w11wo commited on
Commit
5d161f0
1 Parent(s): 5679ecf

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_cer": 0.3173159976360413,
4
+ "eval_loss": 0.8089390397071838,
5
+ "eval_runtime": 116.9576,
6
+ "eval_samples": 2302,
7
+ "eval_samples_per_second": 19.682,
8
+ "eval_steps_per_second": 2.462,
9
+ "eval_wer": 1.2498917280207882,
10
+ "train_loss": 3.7852419735087786,
11
+ "train_runtime": 72640.1075,
12
+ "train_samples": 11949,
13
+ "train_samples_per_second": 16.45,
14
+ "train_steps_per_second": 0.513
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_cer": 0.3173159976360413,
4
+ "eval_loss": 0.8089390397071838,
5
+ "eval_runtime": 116.9576,
6
+ "eval_samples": 2302,
7
+ "eval_samples_per_second": 19.682,
8
+ "eval_steps_per_second": 2.462,
9
+ "eval_wer": 1.2498917280207882
10
+ }
nohup.out CHANGED
@@ -23239,3 +23239,26 @@ Configuration saved in ./preprocessor_config.json
23239
 
23240
  Dropping the following result as it does not have all the necessary fields:
23241
  {'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'zh-HK'}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23242
  0%| | 0/288 [00:00<?, ?it/s]
23243
  1%| | 2/288 [00:00<00:40, 7.05it/s]
23244
  1%| | 3/288 [00:00<01:04, 4.42it/s]
23245
  1%|▏ | 4/288 [00:00<01:14, 3.84it/s]
23246
  2%|▏ | 5/288 [00:01<01:12, 3.88it/s]
23247
  2%|▏ | 6/288 [00:01<01:15, 3.74it/s]
23248
  2%|▏ | 7/288 [00:01<01:18, 3.58it/s]
23249
  3%|▎ | 8/288 [00:02<01:15, 3.72it/s]
23250
  3%|▎ | 9/288 [00:02<01:19, 3.53it/s]
23251
  3%|▎ | 10/288 [00:02<01:26, 3.20it/s]
23252
  4%|▍ | 11/288 [00:03<01:28, 3.12it/s]
23253
  4%|▍ | 12/288 [00:03<01:23, 3.29it/s]
23254
  5%|▍ | 13/288 [00:03<01:25, 3.21it/s]
23255
  5%|▍ | 14/288 [00:03<01:24, 3.26it/s]
23256
  5%|▌ | 15/288 [00:04<01:20, 3.38it/s]
23257
  6%|▌ | 16/288 [00:04<01:23, 3.24it/s]
23258
  6%|▌ | 17/288 [00:04<01:21, 3.33it/s]
23259
  6%|▋ | 18/288 [00:05<01:23, 3.23it/s]
23260
  7%|▋ | 19/288 [00:05<01:25, 3.16it/s]
23261
  7%|▋ | 20/288 [00:05<01:22, 3.25it/s]
23262
  7%|▋ | 21/288 [00:06<01:21, 3.28it/s]
23263
  8%|▊ | 22/288 [00:06<01:18, 3.38it/s]
23264
  8%|▊ | 23/288 [00:06<01:19, 3.34it/s]
23265
  8%|▊ | 24/288 [00:06<01:20, 3.29it/s]
23266
  9%|▊ | 25/288 [00:07<01:18, 3.34it/s]
23267
  9%|▉ | 26/288 [00:07<01:21, 3.20it/s]
23268
  9%|▉ | 27/288 [00:07<01:21, 3.21it/s]
23269
  10%|▉ | 28/288 [00:08<01:18, 3.33it/s]
23270
  10%|█ | 29/288 [00:08<01:14, 3.50it/s]
23271
  10%|█ | 30/288 [00:08<01:07, 3.85it/s]
23272
  11%|█ | 31/288 [00:08<01:05, 3.90it/s]
23273
  11%|█ | 32/288 [00:09<01:08, 3.76it/s]
23274
  11%|█▏ | 33/288 [00:09<01:06, 3.86it/s]
23275
  12%|█▏ | 34/288 [00:09<01:06, 3.80it/s]
23276
  12%|█▏ | 35/288 [00:10<01:08, 3.69it/s]
23277
  12%|█▎ | 36/288 [00:10<01:09, 3.63it/s]
23278
  13%|█▎ | 37/288 [00:10<01:08, 3.64it/s]
23279
  13%|█▎ | 38/288 [00:10<01:08, 3.66it/s]
23280
  14%|█▎ | 39/288 [00:11<01:09, 3.59it/s]
23281
  14%|█▍ | 40/288 [00:11<01:11, 3.49it/s]
23282
  14%|█▍ | 41/288 [00:11<01:09, 3.56it/s]
23283
  15%|█▍ | 42/288 [00:12<01:11, 3.43it/s]
23284
  15%|█▍ | 43/288 [00:12<01:13, 3.34it/s]
23285
  15%|█▌ | 44/288 [00:12<01:12, 3.36it/s]
23286
  16%|█▌ | 45/288 [00:12<01:12, 3.35it/s]
23287
  16%|█▌ | 46/288 [00:13<01:10, 3.43it/s]
23288
  16%|█▋ | 47/288 [00:13<01:12, 3.34it/s]
23289
  17%|█▋ | 48/288 [00:13<01:15, 3.16it/s]
23290
  17%|█▋ | 49/288 [00:14<01:13, 3.26it/s]
23291
  17%|█▋ | 50/288 [00:14<01:11, 3.34it/s]
23292
  18%|█▊ | 51/288 [00:14<01:09, 3.40it/s]
23293
  18%|█▊ | 52/288 [00:15<01:10, 3.35it/s]
23294
  18%|█▊ | 53/288 [00:15<01:10, 3.33it/s]
23295
  19%|█▉ | 54/288 [00:15<01:09, 3.37it/s]
23296
  19%|█▉ | 55/288 [00:15<01:11, 3.26it/s]
23297
  19%|█▉ | 56/288 [00:16<01:09, 3.34it/s]
23298
  20%|█▉ | 57/288 [00:16<01:08, 3.39it/s]
23299
  20%|██ | 58/288 [00:16<01:05, 3.49it/s]
23300
  20%|██ | 59/288 [00:17<01:04, 3.58it/s]
23301
  21%|██ | 60/288 [00:17<01:00, 3.74it/s]
23302
  21%|██ | 61/288 [00:17<01:05, 3.46it/s]
23303
  22%|██▏ | 62/288 [00:17<01:06, 3.39it/s]
23304
  22%|██▏ | 63/288 [00:18<01:07, 3.31it/s]
23305
  22%|██▏ | 64/288 [00:18<01:06, 3.39it/s]
23306
  23%|██▎ | 65/288 [00:18<01:08, 3.27it/s]
23307
  23%|██▎ | 66/288 [00:19<01:09, 3.17it/s]
23308
  23%|██▎ | 67/288 [00:19<01:07, 3.27it/s]
