"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/trainer_state.json +427 -4
- model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629671765.7944226/events.out.tfevents.1629671765.91f414e9573a.903.241 +3 -0
- model-bin/finetune/base/log/1629672429.8969986/events.out.tfevents.1629672429.91f414e9573a.903.243 +3 -0
- model-bin/finetune/base/log/1629673108.0229526/events.out.tfevents.1629673108.91f414e9573a.903.245 +3 -0
- model-bin/finetune/base/log/1629673771.683967/events.out.tfevents.1629673771.91f414e9573a.903.247 +3 -0
- model-bin/finetune/base/log/1629674445.5341618/events.out.tfevents.1629674445.91f414e9573a.903.249 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629671765.91f414e9573a.903.240 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629672429.91f414e9573a.903.242 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629673108.91f414e9573a.903.244 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629673771.91f414e9573a.903.246 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629674445.91f414e9573a.903.248 +3 -0
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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:b23dbe92b9a9b0f2545d389b2b4c38410b55351c56ad7cf8e667491d3ce606fd
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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:dc3ea9c5d0032cde98d6560845239f95bca2b29a4f78571f1e6301ef5dfdb54d
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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 sha256:9727be6c4907087a48a0644db120d7f803a56e674620ce3c4c070c5c8866c9a4
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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:a43017a9130647d3ace207df915608f175aadac0540d528125a92d3763deb621
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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:be5bdf1320f5c507d6f816207a97491072b25df99d59cb915e16d49e95f9a299
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/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,
|
|
@@ -147546,11 +147546,434 @@
|
|
| 147546 |
"eval_steps_per_second": 0.652,
|
| 147547 |
"eval_wer": 0.21095204008589835,
|
| 147548 |
"step": 37579
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147549 |
}
|
| 147550 |
],
|
| 147551 |
-
"max_steps":
|
| 147552 |
"num_train_epochs": 5000,
|
| 147553 |
-
"total_flos": 1.
|
| 147554 |
"trial_name": null,
|
| 147555 |
"trial_params": null
|
| 147556 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.20553532410779315,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-31352",
|
| 4 |
+
"epoch": 305.0,
|
| 5 |
+
"global_step": 38202,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 147546 |
"eval_steps_per_second": 0.652,
|
| 147547 |
"eval_wer": 0.21095204008589835,
|
| 147548 |
"step": 37579
|
| 147549 |
+
},
|
| 147550 |
+
{
|
| 147551 |
+
"epoch": 300.01,
|
| 147552 |
+
"learning_rate": 9.409256865912764e-06,
|
| 147553 |
+
"loss": 0.477,
|
| 147554 |
+
"step": 37580
|
| 147555 |
+
},
|
| 147556 |
+
{
|
| 147557 |
+
"epoch": 300.09,
|
| 147558 |
