"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629648381.0423262/events.out.tfevents.1629648381.91f414e9573a.903.171 +3 -0
- model-bin/finetune/base/log/1629649028.964446/events.out.tfevents.1629649028.91f414e9573a.903.173 +3 -0
- model-bin/finetune/base/log/1629649677.5088608/events.out.tfevents.1629649677.91f414e9573a.903.175 +3 -0
- model-bin/finetune/base/log/1629650332.2794514/events.out.tfevents.1629650332.91f414e9573a.903.177 +3 -0
- model-bin/finetune/base/log/1629650986.7762256/events.out.tfevents.1629650986.91f414e9573a.903.179 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629648381.91f414e9573a.903.170 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629649028.91f414e9573a.903.172 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629649677.91f414e9573a.903.174 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629650332.91f414e9573a.903.176 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629650986.91f414e9573a.903.178 +3 -0
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f0a4e5c5605123d444d1999eb048b6a294665a2e8fb959e481a461593203f9
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5e2f28035974664f17dd7edd6464418b9e427c0f9fc6609d85e0133a80e2ea5
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/rng_state.pth
RENAMED
|
@@ -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:ec1bafafb3d17335851d46d5908c630f2a1ae02f6a1707f1733fad584a521fb4
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/scaler.pt
RENAMED
|
@@ -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:bc7936a5f90689724c8fa26c78b2cdf2f08c5d488cad866fd2affba896c5e48d
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/scheduler.pt
RENAMED
|
@@ -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 sha256:1bf443679655490fc615e37d330a5dc6abf54a8a7093b5b65217de4c2b51f228
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20553532410779315,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -144621,11 +144621,428 @@
|
|
| 144621 |
"eval_steps_per_second": 0.657,
|
| 144622 |
"eval_wer": 0.2105802297504939,
|
| 144623 |
"step": 33220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144624 |
}
|
| 144625 |
],
|
| 144626 |
-
"max_steps":
|
| 144627 |
"num_train_epochs": 5000,
|
| 144628 |
-
"total_flos": 9.
|
| 144629 |
"trial_name": null,
|
| 144630 |
"trial_params": null
|
| 144631 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20553532410779315,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
+
"epoch": 270.0,
|
| 5 |
+
"global_step": 33843,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 144621 |
"eval_steps_per_second": 0.657,
|
| 144622 |
"eval_wer": 0.2105802297504939,
|
| 144623 |
"step": 33220
|
| 144624 |
+
},
|
| 144625 |
+
{
|
| 144626 |
+
"epoch": 267.08,
|
| 144627 |
+
"learning_rate": 9.479531502423264e-06,
|
| 144628 |
+
"loss": 0.4258,
|
| 144629 |
+
"step": 33230
|
| 144630 |
+
},
|
| 144631 |
+
{
|
| 144632 |
+
"epoch": 267.16,
|
| 144633 |
+
"learning_rate": 9.479369951534734e-06,
|
| 144634 |
+
"loss": 0.4932,
