
"step": 370
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.375,
|
| 588 |
+
"grad_norm": 232.22654724121094,
|
| 589 |
+
"learning_rate": 0.00014316013804614643,
|
| 590 |
+
"loss": 3.5867897033691407,
|
| 591 |
+
"step": 375
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.38,
|
| 595 |
+
"grad_norm": 34.94912338256836,
|
| 596 |
+
"learning_rate": 0.00014170130800648814,
|
| 597 |
+
"loss": 3.5861190795898437,
|
| 598 |
+
"step": 380
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.385,
|
| 602 |
+
"grad_norm": 91.70198059082031,
|
| 603 |
+
"learning_rate": 0.0001402316543899493,
|
| 604 |
+
"loss": 3.66529541015625,
|
| 605 |
+
"step": 385
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.39,
|
| 609 |
+
"grad_norm": 25.11287498474121,
|
| 610 |
+
"learning_rate": 0.0001387515586452103,
|
| 611 |
+
"loss": 3.6498741149902343,
|
| 612 |
+
"step": 390
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.395,
|
| 616 |
+
"grad_norm": 93.66793060302734,
|
| 617 |
+
"learning_rate": 0.0001372614049312064,
|
| 618 |
+
"loss": 3.352254867553711,
|
| 619 |
+
"step": 395
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4,
|
| 623 |
+
"grad_norm": 4.588032245635986,
|
| 624 |
+
"learning_rate": 0.00013576158001741932,
|
| 625 |
+
"loss": 3.517344665527344,
|
| 626 |
+
"step": 400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4,
|
| 630 |
+
"eval_loss": 3.753708839416504,
|
| 631 |
+
"eval_runtime": 200.6183,
|
| 632 |
+
"eval_samples_per_second": 1.485,
|
| 633 |
+
"eval_steps_per_second": 0.299,
|
| 634 |
+
"step": 400
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 5,
|
|
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
+
"total_flos": 1904846517043200.0,
|
| 655 |
"train_batch_size": 2,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|