+
"learning_rate": 9.409095315024234e-06,
|
| 147559 |
+
"loss": 0.4243,
|
| 147560 |
+
"step": 37590
|
| 147561 |
+
},
|
| 147562 |
+
{
|
| 147563 |
+
"epoch": 300.17,
|
| 147564 |
+
"learning_rate": 9.408933764135704e-06,
|
| 147565 |
+
"loss": 0.5291,
|
| 147566 |
+
"step": 37600
|
| 147567 |
+
},
|
| 147568 |
+
{
|
| 147569 |
+
"epoch": 300.25,
|
| 147570 |
+
"learning_rate": 9.408772213247174e-06,
|
| 147571 |
+
"loss": 0.802,
|
| 147572 |
+
"step": 37610
|
| 147573 |
+
},
|
| 147574 |
+
{
|
| 147575 |
+
"epoch": 300.33,
|
| 147576 |
+
"learning_rate": 9.408610662358644e-06,
|
| 147577 |
+
"loss": 0.4141,
|
| 147578 |
+
"step": 37620
|
| 147579 |
+
},
|
| 147580 |
+
{
|
| 147581 |
+
"epoch": 300.41,
|
| 147582 |
+
"learning_rate": 9.408465266558967e-06,
|
| 147583 |
+
"loss": 1.153,
|
| 147584 |
+
"step": 37630
|
| 147585 |
+
},
|
| 147586 |
+
{
|
| 147587 |
+
"epoch": 300.49,
|
| 147588 |
+
"learning_rate": 9.408303715670437e-06,
|
| 147589 |
+
"loss": 0.417,
|
| 147590 |
+
"step": 37640
|
| 147591 |
+
},
|
| 147592 |
+
{
|
| 147593 |
+
"epoch": 300.57,
|
| 147594 |
+
"learning_rate": 9.408142164781907e-06,
|
| 147595 |
+
"loss": 0.5171,
|
| 147596 |
+
"step": 37650
|
| 147597 |
+
},
|
| 147598 |
+
{
|
| 147599 |
+
"epoch": 300.65,
|
| 147600 |
+
"learning_rate": 9.407980613893377e-06,
|
| 147601 |
+
"loss": 0.8991,
|
| 147602 |
+
"step": 37660
|
| 147603 |
+
},
|
| 147604 |
+
{
|
| 147605 |
+
"epoch": 300.73,
|
| 147606 |
+
"learning_rate": 9.407819063004847e-06,
|
| 147607 |
+
"loss": 0.3749,
|
| 147608 |
+
"step": 37670
|
| 147609 |
+
},
|
| 147610 |
+
{
|
| 147611 |
+
"epoch": 300.81,
|
| 147612 |
+
"learning_rate": 9.407657512116317e-06,
|
| 147613 |
+
"loss": 0.8874,
|
| 147614 |
+
"step": 37680
|
| 147615 |
+
},
|
| 147616 |
+
{
|
| 147617 |
+
"epoch": 300.89,
|
| 147618 |
+
"learning_rate": 9.407495961227787e-06,
|
| 147619 |
+
"loss": 0.3513,
|
| 147620 |
+
"step": 37690
|
| 147621 |
+
},
|
| 147622 |
+
{
|
| 147623 |
+
"epoch": 300.97,
|
| 147624 |
+
"learning_rate": 9.407334410339257e-06,
|
| 147625 |
+
"loss": 0.5352,
|
| 147626 |
+
"step": 37700
|
| 147627 |
+
},
|
| 147628 |
+
{
|
| 147629 |
+
"epoch": 301.0,
|
| 147630 |
+
"eval_loss": 0.505283534526825,
|
| 147631 |
+
"eval_runtime": 40.722,
|
| 147632 |
+
"eval_samples_per_second": 20.726,
|
| 147633 |
+
"eval_steps_per_second": 0.663,
|
| 147634 |
+
"eval_wer": 0.2201711946408634,
|
| 147635 |
+
"step": 37704
|
| 147636 |
+
},
|
| 147637 |
+
{
|
| 147638 |
+
"epoch": 304.05,
|
| 147639 |
+
"learning_rate": 9.407172859450727e-06,
|
| 147640 |
+
"loss": 0.3985,
|
| 147641 |
+
"step": 37710
|
| 147642 |
+
},
|
| 147643 |
+
{
|
| 147644 |
+
"epoch": 304.13,
|
| 147645 |
+
"learning_rate": 9.407011308562198e-06,
|
| 147646 |
+
"loss": 0.4454,
|
| 147647 |
+
"step": 37720
|
| 147648 |
+
},
|
| 147649 |
+
{
|
| 147650 |
+
"epoch": 304.21,
|
| 147651 |
+
"learning_rate": 9.406849757673668e-06,
|
| 147652 |
+
"loss": 0.9572,
|
| 147653 |
+
"step": 37730
|
| 147654 |
+
},
|
| 147655 |
+
{
|
| 147656 |
+
"epoch": 304.29,
|
| 147657 |
+