23309
  24%|██▎ | 68/288 [00:19<01:09, 3.18it/s]
23310
  24%|██▍ | 69/288 [00:20<01:10, 3.13it/s]
23311
  24%|██▍ | 70/288 [00:20<01:09, 3.16it/s]
23312
  25%|██▍ | 71/288 [00:20<01:11, 3.03it/s]
23313
  25%|██▌ | 72/288 [00:21<01:09, 3.11it/s]
23314
  25%|██▌ | 73/288 [00:21<01:08, 3.15it/s]
23315
  26%|██▌ | 74/288 [00:21<01:09, 3.07it/s]
23316
  26%|██▌ | 75/288 [00:22<01:10, 3.00it/s]
23317
  26%|██▋ | 76/288 [00:22<01:08, 3.08it/s]
23318
  27%|██▋ | 77/288 [00:22<01:09, 3.06it/s]
23319
  27%|██▋ | 78/288 [00:23<01:08, 3.09it/s]
23320
  27%|██▋ | 79/288 [00:23<01:06, 3.14it/s]
23321
  28%|██▊ | 80/288 [00:23<01:04, 3.24it/s]
23322
  28%|██▊ | 81/288 [00:24<01:05, 3.18it/s]
23323
  28%|██▊ | 82/288 [00:24<01:03, 3.26it/s]
23324
  29%|██▉ | 83/288 [00:24<01:04, 3.17it/s]
23325
  29%|██▉ | 84/288 [00:24<01:00, 3.38it/s]
23326
  30%|██▉ | 85/288 [00:25<00:58, 3.45it/s]
23327
  30%|██▉ | 86/288 [00:25<01:02, 3.23it/s]
23328
  30%|███ | 87/288 [00:25<01:02, 3.21it/s]
23329
  31%|███ | 88/288 [00:26<01:02, 3.18it/s]
23330
  31%|███ | 89/288 [00:26<01:01, 3.24it/s]
23331
  31%|███▏ | 90/288 [00:26<01:00, 3.29it/s]
23332
  32%|███▏ | 91/288 [00:27<01:01, 3.22it/s]
23333
  32%|███▏ | 92/288 [00:27<00:59, 3.28it/s]
23334
  32%|███▏ | 93/288 [00:27<01:01, 3.15it/s]
23335
  33%|███▎ | 94/288 [00:28<01:01, 3.18it/s]
23336
  33%|███▎ | 95/288 [00:28<01:00, 3.21it/s]
23337
  33%|███▎ | 96/288 [00:28<00:57, 3.35it/s]
23338
  34%|███▎ | 97/288 [00:28<00:55, 3.41it/s]
23339
  34%|███▍ | 98/288 [00:29<00:57, 3.29it/s]
23340
  34%|███▍ | 99/288 [00:29<00:59, 3.16it/s]
23341
  35%|███▍ | 100/288 [00:29<00:58, 3.21it/s]
23342
  35%|███▌ | 101/288 [00:30<00:57, 3.26it/s]
23343
  35%|███▌ | 102/288 [00:30<00:55, 3.35it/s]
23344
  36%|███▌ | 103/288 [00:30<00:55, 3.34it/s]
23345
  36%|███▌ | 104/288 [00:31<00:56, 3.24it/s]
23346
  36%|███▋ | 105/288 [00:31<00:53, 3.40it/s]
23347
  37%|███▋ | 106/288 [00:31<00:56, 3.24it/s]
23348
  37%|███▋ | 107/288 [00:31<00:56, 3.19it/s]
23349
  38%|███▊ | 108/288 [00:32<00:56, 3.18it/s]
23350
  38%|███▊ | 109/288 [00:32<00:56, 3.15it/s]
23351
  38%|███▊ | 110/288 [00:32<00:55, 3.20it/s]
23352
  39%|███▊ | 111/288 [00:33<00:54, 3.22it/s]
23353
  39%|███▉ | 112/288 [00:33<00:55, 3.17it/s]
23354
  39%|███▉ | 113/288 [00:33<00:55, 3.16it/s]
23355
  40%|███▉ | 114/288 [00:34<00:55, 3.14it/s]
23356
  40%|███▉ | 115/288 [00:34<00:54, 3.19it/s]
23357
  40%|████ | 116/288 [00:34<00:54, 3.14it/s]
23358
  41%|████ | 117/288 [00:35<00:54, 3.16it/s]
23359
  41%|████ | 118/288 [00:35<00:51, 3.33it/s]
23360
  41%|████▏ | 119/288 [00:35<00:52, 3.23it/s]
23361
  42%|████▏ | 120/288 [00:36<00:53, 3.16it/s]
23362
  42%|████▏ | 121/288 [00:36<00:51, 3.26it/s]
23363
  42%|████▏ | 122/288 [00:36<00:48, 3.41it/s]
23364
  43%|████▎ | 123/288 [00:36<00:51, 3.17it/s]
23365
  43%|████▎ | 124/288 [00:37<00:51, 3.18it/s]
23366
  43%|████▎ | 125/288 [00:37<00:51, 3.17it/s]
23367
  44%|████▍ | 126/288 [00:37<00:52, 3.06it/s]
23368
  44%|████▍ | 127/288 [00:38<00:51, 3.13it/s]
23369
  44%|████▍ | 128/288 [00:38<00:50, 3.14it/s]
23370
  45%|████▍ | 129/288 [00:38<00:52, 3.00it/s]
23371
  45%|████▌ | 130/288 [00:39<00:52, 3.03it/s]
23372
  45%|████▌ | 131/288 [00:39<00:50, 3.09it/s]
23373
  46%|████▌ | 132/288 [00:39<00:50, 3.08it/s]
23374
  46%|████▌ | 133/288 [00:40<00:52, 2.97it/s]
23375
  47%|████▋ | 134/288 [00:40<00:51, 2.96it/s]
23376
  47%|████▋ | 135/288 [00:40<00:51, 2.99it/s]
23377
  47%|████▋ | 136/288 [00:41<00:49, 3.06it/s]
23378
  48%|████▊ | 137/288 [00:41<00:48, 3.09it/s]
23379
  48%|████▊ | 138/288 [00:41<00:49, 3.05it/s]
23380
  48%|████▊ | 139/288 [00:42<00:49, 3.01it/s]
23381
  49%|████▊ | 140/288 [00:42<00:49, 3.01it/s]
23382
  49%|████▉ | 141/288 [00:42<00:50, 2.94it/s]
23383
  49%|████▉ | 142/288 [00:43<00:48, 3.03it/s]
23384
  50%|████▉ | 143/288 [00:43<00:48, 2.99it/s]
23385
  50%|█████ | 144/288 [00:43<00:44, 3.27it/s]
23386
  50%|█████ | 145/288 [00:44<00:43, 3.26it/s]
23387
  51%|█████ | 146/288 [00:44<00:42, 3.31it/s]
23388
  51%|█████ | 147/288 [00:44<00:43, 3.27it/s]
23389
  51%|█████▏ | 148/288 [00:45<00:44, 3.17it/s]
23390
  52%|█████▏ | 149/288 [00:45<00:43, 3.18it/s]
23391
  52%|█████▏ | 150/288 [00:45<00:44, 3.11it/s]
23392
  52%|█████▏ | 151/288 [00:45<00:42, 3.24it/s]
