Training in progress, step 1950000
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 +383 -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 893439185
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24480137122a3ca1298b2aa2acbf1d8e05d75ba9f182abd41ff9618c60e00071
|
| 3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4158aaedff079b2378ceb72199c920ad399c00fbc03838dbc3a2204ee0d64219
|
| 3 |
size 449471589
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a16c585a386790723cc51bc4a838a254dc71110b475f7ebf887ed7011d90a8f
|
| 3 |
size 21579
|
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:abaeb1638369c701afb9b3b4e706b5c028681adb6ebf26ba2bfe37402d287efd
|
| 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 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2c8322c0057a49117b93f76b6d690bf483c56843cf994e2b3614611effcb47d
|
| 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": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -14446,11 +14446,391 @@
|
|
| 14446 |
"eval_samples_per_second": 79.467,
|
| 14447 |
"eval_steps_per_second": 0.621,
|
| 14448 |
"step": 1900000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14449 |
}
|
| 14450 |
],
|
| 14451 |
"max_steps": 2000000,
|
| 14452 |
"num_train_epochs": 9223372036854775807,
|
| 14453 |
-
"total_flos": 1.
|
| 14454 |
"trial_name": null,
|
| 14455 |
"trial_params": null
|
| 14456 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.075,
|
| 5 |
+
"global_step": 1950000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 14446 |
"eval_samples_per_second": 79.467,
|
| 14447 |
"eval_steps_per_second": 0.621,
|
| 14448 |
"step": 1900000
|
| 14449 |
+
},
|
| 14450 |
+
{
|
| 14451 |
+
"epoch": 0.05,
|
| 14452 |
+
"learning_rate": 1.105744066188684e-05,
|
| 14453 |
+
"loss": 0.4371,
|
| 14454 |
+
"step": 1901000
|
| 14455 |
+
},
|
| 14456 |
+
{
|
| 14457 |
+
"epoch": 0.05,
|
| 14458 |
+
"learning_rate": 1.1036390191576373e-05,
|
| 14459 |
+
"loss": 0.4379,
|
| 14460 |
+
"step": 1902000
|
| 14461 |
+
},
|
| 14462 |
+
{
|
| 14463 |
+
"epoch": 0.05,
|
| 14464 |
+
"learning_rate": 1.1015549796381372e-05,
|
| 14465 |
+
"loss": 0.4373,
|
| 14466 |
+
"step": 1903000
|
| 14467 |
+
},
|
| 14468 |
+
{
|
| 14469 |
+
"epoch": 0.05,
|
| 14470 |
+
"learning_rate": 1.0994960590538279e-05,
|
| 14471 |
+
"loss": 0.4375,
|
| 14472 |
+
"step": 1904000
|
| 14473 |
+
},
|
| 14474 |
+
{
|
| 14475 |
+
"epoch": 0.05,
|
| 14476 |
+
"learning_rate": 1.0974540114919287e-05,
|
| 14477 |
+
"loss": 0.4363,
|
| 14478 |
+
"step": 1905000
|
| 14479 |
+
},
|
| 14480 |
+
{
|
| 14481 |
+
"epoch": 0.05,
|
| 14482 |
+
"eval_loss": 0.4150693416595459,
|
| 14483 |
+
"eval_runtime": 80.8571,
|
| 14484 |
+
"eval_samples_per_second": 79.152,
|
| 14485 |
