Training in progress, step 180000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +2 -2
- last-checkpoint/rng_state_4.pth +2 -2
- last-checkpoint/rng_state_5.pth +2 -2
- last-checkpoint/rng_state_6.pth +2 -2
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -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 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8eebb295812a5e59b8cc81c26f38269a2b08ced33ac052f5cd4b925818f5ad7
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cad91391dc5d3c8f6ec4db59f2a7b1f5a82dacf011d8f90595ac52d0f99d9d8
|
3 |
size 102501541
|
last-checkpoint/rng_state_0.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 sha256:90eeea7f53a505f798ef8d829ace86d5cfaf983bbaaec27adfb70669887b824d
|
3 |
size 14503
|
last-checkpoint/rng_state_1.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 sha256:661c5515c8356a401fd066b8dfe773c64b8d80125a03d5ce30709a3a7883c490
|
3 |
size 14503
|
last-checkpoint/rng_state_2.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 sha256:91d12617c44eee325f10a9bfc4a4d50be13d022c2f2b636ad533f25275cb2ce6
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf7bfc913575f8c458dbba1253c52eaa4a215c1e077041531924e651fe1b687
|
3 |
+
size 14439
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e827d4a09db28f6f15911529cb7e65d53bf0d6e77e09abaca568307ff57a5e8d
|
3 |
+
size 14439
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ce0c65fe2433cee8a1d4fc61a73546de1da6376b2797efc2e963c2e94a2a3d4
|
3 |
+
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6c93cf27841b4116537c16edba24b72b1b9aa431a487c8e03a40b2f1160bf8
|
3 |
+
size 14503
|
last-checkpoint/rng_state_7.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 sha256:93072fbc8e9c76b2b9e666aaadf09c064512ce4d01764f763a49ebfaf01f5177
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a265c146087c7b525f93e19ac9e51ad44bfb6af09ebd3ea4e38ee99de52c725
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 5.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3406,11 +3406,211 @@
|
|
3406 |
"eval_samples_per_second": 1892.002,
|
3407 |
"eval_steps_per_second": 30.272,
|
3408 |
"step": 170000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3409 |
}
|
3410 |
],
|
3411 |
"max_steps": 500000,
|
3412 |
"num_train_epochs": 16,
|
3413 |
-
"total_flos": 5.
|
3414 |
"trial_name": null,
|
3415 |
"trial_params": null
|
3416 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.514874842979258,
|
5 |
+
"global_step": 180000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3406 |
"eval_samples_per_second": 1892.002,
|
3407 |
"eval_steps_per_second": 30.272,
|
3408 |
"step": 170000
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 5.22,
|
3412 |
+
"learning_rate": 0.0002378846657362306,
|
3413 |
+
"loss": 0.3518,
|
3414 |
+
"step": 170500
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 5.24,
|
3418 |
+