23393
  53%|█████▎ | 152/288 [00:46<00:42, 3.21it/s]
23394
  53%|█████▎ | 153/288 [00:46<00:40, 3.30it/s]
23395
  53%|█████▎ | 154/288 [00:46<00:42, 3.13it/s]
23396
  54%|█████▍ | 155/288 [00:47<00:42, 3.12it/s]
23397
  54%|█████▍ | 156/288 [00:47<00:41, 3.16it/s]
23398
  55%|█████▍ | 157/288 [00:47<00:41, 3.14it/s]
23399
  55%|█████▍ | 158/288 [00:48<00:41, 3.11it/s]
23400
  55%|█████▌ | 159/288 [00:48<00:41, 3.12it/s]
23401
  56%|█████▌ | 160/288 [00:48<00:39, 3.20it/s]
23402
  56%|█████▌ | 161/288 [00:49<00:38, 3.29it/s]
23403
  56%|█████▋ | 162/288 [00:49<00:37, 3.36it/s]
23404
  57%|█████▋ | 163/288 [00:49<00:38, 3.26it/s]
23405
  57%|█████▋ | 164/288 [00:50<00:37, 3.32it/s]
23406
  57%|█████▋ | 165/288 [00:50<00:37, 3.29it/s]
23407
  58%|█████▊ | 166/288 [00:50<00:37, 3.24it/s]
23408
  58%|█████▊ | 167/288 [00:50<00:37, 3.27it/s]
23409
  58%|█████▊ | 168/288 [00:51<00:38, 3.15it/s]
23410
  59%|█████▊ | 169/288 [00:51<00:37, 3.18it/s]
23411
  59%|█████▉ | 170/288 [00:51<00:37, 3.16it/s]
23412
  59%|█████▉ | 171/288 [00:52<00:37, 3.14it/s]
23413
  60%|█████▉ | 172/288 [00:52<00:37, 3.12it/s]
23414
  60%|██████ | 173/288 [00:52<00:37, 3.06it/s]
23415
  60%|██████ | 174/288 [00:53<00:36, 3.09it/s]
23416
  61%|██████ | 175/288 [00:53<00:35, 3.20it/s]
23417
  61%|██████ | 176/288 [00:53<00:37, 2.99it/s]
23418
  61%|██████▏ | 177/288 [00:54<00:36, 3.01it/s]
23419
  62%|██████▏ | 178/288 [00:54<00:36, 2.99it/s]
23420
  62%|██████▏ | 179/288 [00:54<00:35, 3.05it/s]
23421
  62%|██████▎ | 180/288 [00:55<00:35, 3.07it/s]
23422
  63%|██████▎ | 181/288 [00:55<00:33, 3.24it/s]
23423
  63%|██████▎ | 182/288 [00:55<00:34, 3.12it/s]
23424
  64%|██████▎ | 183/288 [00:56<00:33, 3.14it/s]
23425
  64%|██████▍ | 184/288 [00:56<00:33, 3.11it/s]
23426
  64%|██████▍ | 185/288 [00:56<00:32, 3.15it/s]
23427
  65%|██████▍ | 186/288 [00:57<00:30, 3.33it/s]
23428
  65%|██████▍ | 187/288 [00:57<00:32, 3.10it/s]
23429
  65%|██████▌ | 188/288 [00:57<00:32, 3.12it/s]
23430
  66%|██████▌ | 189/288 [00:58<00:30, 3.22it/s]
23431
  66%|██████▌ | 190/288 [00:58<00:31, 3.08it/s]
23432
  66%|██████▋ | 191/288 [00:58<00:31, 3.10it/s]
23433
  67%|██████▋ | 192/288 [00:58<00:30, 3.19it/s]
23434
  67%|██████▋ | 193/288 [00:59<00:29, 3.21it/s]
23435
  67%|██████▋ | 194/288 [00:59<00:31, 3.03it/s]
23436
  68%|██████▊ | 195/288 [00:59<00:30, 3.07it/s]
23437
  68%|██████▊ | 196/288 [01:00<00:30, 2.97it/s]
23438
  68%|██████▊ | 197/288 [01:00<00:30, 2.98it/s]
23439
  69%|██████▉ | 198/288 [01:00<00:28, 3.15it/s]
23440
  69%|██████▉ | 199/288 [01:01<00:28, 3.13it/s]
23441
  69%|██████▉ | 200/288 [01:01<00:26, 3.27it/s]
23442
  70%|██████▉ | 201/288 [01:01<00:27, 3.17it/s]
23443
  70%|███████ | 202/288 [01:02<00:27, 3.16it/s]
23444
  70%|███████ | 203/288 [01:02<00:27, 3.15it/s]
23445
  71%|███████ | 204/288 [01:02<00:26, 3.12it/s]
23446
  71%|███████ | 205/288 [01:03<00:25, 3.21it/s]
23447
  72%|███████▏ | 206/288 [01:03<00:26, 3.12it/s]
23448
  72%|███████▏ | 207/288 [01:03<00:26, 3.03it/s]
23449
  72%|███████▏ | 208/288 [01:04<00:26, 2.98it/s]
23450
  73%|███████▎ | 209/288 [01:04<00:26, 2.94it/s]
23451
  73%|███████▎ | 210/288 [01:04<00:24, 3.17it/s]
23452
  73%|███████▎ | 211/288 [01:05<00:23, 3.24it/s]
23453
  74%|███████▎ | 212/288 [01:05<00:22, 3.32it/s]
23454
  74%|███████▍ | 213/288 [01:05<00:24, 3.08it/s]
23455
  74%|███████▍ | 214/288 [01:06<00:23, 3.15it/s]
23456
  75%|███████▍ | 215/288 [01:06<00:23, 3.06it/s]
23457
  75%|███████▌ | 216/288 [01:06<00:23, 3.03it/s]
23458
  75%|███████▌ | 217/288 [01:07<00:22, 3.15it/s]
23459
  76%|███████▌ | 218/288 [01:07<00:22, 3.11it/s]
23460
  76%|███████▌ | 219/288 [01:07<00:22, 3.11it/s]
23461
  76%|███████▋ | 220/288 [01:08<00:23, 2.94it/s]
23462
  77%|███████▋ | 221/288 [01:08<00:22, 2.97it/s]
23463
  77%|███████▋ | 222/288 [01:08<00:22, 2.92it/s]
23464
  77%|███████▋ | 223/288 [01:09<00:20, 3.11it/s]
23465
  78%|███████▊ | 224/288 [01:09<00:20, 3.07it/s]
23466
  78%|███████▊ | 225/288 [01:09<00:20, 3.10it/s]
23467
  78%|███████▊ | 226/288 [01:09<00:19, 3.13it/s]
23468
  79%|███████▉ | 227/288 [01:10<00:20, 3.03it/s]
23469
  79%|███████▉ | 228/288 [01:10<00:19, 3.01it/s]
23470
  80%|███████▉ | 229/288 [01:10<00:19, 3.04it/s]
23471
  80%|███████▉ | 230/288 [01:11<00:18, 3.07it/s]