+
"eval_steps_per_second": 0.618,
|
| 14486 |
+
"step": 1905000
|
| 14487 |
+
},
|
| 14488 |
+
{
|
| 14489 |
+
"epoch": 0.05,
|
| 14490 |
+
"learning_rate": 1.0954329902821809e-05,
|
| 14491 |
+
"loss": 0.4375,
|
| 14492 |
+
"step": 1906000
|
| 14493 |
+
},
|
| 14494 |
+
{
|
| 14495 |
+
"epoch": 0.05,
|
| 14496 |
+
"learning_rate": 1.0934330015809674e-05,
|
| 14497 |
+
"loss": 0.437,
|
| 14498 |
+
"step": 1907000
|
| 14499 |
+
},
|
| 14500 |
+
{
|
| 14501 |
+
"epoch": 0.05,
|
| 14502 |
+
"learning_rate": 1.0914560199199067e-05,
|
| 14503 |
+
"loss": 0.4379,
|
| 14504 |
+
"step": 1908000
|
| 14505 |
+
},
|
| 14506 |
+
{
|
| 14507 |
+
"epoch": 0.05,
|
| 14508 |
+
"learning_rate": 1.0894980934009906e-05,
|
| 14509 |
+
"loss": 0.4372,
|
| 14510 |
+
"step": 1909000
|
| 14511 |
+
},
|
| 14512 |
+
{
|
| 14513 |
+
"epoch": 0.06,
|
| 14514 |
+
"learning_rate": 1.0875612174693328e-05,
|
| 14515 |
+
"loss": 0.437,
|
| 14516 |
+
"step": 1910000
|
| 14517 |
+
},
|
| 14518 |
+
{
|
| 14519 |
+
"epoch": 0.06,
|
| 14520 |
+
"eval_loss": 0.4164562225341797,
|
| 14521 |
+
"eval_runtime": 79.4864,
|
| 14522 |
+
"eval_samples_per_second": 80.517,
|
| 14523 |
+
"eval_steps_per_second": 0.629,
|
| 14524 |
+
"step": 1910000
|
| 14525 |
+
},
|
| 14526 |
+
{
|
| 14527 |
+
"epoch": 0.06,
|
| 14528 |
+
"learning_rate": 1.0856473033247752e-05,
|
| 14529 |
+
"loss": 0.4369,
|
| 14530 |
+
"step": 1911000
|
| 14531 |
+
},
|
| 14532 |
+
{
|
| 14533 |
+
"epoch": 0.06,
|
| 14534 |
+
"learning_rate": 1.0837525251384567e-05,
|
| 14535 |
+
"loss": 0.4367,
|
| 14536 |
+
"step": 1912000
|
| 14537 |
+
},
|
| 14538 |
+
{
|
| 14539 |
+
"epoch": 0.06,
|
| 14540 |
+
"learning_rate": 1.0818806782260748e-05,
|
| 14541 |
+
"loss": 0.4367,
|
| 14542 |
+
"step": 1913000
|
| 14543 |
+
},
|
| 14544 |
+
{
|
| 14545 |
+
"epoch": 0.06,
|
| 14546 |
+
"learning_rate": 1.0800280208492865e-05,
|
| 14547 |
+
"loss": 0.4379,
|
| 14548 |
+
"step": 1914000
|
| 14549 |
+
},
|
| 14550 |
+
{
|
| 14551 |
+
"epoch": 0.06,
|
| 14552 |
+
"learning_rate": 1.0781982639541429e-05,
|
| 14553 |
+
"loss": 0.4373,
|
| 14554 |
+
"step": 1915000
|
| 14555 |
+
},
|
| 14556 |
+
{
|
| 14557 |
+
"epoch": 0.06,
|
| 14558 |
+
"eval_loss": 0.4175663888454437,
|
| 14559 |
+
"eval_runtime": 80.7249,
|
| 14560 |
+
"eval_samples_per_second": 79.282,
|
| 14561 |
+
"eval_steps_per_second": 0.619,
|
| 14562 |
+
"step": 1915000
|
| 14563 |
+
},
|
| 14564 |
+
{
|
| 14565 |
+
"epoch": 0.06,
|
| 14566 |
+
"learning_rate": 1.0763895499185767e-05,
|
| 14567 |
+
"loss": 0.4362,
|
| 14568 |
+
"step": 1916000
|
| 14569 |
+
},
|
| 14570 |
+
{
|
| 14571 |
+
"epoch": 0.06,
|
| 14572 |
+
"learning_rate": 1.0746001053331784e-05,
|
| 14573 |
+
"loss": 0.4367,
|
| 14574 |
+
"step": 1917000