"learning_rate": 0.00023749076897000928,
|
3419 |
+
"loss": 0.3518,
|
3420 |
+
"step": 171000
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 5.24,
|
3424 |
+
"eval_loss": 0.7876036167144775,
|
3425 |
+
"eval_runtime": 0.5137,
|
3426 |
+
"eval_samples_per_second": 1946.703,
|
3427 |
+
"eval_steps_per_second": 31.147,
|
3428 |
+
"step": 171000
|
3429 |
+
},
|
3430 |
+
{
|
3431 |
+
"epoch": 5.25,
|
3432 |
+
"learning_rate": 0.00023709597009795465,
|
3433 |
+
"loss": 0.3517,
|
3434 |
+
"step": 171500
|
3435 |
+
},
|
3436 |
+
{
|
3437 |
+
"epoch": 5.27,
|
3438 |
+
"learning_rate": 0.000236700273437524,
|
3439 |
+
"loss": 0.3515,
|
3440 |
+
"step": 172000
|
3441 |
+
},
|
3442 |
+
{
|
3443 |
+
"epoch": 5.27,
|
3444 |
+
"eval_loss": 0.780876100063324,
|
3445 |
+
"eval_runtime": 0.5145,
|
3446 |
+
"eval_samples_per_second": 1943.544,
|
3447 |
+
"eval_steps_per_second": 31.097,
|
3448 |
+
"step": 172000
|
3449 |
+
},
|
3450 |
+
{
|
3451 |
+
"epoch": 5.29,
|
3452 |
+
"learning_rate": 0.0002363036833159925,
|
3453 |
+
"loss": 0.3509,
|
3454 |
+
"step": 172500
|
3455 |
+
},
|
3456 |
+
{
|
3457 |
+
"epoch": 5.3,
|
3458 |
+
"learning_rate": 0.00023590620407040633,
|
3459 |
+
"loss": 0.351,
|
3460 |
+
"step": 173000
|
3461 |
+
},
|
3462 |
+
{
|
3463 |
+
"epoch": 5.3,
|
3464 |
+
"eval_loss": 0.7936240434646606,
|
3465 |
+
"eval_runtime": 0.5234,
|
3466 |
+
"eval_samples_per_second": 1910.641,
|
3467 |
+
"eval_steps_per_second": 30.57,
|
3468 |
+
"step": 173000
|
3469 |
+
},
|
3470 |
+
{
|
3471 |
+
"epoch": 5.32,
|
3472 |
+
"learning_rate": 0.00023550784004753471,
|
3473 |
+
"loss": 0.3512,
|
3474 |
+
"step": 173500
|
3475 |
+
},
|
3476 |
+
{
|
3477 |
+
"epoch": 5.33,
|
3478 |
+
"learning_rate": 0.0002351085956038229,
|
3479 |
+
"loss": 0.3508,
|
3480 |
+
"step": 174000
|
3481 |
+
},
|
3482 |
+
{
|
3483 |
+
"epoch": 5.33,
|
3484 |
+
"eval_loss": 0.7791932225227356,
|
3485 |
+
"eval_runtime": 0.5202,
|
3486 |
+
"eval_samples_per_second": 1922.513,
|
3487 |
+
"eval_steps_per_second": 30.76,
|
3488 |
+
"step": 174000
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 5.35,
|
3492 |
+
"learning_rate": 0.00023470847510534407,
|
3493 |
+
"loss": 0.3507,
|
3494 |
+
"step": 174500
|
3495 |
+
},
|
3496 |
+
{
|
3497 |
+
"epoch": 5.36,
|
3498 |
+
"learning_rate": 0.00023430748292775188,
|
3499 |
+
"loss": 0.3508,
|
3500 |
+
"step": 175000
|
3501 |
+
},
|
3502 |
+
{
|
3503 |
+
"epoch": 5.36,
|
3504 |
+
"eval_loss": 0.783431887626648,
|
3505 |
+
"eval_runtime": 0.5231,
|
3506 |
+
"eval_samples_per_second": 1911.723,
|
3507 |
+
"eval_steps_per_second": 30.588,
|
3508 |
+
"step": 175000
|
3509 |
+
},
|
3510 |
+
{
|
3511 |
+
"epoch": 5.38,
|
3512 |
+
"learning_rate": 0.0002339056234562326,
|
3513 |
+
"loss": 0.3505,
|
3514 |
+
"step": 175500
|
3515 |
+
},
|
3516 |
+
{
|
3517 |
+
"epoch": 5.39,
|
3518 |
+
"learning_rate": 0.00023350290108545694,
|
3519 |
+