23472
  80%|████████ | 231/288 [01:11<00:19, 2.99it/s]
23473
  81%|████████ | 232/288 [01:11<00:18, 3.04it/s]
23474
  81%|████████ | 233/288 [01:12<00:18, 2.94it/s]
23475
  81%|████████▏ | 234/288 [01:12<00:17, 3.01it/s]
23476
  82%|████████▏ | 235/288 [01:12<00:17, 3.01it/s]
23477
  82%|████████▏ | 236/288 [01:13<00:17, 2.92it/s]
23478
  82%|████████▏ | 237/288 [01:13<00:17, 2.89it/s]
23479
  83%|████████▎ | 238/288 [01:14<00:17, 2.92it/s]
23480
  83%|████████▎ | 239/288 [01:14<00:16, 3.01it/s]
23481
  83%|████████▎ | 240/288 [01:14<00:15, 3.14it/s]
23482
  84%|████████▎ | 241/288 [01:14<00:15, 3.09it/s]
23483
  84%|████████▍ | 242/288 [01:15<00:15, 3.05it/s]
23484
  84%|████████▍ | 243/288 [01:15<00:14, 3.13it/s]
23485
  85%|████████▍ | 244/288 [01:15<00:14, 3.06it/s]
23486
  85%|████████▌ | 245/288 [01:16<00:14, 3.04it/s]
23487
  85%|████████▌ | 246/288 [01:16<00:14, 2.98it/s]
23488
  86%|████████▌ | 247/288 [01:16<00:13, 3.11it/s]
23489
  86%|████████▌ | 248/288 [01:17<00:12, 3.12it/s]
23490
  86%|████████▋ | 249/288 [01:17<00:12, 3.04it/s]
23491
  87%|████████▋ | 250/288 [01:17<00:12, 3.00it/s]
23492
  87%|████████▋ | 251/288 [01:18<00:12, 2.91it/s]
23493
  88%|████████▊ | 252/288 [01:18<00:12, 2.84it/s]
23494
  88%|████████▊ | 253/288 [01:18<00:11, 2.99it/s]
23495
  88%|████████▊ | 254/288 [01:19<00:11, 3.09it/s]
23496
  89%|████████▊ | 255/288 [01:19<00:10, 3.16it/s]
23497
  89%|████████▉ | 256/288 [01:19<00:10, 3.14it/s]
23498
  89%|████████▉ | 257/288 [01:20<00:09, 3.16it/s]
23499
  90%|████████▉ | 258/288 [01:20<00:10, 2.93it/s]
23500
  90%|████████▉ | 259/288 [01:20<00:10, 2.85it/s]
23501
  90%|█████████ | 260/288 [01:21<00:09, 2.87it/s]
23502
  91%|█████████ | 261/288 [01:21<00:09, 2.84it/s]
23503
  91%|█████████ | 262/288 [01:22<00:09, 2.87it/s]
23504
  91%|█████████▏| 263/288 [01:22<00:08, 2.95it/s]
23505
  92%|█████████▏| 264/288 [01:22<00:08, 2.88it/s]
23506
  92%|█████████▏| 265/288 [01:23<00:07, 2.88it/s]
23507
  92%|█████████▏| 266/288 [01:23<00:07, 2.92it/s]
23508
  93%|█████████▎| 267/288 [01:23<00:07, 2.84it/s]
23509
  93%|█████████▎| 268/288 [01:24<00:06, 2.90it/s]
23510
  93%|█████████▎| 269/288 [01:24<00:06, 2.80it/s]
23511
  94%|█████████▍| 270/288 [01:24<00:06, 2.71it/s]
23512
  94%|█████████▍| 271/288 [01:25<00:06, 2.75it/s]
23513
  94%|█████████▍| 272/288 [01:25<00:05, 2.80it/s]
23514
  95%|█████████▍| 273/288 [01:25<00:05, 2.85it/s]
23515
  95%|█████████▌| 274/288 [01:26<00:04, 2.92it/s]
23516
  95%|█████████▌| 275/288 [01:26<00:04, 3.00it/s]
23517
  96%|█████████▌| 276/288 [01:26<00:03, 3.02it/s]
23518
  96%|█████████▌| 277/288 [01:27<00:03, 2.98it/s]
23519
  97%|█████████▋| 278/288 [01:27<00:03, 2.85it/s]
23520
  97%|█████████▋| 279/288 [01:27<00:03, 2.98it/s]
23521
  97%|█████████▋| 280/288 [01:28<00:02, 2.97it/s]
23522
  98%|█████████▊| 281/288 [01:28<00:02, 3.04it/s]
23523
  98%|█████████▊| 282/288 [01:28<00:01, 3.04it/s]
23524
  98%|█████████▊| 283/288 [01:29<00:01, 2.90it/s]
23525
  99%|█████████▊| 284/288 [01:29<00:01, 3.02it/s]
23526
  99%|█████████▉| 285/288 [01:29<00:00, 3.06it/s]
23527
  99%|█████████▉| 286/288 [01:30<00:00, 3.10it/s]
 
 
 
 
 
23239
 
23240
  Dropping the following result as it does not have all the necessary fields:
23241
  {'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'zh-HK'}}
23242
+ To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2
23243
+ ace94fa..5679ecf main -> main
23244
+
23245
+ 02/07/2022 12:45:57 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2
23246
+ ace94fa..5679ecf main -> main
23247
+
23248
+ ***** train metrics *****
23249
+ epoch = 100.0
23250
+ train_loss = 3.7852
23251
+ train_runtime = 20:10:40.10
23252
+ train_samples = 11949
23253
+ train_samples_per_second = 16.45
23254
+ train_steps_per_second = 0.513
23255
+ 02/07/2022 12:46:00 - INFO - __main__ - *** Evaluate ***
23256
+ The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
23257
+ ***** Running Evaluation *****
23258
+ Num examples = 2302
23259
+ Batch size = 8
23260
+
23261
  0%| | 0/288 [00:00<?, ?it/s]
23262
  1%| | 2/288 [00:00<00:40, 7.05it/s]
23263
  1%| | 3/288 [00:00<01:04, 4.42it/s]
23264
  1%|▏ | 4/288 [00:00<01:14, 3.84it/s]
23265
  2%|▏ | 5/288 [00:01<01:12, 3.88it/s]
23266
  2%|▏ | 6/288 [00:01<01:15, 3.74it/s]