|
| 144635 |
+
"step": 33240
|
| 144636 |
+
},
|
| 144637 |
+
{
|
| 144638 |
+
"epoch": 267.24,
|
| 144639 |
+
"learning_rate": 9.479208400646205e-06,
|
| 144640 |
+
"loss": 0.9756,
|
| 144641 |
+
"step": 33250
|
| 144642 |
+
},
|
| 144643 |
+
{
|
| 144644 |
+
"epoch": 267.32,
|
| 144645 |
+
"learning_rate": 9.479046849757675e-06,
|
| 144646 |
+
"loss": 0.3886,
|
| 144647 |
+
"step": 33260
|
| 144648 |
+
},
|
| 144649 |
+
{
|
| 144650 |
+
"epoch": 267.4,
|
| 144651 |
+
"learning_rate": 9.478885298869145e-06,
|
| 144652 |
+
"loss": 1.0433,
|
| 144653 |
+
"step": 33270
|
| 144654 |
+
},
|
| 144655 |
+
{
|
| 144656 |
+
"epoch": 267.48,
|
| 144657 |
+
"learning_rate": 9.478723747980615e-06,
|
| 144658 |
+
"loss": 0.393,
|
| 144659 |
+
"step": 33280
|
| 144660 |
+
},
|
| 144661 |
+
{
|
| 144662 |
+
"epoch": 267.56,
|
| 144663 |
+
"learning_rate": 9.478562197092085e-06,
|
| 144664 |
+
"loss": 0.506,
|
| 144665 |
+
"step": 33290
|
| 144666 |
+
},
|
| 144667 |
+
{
|
| 144668 |
+
"epoch": 267.64,
|
| 144669 |
+
"learning_rate": 9.478400646203555e-06,
|
| 144670 |
+
"loss": 0.813,
|
| 144671 |
+
"step": 33300
|
| 144672 |
+
},
|
| 144673 |
+
{
|
| 144674 |
+
"epoch": 267.72,
|
| 144675 |
+
"learning_rate": 9.478239095315025e-06,
|
| 144676 |
+
"loss": 0.3862,
|
| 144677 |
+
"step": 33310
|
| 144678 |
+
},
|
| 144679 |
+
{
|
| 144680 |
+
"epoch": 267.8,
|
| 144681 |
+
"learning_rate": 9.478077544426495e-06,
|
| 144682 |
+
"loss": 0.9426,
|
| 144683 |
+
"step": 33320
|
| 144684 |
+
},
|
| 144685 |
+
{
|
| 144686 |
+
"epoch": 267.88,
|
| 144687 |
+
"learning_rate": 9.477915993537965e-06,
|
| 144688 |
+
"loss": 0.3927,
|
| 144689 |
+
"step": 33330
|
| 144690 |
+
},
|
| 144691 |
+
{
|
| 144692 |
+
"epoch": 267.96,
|
| 144693 |
+
"learning_rate": 9.477754442649435e-06,
|
| 144694 |
+
"loss": 0.4914,
|
| 144695 |
+
"step": 33340
|
| 144696 |
+
},
|
| 144697 |
+
{
|
| 144698 |
+
"epoch": 268.0,
|
| 144699 |
+
"eval_loss": 0.49841153621673584,
|
| 144700 |
+
"eval_runtime": 41.0448,
|
| 144701 |
+
"eval_samples_per_second": 20.465,
|
| 144702 |
+
"eval_steps_per_second": 0.658,
|
| 144703 |
+
"eval_wer": 0.22485207100591717,
|
| 144704 |
+
"step": 33344
|
| 144705 |
+
},
|
| 144706 |
+
{
|
| 144707 |
+
"epoch": 266.05,
|
| 144708 |
+
"learning_rate": 9.477592891760905e-06,
|
| 144709 |
+
"loss": 0.3622,
|
| 144710 |
+
"step": 33350
|
| 144711 |
+
},
|
| 144712 |
+
{
|
| 144713 |
+
"epoch": 266.13,
|
| 144714 |
+
"learning_rate": 9.477431340872375e-06,
|
| 144715 |
+
"loss": 0.3799,
|
| 144716 |
+
"step": 33360
|
| 144717 |
+
},
|
| 144718 |
+
{
|
| 144719 |
+
"epoch": 266.21,
|
| 144720 |
+
"learning_rate": 9.477269789983847e-06,
|
| 144721 |
+
"loss": 0.9389,
|
| 144722 |
+
"step": 33370
|
| 144723 |
+
},
|
| 144724 |
+
{
|
| 144725 |
+
"epoch": 266.29,
|
| 144726 |
+
"learning_rate": 9.477108239095317e-06,
|
| 144727 |
+
"loss": 0.4271,
|
| 144728 |
+
"step": 33380
|
| 144729 |
+
},
|
| 144730 |
+
{
|
| 144731 |
+
"epoch": 266.37,
|
| 144732 |
+
"learning_rate": 9.476946688206787e-06,
