Hugging Face's logo

Check
/
vaw2tmp

TensorBoard
Model card Files
xet
 Metrics Community
Check commited on
Commit
4a381dd
·
1 Parent(s): 558fc8a

"auto-commit"

Browse files
Files changed (28) hide show
  1. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/config.json +0 -0
  2. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/optimizer.pt +1 -1
  3. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/preprocessor_config.json +0 -0
  4. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/pytorch_model.bin +1 -1
  5. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/rng_state.pth +1 -1
  6. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/scaler.pt +1 -1
  7. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/scheduler.pt +1 -1
  8. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/trainer_state.json +173 -5
  9. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/training_args.bin +0 -0
  10. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/config.json +0 -0
  11. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/optimizer.pt +1 -1
  12. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/preprocessor_config.json +0 -0
  13. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/pytorch_model.bin +1 -1
  14. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/rng_state.pth +1 -1
  15. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/scaler.pt +1 -1
  16. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/scheduler.pt +1 -1
  17. model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/trainer_state.json +590 -5
  18. model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/training_args.bin +0 -0
  19. model-bin/finetune/base/log/1629631576.8245854/events.out.tfevents.1629631576.91f414e9573a.903.121 +3 -0
  20. model-bin/finetune/base/log/1629632245.5141647/events.out.tfevents.1629632245.91f414e9573a.903.123 +3 -0
  21. model-bin/finetune/base/log/1629632908.002072/events.out.tfevents.1629632908.91f414e9573a.903.125 +3 -0
  22. model-bin/finetune/base/log/1629633565.1667113/events.out.tfevents.1629633565.91f414e9573a.903.127 +3 -0
  23. model-bin/finetune/base/log/1629634215.195126/events.out.tfevents.1629634215.91f414e9573a.903.129 +3 -0
  24. model-bin/finetune/base/log/events.out.tfevents.1629631576.91f414e9573a.903.120 +3 -0
  25. model-bin/finetune/base/log/events.out.tfevents.1629632245.91f414e9573a.903.122 +3 -0
  26. model-bin/finetune/base/log/events.out.tfevents.1629632907.91f414e9573a.903.124 +3 -0
  27. model-bin/finetune/base/log/events.out.tfevents.1629633565.91f414e9573a.903.126 +3 -0
  28. model-bin/finetune/base/log/events.out.tfevents.1629634215.91f414e9573a.903.128 +3 -0
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/config.json RENAMED
File without changes
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec0e229020f67c2d68dd952f7dcc4657f9a5452192a5e6730ab0da35ab965c31
3
  size 722165009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9ee8d766214d031cdc985f4d958ed8ec67ad37612c118468e8e9c073edcd03
3
  size 722165009
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/preprocessor_config.json RENAMED
File without changes
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d37eaf44d655f05cbf9b7cddc5dc43e671d116c17dbe3cb595e5b79acbca047
3
  size 377909911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ee96b444f7db9a09b869a8f3bc62708a8a1f4b43155eada0751d8a4bf2595d
3
  size 377909911
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cda43cf035dad1ae1b31e1f29afdb614a52bc44b561c2247dddf21e7685b82a
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317d760f12bb3cfed8a67e00f24c419e4bba159c5f040f68dbe6cfbb08d72488
3