"learning_rate": 9.406688206785138e-06,
|
| 147658 |
+
"loss": 0.4109,
|
| 147659 |
+
"step": 37740
|
| 147660 |
+
},
|
| 147661 |
+
{
|
| 147662 |
+
"epoch": 304.37,
|
| 147663 |
+
"learning_rate": 9.406526655896608e-06,
|
| 147664 |
+
"loss": 0.5354,
|
| 147665 |
+
"step": 37750
|
| 147666 |
+
},
|
| 147667 |
+
{
|
| 147668 |
+
"epoch": 304.45,
|
| 147669 |
+
"learning_rate": 9.406365105008078e-06,
|
| 147670 |
+
"loss": 0.8301,
|
| 147671 |
+
"step": 37760
|
| 147672 |
+
},
|
| 147673 |
+
{
|
| 147674 |
+
"epoch": 304.53,
|
| 147675 |
+
"learning_rate": 9.406203554119548e-06,
|
| 147676 |
+
"loss": 0.3732,
|
| 147677 |
+
"step": 37770
|
| 147678 |
+
},
|
| 147679 |
+
{
|
| 147680 |
+
"epoch": 304.61,
|
| 147681 |
+
"learning_rate": 9.406042003231018e-06,
|
| 147682 |
+
"loss": 1.0021,
|
| 147683 |
+
"step": 37780
|
| 147684 |
+
},
|
| 147685 |
+
{
|
| 147686 |
+
"epoch": 304.69,
|
| 147687 |
+
"learning_rate": 9.405880452342488e-06,
|
| 147688 |
+
"loss": 0.3925,
|
| 147689 |
+
"step": 37790
|
| 147690 |
+
},
|
| 147691 |
+
{
|
| 147692 |
+
"epoch": 304.77,
|
| 147693 |
+
"learning_rate": 9.405718901453958e-06,
|
| 147694 |
+
"loss": 0.5981,
|
| 147695 |
+
"step": 37800
|
| 147696 |
+
},
|
| 147697 |
+
{
|
| 147698 |
+
"epoch": 304.85,
|
| 147699 |
+
"learning_rate": 9.405557350565428e-06,
|
| 147700 |
+
"loss": 0.8206,
|
| 147701 |
+
"step": 37810
|
| 147702 |
+
},
|
| 147703 |
+
{
|
| 147704 |
+
"epoch": 304.93,
|
| 147705 |
+
"learning_rate": 9.405395799676898e-06,
|
| 147706 |
+
"loss": 0.4232,
|
| 147707 |
+
"step": 37820
|
| 147708 |
+
},
|
| 147709 |
+
{
|
| 147710 |
+
"epoch": 305.0,
|
| 147711 |
+
"eval_loss": 0.4600079357624054,
|
| 147712 |
+
"eval_runtime": 41.2935,
|
| 147713 |
+
"eval_samples_per_second": 20.439,
|
| 147714 |
+
"eval_steps_per_second": 0.654,
|
| 147715 |
+
"eval_wer": 0.21618017484071714,
|
| 147716 |
+
"step": 37828
|
| 147717 |
+
},
|
| 147718 |
+
{
|
| 147719 |
+
"epoch": 302.02,
|
| 147720 |
+
"learning_rate": 9.40523424878837e-06,
|
| 147721 |
+
"loss": 0.4022,
|
| 147722 |
+
"step": 37830
|
| 147723 |
+
},
|
| 147724 |
+
{
|
| 147725 |
+
"epoch": 302.1,
|
| 147726 |
+
"learning_rate": 9.40507269789984e-06,
|
| 147727 |
+
"loss": 0.3796,
|
| 147728 |
+
"step": 37840
|
| 147729 |
+
},
|
| 147730 |
+
{
|
| 147731 |
+
"epoch": 302.18,
|
| 147732 |
+
"learning_rate": 9.40491114701131e-06,
|
| 147733 |
+
"loss": 0.5669,
|
| 147734 |
+
"step": 37850
|
| 147735 |
+
},
|
| 147736 |
+
{
|
| 147737 |
+
"epoch": 302.26,
|
| 147738 |
+
"learning_rate": 9.40474959612278e-06,
|
| 147739 |
+
"loss": 0.7573,
|
| 147740 |
+
"step": 37860
|
| 147741 |
+
},
|
| 147742 |
+
{
|
| 147743 |
+
"epoch": 302.34,
|
| 147744 |
+
"learning_rate": 9.40458804523425e-06,
|
| 147745 |
+
"loss": 0.4082,
|
| 147746 |
+
"step": 37870
|
| 147747 |
+
},
|
| 147748 |
+
{
|
| 147749 |
+
"epoch": 302.42,
|
| 147750 |
+
"learning_rate": 9.40442649434572e-06,
|
| 147751 |
+
"loss": 0.9922,
|
| 147752 |
+
"step": 37880
|
| 147753 |
+
},
|
| 147754 |
+
{
|
| 147755 |
+
"epoch": 302.5,
|
| 147756 |
+
"learning_rate": 9.40426494345719e-06,