23267
  2%|▏ | 7/288 [00:01<01:18, 3.58it/s]
23268
  3%|▎ | 8/288 [00:02<01:15, 3.72it/s]
23269
  3%|▎ | 9/288 [00:02<01:19, 3.53it/s]
23270
  3%|▎ | 10/288 [00:02<01:26, 3.20it/s]
23271
  4%|▍ | 11/288 [00:03<01:28, 3.12it/s]
23272
  4%|▍ | 12/288 [00:03<01:23, 3.29it/s]
23273
  5%|▍ | 13/288 [00:03<01:25, 3.21it/s]
23274
  5%|▍ | 14/288 [00:03<01:24, 3.26it/s]
23275
  5%|▌ | 15/288 [00:04<01:20, 3.38it/s]
23276
  6%|▌ | 16/288 [00:04<01:23, 3.24it/s]
23277
  6%|▌ | 17/288 [00:04<01:21, 3.33it/s]
23278
  6%|▋ | 18/288 [00:05<01:23, 3.23it/s]
23279
  7%|▋ | 19/288 [00:05<01:25, 3.16it/s]
23280
  7%|▋ | 20/288 [00:05<01:22, 3.25it/s]
23281
  7%|▋ | 21/288 [00:06<01:21, 3.28it/s]
23282
  8%|▊ | 22/288 [00:06<01:18, 3.38it/s]
23283
  8%|▊ | 23/288 [00:06<01:19, 3.34it/s]
23284
  8%|▊ | 24/288 [00:06<01:20, 3.29it/s]
23285
  9%|▊ | 25/288 [00:07<01:18, 3.34it/s]
23286
  9%|▉ | 26/288 [00:07<01:21, 3.20it/s]
23287
  9%|▉ | 27/288 [00:07<01:21, 3.21it/s]
23288
  10%|▉ | 28/288 [00:08<01:18, 3.33it/s]
23289
  10%|█ | 29/288 [00:08<01:14, 3.50it/s]
23290
  10%|█ | 30/288 [00:08<01:07, 3.85it/s]
23291
  11%|█ | 31/288 [00:08<01:05, 3.90it/s]
23292
  11%|█ | 32/288 [00:09<01:08, 3.76it/s]
23293
  11%|█▏ | 33/288 [00:09<01:06, 3.86it/s]
23294
  12%|█▏ | 34/288 [00:09<01:06, 3.80it/s]
23295
  12%|█▏ | 35/288 [00:10<01:08, 3.69it/s]
23296
  12%|█▎ | 36/288 [00:10<01:09, 3.63it/s]
23297
  13%|█▎ | 37/288 [00:10<01:08, 3.64it/s]
23298
  13%|█▎ | 38/288 [00:10<01:08, 3.66it/s]
23299
  14%|█▎ | 39/288 [00:11<01:09, 3.59it/s]
23300
  14%|█▍ | 40/288 [00:11<01:11, 3.49it/s]
23301
  14%|█▍ | 41/288 [00:11<01:09, 3.56it/s]
23302
  15%|█▍ | 42/288 [00:12<01:11, 3.43it/s]
23303
  15%|█▍ | 43/288 [00:12<01:13, 3.34it/s]
23304
  15%|█▌ | 44/288 [00:12<01:12, 3.36it/s]
23305
  16%|█▌ | 45/288 [00:12<01:12, 3.35it/s]
23306
  16%|█▌ | 46/288 [00:13<01:10, 3.43it/s]
23307
  16%|█▋ | 47/288 [00:13<01:12, 3.34it/s]
23308
  17%|█▋ | 48/288 [00:13<01:15, 3.16it/s]
23309
  17%|█▋ | 49/288 [00:14<01:13, 3.26it/s]
23310
  17%|█▋ | 50/288 [00:14<01:11, 3.34it/s]
23311
  18%|█▊ | 51/288 [00:14<01:09, 3.40it/s]
23312
  18%|█▊ | 52/288 [00:15<01:10, 3.35it/s]
23313
  18%|█▊ | 53/288 [00:15<01:10, 3.33it/s]
23314
  19%|█▉ | 54/288 [00:15<01:09, 3.37it/s]
23315
  19%|█▉ | 55/288 [00:15<01:11, 3.26it/s]
23316
  19%|█▉ | 56/288 [00:16<01:09, 3.34it/s]
23317
  20%|█▉ | 57/288 [00:16<01:08, 3.39it/s]
23318
  20%|██ | 58/288 [00:16<01:05, 3.49it/s]
23319
  20%|██ | 59/288 [00:17<01:04, 3.58it/s]
23320
  21%|██ | 60/288 [00:17<01:00, 3.74it/s]
23321
  21%|██ | 61/288 [00:17<01:05, 3.46it/s]
23322
  22%|██▏ | 62/288 [00:17<01:06, 3.39it/s]
23323
  22%|██▏ | 63/288 [00:18<01:07, 3.31it/s]
23324
  22%|██▏ | 64/288 [00:18<01:06, 3.39it/s]
23325
  23%|██▎ | 65/288 [00:18<01:08, 3.27it/s]
23326
  23%|██▎ | 66/288 [00:19<01:09, 3.17it/s]
23327
  23%|██▎ | 67/288 [00:19<01:07, 3.27it/s]
23328
  24%|██▎ | 68/288 [00:19<01:09, 3.18it/s]
23329
  24%|██▍ | 69/288 [00:20<01:10, 3.13it/s]
23330
  24%|██▍ | 70/288 [00:20<01:09, 3.16it/s]
23331
  25%|██▍ | 71/288 [00:20<01:11, 3.03it/s]
23332
  25%|██▌ | 72/288 [00:21<01:09, 3.11it/s]
23333
  25%|██▌ | 73/288 [00:21<01:08, 3.15it/s]
23334
  26%|██▌ | 74/288 [00:21<01:09, 3.07it/s]
23335
  26%|██▌ | 75/288 [00:22<01:10, 3.00it/s]
23336
  26%|██▋ | 76/288 [00:22<01:08, 3.08it/s]
23337
  27%|██▋ | 77/288 [00:22<01:09, 3.06it/s]
23338
  27%|██▋ | 78/288 [00:23<01:08, 3.09it/s]
23339
  27%|██▋ | 79/288 [00:23<01:06, 3.14it/s]
23340
  28%|██▊ | 80/288 [00:23<01:04, 3.24it/s]
23341
  28%|██▊ | 81/288 [00:24<01:05, 3.18it/s]
23342
  28%|██▊ | 82/288 [00:24<01:03, 3.26it/s]
23343
  29%|██▉ | 83/288 [00:24<01:04, 3.17it/s]
23344
  29%|██▉ | 84/288 [00:24<01:00, 3.38it/s]
23345
  30%|██▉ | 85/288 [00:25<00:58, 3.45it/s]
23346
  30%|██▉ | 86/288 [00:25<01:02, 3.23it/s]
23347
  30%|███ | 87/288 [00:25<01:02, 3.21it/s]
23348
  31%|███ | 88/288 [00:26<01:02, 3.18it/s]
23349
  31%|███ | 89/288 [00:26<01:01, 3.24it/s]
23350
  31%|███▏ | 90/288 [00:26<01:00, 3.29it/s]
23351
  32%|███▏ | 91/288 [00:27<01:01, 3.22it/s]
23352
  32%|███▏ | 92/288 [00:27<00:59, 3.28it/s]
23353
  32%|███▏ | 93/288 [00:27<01:01, 3.15it/s]
23354
  33%|███▎ | 94/288 [00:28<01:01, 3.18it/s]
23355
  33%|███▎ | 95/288 [00:28<01:00, 3.21it/s]