  size 14503
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e823e293f122f500d37aed0e4cbb93f2648f03767613829430ff15253fe550c6
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3b1810a033427b234e2bffc73d00c710ede62d1be2ca4c7afaaf9e382d34f3
3
  size 559
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5df7e5a9c44d1626634682fbeeff2e3b7498a14b177073babc59285d7b637663
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f8965a6462743a6c2b77f38ebb0292c9257d6107d272e3fead403cfb0f44ef
3
  size 623
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30356}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.21391886862672124,
3
- "best_model_checkpoint": "./model-bin/finetune/base/checkpoint-29856",
4
- "epoch": 240.0,
5
- "global_step": 30106,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -142524,11 +142524,179 @@
142524
  "eval_steps_per_second": 0.64,
142525
  "eval_wer": 0.21980373349074006,
142526
  "step": 30106
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142527
  }
142528
  ],
142529
  "max_steps": 625000,
142530
  "num_train_epochs": 5000,
142531
- "total_flos": 8.470893127626274e+19,
142532
  "trial_name": null,
142533
  "trial_params": null
142534
  }
 
1
  {
2
+ "best_metric": 0.20691915513474143,
3
+ "best_model_checkpoint": "./model-bin/finetune/base/checkpoint-30356",
4
+ "epoch": 242.0,
5
+ "global_step": 30356,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
142524
  "eval_steps_per_second": 0.64,
142525
  "eval_wer": 0.21980373349074006,
142526
  "step": 30106
142527
+ },
142528
+ {
142529
+ "epoch": 240.03,
142530
+ "learning_rate": 9.52988691437803e-06,
142531
+ "loss": 0.4113,
142532
+ "step": 30110
142533
+ },
142534
+ {
142535
+ "epoch": 240.11,
142536
+ "learning_rate": 9.5297253634895e-06,
142537
+ "loss": 0.4046,
142538
+ "step": 30120
142539
+ },
142540
+ {
142541
+ "epoch": 240.19,
142542
+ "learning_rate": 9.52956381260097e-06,
142543
+ "loss": 0.7785,
142544
+ "step": 30130
142545
+ },
142546
+ {
142547
+ "epoch": 240.27,
142548
+ "learning_rate": 9.52940226171244e-06,
142549
+ "loss": 0.586,
142550
+ "step": 30140
142551
+ },
142552
+ {
142553
+ "epoch": 240.35,
142554
+ "learning_rate": 9.52924071082391e-06,
142555
+ "loss": 0.4595,
142556
+ "step": 30150
142557
+ },
142558
+ {
142559
+ "epoch": 240.43,
142560
+ "learning_rate": 9.529079159935381e-06,
142561
+ "loss": 1.0085,
142562
+ "step": 30160
142563
+ },
142564
+ {
142565
+ "epoch": 240.51,
142566
+ "learning_rate": 9.528917609046851e-06,
142567
+ "loss": 0.4297,
142568
+ "step": 30170
142569
+ },
142570
+ {
142571
+ "epoch": 240.59,
142572
+ "learning_rate": 9.528756058158321e-06,
142573
+ "loss": 0.8259,
142574
+ "step": 30180
142575
+ },
142576
+ {
142577
+ "epoch": 240.67,
142578
+ "learning_rate": 9.528610662358644e-06,
142579
+ "loss": 0.6529,
142580
+ "step": 30190
142581
+ },
142582
+ {
142583
+ "epoch": 240.75,
142584
+ "learning_rate": 9.528449111470114e-06,
142585
+ "loss": 0.5276,
142586
+ "step": 30200
142587
+ },
142588
+ {
142589
+ "epoch": 240.83,
142590
+ "learning_rate": 9.528287560581584e-06,
142591
+ "loss": 1.0096,
142592
+ "step": 30210
142593
+ },
142594
+ {
142595
+ "epoch": 240.91,
142596
+ "learning_rate": 9.528126009693054e-06,
142597
+ "loss": 0.4087,
142598
+ "step": 30220
142599
+ },
142600
+ {
142601
+ "epoch": 240.99,
142602
+ "learning_rate": 9.527964458804524e-06,
142603
+ "loss": 0.7512,
142604
+ "step": 30230
142605
+ },
142606
+ {
142607
+ "epoch": 241.0,
142608
+ "eval_loss": 0.514737606048584,
142609
+ "eval_runtime": 39.9838,
142610
+ "eval_samples_per_second": 20.808,
142611
+ "eval_steps_per_second": 0.65,
142612
+ "eval_wer": 0.22400180464696592,
