Training in progress, step 120000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 586828837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05e2d269f333c96c29da8075e36a6de506892a84e8ab7a1d79c6b5baf653edf5
|
| 3 |
size 586828837
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cc943ae46672312ee4175b7b0df7b2bcb16bb1598452afd869122102f93e701
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3e3ff5ca04195d00ae182843134a34efdb2e565df68413f5842b7a4a84c37b
|
| 3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17a6c740782a206d1a7821b1fbc9827af7a83dbc888bd997056c93056ef861be
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 733555848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2812a708855da00be5c7a2b5b6519990cb027a8d82f04f202c74834685819f6
|
| 3 |
size 733555848
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -3306,11 +3306,311 @@
|
|
| 3306 |
"learning_rate": 0.003245247489550804,
|
| 3307 |
"loss": 8.6364,
|
| 3308 |
"step": 110000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3309 |
}
|
| 3310 |
],
|
| 3311 |
"max_steps": 1000000,
|
| 3312 |
"num_train_epochs": 5,
|
| 3313 |
-
"total_flos": 1.
|
| 3314 |
"trial_name": null,
|
| 3315 |
"trial_params": null
|
| 3316 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.51566991968441,
|
| 5 |
+
"global_step": 120000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 3306 |
"learning_rate": 0.003245247489550804,
|
| 3307 |
"loss": 8.6364,
|
| 3308 |
"step": 110000
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 0.47,
|
| 3312 |
+
"learning_rate": 0.0032544335062216403,
|
| 3313 |
+
"loss": 8.6422,
|
| 3314 |
+
"step": 110200
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.47,
|
| 3318 |
+
"learning_rate": 0.0032636280571558636,
|
| 3319 |
+
"loss": 8.618,
|
| 3320 |
+
"step": 110400
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 0.48,
|
| 3324 |
+
"learning_rate": 0.003272831102021408,
|
| 3325 |
+
"loss": 8.6276,
|
| 3326 |
+
"step": 110600
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 0.48,
|
| 3330 |
+
"learning_rate": 0.003282042600448948,
|
| 3331 |
+
"loss": 8.6454,
|
| 3332 |
+
"step": 110800
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 0.48,
|
| 3336 |
+
"learning_rate": 0.0032912625120320753,
|
| 3337 |
+
"loss": 8.6388,
|
| 3338 |
+
"step": 111000
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 0.48,
|
| 3342 |
+
"learning_rate": 0.0033004907963274733,
|
| 3343 |
+
"loss": 8.6339,
|
| 3344 |
+
"step": 111200
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 0.48,
|
| 3348 |
+
"learning_rate": 0.003309727412855108,
|
| 3349 |
+
"loss": 8.6243,
|
| 3350 |
+
"step": 111400
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 0.48,
|
| 3354 |
+
"learning_rate": 0.0033189723210983865,
|
| 3355 |
+
"loss": 8.6264,
|
| 3356 |
+
"step": 111600
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.48,
|
| 3360 |
+
"learning_rate": 0.0033282254805043487,
|
| 3361 |
+
"loss": 8.6401,
|
| 3362 |
+
"step": 111800
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 0.48,
|
| 3366 |
+
"learning_rate": 0.003337440523277331,
|
| 3367 |
+
"loss": 8.6366,
|
| 3368 |
+
"step": 112000
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 0.48,
|
| 3372 |
+
"learning_rate": 0.0033467100224565524,
|
| 3373 |
+
"loss": 8.6338,
|
| 3374 |
+
"step": 112200
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 0.48,
|
| 3378 |
+
"learning_rate": 0.003355987651126521,