23356
  33%|███▎ | 96/288 [00:28<00:57, 3.35it/s]
23357
  34%|███▎ | 97/288 [00:28<00:55, 3.41it/s]
23358
  34%|███▍ | 98/288 [00:29<00:57, 3.29it/s]
23359
  34%|███▍ | 99/288 [00:29<00:59, 3.16it/s]
23360
  35%|███▍ | 100/288 [00:29<00:58, 3.21it/s]
23361
  35%|███▌ | 101/288 [00:30<00:57, 3.26it/s]
23362
  35%|███▌ | 102/288 [00:30<00:55, 3.35it/s]
23363
  36%|███▌ | 103/288 [00:30<00:55, 3.34it/s]
23364
  36%|███▌ | 104/288 [00:31<00:56, 3.24it/s]
23365
  36%|███▋ | 105/288 [00:31<00:53, 3.40it/s]
23366
  37%|███▋ | 106/288 [00:31<00:56, 3.24it/s]
23367
  37%|███▋ | 107/288 [00:31<00:56, 3.19it/s]
23368
  38%|███▊ | 108/288 [00:32<00:56, 3.18it/s]
23369
  38%|███▊ | 109/288 [00:32<00:56, 3.15it/s]
23370
  38%|███▊ | 110/288 [00:32<00:55, 3.20it/s]
23371
  39%|███▊ | 111/288 [00:33<00:54, 3.22it/s]
23372
  39%|███▉ | 112/288 [00:33<00:55, 3.17it/s]
23373
  39%|███▉ | 113/288 [00:33<00:55, 3.16it/s]
23374
  40%|███▉ | 114/288 [00:34<00:55, 3.14it/s]
23375
  40%|███▉ | 115/288 [00:34<00:54, 3.19it/s]
23376
  40%|████ | 116/288 [00:34<00:54, 3.14it/s]
23377
  41%|████ | 117/288 [00:35<00:54, 3.16it/s]
23378
  41%|████ | 118/288 [00:35<00:51, 3.33it/s]
23379
  41%|████▏ | 119/288 [00:35<00:52, 3.23it/s]
23380
  42%|████▏ | 120/288 [00:36<00:53, 3.16it/s]
23381
  42%|████▏ | 121/288 [00:36<00:51, 3.26it/s]
23382
  42%|████▏ | 122/288 [00:36<00:48, 3.41it/s]
23383
  43%|████▎ | 123/288 [00:36<00:51, 3.17it/s]
23384
  43%|████▎ | 124/288 [00:37<00:51, 3.18it/s]
23385
  43%|████▎ | 125/288 [00:37<00:51, 3.17it/s]
23386
  44%|████▍ | 126/288 [00:37<00:52, 3.06it/s]
23387
  44%|████▍ | 127/288 [00:38<00:51, 3.13it/s]
23388
  44%|████▍ | 128/288 [00:38<00:50, 3.14it/s]
23389
  45%|████▍ | 129/288 [00:38<00:52, 3.00it/s]
23390
  45%|████▌ | 130/288 [00:39<00:52, 3.03it/s]
23391
  45%|████▌ | 131/288 [00:39<00:50, 3.09it/s]
23392
  46%|████▌ | 132/288 [00:39<00:50, 3.08it/s]
23393
  46%|████▌ | 133/288 [00:40<00:52, 2.97it/s]
23394
  47%|████▋ | 134/288 [00:40<00:51, 2.96it/s]
23395
  47%|████▋ | 135/288 [00:40<00:51, 2.99it/s]
23396
  47%|████▋ | 136/288 [00:41<00:49, 3.06it/s]
23397
  48%|████▊ | 137/288 [00:41<00:48, 3.09it/s]
23398
  48%|████▊ | 138/288 [00:41<00:49, 3.05it/s]
23399
  48%|████▊ | 139/288 [00:42<00:49, 3.01it/s]
23400
  49%|████▊ | 140/288 [00:42<00:49, 3.01it/s]
23401
  49%|████▉ | 141/288 [00:42<00:50, 2.94it/s]
23402
  49%|████▉ | 142/288 [00:43<00:48, 3.03it/s]
23403
  50%|████▉ | 143/288 [00:43<00:48, 2.99it/s]
23404
  50%|█████ | 144/288 [00:43<00:44, 3.27it/s]
23405
  50%|█████ | 145/288 [00:44<00:43, 3.26it/s]
23406
  51%|█████ | 146/288 [00:44<00:42, 3.31it/s]
23407
  51%|█████ | 147/288 [00:44<00:43, 3.27it/s]
23408
  51%|█████▏ | 148/288 [00:45<00:44, 3.17it/s]
23409
  52%|█████▏ | 149/288 [00:45<00:43, 3.18it/s]
23410
  52%|█████▏ | 150/288 [00:45<00:44, 3.11it/s]
23411
  52%|█████▏ | 151/288 [00:45<00:42, 3.24it/s]
23412
  53%|█████▎ | 152/288 [00:46<00:42, 3.21it/s]
23413
  53%|█████▎ | 153/288 [00:46<00:40, 3.30it/s]
23414
  53%|█████▎ | 154/288 [00:46<00:42, 3.13it/s]
23415
  54%|█████▍ | 155/288 [00:47<00:42, 3.12it/s]
23416
  54%|█████▍ | 156/288 [00:47<00:41, 3.16it/s]
23417
  55%|█████▍ | 157/288 [00:47<00:41, 3.14it/s]
23418
  55%|█████▍ | 158/288 [00:48<00:41, 3.11it/s]
23419
  55%|█████▌ | 159/288 [00:48<00:41, 3.12it/s]
23420
  56%|█████▌ | 160/288 [00:48<00:39, 3.20it/s]
23421
  56%|█████▌ | 161/288 [00:49<00:38, 3.29it/s]
23422
  56%|█████▋ | 162/288 [00:49<00:37, 3.36it/s]
23423
  57%|█████▋ | 163/288 [00:49<00:38, 3.26it/s]
23424
  57%|█████▋ | 164/288 [00:50<00:37, 3.32it/s]
23425
  57%|█████▋ | 165/288 [00:50<00:37, 3.29it/s]
23426
  58%|█████▊ | 166/288 [00:50<00:37, 3.24it/s]
23427
  58%|█████▊ | 167/288 [00:50<00:37, 3.27it/s]
23428
  58%|█████▊ | 168/288 [00:51<00:38, 3.15it/s]
23429
  59%|█████▊ | 169/288 [00:51<00:37, 3.18it/s]
23430
  59%|█████▉ | 170/288 [00:51<00:37, 3.16it/s]
23431
  59%|█████▉ | 171/288 [00:52<00:37, 3.14it/s]
23432
  60%|█████▉ | 172/288 [00:52<00:37, 3.12it/s]
23433
  60%|██████ | 173/288 [00:52<00:37, 3.06it/s]
23434
  60%|██████ | 174/288 [00:53<00:36, 3.09it/s]
23435
  61%|██████ | 175/288 [00:53<00:35, 3.20it/s]
23436
  61%|██████ | 176/288 [00:53<00:37, 2.99it/s]
23437
  61%|██████▏ | 177/288 [00:54<00:36, 3.01it/s]