|
| 14575 |
+
},
|
| 14576 |
+
{
|
| 14577 |
+
"epoch": 0.06,
|
| 14578 |
+
"learning_rate": 1.0728317567168942e-05,
|
| 14579 |
+
"loss": 0.4373,
|
| 14580 |
+
"step": 1918000
|
| 14581 |
+
},
|
| 14582 |
+
{
|
| 14583 |
+
"epoch": 0.06,
|
| 14584 |
+
"learning_rate": 1.0710845094564199e-05,
|
| 14585 |
+
"loss": 0.4377,
|
| 14586 |
+
"step": 1919000
|
| 14587 |
+
},
|
| 14588 |
+
{
|
| 14589 |
+
"epoch": 0.06,
|
| 14590 |
+
"learning_rate": 1.0693583688741745e-05,
|
| 14591 |
+
"loss": 0.4364,
|
| 14592 |
+
"step": 1920000
|
| 14593 |
+
},
|
| 14594 |
+
{
|
| 14595 |
+
"epoch": 0.06,
|
| 14596 |
+
"eval_loss": 0.4133068919181824,
|
| 14597 |
+
"eval_runtime": 78.4611,
|
| 14598 |
+
"eval_samples_per_second": 81.569,
|
| 14599 |
+
"eval_steps_per_second": 0.637,
|
| 14600 |
+
"step": 1920000
|
| 14601 |
+
},
|
| 14602 |
+
{
|
| 14603 |
+
"epoch": 0.06,
|
| 14604 |
+
"learning_rate": 1.0676550347097805e-05,
|
| 14605 |
+
"loss": 0.4376,
|
| 14606 |
+
"step": 1921000
|
| 14607 |
+
},
|
| 14608 |
+
{
|
| 14609 |
+
"epoch": 0.06,
|
| 14610 |
+
"learning_rate": 1.06597110207435e-05,
|
| 14611 |
+
"loss": 0.437,
|
| 14612 |
+
"step": 1922000
|
| 14613 |
+
},
|
| 14614 |
+
{
|
| 14615 |
+
"epoch": 0.06,
|
| 14616 |
+
"learning_rate": 1.0643082916934733e-05,
|
| 14617 |
+
"loss": 0.4378,
|
| 14618 |
+
"step": 1923000
|
| 14619 |
+
},
|
| 14620 |
+
{
|
| 14621 |
+
"epoch": 0.06,
|
| 14622 |
+
"learning_rate": 1.0626682397606544e-05,
|
| 14623 |
+
"loss": 0.4365,
|
| 14624 |
+
"step": 1924000
|
| 14625 |
+
},
|
| 14626 |
+
{
|
| 14627 |
+
"epoch": 0.06,
|
| 14628 |
+
"learning_rate": 1.0610492778999931e-05,
|
| 14629 |
+
"loss": 0.4366,
|
| 14630 |
+
"step": 1925000
|
| 14631 |
+
},
|
| 14632 |
+
{
|
| 14633 |
+
"epoch": 0.06,
|
| 14634 |
+
"eval_loss": 0.41611722111701965,
|
| 14635 |
+
"eval_runtime": 81.6547,
|
| 14636 |
+
"eval_samples_per_second": 78.379,
|
| 14637 |
+
"eval_steps_per_second": 0.612,
|
| 14638 |
+
"step": 1925000
|
| 14639 |
+
},
|
| 14640 |
+
{
|
| 14641 |
+
"epoch": 0.06,
|
| 14642 |
+
"learning_rate": 1.059449822137189e-05,
|
| 14643 |
+
"loss": 0.4372,
|
| 14644 |
+
"step": 1926000
|
| 14645 |
+
},
|
| 14646 |
+
{
|
| 14647 |
+
"epoch": 0.06,
|
| 14648 |
+
"learning_rate": 1.0578715084938887e-05,
|
| 14649 |
+
"loss": 0.4374,
|
| 14650 |
+
"step": 1927000
|
| 14651 |
+
},
|
| 14652 |
+
{
|
| 14653 |
+
"epoch": 0.06,
|
| 14654 |
+
"learning_rate": 1.0563143417779096e-05,
|
| 14655 |
+
"loss": 0.4366,
|
| 14656 |
+
"step": 1928000
|
| 14657 |
+
},
|
| 14658 |
+
{
|
| 14659 |
+
"epoch": 0.06,
|
| 14660 |
+
"learning_rate": 1.0547798521808734e-05,
|
| 14661 |
+
"loss": 0.437,
|
| 14662 |
+
"step": 1929000
|
| 14663 |
+
},
|
| 14664 |
+
{
|
| 14665 |
+
"epoch": 0.07,
|