142613
+ "step": 30231
142614
+ },
142615
+ {
142616
+ "epoch": 241.07,
142617
+ "learning_rate": 9.527802907915994e-06,
142618
+ "loss": 0.4392,
142619
+ "step": 30240
142620
+ },
142621
+ {
142622
+ "epoch": 241.15,
142623
+ "learning_rate": 9.527641357027464e-06,
142624
+ "loss": 0.4566,
142625
+ "step": 30250
142626
+ },
142627
+ {
142628
+ "epoch": 241.23,
142629
+ "learning_rate": 9.527479806138936e-06,
142630
+ "loss": 0.934,
142631
+ "step": 30260
142632
+ },
142633
+ {
142634
+ "epoch": 241.31,
142635
+ "learning_rate": 9.527318255250406e-06,
142636
+ "loss": 0.4267,
142637
+ "step": 30270
142638
+ },
142639
+ {
142640
+ "epoch": 241.39,
142641
+ "learning_rate": 9.527156704361876e-06,
142642
+ "loss": 0.7369,
142643
+ "step": 30280
142644
+ },
142645
+ {
142646
+ "epoch": 241.47,
142647
+ "learning_rate": 9.526995153473346e-06,
142648
+ "loss": 0.6622,
142649
+ "step": 30290
142650
+ },
142651
+ {
142652
+ "epoch": 241.55,
142653
+ "learning_rate": 9.526833602584816e-06,
142654
+ "loss": 0.5133,
142655
+ "step": 30300
142656
+ },
142657
+ {
142658
+ "epoch": 241.63,
142659
+ "learning_rate": 9.526672051696286e-06,
142660
+ "loss": 1.0124,
142661
+ "step": 30310
142662
+ },
142663
+ {
142664
+ "epoch": 241.71,
142665
+ "learning_rate": 9.526510500807756e-06,
142666
+ "loss": 0.3958,
142667
+ "step": 30320
142668
+ },
142669
+ {
142670
+ "epoch": 241.79,
142671
+ "learning_rate": 9.526348949919226e-06,
142672
+ "loss": 0.8131,
142673
+ "step": 30330
142674
+ },
142675
+ {
142676
+ "epoch": 241.87,
142677
+ "learning_rate": 9.526187399030696e-06,
142678
+ "loss": 0.6662,
142679
+ "step": 30340
142680
+ },
142681
+ {
142682
+ "epoch": 241.95,
142683
+ "learning_rate": 9.526025848142166e-06,
142684
+ "loss": 0.4881,
142685
+ "step": 30350
142686
+ },
142687
+ {
142688
+ "epoch": 242.0,
142689
+ "eval_loss": 0.40769943594932556,
142690
+ "eval_runtime": 40.4196,
142691
+ "eval_samples_per_second": 20.584,
142692
+ "eval_steps_per_second": 0.643,
142693
+ "eval_wer": 0.20691915513474143,
142694
+ "step": 30356
142695
  }
142696
  ],
142697
  "max_steps": 625000,
142698
  "num_train_epochs": 5000,
142699
+ "total_flos": 8.541373733690317e+19,
142700
  "trial_name": null,
142701
  "trial_params": null
142702
  }
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30356}/training_args.bin RENAMED
File without changes
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/config.json RENAMED
File without changes
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75f68f6958c673658002da4e854abde526b8372ce0268256255296a13d2ec580
3
  size 722165009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae027878a1e79cdfb49209caaaf9d1485dcb0fd94e1e91549e907fc5eb80baf
3
  size 722165009
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/preprocessor_config.json RENAMED
File without changes
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8de85c0474cea29ce9b2f342a56c6d77ee15db324fd359f643c3bfaea70f9f65
3
  size 377909911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198125987e8a6eeee499b4ea81d5f288377cb0f67e9613ee3451cf533e5146c8
3
  size 377909911
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71650cc08dda89f9b9059459065e2206969491848876e05136c1deb6871123be
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e5029af02330788ebf0a586f934732ba1bde2ae2738f250bc7eb406baa058d
3
  size 14503
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b9c27330b81604815985c154bf16a32db526f05d66bf804114abdf31655bc6
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5907ab969172c4a2f6d995f99923d2f3f9b046d3654c208d7ce53b5e3f7a6ccb
3
  size 559