23438
  62%|██████▏ | 178/288 [00:54<00:36, 2.99it/s]
23439
  62%|██████▏ | 179/288 [00:54<00:35, 3.05it/s]
23440
  62%|██████▎ | 180/288 [00:55<00:35, 3.07it/s]
23441
  63%|██████▎ | 181/288 [00:55<00:33, 3.24it/s]
23442
  63%|██████▎ | 182/288 [00:55<00:34, 3.12it/s]
23443
  64%|██████▎ | 183/288 [00:56<00:33, 3.14it/s]
23444
  64%|██████▍ | 184/288 [00:56<00:33, 3.11it/s]
23445
  64%|██████▍ | 185/288 [00:56<00:32, 3.15it/s]
23446
  65%|██████▍ | 186/288 [00:57<00:30, 3.33it/s]
23447
  65%|██████▍ | 187/288 [00:57<00:32, 3.10it/s]
23448
  65%|██████▌ | 188/288 [00:57<00:32, 3.12it/s]
23449
  66%|██████▌ | 189/288 [00:58<00:30, 3.22it/s]
23450
  66%|██████▌ | 190/288 [00:58<00:31, 3.08it/s]
23451
  66%|██████▋ | 191/288 [00:58<00:31, 3.10it/s]
23452
  67%|██████▋ | 192/288 [00:58<00:30, 3.19it/s]
23453
  67%|██████▋ | 193/288 [00:59<00:29, 3.21it/s]
23454
  67%|██████▋ | 194/288 [00:59<00:31, 3.03it/s]
23455
  68%|██████▊ | 195/288 [00:59<00:30, 3.07it/s]
23456
  68%|██████▊ | 196/288 [01:00<00:30, 2.97it/s]
23457
  68%|██████▊ | 197/288 [01:00<00:30, 2.98it/s]
23458
  69%|██████▉ | 198/288 [01:00<00:28, 3.15it/s]
23459
  69%|██████▉ | 199/288 [01:01<00:28, 3.13it/s]
23460
  69%|██████▉ | 200/288 [01:01<00:26, 3.27it/s]
23461
  70%|██████▉ | 201/288 [01:01<00:27, 3.17it/s]
23462
  70%|███████ | 202/288 [01:02<00:27, 3.16it/s]
23463
  70%|███████ | 203/288 [01:02<00:27, 3.15it/s]
23464
  71%|███████ | 204/288 [01:02<00:26, 3.12it/s]
23465
  71%|███████ | 205/288 [01:03<00:25, 3.21it/s]
23466
  72%|███████▏ | 206/288 [01:03<00:26, 3.12it/s]
23467
  72%|███████▏ | 207/288 [01:03<00:26, 3.03it/s]
23468
  72%|███████▏ | 208/288 [01:04<00:26, 2.98it/s]
23469
  73%|███████▎ | 209/288 [01:04<00:26, 2.94it/s]
23470
  73%|███████▎ | 210/288 [01:04<00:24, 3.17it/s]
23471
  73%|███████▎ | 211/288 [01:05<00:23, 3.24it/s]
23472
  74%|███████▎ | 212/288 [01:05<00:22, 3.32it/s]
23473
  74%|███████▍ | 213/288 [01:05<00:24, 3.08it/s]
23474
  74%|███████▍ | 214/288 [01:06<00:23, 3.15it/s]
23475
  75%|███████▍ | 215/288 [01:06<00:23, 3.06it/s]
23476
  75%|███████▌ | 216/288 [01:06<00:23, 3.03it/s]
23477
  75%|███████▌ | 217/288 [01:07<00:22, 3.15it/s]
23478
  76%|███████▌ | 218/288 [01:07<00:22, 3.11it/s]
23479
  76%|███████▌ | 219/288 [01:07<00:22, 3.11it/s]
23480
  76%|███████▋ | 220/288 [01:08<00:23, 2.94it/s]
23481
  77%|███████▋ | 221/288 [01:08<00:22, 2.97it/s]
23482
  77%|███████▋ | 222/288 [01:08<00:22, 2.92it/s]
23483
  77%|███████▋ | 223/288 [01:09<00:20, 3.11it/s]
23484
  78%|███████▊ | 224/288 [01:09<00:20, 3.07it/s]
23485
  78%|███████▊ | 225/288 [01:09<00:20, 3.10it/s]
23486
  78%|███████▊ | 226/288 [01:09<00:19, 3.13it/s]
23487
  79%|███████▉ | 227/288 [01:10<00:20, 3.03it/s]
23488
  79%|███████▉ | 228/288 [01:10<00:19, 3.01it/s]
23489
  80%|███████▉ | 229/288 [01:10<00:19, 3.04it/s]
23490
  80%|███████▉ | 230/288 [01:11<00:18, 3.07it/s]
23491
  80%|████████ | 231/288 [01:11<00:19, 2.99it/s]
23492
  81%|████████ | 232/288 [01:11<00:18, 3.04it/s]
23493
  81%|████████ | 233/288 [01:12<00:18, 2.94it/s]
23494
  81%|████████▏ | 234/288 [01:12<00:17, 3.01it/s]
23495
  82%|████████▏ | 235/288 [01:12<00:17, 3.01it/s]
23496
  82%|████████▏ | 236/288 [01:13<00:17, 2.92it/s]
23497
  82%|████████▏ | 237/288 [01:13<00:17, 2.89it/s]
23498
  83%|████████▎ | 238/288 [01:14<00:17, 2.92it/s]
23499
  83%|████████▎ | 239/288 [01:14<00:16, 3.01it/s]
23500
  83%|████████▎ | 240/288 [01:14<00:15, 3.14it/s]
23501
  84%|████████▎ | 241/288 [01:14<00:15, 3.09it/s]
23502
  84%|████████▍ | 242/288 [01:15<00:15, 3.05it/s]
23503
  84%|████████▍ | 243/288 [01:15<00:14, 3.13it/s]
23504
  85%|████████▍ | 244/288 [01:15<00:14, 3.06it/s]
23505
  85%|████████▌ | 245/288 [01:16<00:14, 3.04it/s]
23506
  85%|████████▌ | 246/288 [01:16<00:14, 2.98it/s]
23507
  86%|████████▌ | 247/288 [01:16<00:13, 3.11it/s]
23508
  86%|████████▌ | 248/288 [01:17<00:12, 3.12it/s]
23509
  86%|████████▋ | 249/288 [01:17<00:12, 3.04it/s]
23510
  87%|████████▋ | 250/288 [01:17<00:12, 3.00it/s]
23511
  87%|████████▋ | 251/288 [01:18<00:12, 2.91it/s]
23512
  88%|████████▊ | 252/288 [01:18<00:12, 2.84it/s]
23513
  88%|████████▊ | 253/288 [01:18<00:11, 2.99it/s]
23514
  88%|████████▊ | 254/288 [01:19<00:11, 3.09it/s]
23515