| 14666 |
+
"learning_rate": 1.0532649723266384e-05,
|
| 14667 |
+
"loss": 0.4365,
|
| 14668 |
+
"step": 1930000
|
| 14669 |
+
},
|
| 14670 |
+
{
|
| 14671 |
+
"epoch": 0.07,
|
| 14672 |
+
"eval_loss": 0.4162156581878662,
|
| 14673 |
+
"eval_runtime": 80.1168,
|
| 14674 |
+
"eval_samples_per_second": 79.883,
|
| 14675 |
+
"eval_steps_per_second": 0.624,
|
| 14676 |
+
"step": 1930000
|
| 14677 |
+
},
|
| 14678 |
+
{
|
| 14679 |
+
"epoch": 0.07,
|
| 14680 |
+
"learning_rate": 1.0517727365795085e-05,
|
| 14681 |
+
"loss": 0.4369,
|
| 14682 |
+
"step": 1931000
|
| 14683 |
+
},
|
| 14684 |
+
{
|
| 14685 |
+
"epoch": 0.07,
|
| 14686 |
+
"learning_rate": 1.0503001620268975e-05,
|
| 14687 |
+
"loss": 0.4373,
|
| 14688 |
+
"step": 1932000
|
| 14689 |
+
},
|
| 14690 |
+
{
|
| 14691 |
+
"epoch": 0.07,
|
| 14692 |
+
"learning_rate": 1.0488487574652423e-05,
|
| 14693 |
+
"loss": 0.4374,
|
| 14694 |
+
"step": 1933000
|
| 14695 |
+
},
|
| 14696 |
+
{
|
| 14697 |
+
"epoch": 0.07,
|
| 14698 |
+
"learning_rate": 1.0474199469678468e-05,
|
| 14699 |
+
"loss": 0.437,
|
| 14700 |
+
"step": 1934000
|
| 14701 |
+
},
|
| 14702 |
+
{
|
| 14703 |
+
"epoch": 0.07,
|
| 14704 |
+
"learning_rate": 1.0460108744063674e-05,
|
| 14705 |
+
"loss": 0.4369,
|
| 14706 |
+
"step": 1935000
|
| 14707 |
+
},
|
| 14708 |
+
{
|
| 14709 |
+
"epoch": 0.07,
|
| 14710 |
+
"eval_loss": 0.4142652451992035,
|
| 14711 |
+
"eval_runtime": 77.8865,
|
| 14712 |
+
"eval_samples_per_second": 82.171,
|
| 14713 |
+
"eval_steps_per_second": 0.642,
|
| 14714 |
+
"step": 1935000
|
| 14715 |
+
},
|
| 14716 |
+
{
|
| 14717 |
+
"epoch": 0.07,
|
| 14718 |
+
"learning_rate": 1.0446243622089129e-05,
|
| 14719 |
+
"loss": 0.4389,
|
| 14720 |
+
"step": 1936000
|
| 14721 |
+
},
|
| 14722 |
+
{
|
| 14723 |
+
"epoch": 0.07,
|
| 14724 |
+
"learning_rate": 1.0432576387995491e-05,
|
| 14725 |
+
"loss": 0.4371,
|
| 14726 |
+
"step": 1937000
|
| 14727 |
+
},
|
| 14728 |
+
{
|
| 14729 |
+
"epoch": 0.07,
|
| 14730 |
+
"learning_rate": 1.0419121068338878e-05,
|
| 14731 |
+
"loss": 0.4372,
|
| 14732 |
+
"step": 1938000
|
| 14733 |
+
},
|
| 14734 |
+
{
|
| 14735 |
+
"epoch": 0.07,
|
| 14736 |
+
"learning_rate": 1.0405877704106532e-05,
|
| 14737 |
+
"loss": 0.4366,
|
| 14738 |
+
"step": 1939000
|
| 14739 |
+
},
|
| 14740 |
+
{
|
| 14741 |
+
"epoch": 0.07,
|
| 14742 |
+
"learning_rate": 1.0392859261103349e-05,
|
| 14743 |
+
"loss": 0.4355,
|
| 14744 |
+
"step": 1940000
|
| 14745 |
+
},
|
| 14746 |
+
{
|
| 14747 |
+
"epoch": 0.07,
|
| 14748 |
+
"eval_loss": 0.4190742075443268,
|
| 14749 |
+
"eval_runtime": 80.8959,
|
| 14750 |
+
"eval_samples_per_second": 79.114,
|
| 14751 |
+
"eval_steps_per_second": 0.618,
|
| 14752 |
+
"step": 1940000
|
| 14753 |
+
},
|
| 14754 |
+