|
| 144733 |
+
"loss": 0.5177,
|
| 144734 |
+
"step": 33390
|
| 144735 |
+
},
|
| 144736 |
+
{
|
| 144737 |
+
"epoch": 266.45,
|
| 144738 |
+
"learning_rate": 9.476785137318257e-06,
|
| 144739 |
+
"loss": 0.8914,
|
| 144740 |
+
"step": 33400
|
| 144741 |
+
},
|
| 144742 |
+
{
|
| 144743 |
+
"epoch": 266.53,
|
| 144744 |
+
"learning_rate": 9.476623586429727e-06,
|
| 144745 |
+
"loss": 0.4472,
|
| 144746 |
+
"step": 33410
|
| 144747 |
+
},
|
| 144748 |
+
{
|
| 144749 |
+
"epoch": 266.61,
|
| 144750 |
+
"learning_rate": 9.476462035541197e-06,
|
| 144751 |
+
"loss": 1.1295,
|
| 144752 |
+
"step": 33420
|
| 144753 |
+
},
|
| 144754 |
+
{
|
| 144755 |
+
"epoch": 266.69,
|
| 144756 |
+
"learning_rate": 9.476300484652667e-06,
|
| 144757 |
+
"loss": 0.5065,
|
| 144758 |
+
"step": 33430
|
| 144759 |
+
},
|
| 144760 |
+
{
|
| 144761 |
+
"epoch": 266.77,
|
| 144762 |
+
"learning_rate": 9.476138933764137e-06,
|
| 144763 |
+
"loss": 0.515,
|
| 144764 |
+
"step": 33440
|
| 144765 |
+
},
|
| 144766 |
+
{
|
| 144767 |
+
"epoch": 266.85,
|
| 144768 |
+
"learning_rate": 9.475977382875607e-06,
|
| 144769 |
+
"loss": 0.8245,
|
| 144770 |
+
"step": 33450
|
| 144771 |
+
},
|
| 144772 |
+
{
|
| 144773 |
+
"epoch": 266.93,
|
| 144774 |
+
"learning_rate": 9.475815831987077e-06,
|
| 144775 |
+
"loss": 0.3753,
|
| 144776 |
+
"step": 33460
|
| 144777 |
+
},
|
| 144778 |
+
{
|
| 144779 |
+
"epoch": 267.0,
|
| 144780 |
+
"eval_loss": 0.38803958892822266,
|
| 144781 |
+
"eval_runtime": 39.6148,
|
| 144782 |
+
"eval_samples_per_second": 21.204,
|
| 144783 |
+
"eval_steps_per_second": 0.682,
|
| 144784 |
+
"eval_wer": 0.2110449454132993,
|
| 144785 |
+
"step": 33469
|
| 144786 |
+
},
|
| 144787 |
+
{
|
| 144788 |
+
"epoch": 269.01,
|
| 144789 |
+
"learning_rate": 9.475654281098547e-06,
|
| 144790 |
+
"loss": 0.3798,
|
| 144791 |
+
"step": 33470
|
| 144792 |
+
},
|
| 144793 |
+
{
|
| 144794 |
+
"epoch": 269.09,
|
| 144795 |
+
"learning_rate": 9.475492730210018e-06,
|
| 144796 |
+
"loss": 0.3779,
|
| 144797 |
+
"step": 33480
|
| 144798 |
+
},
|
| 144799 |
+
{
|
| 144800 |
+
"epoch": 269.17,
|
| 144801 |
+
"learning_rate": 9.475331179321488e-06,
|
| 144802 |
+
"loss": 0.6886,
|
| 144803 |
+
"step": 33490
|
| 144804 |
+
},
|
| 144805 |
+
{
|
| 144806 |
+
"epoch": 269.25,
|
| 144807 |
+
"learning_rate": 9.475169628432958e-06,
|
| 144808 |
+
"loss": 0.8083,
|
| 144809 |
+
"step": 33500
|
| 144810 |
+
},
|
| 144811 |
+
{
|
| 144812 |
+
"epoch": 269.33,
|
| 144813 |
+
"learning_rate": 9.475008077544428e-06,
|
| 144814 |
+
"loss": 0.4222,
|
| 144815 |
+
"step": 33510
|
| 144816 |
+
},
|
| 144817 |
+
{
|
| 144818 |
+
"epoch": 269.41,
|
| 144819 |
+
"learning_rate": 9.474846526655898e-06,
|
| 144820 |
+
"loss": 1.003,
|
| 144821 |
+
"step": 33520
|
| 144822 |
+
},
|
| 144823 |
+
{
|
| 144824 |
+
"epoch": 269.49,
|
| 144825 |
+
"learning_rate": 9.474684975767368e-06,
|
| 144826 |
+
"loss": 0.4091,
|
| 144827 |
+
"step": 33530
|
| 144828 |
+
},
|
| 144829 |
+
{
|
| 144830 |
+
"epoch": 269.57,
|