|
| 3379 |
+
"loss": 8.6377,
|
| 3380 |
+
"step": 112400
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 0.48,
|
| 3384 |
+
"learning_rate": 0.0033652733685907424,
|
| 3385 |
+
"loss": 8.6414,
|
| 3386 |
+
"step": 112600
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 0.48,
|
| 3390 |
+
"learning_rate": 0.0033745671341172496,
|
| 3391 |
+
"loss": 8.6264,
|
| 3392 |
+
"step": 112800
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.49,
|
| 3396 |
+
"learning_rate": 0.0033838689069387654,
|
| 3397 |
+
"loss": 8.6289,
|
| 3398 |
+
"step": 113000
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 0.49,
|
| 3402 |
+
"learning_rate": 0.00339317864625289,
|
| 3403 |
+
"loss": 8.6244,
|
| 3404 |
+
"step": 113200
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 0.49,
|
| 3408 |
+
"learning_rate": 0.003402496311222283,
|
| 3409 |
+
"loss": 8.6287,
|
| 3410 |
+
"step": 113400
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 0.49,
|
| 3414 |
+
"learning_rate": 0.0034118218609748346,
|
| 3415 |
+
"loss": 8.6251,
|
| 3416 |
+
"step": 113600
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 0.49,
|
| 3420 |
+
"learning_rate": 0.003421155254603846,
|
| 3421 |
+
"loss": 8.6214,
|
| 3422 |
+
"step": 113800
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 0.49,
|
| 3426 |
+
"learning_rate": 0.0034304964511682147,
|
| 3427 |
+
"loss": 8.6303,
|
| 3428 |
+
"step": 114000
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 0.49,
|
| 3432 |
+
"learning_rate": 0.0034398454096926092,
|
| 3433 |
+
"loss": 8.6369,
|
| 3434 |
+
"step": 114200
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.49,
|
| 3438 |
+
"learning_rate": 0.003449202089167651,
|
| 3439 |
+
"loss": 8.6236,
|
| 3440 |
+
"step": 114400
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 0.49,
|
| 3444 |
+
"learning_rate": 0.0034585196077173436,
|
| 3445 |
+
"loss": 8.6251,
|
| 3446 |
+
"step": 114600
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 0.49,
|
| 3450 |
+
"learning_rate": 0.003467891567838331,
|
| 3451 |
+
"loss": 8.6295,
|
| 3452 |
+
"step": 114800
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 0.49,
|
| 3456 |
+
"learning_rate": 0.003477271125884973,
|
| 3457 |
+
"loss": 8.6219,
|
| 3458 |
+
"step": 115000
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"epoch": 0.5,
|
| 3462 |
+
"learning_rate": 0.0034866582407136653,
|
| 3463 |
+
"loss": 8.6271,
|
| 3464 |
+
"step": 115200
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 0.5,
|
| 3468 |
+
"learning_rate": 0.003496052871147656,
|
| 3469 |
+
"loss": 8.6372,
|
| 3470 |
+
"step": 115400
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.5,
|
| 3474 |
+
"learning_rate": 0.0035054549759772242,
|
| 3475 |
+
"loss": 8.6238,
|
| 3476 |
+
"step": 115600
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 0.5,
|
| 3480 |
+
"learning_rate": 0.0035148645139598637,
|
| 3481 |
+
"loss": 8.6207,
|
| 3482 |
+
"step": 115800
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 0.5,
|
| 3486 |
+
"learning_rate": 0.0035242814438204637,
|
| 3487 |
+
"loss": 8.6099,
|
| 3488 |
+
"step": 116000
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 0.5,
|
| 3492 |
+
"learning_rate": 0.0035337057242514833,
|
| 3493 |
+
"loss": 8.6142,
|
| 3494 |
+
"step": 116200
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 0.5,
|
| 3498 |
+
"learning_rate": 0.0035431373139131472,
|
| 3499 |
+
"loss": 8.6033,