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b006bdcf47efcda5d0c1868316fc2ddfa9e9a62161fe48b856e3c4a7d29c1e55
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6509029695a6ad680a84bef19896aa08a5830a942d58cd7f0f0e44cb827ecd
3
  size 623
model-bin/finetune/base/{checkpoint-29856 → checkpoint-30729}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.21391886862672124,
3
- "best_model_checkpoint": "./model-bin/finetune/base/checkpoint-29856",
4
- "epoch": 240.0,
5
- "global_step": 29856,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -142356,11 +142356,596 @@
142356
  "eval_steps_per_second": 0.635,
142357
  "eval_wer": 0.21391886862672124,
142358
  "step": 29856
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142359
  }
142360
  ],
142361
  "max_steps": 620000,
142362
  "num_train_epochs": 5000,
142363
- "total_flos": 8.40101128323434e+19,
142364
  "trial_name": null,
142365
  "trial_params": null
142366
  }
 
1
  {
2
+ "best_metric": 0.20691915513474143,
3
+ "best_model_checkpoint": "./model-bin/finetune/base/checkpoint-30356",
4
+ "epoch": 247.0,
5
+ "global_step": 30729,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
142356
  "eval_steps_per_second": 0.635,
142357
  "eval_wer": 0.21391886862672124,
142358
  "step": 29856
142359
+ },
142360
+ {
142361
+ "epoch": 238.03,
142362
+ "learning_rate": 9.533925686591277e-06,
142363
+ "loss": 0.446,
142364
+ "step": 29860
142365
+ },
142366
+ {
142367
+ "epoch": 238.11,
142368
+ "learning_rate": 9.533764135702747e-06,
142369
+ "loss": 0.3785,
142370
+ "step": 29870
142371
+ },
142372
+ {
142373
+ "epoch": 238.19,
142374
+ "learning_rate": 9.533602584814217e-06,
142375
+ "loss": 0.8141,
142376
+ "step": 29880
142377
+ },
142378
+ {
142379
+ "epoch": 238.27,
142380
+ "learning_rate": 9.533441033925689e-06,
142381
+ "loss": 0.8114,
142382
+ "step": 29890
142383
+ },
142384
+ {
142385
+ "epoch": 238.35,
142386
+ "learning_rate": 9.533279483037159e-06,
142387
+ "loss": 0.596,
142388
+ "step": 29900
142389
+ },
142390
+ {
142391
+ "epoch": 238.43,
142392
+ "learning_rate": 9.533117932148629e-06,
142393
+ "loss": 1.0448,
142394
+ "step": 29910
142395
+ },
142396
+ {
142397
+ "epoch": 238.51,
142398
+ "learning_rate": 9.532956381260099e-06,
142399
+ "loss": 0.3815,
142400
+ "step": 29920
142401
+ },
142402
+ {
142403
+ "epoch": 238.59,
142404
+ "learning_rate": 9.532794830371568e-06,
142405
+ "loss": 0.8454,
142406
+ "step": 29930
142407
+ },
142408
+ {
142409
+ "epoch": 238.67,
142410
+ "learning_rate": 9.532633279483038e-06,
142411
+ "loss": 0.6457,
142412
+ "step": 29940
142413
+ },
142414
+ {
142415
+ "epoch": 238.75,
142416
+ "learning_rate": 9.532471728594508e-06,
142417
+ "loss": 0.4752,
142418
+ "step": 29950
142419
+ },
142420
+ {
142421
+ "epoch": 238.83,
142422
+ "learning_rate": 9.532310177705978e-06,
142423
+ "loss": 0.9449,
142424
+ "step": 29960
142425
+ },
142426
+ {
142427
+ "epoch": 238.91,
142428
+ "learning_rate": 9.532148626817448e-06,
142429
+ "loss": 0.3918,
142430
+ "step": 29970
142431
+ },
142432
+ {
142433
+ "epoch": 238.99,
142434
+ "learning_rate": 9.531987075928918e-06,
142435
+ "loss": 0.7728,
142436
+ "step": 29980
142437
+ },
142438
+ {
142439
+ "epoch": 239.0,
142440
+ "eval_loss": 0.46851950883865356,
142441
+ "eval_runtime": 39.8588,
142442
+ "eval_samples_per_second": 20.849,
142443
+ "eval_steps_per_second": 0.652,
142444
+ "eval_wer": 0.2176783004552352,
142445
+ "step": 29981
142446
+ },
142447
+ {
142448
+ "epoch": 239.07,
142449
+ "learning_rate": 9.531825525040388e-06,
142450
+ "loss": 0.4022,
142451
+ "step": 29990
142452
+ },
142453
+ {
142454
+ "epoch": 239.15,
142455
+ "learning_rate": 9.531663974151858e-06,
142456
+ "loss": 0.4993,
142457