{
|
| 14755 |
+
"epoch": 0.07,
|
| 14756 |
+
"learning_rate": 1.0380039716043426e-05,
|
| 14757 |
+
"loss": 0.4357,
|
| 14758 |
+
"step": 1941000
|
| 14759 |
+
},
|
| 14760 |
+
{
|
| 14761 |
+
"epoch": 0.07,
|
| 14762 |
+
"learning_rate": 1.0367432245456347e-05,
|
| 14763 |
+
"loss": 0.4362,
|
| 14764 |
+
"step": 1942000
|
| 14765 |
+
},
|
| 14766 |
+
{
|
| 14767 |
+
"epoch": 0.07,
|
| 14768 |
+
"learning_rate": 1.0355049177141353e-05,
|
| 14769 |
+
"loss": 0.4362,
|
| 14770 |
+
"step": 1943000
|
| 14771 |
+
},
|
| 14772 |
+
{
|
| 14773 |
+
"epoch": 0.07,
|
| 14774 |
+
"learning_rate": 1.0342865757898152e-05,
|
| 14775 |
+
"loss": 0.437,
|
| 14776 |
+
"step": 1944000
|
| 14777 |
+
},
|
| 14778 |
+
{
|
| 14779 |
+
"epoch": 0.07,
|
| 14780 |
+
"learning_rate": 1.0330906391597708e-05,
|
| 14781 |
+
"loss": 0.4357,
|
| 14782 |
+
"step": 1945000
|
| 14783 |
+
},
|
| 14784 |
+
{
|
| 14785 |
+
"epoch": 0.07,
|
| 14786 |
+
"eval_loss": 0.4155297577381134,
|
| 14787 |
+
"eval_runtime": 77.8064,
|
| 14788 |
+
"eval_samples_per_second": 82.255,
|
| 14789 |
+
"eval_steps_per_second": 0.643,
|
| 14790 |
+
"step": 1945000
|
| 14791 |
+
},
|
| 14792 |
+
{
|
| 14793 |
+
"epoch": 0.07,
|
| 14794 |
+
"learning_rate": 1.0319147172001108e-05,
|
| 14795 |
+
"loss": 0.4367,
|
| 14796 |
+
"step": 1946000
|
| 14797 |
+
},
|
| 14798 |
+
{
|
| 14799 |
+
"epoch": 0.07,
|
| 14800 |
+
"learning_rate": 1.0307600212366596e-05,
|
| 14801 |
+
"loss": 0.4355,
|
| 14802 |
+
"step": 1947000
|
| 14803 |
+
},
|
| 14804 |
+
{
|
| 14805 |
+
"epoch": 0.07,
|
| 14806 |
+
"learning_rate": 1.029627677647975e-05,
|
| 14807 |
+
"loss": 0.4367,
|
| 14808 |
+
"step": 1948000
|
| 14809 |
+
},
|
| 14810 |
+
{
|
| 14811 |
+
"epoch": 0.07,
|
| 14812 |
+
"learning_rate": 1.0285154229298157e-05,
|
| 14813 |
+
"loss": 0.4369,
|
| 14814 |
+
"step": 1949000
|
| 14815 |
+
},
|
| 14816 |
+
{
|
| 14817 |
+
"epoch": 0.07,
|
| 14818 |
+
"learning_rate": 1.0274244045627054e-05,
|
| 14819 |
+
"loss": 0.4373,
|
| 14820 |
+
"step": 1950000
|
| 14821 |
+
},
|
| 14822 |
+
{
|
| 14823 |
+
"epoch": 0.07,
|
| 14824 |
+
"eval_loss": 0.41703131794929504,
|
| 14825 |
+
"eval_runtime": 77.2751,
|
| 14826 |
+
"eval_samples_per_second": 82.821,
|
| 14827 |
+
"eval_steps_per_second": 0.647,
|
| 14828 |
+
"step": 1950000
|
| 14829 |
}
|
| 14830 |
],
|
| 14831 |
"max_steps": 2000000,
|
| 14832 |
"num_train_epochs": 9223372036854775807,
|
| 14833 |
+
"total_flos": 1.7086938841350144e+22,
|
| 14834 |
"trial_name": null,
|
| 14835 |
"trial_params": null
|
| 14836 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 449471589
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4158aaedff079b2378ceb72199c920ad399c00fbc03838dbc3a2204ee0d64219
|
| 3 |
size 449471589
|