|
| 3500 |
+
"step": 116400
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 0.5,
|
| 3504 |
+
"learning_rate": 0.0035525761714336104,
|
| 3505 |
+
"loss": 8.6178,
|
| 3506 |
+
"step": 116600
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 0.5,
|
| 3510 |
+
"learning_rate": 0.0035619750070819923,
|
| 3511 |
+
"loss": 8.6138,
|
| 3512 |
+
"step": 116800
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.5,
|
| 3516 |
+
"learning_rate": 0.0035714282402552104,
|
| 3517 |
+
"loss": 8.6143,
|
| 3518 |
+
"step": 117000
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 0.5,
|
| 3522 |
+
"learning_rate": 0.0035808886171885554,
|
| 3523 |
+
"loss": 8.6034,
|
| 3524 |
+
"step": 117200
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 0.5,
|
| 3528 |
+
"learning_rate": 0.0035903560963839124,
|
| 3529 |
+
"loss": 8.6156,
|
| 3530 |
+
"step": 117400
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 0.51,
|
| 3534 |
+
"learning_rate": 0.0035998306363120057,
|
| 3535 |
+
"loss": 8.6148,
|
| 3536 |
+
"step": 117600
|
| 3537 |
+
},
|
| 3538 |
+
{
|
| 3539 |
+
"epoch": 0.51,
|
| 3540 |
+
"learning_rate": 0.0036093121954125906,
|
| 3541 |
+
"loss": 8.6039,
|
| 3542 |
+
"step": 117800
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 0.51,
|
| 3546 |
+
"learning_rate": 0.003618800732094636,
|
| 3547 |
+
"loss": 8.6107,
|
| 3548 |
+
"step": 118000
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.51,
|
| 3552 |
+
"learning_rate": 0.0036282962047364973,
|
| 3553 |
+
"loss": 8.6094,
|
| 3554 |
+
"step": 118200
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 0.51,
|
| 3558 |
+
"learning_rate": 0.0036377985716861084,
|
| 3559 |
+
"loss": 8.616,
|
| 3560 |
+
"step": 118400
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 0.51,
|
| 3564 |
+
"learning_rate": 0.003647307791261164,
|
| 3565 |
+
"loss": 8.6135,
|
| 3566 |
+
"step": 118600
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 0.51,
|
| 3570 |
+
"learning_rate": 0.003656823821749292,
|
| 3571 |
+
"loss": 8.6062,
|
| 3572 |
+
"step": 118800
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 0.51,
|
| 3576 |
+
"learning_rate": 0.0036662989906407328,
|
| 3577 |
+
"loss": 8.6029,
|
| 3578 |
+
"step": 119000
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 0.51,
|
| 3582 |
+
"learning_rate": 0.0036758284841655496,
|
| 3583 |
+
"loss": 8.6011,
|
| 3584 |
+
"step": 119200
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"epoch": 0.51,
|
| 3588 |
+
"learning_rate": 0.0036853646634968946,
|
| 3589 |
+
"loss": 8.5993,
|
| 3590 |
+
"step": 119400
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.51,
|
| 3594 |
+
"learning_rate": 0.003694907486804143,
|
| 3595 |
+
"loss": 8.6029,
|
| 3596 |
+
"step": 119600
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 0.51,
|
| 3600 |
+
"learning_rate": 0.00370445691222752,
|
| 3601 |
+
"loss": 8.6018,
|
| 3602 |
+
"step": 119800
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 0.52,
|
| 3606 |
+
"learning_rate": 0.003714012897878298,
|
| 3607 |
+
"loss": 8.5978,
|
| 3608 |
+
"step": 120000
|
| 3609 |
}
|
| 3610 |
],
|
| 3611 |
"max_steps": 1000000,
|
| 3612 |
"num_train_epochs": 5,
|
| 3613 |
+
"total_flos": 1.9125959786496e+17,
|
| 3614 |
"trial_name": null,
|
| 3615 |
"trial_params": null
|
| 3616 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cc943ae46672312ee4175b7b0df7b2bcb16bb1598452afd869122102f93e701
|
| 3 |
size 146774203
|