"loss": 0.3505,
|
3520 |
+
"step": 176000
|
3521 |
+
},
|
3522 |
+
{
|
3523 |
+
"epoch": 5.39,
|
3524 |
+
"eval_loss": 0.787056028842926,
|
3525 |
+
"eval_runtime": 0.5298,
|
3526 |
+
"eval_samples_per_second": 1887.522,
|
3527 |
+
"eval_steps_per_second": 30.2,
|
3528 |
+
"step": 176000
|
3529 |
+
},
|
3530 |
+
{
|
3531 |
+
"epoch": 5.41,
|
3532 |
+
"learning_rate": 0.00023309932021953238,
|
3533 |
+
"loss": 0.3502,
|
3534 |
+
"step": 176500
|
3535 |
+
},
|
3536 |
+
{
|
3537 |
+
"epoch": 5.42,
|
3538 |
+
"learning_rate": 0.00023269488527195446,
|
3539 |
+
"loss": 0.3504,
|
3540 |
+
"step": 177000
|
3541 |
+
},
|
3542 |
+
{
|
3543 |
+
"epoch": 5.42,
|
3544 |
+
"eval_loss": 0.7937799692153931,
|
3545 |
+
"eval_runtime": 0.5254,
|
3546 |
+
"eval_samples_per_second": 1903.32,
|
3547 |
+
"eval_steps_per_second": 30.453,
|
3548 |
+
"step": 177000
|
3549 |
+
},
|
3550 |
+
{
|
3551 |
+
"epoch": 5.44,
|
3552 |
+
"learning_rate": 0.00023228960066555907,
|
3553 |
+
"loss": 0.3515,
|
3554 |
+
"step": 177500
|
3555 |
+
},
|
3556 |
+
{
|
3557 |
+
"epoch": 5.45,
|
3558 |
+
"learning_rate": 0.00023188347083247365,
|
3559 |
+
"loss": 0.3499,
|
3560 |
+
"step": 178000
|
3561 |
+
},
|
3562 |
+
{
|
3563 |
+
"epoch": 5.45,
|
3564 |
+
"eval_loss": 0.7750864028930664,
|
3565 |
+
"eval_runtime": 0.5058,
|
3566 |
+
"eval_samples_per_second": 1977.117,
|
3567 |
+
"eval_steps_per_second": 31.634,
|
3568 |
+
"step": 178000
|
3569 |
+
},
|
3570 |
+
{
|
3571 |
+
"epoch": 5.47,
|
3572 |
+
"learning_rate": 0.00023147650021406905,
|
3573 |
+
"loss": 0.3502,
|
3574 |
+
"step": 178500
|
3575 |
+
},
|
3576 |
+
{
|
3577 |
+
"epoch": 5.48,
|
3578 |
+
"learning_rate": 0.00023106869326091075,
|
3579 |
+
"loss": 0.3493,
|
3580 |
+
"step": 179000
|
3581 |
+
},
|
3582 |
+
{
|
3583 |
+
"epoch": 5.48,
|
3584 |
+
"eval_loss": 0.7836278080940247,
|
3585 |
+
"eval_runtime": 0.5246,
|
3586 |
+
"eval_samples_per_second": 1906.272,
|
3587 |
+
"eval_steps_per_second": 30.5,
|
3588 |
+
"step": 179000
|
3589 |
+
},
|
3590 |
+
{
|
3591 |
+
"epoch": 5.5,
|
3592 |
+
"learning_rate": 0.00023066005443271017,
|
3593 |
+
"loss": 0.3496,
|
3594 |
+
"step": 179500
|
3595 |
+
},
|
3596 |
+
{
|
3597 |
+
"epoch": 5.51,
|
3598 |
+
"learning_rate": 0.00023025058819827618,
|
3599 |
+
"loss": 0.349,
|
3600 |
+
"step": 180000
|
3601 |
+
},
|
3602 |
+
{
|
3603 |
+
"epoch": 5.51,
|
3604 |
+
"eval_loss": 0.7845665216445923,
|
3605 |
+
"eval_runtime": 0.5357,
|
3606 |
+
"eval_samples_per_second": 1866.879,
|
3607 |
+
"eval_steps_per_second": 29.87,
|
3608 |
+
"step": 180000
|
3609 |
}
|
3610 |
],
|
3611 |
"max_steps": 500000,
|
3612 |
"num_train_epochs": 16,
|
3613 |
+
"total_flos": 5.750728558181121e+21,
|
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 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cad91391dc5d3c8f6ec4db59f2a7b1f5a82dacf011d8f90595ac52d0f99d9d8
|
3 |
size 102501541
|