+ "step": 30000
142458
+ },
142459
+ {
142460
+ "epoch": 239.23,
142461
+ "learning_rate": 9.531502423263328e-06,
142462
+ "loss": 0.9728,
142463
+ "step": 30010
142464
+ },
142465
+ {
142466
+ "epoch": 239.31,
142467
+ "learning_rate": 9.531340872374798e-06,
142468
+ "loss": 0.4341,
142469
+ "step": 30020
142470
+ },
142471
+ {
142472
+ "epoch": 239.39,
142473
+ "learning_rate": 9.53117932148627e-06,
142474
+ "loss": 0.7961,
142475
+ "step": 30030
142476
+ },
142477
+ {
142478
+ "epoch": 239.47,
142479
+ "learning_rate": 9.53101777059774e-06,
142480
+ "loss": 0.5954,
142481
+ "step": 30040
142482
+ },
142483
+ {
142484
+ "epoch": 239.55,
142485
+ "learning_rate": 9.53085621970921e-06,
142486
+ "loss": 0.4416,
142487
+ "step": 30050
142488
+ },
142489
+ {
142490
+ "epoch": 239.63,
142491
+ "learning_rate": 9.53069466882068e-06,
142492
+ "loss": 0.9062,
142493
+ "step": 30060
142494
+ },
142495
+ {
142496
+ "epoch": 239.71,
142497
+ "learning_rate": 9.53053311793215e-06,
142498
+ "loss": 0.3867,
142499
+ "step": 30070
142500
+ },
142501
+ {
142502
+ "epoch": 239.79,
142503
+ "learning_rate": 9.53037156704362e-06,
142504
+ "loss": 0.8306,
142505
+ "step": 30080
142506
+ },
142507
+ {
142508
+ "epoch": 239.87,
142509
+ "learning_rate": 9.53021001615509e-06,
142510
+ "loss": 0.5908,
142511
+ "step": 30090
142512
+ },
142513
+ {
142514
+ "epoch": 239.95,
142515
+ "learning_rate": 9.53004846526656e-06,
142516
+ "loss": 0.4622,
142517
+ "step": 30100
142518
+ },
142519
+ {
142520
+ "epoch": 240.0,
142521
+ "eval_loss": 0.4885600209236145,
142522
+ "eval_runtime": 40.6389,
142523
+ "eval_samples_per_second": 20.473,
142524
+ "eval_steps_per_second": 0.64,
142525
+ "eval_wer": 0.21980373349074006,
142526
+ "step": 30106
142527
+ },
142528
+ {
142529
+ "epoch": 240.03,
142530
+ "learning_rate": 9.52988691437803e-06,
142531
+ "loss": 0.4113,
142532
+ "step": 30110
142533
+ },
142534
+ {
142535
+ "epoch": 240.11,
142536
+ "learning_rate": 9.5297253634895e-06,
142537
+ "loss": 0.4046,
142538
+ "step": 30120
142539
+ },
142540
+ {
142541
+ "epoch": 240.19,
142542
+ "learning_rate": 9.52956381260097e-06,
142543
+ "loss": 0.7785,
142544
+ "step": 30130
142545
+ },
142546
+ {
142547
+ "epoch": 240.27,
142548
+ "learning_rate": 9.52940226171244e-06,
142549
+ "loss": 0.586,
142550
+ "step": 30140
142551
+ },
142552
+ {
142553
+ "epoch": 240.35,
142554
+ "learning_rate": 9.52924071082391e-06,
142555
+ "loss": 0.4595,
142556
+ "step": 30150
142557
+ },
142558
+ {
142559
+ "epoch": 240.43,
142560
+ "learning_rate": 9.529079159935381e-06,
142561
+ "loss": 1.0085,
142562
+ "step": 30160
142563
+ },
142564
+ {
142565
+ "epoch": 240.51,
142566
+ "learning_rate": 9.528917609046851e-06,
142567
+ "loss": 0.4297,
142568
+ "step": 30170
142569
+ },
142570
+ {
142571
+ "epoch": 240.59,
142572
+ "learning_rate": 9.528756058158321e-06,
142573
+ "loss": 0.8259,
142574
+ "step": 30180
142575
+ },
142576
+ {
142577
+ "epoch": 240.67,
142578
+ "learning_rate": 9.528610662358644e-06,
142579
+ "loss": 0.6529,
142580
+ "step": 30190
142581
+ },
142582
+ {
142583
+ "epoch": 240.75,
142584
+ "learning_rate": 9.528449111470114e-06,
142585
+ "loss": 0.5276,
142586
+ "step": 30200
142587
+ },
142588
+ {
142589
+ "epoch": 240.83,
142590
+ "learning_rate": 9.528287560581584e-06,
142591
+ "loss": 1.0096,
142592
+ "step": 30210
142593
+ },
142594
+ {
142595
+ "epoch": 240.91,
142596
+ "learning_rate": 9.528126009693054e-06,
142597
+ "loss": 0.4087,
142598
+ "step": 30220
142599
+ },
142600
+ {
142601
+ "epoch": 240.99,
142602
+ "learning_rate": 9.527964458804524e-06,
142603
+ "loss": 0.7512,
142604
+ "step": 30230
142605
+ },
142606
+ {
142607