| 144831 |
+
"learning_rate": 9.474523424878838e-06,
|
| 144832 |
+
"loss": 0.5371,
|
| 144833 |
+
"step": 33540
|
| 144834 |
+
},
|
| 144835 |
+
{
|
| 144836 |
+
"epoch": 269.65,
|
| 144837 |
+
"learning_rate": 9.474361873990308e-06,
|
| 144838 |
+
"loss": 0.9586,
|
| 144839 |
+
"step": 33550
|
| 144840 |
+
},
|
| 144841 |
+
{
|
| 144842 |
+
"epoch": 269.73,
|
| 144843 |
+
"learning_rate": 9.474200323101778e-06,
|
| 144844 |
+
"loss": 0.4346,
|
| 144845 |
+
"step": 33560
|
| 144846 |
+
},
|
| 144847 |
+
{
|
| 144848 |
+
"epoch": 269.81,
|
| 144849 |
+
"learning_rate": 9.474038772213248e-06,
|
| 144850 |
+
"loss": 0.9465,
|
| 144851 |
+
"step": 33570
|
| 144852 |
+
},
|
| 144853 |
+
{
|
| 144854 |
+
"epoch": 269.9,
|
| 144855 |
+
"learning_rate": 9.473877221324718e-06,
|
| 144856 |
+
"loss": 0.4149,
|
| 144857 |
+
"step": 33580
|
| 144858 |
+
},
|
| 144859 |
+
{
|
| 144860 |
+
"epoch": 269.98,
|
| 144861 |
+
"learning_rate": 9.473715670436188e-06,
|
| 144862 |
+
"loss": 0.5937,
|
| 144863 |
+
"step": 33590
|
| 144864 |
+
},
|
| 144865 |
+
{
|
| 144866 |
+
"epoch": 270.0,
|
| 144867 |
+
"eval_loss": 0.4329717755317688,
|
| 144868 |
+
"eval_runtime": 42.5863,
|
| 144869 |
+
"eval_samples_per_second": 19.725,
|
| 144870 |
+
"eval_steps_per_second": 0.634,
|
| 144871 |
+
"eval_wer": 0.22144787370217608,
|
| 144872 |
+
"step": 33593
|
| 144873 |
+
},
|
| 144874 |
+
{
|
| 144875 |
+
"epoch": 268.06,
|
| 144876 |
+
"learning_rate": 9.473554119547658e-06,
|
| 144877 |
+
"loss": 0.4024,
|
| 144878 |
+
"step": 33600
|
| 144879 |
+
},
|
| 144880 |
+
{
|
| 144881 |
+
"epoch": 268.14,
|
| 144882 |
+
"learning_rate": 9.47339256865913e-06,
|
| 144883 |
+
"loss": 0.4606,
|
| 144884 |
+
"step": 33610
|
| 144885 |
+
},
|
| 144886 |
+
{
|
| 144887 |
+
"epoch": 268.22,
|
| 144888 |
+
"learning_rate": 9.4732310177706e-06,
|
| 144889 |
+
"loss": 1.0313,
|
| 144890 |
+
"step": 33620
|
| 144891 |
+
},
|
| 144892 |
+
{
|
| 144893 |
+
"epoch": 268.3,
|
| 144894 |
+
"learning_rate": 9.47306946688207e-06,
|
| 144895 |
+
"loss": 0.4023,
|
| 144896 |
+
"step": 33630
|
| 144897 |
+
},
|
| 144898 |
+
{
|
| 144899 |
+
"epoch": 268.38,
|
| 144900 |
+
"learning_rate": 9.47290791599354e-06,
|
| 144901 |
+
"loss": 0.6211,
|
| 144902 |
+
"step": 33640
|
| 144903 |
+
},
|
| 144904 |
+
{
|
| 144905 |
+
"epoch": 268.46,
|
| 144906 |
+
"learning_rate": 9.47274636510501e-06,
|
| 144907 |
+
"loss": 0.7392,
|
| 144908 |
+
"step": 33650
|
| 144909 |
+
},
|
| 144910 |
+
{
|
| 144911 |
+
"epoch": 268.54,
|
| 144912 |
+
"learning_rate": 9.47258481421648e-06,
|
| 144913 |
+
"loss": 0.4491,
|
| 144914 |
+
"step": 33660
|
| 144915 |
+
},
|
| 144916 |
+
{
|
| 144917 |
+
"epoch": 268.62,
|
| 144918 |
+
"learning_rate": 9.47242326332795e-06,
|
| 144919 |
+
"loss": 1.084,
|
| 144920 |
+
"step": 33670
|
| 144921 |
+
},
|
| 144922 |
+
{
|
| 144923 |
+
"epoch": 268.7,
|
| 144924 |
+
"learning_rate": 9.47226171243942e-06,
|
| 144925 |
+
"loss": 0.3731,
|
| 144926 |
+
"step": 33680
|
| 144927 |
+
},
|
| 144928 |
+
{
|
| 144929 |