|
| 147757 |
+
"loss": 0.3908,
|
| 147758 |
+
"step": 37890
|
| 147759 |
+
},
|
| 147760 |
+
{
|
| 147761 |
+
"epoch": 302.58,
|
| 147762 |
+
"learning_rate": 9.40410339256866e-06,
|
| 147763 |
+
"loss": 0.5494,
|
| 147764 |
+
"step": 37900
|
| 147765 |
+
},
|
| 147766 |
+
{
|
| 147767 |
+
"epoch": 302.66,
|
| 147768 |
+
"learning_rate": 9.40394184168013e-06,
|
| 147769 |
+
"loss": 0.7454,
|
| 147770 |
+
"step": 37910
|
| 147771 |
+
},
|
| 147772 |
+
{
|
| 147773 |
+
"epoch": 302.74,
|
| 147774 |
+
"learning_rate": 9.4037802907916e-06,
|
| 147775 |
+
"loss": 0.4069,
|
| 147776 |
+
"step": 37920
|
| 147777 |
+
},
|
| 147778 |
+
{
|
| 147779 |
+
"epoch": 302.82,
|
| 147780 |
+
"learning_rate": 9.40361873990307e-06,
|
| 147781 |
+
"loss": 0.9064,
|
| 147782 |
+
"step": 37930
|
| 147783 |
+
},
|
| 147784 |
+
{
|
| 147785 |
+
"epoch": 302.9,
|
| 147786 |
+
"learning_rate": 9.40345718901454e-06,
|
| 147787 |
+
"loss": 0.3413,
|
| 147788 |
+
"step": 37940
|
| 147789 |
+
},
|
| 147790 |
+
{
|
| 147791 |
+
"epoch": 302.98,
|
| 147792 |
+
"learning_rate": 9.403295638126011e-06,
|
| 147793 |
+
"loss": 0.6149,
|
| 147794 |
+
"step": 37950
|
| 147795 |
+
},
|
| 147796 |
+
{
|
| 147797 |
+
"epoch": 303.0,
|
| 147798 |
+
"eval_loss": 0.45594725012779236,
|
| 147799 |
+
"eval_runtime": 40.0976,
|
| 147800 |
+
"eval_samples_per_second": 21.024,
|
| 147801 |
+
"eval_steps_per_second": 0.673,
|
| 147802 |
+
"eval_wer": 0.21173762945914845,
|
| 147803 |
+
"step": 37953
|
| 147804 |
+
},
|
| 147805 |
+
{
|
| 147806 |
+
"epoch": 306.06,
|
| 147807 |
+
"learning_rate": 9.403134087237481e-06,
|
| 147808 |
+
"loss": 0.4376,
|
| 147809 |
+
"step": 37960
|
| 147810 |
+
},
|
| 147811 |
+
{
|
| 147812 |
+
"epoch": 306.14,
|
| 147813 |
+
"learning_rate": 9.402972536348951e-06,
|
| 147814 |
+
"loss": 0.3605,
|
| 147815 |
+
"step": 37970
|
| 147816 |
+
},
|
| 147817 |
+
{
|
| 147818 |
+
"epoch": 306.22,
|
| 147819 |
+
"learning_rate": 9.402810985460421e-06,
|
| 147820 |
+
"loss": 0.8797,
|
| 147821 |
+
"step": 37980
|
| 147822 |
+
},
|
| 147823 |
+
{
|
| 147824 |
+
"epoch": 306.3,
|
| 147825 |
+
"learning_rate": 9.402649434571891e-06,
|
| 147826 |
+
"loss": 0.5005,
|
| 147827 |
+
"step": 37990
|
| 147828 |
+
},
|
| 147829 |
+
{
|
| 147830 |
+
"epoch": 306.38,
|
| 147831 |
+
"learning_rate": 9.402487883683361e-06,
|
| 147832 |
+
"loss": 0.634,
|
| 147833 |
+
"step": 38000
|
| 147834 |
+
},
|
| 147835 |
+
{
|
| 147836 |
+
"epoch": 306.46,
|
| 147837 |
+
"learning_rate": 9.402326332794831e-06,
|
| 147838 |
+
"loss": 0.8219,
|
| 147839 |
+
"step": 38010
|
| 147840 |
+
},
|
| 147841 |
+
{
|
| 147842 |
+
"epoch": 306.54,
|
| 147843 |
+
"learning_rate": 9.402164781906301e-06,
|
| 147844 |
+
"loss": 0.3793,
|
| 147845 |
+
"step": 38020
|
| 147846 |
+
},
|
| 147847 |
+
{
|
| 147848 |
+
"epoch": 306.62,
|
| 147849 |
+
"learning_rate": 9.402003231017771e-06,
|
| 147850 |
+
"loss": 0.9421,
|
| 147851 |
+
"step": 38030
|
| 147852 |
+
},
|
| 147853 |
+
{
|
| 147854 |
+
"epoch": 306.7,
|
| 147855 |
+
"learning_rate": 9.401841680129241e-06,
|
| 147856 |
+