+ "epoch": 241.0,
142608
+ "eval_loss": 0.514737606048584,
142609
+ "eval_runtime": 39.9838,
142610
+ "eval_samples_per_second": 20.808,
142611
+ "eval_steps_per_second": 0.65,
142612
+ "eval_wer": 0.22400180464696592,
142613
+ "step": 30231
142614
+ },
142615
+ {
142616
+ "epoch": 241.07,
142617
+ "learning_rate": 9.527802907915994e-06,
142618
+ "loss": 0.4392,
142619
+ "step": 30240
142620
+ },
142621
+ {
142622
+ "epoch": 241.15,
142623
+ "learning_rate": 9.527641357027464e-06,
142624
+ "loss": 0.4566,
142625
+ "step": 30250
142626
+ },
142627
+ {
142628
+ "epoch": 241.23,
142629
+ "learning_rate": 9.527479806138936e-06,
142630
+ "loss": 0.934,
142631
+ "step": 30260
142632
+ },
142633
+ {
142634
+ "epoch": 241.31,
142635
+ "learning_rate": 9.527318255250406e-06,
142636
+ "loss": 0.4267,
142637
+ "step": 30270
142638
+ },
142639
+ {
142640
+ "epoch": 241.39,
142641
+ "learning_rate": 9.527156704361876e-06,
142642
+ "loss": 0.7369,
142643
+ "step": 30280
142644
+ },
142645
+ {
142646
+ "epoch": 241.47,
142647
+ "learning_rate": 9.526995153473346e-06,
142648
+ "loss": 0.6622,
142649
+ "step": 30290
142650
+ },
142651
+ {
142652
+ "epoch": 241.55,
142653
+ "learning_rate": 9.526833602584816e-06,
142654
+ "loss": 0.5133,
142655
+ "step": 30300
142656
+ },
142657
+ {
142658
+ "epoch": 241.63,
142659
+ "learning_rate": 9.526672051696286e-06,
142660
+ "loss": 1.0124,
142661
+ "step": 30310
142662
+ },
142663
+ {
142664
+ "epoch": 241.71,
142665
+ "learning_rate": 9.526510500807756e-06,
142666
+ "loss": 0.3958,
142667
+ "step": 30320
142668
+ },
142669
+ {
142670
+ "epoch": 241.79,
142671
+ "learning_rate": 9.526348949919226e-06,
142672
+ "loss": 0.8131,
142673
+ "step": 30330
142674
+ },
142675
+ {
142676
+ "epoch": 241.87,
142677
+ "learning_rate": 9.526187399030696e-06,
142678
+ "loss": 0.6662,
142679
+ "step": 30340
142680
+ },
142681
+ {
142682
+ "epoch": 241.95,
142683
+ "learning_rate": 9.526025848142166e-06,
142684
+ "loss": 0.4881,
142685
+ "step": 30350
142686
+ },
142687
+ {
142688
+ "epoch": 242.0,
142689
+ "eval_loss": 0.40769943594932556,
142690
+ "eval_runtime": 40.4196,
142691
+ "eval_samples_per_second": 20.584,
142692
+ "eval_steps_per_second": 0.643,
142693
+ "eval_wer": 0.20691915513474143,
142694
+ "step": 30356
142695
+ },
142696
+ {
142697
+ "epoch": 242.03,
142698
+ "learning_rate": 9.525864297253636e-06,
142699
+ "loss": 0.4269,
142700
+ "step": 30360
142701
+ },
142702
+ {
142703
+ "epoch": 242.11,
142704
+ "learning_rate": 9.525702746365106e-06,
142705
+ "loss": 0.5977,
142706
+ "step": 30370
142707
+ },
142708
+ {
142709
+ "epoch": 242.19,
142710
+ "learning_rate": 9.525541195476576e-06,
142711
+ "loss": 0.8203,
142712
+ "step": 30380
142713
+ },
142714
+ {
142715
+ "epoch": 242.27,
142716
+ "learning_rate": 9.525379644588046e-06,
142717
+ "loss": 0.5911,
142718
+ "step": 30390
142719
+ },
142720
+ {
142721
+ "epoch": 242.35,
142722
+ "learning_rate": 9.525218093699517e-06,
142723
+ "loss": 0.476,
142724
+ "step": 30400
142725
+ },
142726
+ {
142727
+ "epoch": 242.43,
142728
+ "learning_rate": 9.525056542810987e-06,
142729
+ "loss": 0.9584,
142730
+ "step": 30410
142731
+ },
142732
+ {
142733
+ "epoch": 242.51,
142734
+ "learning_rate": 9.524894991922457e-06,
142735
+ "loss": 0.4033,
142736
+ "step": 30420
142737
+ },
142738
+ {
142739
+ "epoch": 242.59,
142740
+ "learning_rate": 9.524733441033927e-06,
142741
+ "loss": 0.8297,
142742
+ "step": 30430
142743
+ },
142744
+ {
142745
+ "epoch": 242.67,
142746
+ "learning_rate": 9.524571890145397e-06,
142747
+ "loss": 0.5949,
142748
+ "step": 30440
142749
+ },
142750
+ {
142751
+ "epoch": 242.75,
142752
+ "learning_rate": 9.524410339256867e-06,
