Training in progress, step 80000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- 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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -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:ff5c6edbd27558aca49d30391d1ef6740f42d89e02202741bfa6556c5bb200e6
|
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:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
|
3 |
size 449471589
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d9b61cee8ca67c27f0f3d2f6e201039abcc50fe9c69747f98360b11e440474
|
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 sha256:8a497315615827dbfe07ef4ef54afba40b23c55667dfa82ac40626574a432d00
|
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 sha256:7f62de7b3720d73b36506a2be2c357e852a008b86421c13562a927e573a51594
|
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:b65baacae1e9b6120b362e0290a5ce659aa309c6bbced410beb869eaf2627764
|
3 |
+
size 14439
|
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:e52a6dd6fc2ba6933bc667fca14386a68b07572a9b1700ef8ab0b34bba18efa7
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -524,11 +524,85 @@
|
|
524 |
"eval_samples_per_second": 881.784,
|
525 |
"eval_steps_per_second": 14.109,
|
526 |
"step": 70000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
527 |
}
|
528 |
],
|
529 |
"max_steps": 1000000,
|
530 |
"num_train_epochs": 16,
|
531 |
-
"total_flos":
|
532 |
"trial_name": null,
|
533 |
"trial_params": null
|
534 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2216165040389695,
|
5 |
+
"global_step": 80000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
524 |
"eval_samples_per_second": 881.784,
|
525 |
"eval_steps_per_second": 14.109,
|
526 |
"step": 70000
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.08,
|
530 |
+
"learning_rate": 0.00014983127298555198,
|
531 |
+
"loss": 0.4114,
|
532 |
+
"step": 71000
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.1,
|
536 |
+
"learning_rate": 0.00014981482840217632,
|
537 |
+
"loss": 0.4086,
|
538 |
+
"step": 72000
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.11,
|
542 |
+
"learning_rate": 0.00014979762033502262,
|
543 |
+
"loss": 0.4066,
|
544 |
+
"step": 73000
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.13,
|
548 |
+
"learning_rate": 0.00014977964897227547,
|
549 |
+
"loss": 0.4042,
|
550 |
+
"step": 74000
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.15,
|
554 |
+
"learning_rate": 0.00014976091451046687,
|
555 |
+
"loss": 0.402,
|
556 |
+
"step": 75000
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.15,
|
560 |
+
"eval_runtime": 1.0331,
|
561 |
+
"eval_samples_per_second": 967.957,
|
562 |
+
"eval_steps_per_second": 15.487,
|
563 |
+
"step": 75000
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.16,
|
567 |
+
"learning_rate": 0.00014974141715447386,
|
568 |
+
"loss": 0.3999,
|
569 |
+
"step": 76000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.18,
|
573 |
+
"learning_rate": 0.00014972115711751644,
|
574 |
+
"loss": 0.398,
|
575 |
+
"step": 77000
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 1.19,
|
579 |
+
"learning_rate": 0.00014970013462115505,
|
580 |
+
"loss": 0.3971,
|
581 |
+
"step": 78000
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 1.21,
|
585 |
+
"learning_rate": 0.00014967834989528843,
|
586 |
+
"loss": 0.3942,
|
587 |
+
"step": 79000
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.22,
|
591 |
+
"learning_rate": 0.00014965580317815078,
|
592 |
+
"loss": 0.3926,
|
593 |
+
"step": 80000
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 1.22,
|
597 |
+
"eval_runtime": 1.084,
|
598 |
+
"eval_samples_per_second": 922.521,
|
599 |
+
"eval_steps_per_second": 14.76,
|
600 |
+
"step": 80000
|
601 |
}
|
602 |
],
|
603 |
"max_steps": 1000000,
|
604 |
"num_train_epochs": 16,
|
605 |
+
"total_flos": 5.608014311746284e+21,
|
606 |
"trial_name": null,
|
607 |
"trial_params": null
|
608 |
}
|
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:a1666258a1f724f902b9aa295ec67f13a120dd77f80fd4e6bc4d68349a651a63
|
3 |
size 449471589
|