"loss": 0.3661,
|
| 147857 |
+
"step": 38040
|
| 147858 |
+
},
|
| 147859 |
+
{
|
| 147860 |
+
"epoch": 306.78,
|
| 147861 |
+
"learning_rate": 9.401680129240711e-06,
|
| 147862 |
+
"loss": 0.5791,
|
| 147863 |
+
"step": 38050
|
| 147864 |
+
},
|
| 147865 |
+
{
|
| 147866 |
+
"epoch": 306.86,
|
| 147867 |
+
"learning_rate": 9.401518578352181e-06,
|
| 147868 |
+
"loss": 0.7258,
|
| 147869 |
+
"step": 38060
|
| 147870 |
+
},
|
| 147871 |
+
{
|
| 147872 |
+
"epoch": 306.94,
|
| 147873 |
+
"learning_rate": 9.401357027463653e-06,
|
| 147874 |
+
"loss": 0.4455,
|
| 147875 |
+
"step": 38070
|
| 147876 |
+
},
|
| 147877 |
+
{
|
| 147878 |
+
"epoch": 307.0,
|
| 147879 |
+
"eval_loss": 0.4243174195289612,
|
| 147880 |
+
"eval_runtime": 41.12,
|
| 147881 |
+
"eval_samples_per_second": 20.525,
|
| 147882 |
+
"eval_steps_per_second": 0.657,
|
| 147883 |
+
"eval_wer": 0.20771449170872386,
|
| 147884 |
+
"step": 38077
|
| 147885 |
+
},
|
| 147886 |
+
{
|
| 147887 |
+
"epoch": 304.02,
|
| 147888 |
+
"learning_rate": 9.401195476575123e-06,
|
| 147889 |
+
"loss": 0.4662,
|
| 147890 |
+
"step": 38080
|
| 147891 |
+
},
|
| 147892 |
+
{
|
| 147893 |
+
"epoch": 304.1,
|
| 147894 |
+
"learning_rate": 9.401033925686593e-06,
|
| 147895 |
+
"loss": 0.3685,
|
| 147896 |
+
"step": 38090
|
| 147897 |
+
},
|
| 147898 |
+
{
|
| 147899 |
+
"epoch": 304.18,
|
| 147900 |
+
"learning_rate": 9.400872374798063e-06,
|
| 147901 |
+
"loss": 0.6222,
|
| 147902 |
+
"step": 38100
|
| 147903 |
+
},
|
| 147904 |
+
{
|
| 147905 |
+
"epoch": 304.26,
|
| 147906 |
+
"learning_rate": 9.400710823909533e-06,
|
| 147907 |
+
"loss": 0.7409,
|
| 147908 |
+
"step": 38110
|
| 147909 |
+
},
|
| 147910 |
+
{
|
| 147911 |
+
"epoch": 304.34,
|
| 147912 |
+
"learning_rate": 9.400549273021003e-06,
|
| 147913 |
+
"loss": 0.3942,
|
| 147914 |
+
"step": 38120
|
| 147915 |
+
},
|
| 147916 |
+
{
|
| 147917 |
+
"epoch": 304.42,
|
| 147918 |
+
"learning_rate": 9.400387722132473e-06,
|
| 147919 |
+
"loss": 0.8938,
|
| 147920 |
+
"step": 38130
|
| 147921 |
+
},
|
| 147922 |
+
{
|
| 147923 |
+
"epoch": 304.5,
|
| 147924 |
+
"learning_rate": 9.400226171243942e-06,
|
| 147925 |
+
"loss": 0.3624,
|
| 147926 |
+
"step": 38140
|
| 147927 |
+
},
|
| 147928 |
+
{
|
| 147929 |
+
"epoch": 304.58,
|
| 147930 |
+
"learning_rate": 9.400064620355412e-06,
|
| 147931 |
+
"loss": 0.6232,
|
| 147932 |
+
"step": 38150
|
| 147933 |
+
},
|
| 147934 |
+
{
|
| 147935 |
+
"epoch": 304.66,
|
| 147936 |
+
"learning_rate": 9.399903069466882e-06,
|
| 147937 |
+
"loss": 0.759,
|
| 147938 |
+
"step": 38160
|
| 147939 |
+
},
|
| 147940 |
+
{
|
| 147941 |
+
"epoch": 304.74,
|
| 147942 |
+
"learning_rate": 9.399741518578352e-06,
|
| 147943 |
+
"loss": 0.4746,
|
| 147944 |
+
"step": 38170
|
| 147945 |
+
},
|
| 147946 |
+
{
|
| 147947 |
+
"epoch": 304.82,
|
| 147948 |
+
"learning_rate": 9.399579967689824e-06,
|
| 147949 |
+
"loss": 0.9586,
|
| 147950 |
+
"step": 38180
|
| 147951 |
+
},
|
| 147952 |
+
{
|
| 147953 |
+
"epoch": 304.9,
|
| 147954 |
+
"learning_rate": 9.399418416801294e-06,
|
| 147955 |
+
"loss": 0.382,
|