142753
+ "loss": 0.4561,
142754
+ "step": 30450
142755
+ },
142756
+ {
142757
+ "epoch": 242.83,
142758
+ "learning_rate": 9.524248788368337e-06,
142759
+ "loss": 1.0078,
142760
+ "step": 30460
142761
+ },
142762
+ {
142763
+ "epoch": 242.91,
142764
+ "learning_rate": 9.524087237479807e-06,
142765
+ "loss": 0.459,
142766
+ "step": 30470
142767
+ },
142768
+ {
142769
+ "epoch": 242.99,
142770
+ "learning_rate": 9.523925686591277e-06,
142771
+ "loss": 0.8402,
142772
+ "step": 30480
142773
+ },
142774
+ {
142775
+ "epoch": 243.0,
142776
+ "eval_loss": 0.5306538939476013,
142777
+ "eval_runtime": 40.484,
142778
+ "eval_samples_per_second": 20.551,
142779
+ "eval_steps_per_second": 0.642,
142780
+ "eval_wer": 0.22069377990430622,
142781
+ "step": 30481
142782
+ },
142783
+ {
142784
+ "epoch": 245.07,
142785
+ "learning_rate": 9.523764135702747e-06,
142786
+ "loss": 0.4849,
142787
+ "step": 30490
142788
+ },
142789
+ {
142790
+ "epoch": 245.15,
142791
+ "learning_rate": 9.523602584814217e-06,
142792
+ "loss": 0.4615,
142793
+ "step": 30500
142794
+ },
142795
+ {
142796
+ "epoch": 245.23,
142797
+ "learning_rate": 9.523441033925687e-06,
142798
+ "loss": 0.9455,
142799
+ "step": 30510
142800
+ },
142801
+ {
142802
+ "epoch": 245.31,
142803
+ "learning_rate": 9.523279483037157e-06,
142804
+ "loss": 0.3454,
142805
+ "step": 30520
142806
+ },
142807
+ {
142808
+ "epoch": 245.39,
142809
+ "learning_rate": 9.523117932148629e-06,
142810
+ "loss": 0.8176,
142811
+ "step": 30530
142812
+ },
142813
+ {
142814
+ "epoch": 245.47,
142815
+ "learning_rate": 9.522956381260099e-06,
142816
+ "loss": 0.6493,
142817
+ "step": 30540
142818
+ },
142819
+ {
142820
+ "epoch": 245.55,
142821
+ "learning_rate": 9.522794830371569e-06,
142822
+ "loss": 0.5102,
142823
+ "step": 30550
142824
+ },
142825
+ {
142826
+ "epoch": 245.63,
142827
+ "learning_rate": 9.522633279483039e-06,
142828
+ "loss": 0.9747,
142829
+ "step": 30560
142830
+ },
142831
+ {
142832
+ "epoch": 245.71,
142833
+ "learning_rate": 9.522471728594509e-06,
142834
+ "loss": 0.4284,
142835
+ "step": 30570
142836
+ },
142837
+ {
142838
+ "epoch": 245.8,
142839
+ "learning_rate": 9.522310177705979e-06,
142840
+ "loss": 0.8277,
142841
+ "step": 30580
142842
+ },
142843
+ {
142844
+ "epoch": 245.88,
142845
+ "learning_rate": 9.522148626817448e-06,
142846
+ "loss": 0.606,
142847
+ "step": 30590
142848
+ },
142849
+ {
142850
+ "epoch": 245.96,
142851
+ "learning_rate": 9.521987075928918e-06,
142852
+ "loss": 0.5187,
142853
+ "step": 30600
142854
+ },
142855
+ {
142856
+ "epoch": 246.0,
142857
+ "eval_loss": 0.541337251663208,
142858
+ "eval_runtime": 40.6426,
142859
+ "eval_samples_per_second": 20.471,
142860
+ "eval_steps_per_second": 0.64,
142861
+ "eval_wer": 0.2235569879871081,
142862
+ "step": 30605
142863
+ },
142864
+ {
142865
+ "epoch": 246.04,
142866
+ "learning_rate": 9.521825525040388e-06,
142867
+ "loss": 0.4377,
142868
+ "step": 30610
142869
+ },
142870
+ {
142871
+ "epoch": 246.12,
142872
+ "learning_rate": 9.521663974151858e-06,
142873
+ "loss": 0.4489,
142874
+ "step": 30620
142875
+ },
142876
+ {
142877
+ "epoch": 246.2,
142878
+ "learning_rate": 9.521502423263328e-06,
142879
+ "loss": 1.0363,
142880
+ "step": 30630
142881
+ },
142882
+ {
142883
+ "epoch": 246.28,
142884
+ "learning_rate": 9.521340872374798e-06,
142885
+ "loss": 0.3974,
142886
+ "step": 30640
142887
+ },
142888
+ {
142889
+ "epoch": 246.36,
142890
+ "learning_rate": 9.521179321486268e-06,
142891
+ "loss": 0.4576,
142892
+ "step": 30650
142893
+ },
142894
+ {
142895
+ "epoch": 246.44,
142896
+ "learning_rate": 9.521017770597738e-06,
142897
+ "loss": 0.9549,
142898
+ "step": 30660