+
"epoch": 268.78,
|
| 144930 |
+
"learning_rate": 9.47210016155089e-06,
|
| 144931 |
+
"loss": 0.5748,
|
| 144932 |
+
"step": 33690
|
| 144933 |
+
},
|
| 144934 |
+
{
|
| 144935 |
+
"epoch": 268.86,
|
| 144936 |
+
"learning_rate": 9.47193861066236e-06,
|
| 144937 |
+
"loss": 0.953,
|
| 144938 |
+
"step": 33700
|
| 144939 |
+
},
|
| 144940 |
+
{
|
| 144941 |
+
"epoch": 268.94,
|
| 144942 |
+
"learning_rate": 9.47177705977383e-06,
|
| 144943 |
+
"loss": 0.4137,
|
| 144944 |
+
"step": 33710
|
| 144945 |
+
},
|
| 144946 |
+
{
|
| 144947 |
+
"epoch": 269.0,
|
| 144948 |
+
"eval_loss": 0.5305283069610596,
|
| 144949 |
+
"eval_runtime": 42.181,
|
| 144950 |
+
"eval_samples_per_second": 19.914,
|
| 144951 |
+
"eval_steps_per_second": 0.64,
|
| 144952 |
+
"eval_wer": 0.22041829138603333,
|
| 144953 |
+
"step": 33718
|
| 144954 |
+
},
|
| 144955 |
+
{
|
| 144956 |
+
"epoch": 269.02,
|
| 144957 |
+
"learning_rate": 9.4716155088853e-06,
|
| 144958 |
+
"loss": 0.4809,
|
| 144959 |
+
"step": 33720
|
| 144960 |
+
},
|
| 144961 |
+
{
|
| 144962 |
+
"epoch": 269.1,
|
| 144963 |
+
"learning_rate": 9.47145395799677e-06,
|
| 144964 |
+
"loss": 0.3808,
|
| 144965 |
+
"step": 33730
|
| 144966 |
+
},
|
| 144967 |
+
{
|
| 144968 |
+
"epoch": 269.18,
|
| 144969 |
+
"learning_rate": 9.47129240710824e-06,
|
| 144970 |
+
"loss": 0.5942,
|
| 144971 |
+
"step": 33740
|
| 144972 |
+
},
|
| 144973 |
+
{
|
| 144974 |
+
"epoch": 269.26,
|
| 144975 |
+
"learning_rate": 9.471130856219711e-06,
|
| 144976 |
+
"loss": 0.7758,
|
| 144977 |
+
"step": 33750
|
| 144978 |
+
},
|
| 144979 |
+
{
|
| 144980 |
+
"epoch": 269.34,
|
| 144981 |
+
"learning_rate": 9.470969305331181e-06,
|
| 144982 |
+
"loss": 0.4518,
|
| 144983 |
+
"step": 33760
|
| 144984 |
+
},
|
| 144985 |
+
{
|
| 144986 |
+
"epoch": 269.42,
|
| 144987 |
+
"learning_rate": 9.470807754442651e-06,
|
| 144988 |
+
"loss": 0.9341,
|
| 144989 |
+
"step": 33770
|
| 144990 |
+
},
|
| 144991 |
+
{
|
| 144992 |
+
"epoch": 269.5,
|
| 144993 |
+
"learning_rate": 9.470646203554121e-06,
|
| 144994 |
+
"loss": 0.4235,
|
| 144995 |
+
"step": 33780
|
| 144996 |
+
},
|
| 144997 |
+
{
|
| 144998 |
+
"epoch": 269.58,
|
| 144999 |
+
"learning_rate": 9.470484652665591e-06,
|
| 145000 |
+
"loss": 0.6145,
|
| 145001 |
+
"step": 33790
|
| 145002 |
+
},
|
| 145003 |
+
{
|
| 145004 |
+
"epoch": 269.66,
|
| 145005 |
+
"learning_rate": 9.470323101777061e-06,
|
| 145006 |
+
"loss": 0.8776,
|
| 145007 |
+
"step": 33800
|
| 145008 |
+
},
|
| 145009 |
+
{
|
| 145010 |
+
"epoch": 269.74,
|
| 145011 |
+
"learning_rate": 9.47016155088853e-06,
|
| 145012 |
+
"loss": 0.4326,
|
| 145013 |
+
"step": 33810
|
| 145014 |
+
},
|
| 145015 |
+
{
|
| 145016 |
+
"epoch": 269.82,
|
| 145017 |
+
"learning_rate": 9.47e-06,
|
| 145018 |
+
"loss": 0.9869,
|
| 145019 |
+
"step": 33820
|
| 145020 |
+
},
|
| 145021 |
+
{
|
| 145022 |
+
"epoch": 269.9,
|
| 145023 |
+
"learning_rate": 9.46983844911147e-06,
|
| 145024 |
+
"loss": 0.3321,
|
| 145025 |
+
"step": 33830
|
| 145026 |
+
},
|
| 145027 |