| 147956 |
+
"step": 38190
|
| 147957 |
+
},
|
| 147958 |
+
{
|
| 147959 |
+
"epoch": 304.98,
|
| 147960 |
+
"learning_rate": 9.399256865912764e-06,
|
| 147961 |
+
"loss": 0.7609,
|
| 147962 |
+
"step": 38200
|
| 147963 |
+
},
|
| 147964 |
+
{
|
| 147965 |
+
"epoch": 305.0,
|
| 147966 |
+
"eval_loss": 0.44635945558547974,
|
| 147967 |
+
"eval_runtime": 40.894,
|
| 147968 |
+
"eval_samples_per_second": 20.639,
|
| 147969 |
+
"eval_steps_per_second": 0.66,
|
| 147970 |
+
"eval_wer": 0.2153924492616571,
|
| 147971 |
+
"step": 38202
|
| 147972 |
}
|
| 147973 |
],
|
| 147974 |
+
"max_steps": 625000,
|
| 147975 |
"num_train_epochs": 5000,
|
| 147976 |
+
"total_flos": 1.075021101633704e+20,
|
| 147977 |
"trial_name": null,
|
| 147978 |
"trial_params": null
|
| 147979 |
}
|
model-bin/finetune/base/{checkpoint-37579 → checkpoint-38202}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629671765.7944226/events.out.tfevents.1629671765.91f414e9573a.903.241
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fa4005b628facabf439a4f27fd2b083ff4f01d2265c2a3f2dac5e23ff88332e
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629672429.8969986/events.out.tfevents.1629672429.91f414e9573a.903.243
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1fd9009699da9dd594728649e841d76bea1d4cd942b2338590523f3eed86177
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629673108.0229526/events.out.tfevents.1629673108.91f414e9573a.903.245
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36efd931377bdfe11361e683dbd5237bcc3867a563dae9aec9707d845504fc1f
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629673771.683967/events.out.tfevents.1629673771.91f414e9573a.903.247
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:500af749e179f273d132ce7d984d6c5ce03aa184c5dc2de6af736caafa172c21
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629674445.5341618/events.out.tfevents.1629674445.91f414e9573a.903.249
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5426c0b0cb51eb181cc0e7f62ff603c3833aa8fa1ef4a779640fc31826c22aef
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629671765.91f414e9573a.903.240
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92b46272b1556dc28c00ee7c781e3f8e18d47f9c2903826cfed964eadf5fe962
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629672429.91f414e9573a.903.242
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e80aeba477f525ce8e478c9388f90db41da8ef81aba05ee4b04050a8f290f000
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629673108.91f414e9573a.903.244
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5faa43cb2077bbbbb7270afad4a0cb1b8bbecbd56ba8b3f14b8f138fce54f393
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629673771.91f414e9573a.903.246
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3787546ea3bbbb74557a9eb678c40352d0953c76cc4b7b0f9ba1a6f7a8244ecc
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629674445.91f414e9573a.903.248
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4efd55eead68d7bd03e16967e7496147c285aa276550d2a0d0aeffe2ea3ca4f8
|
| 3 |
+
size 6703
|