142899
+ },
142900
+ {
142901
+ "epoch": 246.52,
142902
+ "learning_rate": 9.52085621970921e-06,
142903
+ "loss": 0.3576,
142904
+ "step": 30670
142905
+ },
142906
+ {
142907
+ "epoch": 246.6,
142908
+ "learning_rate": 9.52069466882068e-06,
142909
+ "loss": 1.095,
142910
+ "step": 30680
142911
+ },
142912
+ {
142913
+ "epoch": 246.69,
142914
+ "learning_rate": 9.52053311793215e-06,
142915
+ "loss": 0.4144,
142916
+ "step": 30690
142917
+ },
142918
+ {
142919
+ "epoch": 246.77,
142920
+ "learning_rate": 9.52037156704362e-06,
142921
+ "loss": 0.5052,
142922
+ "step": 30700
142923
+ },
142924
+ {
142925
+ "epoch": 246.85,
142926
+ "learning_rate": 9.52021001615509e-06,
142927
+ "loss": 0.9081,
142928
+ "step": 30710
142929
+ },
142930
+ {
142931
+ "epoch": 246.93,
142932
+ "learning_rate": 9.52004846526656e-06,
142933
+ "loss": 0.3901,
142934
+ "step": 30720
142935
+ },
142936
+ {
142937
+ "epoch": 247.0,
142938
+ "eval_loss": 0.43034788966178894,
142939
+ "eval_runtime": 40.4735,
142940
+ "eval_samples_per_second": 20.557,
142941
+ "eval_steps_per_second": 0.642,
142942
+ "eval_wer": 0.2156060495360561,
142943
+ "step": 30729
142944
  }
142945
  ],
142946
  "max_steps": 620000,
142947
  "num_train_epochs": 5000,
142948
+ "total_flos": 8.646507906837255e+19,
142949
  "trial_name": null,
142950
  "trial_params": null
142951
  }
model-bin/finetune/base/{checkpoint-30106 → checkpoint-30729}/training_args.bin RENAMED
File without changes
model-bin/finetune/base/log/1629631576.8245854/events.out.tfevents.1629631576.91f414e9573a.903.121 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa1639e534368fe9906857fb7f84a4515d532906ae8cf3b5fb987d1efe46857
3
+ size 4194
model-bin/finetune/base/log/1629632245.5141647/events.out.tfevents.1629632245.91f414e9573a.903.123 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95461ad7a6b0e369e59eb75059d1321b72a71b5c1d2eb48f4c451518c24a8070
3
+ size 4194
model-bin/finetune/base/log/1629632908.002072/events.out.tfevents.1629632908.91f414e9573a.903.125 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32508ec54d35358605100c9841015abe30e1d704cdce9976b151caea9e7e231d
3
+ size 4194
model-bin/finetune/base/log/1629633565.1667113/events.out.tfevents.1629633565.91f414e9573a.903.127 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:114ce5acffee340f6529105d7d3ae8a630727bd186b1789a900521571014cbd5
3
+ size 4194
model-bin/finetune/base/log/1629634215.195126/events.out.tfevents.1629634215.91f414e9573a.903.129 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd98fafaac080166a391b15252fd50e7dc4981d3f6ef5af7c3e2cc28d2ef6cf
3
+ size 4194
model-bin/finetune/base/log/events.out.tfevents.1629631576.91f414e9573a.903.120 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fa0bcc8e17ff17ff136fa4d9ab18f54869ef975bda00c4afe777ae454c5c8d
3
+ size 6703
model-bin/finetune/base/log/events.out.tfevents.1629632245.91f414e9573a.903.122 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773255f85a85ecdfb246381a7777532f6c5667a2d91242fa8d62a276e8567b22
3
+ size 6543
model-bin/finetune/base/log/events.out.tfevents.1629632907.91f414e9573a.903.124 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93998f137846b374db144abfaeca4ea59b50bd038b11772b5bbca023bb025f21
3
+ size 6703
model-bin/finetune/base/log/events.out.tfevents.1629633565.91f414e9573a.903.126 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e949769b6ab0becc1330e42174d3ec8ecc54c40d0a10a86d8068a2553319de
3
+ size 6543
model-bin/finetune/base/log/events.out.tfevents.1629634215.91f414e9573a.903.128 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10705beb8072c198635988546dcc268630cac97380550a092f5f82f36e823457
3
+ size 6543