Baselhany commited on
Commit
b89a67c
·
verified ·
1 Parent(s): 97745b7

Training in progress, epoch 37, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8997172ec14587c1468e462ae452c3802909aaf994457509c48cae590d573a8
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a92b9a7d30ad94d36ff4f760befa05c6bdbb855108d83f4cc6ec52cb51dd138
3
  size 223144592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7821ab5599601f3afeb98d5568fdf76795f52204224b20f7b1c572f01377717
3
  size 281574266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ef6cf350cccc8f4a92a4e5916ee8b45cdb74f8524592b1d885a1bd6f186010
3
  size 281574266
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce4db40421c3e0f3347d03b81a54aac67fd60db49f37d06a2be1cceb1694f79
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7fa8c2fcb9c7fb7e7f97904d5a80c9bd5c3f5b4a6c94df5cd9bf61bf5593fc1
3
  size 14244
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e4e9eaa32613d07fad88ea1ce5ab9cd4184d1eca7a2487e558a72720742b242
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b51f4c7240d53b438f5183ef214715590910c76889af8e07dddb3c4e32f836
3
  size 988
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f47f4d221cadf5a2cd193886d6a15775522c8d20da6364f0b73e50379e2b5f81
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697e244c5323dde1a40a2461670152b5bd6bcb6031f2e73b800d9dd13e7cd04f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 11625,
3
- "best_metric": 0.22325375773651635,
4
- "best_model_checkpoint": "./distil-whisper/checkpoint-11625",
5
- "epoch": 40.0,
6
  "eval_steps": 500,
7
- "global_step": 15000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1445,12 +1445,42 @@
1445
  "eval_steps_per_second": 0.433,
1446
  "eval_wer": 0.22973769525493665,
1447
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1448
  }
1449
  ],
1450
  "logging_steps": 100,
1451
- "max_steps": 15000,
1452
  "num_input_tokens_seen": 0,
1453
- "num_train_epochs": 40,
1454
  "save_steps": 500,
1455
  "stateful_callbacks": {
1456
  "TrainerControl": {
@@ -1459,12 +1489,12 @@
1459
  "should_evaluate": false,
1460
  "should_log": false,
1461
  "should_save": true,
1462
- "should_training_stop": true
1463
  },
1464
  "attributes": {}
1465
  }
1466
  },
1467
- "total_flos": 1.950321588830208e+19,
1468
  "train_batch_size": 8,
1469
  "trial_name": null,
1470
  "trial_params": null
 
1
  {
2
+ "best_global_step": 15314,
3
+ "best_metric": 0.21220159151193635,
4
+ "best_model_checkpoint": "./distil-whisper/checkpoint-15314",
5
+ "epoch": 37.99938003719777,
6
  "eval_steps": 500,
7
+ "global_step": 15314,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1445
  "eval_steps_per_second": 0.433,
1446
  "eval_wer": 0.22973769525493665,
1447
  "step": 15000
1448
+ },
1449
+ {
1450
+ "epoch": 37.46869187848729,
1451
+ "grad_norm": 39.86048126220703,
1452
+ "learning_rate": 2.577608142493639e-05,
1453
+ "loss": 3.5543,
1454
+ "step": 15100
1455
+ },
1456
+ {
1457
+ "epoch": 37.716676999380034,
1458
+ "grad_norm": 53.614952087402344,
1459
+ "learning_rate": 2.5267175572519086e-05,
1460
+ "loss": 3.9955,
1461
+ "step": 15200
1462
+ },
1463
+ {
1464
+ "epoch": 37.964662120272784,
1465
+ "grad_norm": 33.56686019897461,
1466
+ "learning_rate": 2.4758269720101782e-05,
1467
+ "loss": 3.6933,
1468
+ "step": 15300
1469
+ },
1470
+ {
1471
+ "epoch": 37.99938003719777,
1472
+ "eval_loss": 0.10439449548721313,
1473
+ "eval_runtime": 152.7963,
1474
+ "eval_samples_per_second": 3.272,
1475
+ "eval_steps_per_second": 0.412,
1476
+ "eval_wer": 0.21220159151193635,
1477
+ "step": 15314
1478
  }
1479
  ],
1480
  "logging_steps": 100,
1481
+ "max_steps": 20150,
1482
  "num_input_tokens_seen": 0,
1483
+ "num_train_epochs": 50,
1484
  "save_steps": 500,
1485
  "stateful_callbacks": {
1486
  "TrainerControl": {
 
1489
  "should_evaluate": false,
1490
  "should_log": false,
1491
  "should_save": true,
1492
+ "should_training_stop": false
1493
  },
1494
  "attributes": {}
1495
  }
1496
  },
1497
+ "total_flos": 1.991179577327616e+19,
1498
  "train_batch_size": 8,
1499
  "trial_name": null,
1500
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f27d05f3273c8f945251b5f65c09e35bb573ec73ef26f49f569836231c82335d
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c7a30c503115cb763679c55fb2d7d1848597207e83d7661a9d7b9168c44d07
3
  size 5560