wandererupak commited on
Commit
4535125
·
verified ·
1 Parent(s): 65a0c95

Training in progress, step 1664, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b94faea3f068750509be05d3f6f8aed0f9ef2ec490dab917b387241a7b51013
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63660dd7ba5aaae89154206890a231423334c28f59892a8ba855962e47ddc784
3
  size 290403936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7648c512529146cf12d17f92805f2ee67f5f2ac3fad65567bc89da88a55ea6
3
  size 574815371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:314ab3e02358e174b879fa44020687498c2d1f7bc1d4ae3927b15e7930b8b2a5
3
  size 574815371
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528764b06577f16d6a7cd2a2c325f0c6e67252eaa5abf11afd4e1ff1fdaa58e9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446762a6be6e2233a8ce7348611f40f61db00aa6d4bb53c7fa00b56bfd1f5da6
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fabdf440eb8431468ad96f2b5aca4bc6486a0f20f2cfba9fcc6a87c97c21eaf7
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41f23769d1b632a371b476ef54b06a17f954ffbb154db90481815944a1de2ae
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09155a8245f3a513800d6b46c5196cb4ece77f282a0e1290e3af4fe6a2f47250
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720a805e54890efd8dead5a5a032f9798f2252c89f498ab941a56c86ccfabfc3
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 1408,
3
  "best_metric": 64.48311156601842,
4
  "best_model_checkpoint": "whisper-base-ultimate-Augmented/checkpoint-1408",
5
- "epoch": 12.500978473581213,
6
  "eval_steps": 64,
7
- "global_step": 1600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -433,6 +433,23 @@
433
  "eval_steps_per_second": 0.651,
434
  "eval_wer": 65.71136131013307,
435
  "step": 1600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
436
  }
437
  ],
438
  "logging_steps": 64,
@@ -447,7 +464,7 @@
447
  "early_stopping_threshold": 0.0
448
  },
449
  "attributes": {
450
- "early_stopping_patience_counter": 3
451
  }
452
  },
453
  "TrainerControl": {
@@ -456,12 +473,12 @@
456
  "should_evaluate": false,
457
  "should_log": false,
458
  "should_save": true,
459
- "should_training_stop": false
460
  },
461
  "attributes": {}
462
  }
463
  },
464
- "total_flos": 1.6565243019264e+18,
465
  "train_batch_size": 4,
466
  "trial_name": null,
467
  "trial_params": null
 
2
  "best_global_step": 1408,
3
  "best_metric": 64.48311156601842,
4
  "best_model_checkpoint": "whisper-base-ultimate-Augmented/checkpoint-1408",
5
+ "epoch": 13.0,
6
  "eval_steps": 64,
7
+ "global_step": 1664,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
433
  "eval_steps_per_second": 0.651,
434
  "eval_wer": 65.71136131013307,
435
  "step": 1600
436
+ },
437
+ {
438
+ "epoch": 13.0,
439
+ "grad_norm": 12.9113187789917,
440
+ "learning_rate": 3.296307406357855e-06,
441
+ "loss": 0.1477,
442
+ "step": 1664
443
+ },
444
+ {
445
+ "epoch": 13.0,
446
+ "eval_cer": 26.92026335040234,
447
+ "eval_loss": 0.5878623723983765,
448
+ "eval_runtime": 45.8329,
449
+ "eval_samples_per_second": 4.953,
450
+ "eval_steps_per_second": 0.633,
451
+ "eval_wer": 65.19959058341863,
452
+ "step": 1664
453
  }
454
  ],
455
  "logging_steps": 64,
 
464
  "early_stopping_threshold": 0.0
465
  },
466
  "attributes": {
467
+ "early_stopping_patience_counter": 4
468
  }
469
  },
470
  "TrainerControl": {
 
473
  "should_evaluate": false,
474
  "should_log": false,
475
  "should_save": true,
476
+ "should_training_stop": true
477
  },
478
  "attributes": {}
479
  }
480
  },
481
+ "total_flos": 1.72261663801344e+18,
482
  "train_batch_size": 4,
483
  "trial_name": null,
484
  "trial_params": null