+
{
|
| 145028 |
+
"epoch": 269.98,
|
| 145029 |
+
"learning_rate": 9.46967689822294e-06,
|
| 145030 |
+
"loss": 0.6881,
|
| 145031 |
+
"step": 33840
|
| 145032 |
+
},
|
| 145033 |
+
{
|
| 145034 |
+
"epoch": 270.0,
|
| 145035 |
+
"eval_loss": 0.4413001239299774,
|
| 145036 |
+
"eval_runtime": 41.2468,
|
| 145037 |
+
"eval_samples_per_second": 20.341,
|
| 145038 |
+
"eval_steps_per_second": 0.655,
|
| 145039 |
+
"eval_wer": 0.21317914030111282,
|
| 145040 |
+
"step": 33843
|
| 145041 |
}
|
| 145042 |
],
|
| 145043 |
+
"max_steps": 625000,
|
| 145044 |
"num_train_epochs": 5000,
|
| 145045 |
+
"total_flos": 9.523790426533496e+19,
|
| 145046 |
"trial_name": null,
|
| 145047 |
"trial_params": null
|
| 145048 |
}
|
model-bin/finetune/base/{checkpoint-33220 → checkpoint-33843}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629648381.0423262/events.out.tfevents.1629648381.91f414e9573a.903.171
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28360322def68da3118734329fd911343c3ecd27bbea07d102bb184578d7de81
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629649028.964446/events.out.tfevents.1629649028.91f414e9573a.903.173
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3dae132bdb654e09dd5402e923872f084a872cfa83ba8538552c824ef3e77c5
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629649677.5088608/events.out.tfevents.1629649677.91f414e9573a.903.175
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf7e61db90bab8508e01a464a55b0b5d3c2310f69a9a4ae88c9c12adc36e1403
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629650332.2794514/events.out.tfevents.1629650332.91f414e9573a.903.177
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90c585d546202e30a3dd3663349e2b64eb25df0b6de2096a5ecf5cf99df12ed4
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629650986.7762256/events.out.tfevents.1629650986.91f414e9573a.903.179
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09aed055ef9b390ef4c960dda9b0dc49d34f93ae543df8f8dd5a7d9cc51cd81e
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629648381.91f414e9573a.903.170
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5919f75ea3f15dc42400de2e960a884abf4afde36467a6ee0fc114e2656649b2
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629649028.91f414e9573a.903.172
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1c40b1302cc7a8ece015eb0c7308b3ae1e979f07bb8ebcb3581fd17546d2bc7
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629649677.91f414e9573a.903.174
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f0a234ff1136f117fd2455e618f08b54527b8c3b458c793a6c8c807405f16d5
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629650332.91f414e9573a.903.176
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13d19d744c7bdd799b580b9cf50b288d79dad29c342a2bfeccaef78308dbd8c5
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629650986.91f414e9573a.903.178
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:859fa98fa6a4766c9b495ebc68c6fa5d6589099fffc214eb997e284d93a1ceae
|
| 3 |
+
size 6703
|