  89%|████████▊ | 255/288 [01:19<00:10, 3.16it/s]
23516
  89%|████████▉ | 256/288 [01:19<00:10, 3.14it/s]
23517
  89%|████████▉ | 257/288 [01:20<00:09, 3.16it/s]
23518
  90%|████████▉ | 258/288 [01:20<00:10, 2.93it/s]
23519
  90%|████████▉ | 259/288 [01:20<00:10, 2.85it/s]
23520
  90%|█████████ | 260/288 [01:21<00:09, 2.87it/s]
23521
  91%|█████████ | 261/288 [01:21<00:09, 2.84it/s]
23522
  91%|█████████ | 262/288 [01:22<00:09, 2.87it/s]
23523
  91%|█████████▏| 263/288 [01:22<00:08, 2.95it/s]
23524
  92%|█████████▏| 264/288 [01:22<00:08, 2.88it/s]
23525
  92%|█████████▏| 265/288 [01:23<00:07, 2.88it/s]
23526
  92%|█████████▏| 266/288 [01:23<00:07, 2.92it/s]
23527
  93%|█████████▎| 267/288 [01:23<00:07, 2.84it/s]
23528
  93%|█████████▎| 268/288 [01:24<00:06, 2.90it/s]
23529
  93%|█████████▎| 269/288 [01:24<00:06, 2.80it/s]
23530
  94%|█████████▍| 270/288 [01:24<00:06, 2.71it/s]
23531
  94%|█████████▍| 271/288 [01:25<00:06, 2.75it/s]
23532
  94%|█████████▍| 272/288 [01:25<00:05, 2.80it/s]
23533
  95%|█████████▍| 273/288 [01:25<00:05, 2.85it/s]
23534
  95%|█████████▌| 274/288 [01:26<00:04, 2.92it/s]
23535
  95%|█████████▌| 275/288 [01:26<00:04, 3.00it/s]
23536
  96%|█████████▌| 276/288 [01:26<00:03, 3.02it/s]
23537
  96%|█████████▌| 277/288 [01:27<00:03, 2.98it/s]
23538
  97%|█████████▋| 278/288 [01:27<00:03, 2.85it/s]
23539
  97%|█████████▋| 279/288 [01:27<00:03, 2.98it/s]
23540
  97%|█████████▋| 280/288 [01:28<00:02, 2.97it/s]
23541
  98%|█████████▊| 281/288 [01:28<00:02, 3.04it/s]
23542
  98%|█████████▊| 282/288 [01:28<00:01, 3.04it/s]
23543
  98%|█████████▊| 283/288 [01:29<00:01, 2.90it/s]
23544
  99%|█████████▊| 284/288 [01:29<00:01, 3.02it/s]
23545
  99%|█████████▉| 285/288 [01:29<00:00, 3.06it/s]
23546
  99%|█████████▉| 286/288 [01:30<00:00, 3.10it/s]
23547
+ Saving model checkpoint to ./
23548
+ Configuration saved in ./config.json
23549
+ Model weights saved in ./pytorch_model.bin
23550
+ Configuration saved in ./preprocessor_config.json
runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/events.out.tfevents.1644238077.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3677a7083054130a207aacac190502d2c88bc738db7693aebbdea88f938b71d
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 3.7852419735087786,
4
+ "train_runtime": 72640.1075,
5
+ "train_samples": 11949,
6
+ "train_samples_per_second": 16.45,
7
+ "train_steps_per_second": 0.513
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,3003 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 99.99866131191432,
5
+ "global_step": 37300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.27,
12
+ "learning_rate": 4.85e-06,
13
+ "loss": 153.5094,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.54,
18
+ "learning_rate": 9.85e-06,
19
+ "loss": 108.8648,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.8,
24
+ "learning_rate": 1.48e-05,
25
+ "loss": 92.5714,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 1.07,
30
+ "learning_rate": 1.9800000000000004e-05,
31
+ "loss": 79.9356,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 1.34,
36
+ "learning_rate": 2.48e-05,
37
+ "loss": 69.8341,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 1.34,
42
+ "eval_cer": 1.0,
43
+ "eval_loss": 80.07215118408203,
44
+ "eval_runtime": 130.8213,
45
+ "eval_samples_per_second": 17.597,
46
+ "eval_steps_per_second": 2.201,
47
+ "eval_wer": 1.0,
48
+ "step": 500
49
+ },
50
+ {
51
+ "epoch": 1.61,
52
+ "learning_rate": 2.98e-05,
53
+ "loss": 54.2478,
54
+ "step": 600
55
+ },
56
+ {
57
+ "epoch": 1.88,
58
+ "learning_rate": 3.48e-05,
59
+ "loss": 35.5793,
60
+ "step": 700
61
+ },
62
+ {
63
+ "epoch": 2.14,
64
+ "learning_rate": 3.9800000000000005e-05,
65
+ "loss": 17.7978,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 2.41,
70
+ "learning_rate": 4.4800000000000005e-05,
71
+ "loss": 8.1204,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 2.68,
76
+ "learning_rate": 4.9800000000000004e-05,
77
+ "loss": 6.6418,
78
+ "step": 1000
79
+ },
80
+ {
81
+ "epoch": 2.68,
82
+ "eval_cer": 1.0,
83
+ "eval_loss": 6.634645938873291,
84
+ "eval_runtime": 117.0489,
85
+ "eval_samples_per_second": 19.667,
86
+ "eval_steps_per_second": 2.461,
87
+ "eval_wer": 1.0,
88
+ "step": 1000
89
+ },
90
+ {
91
+ "epoch": 2.95,
92
+ "learning_rate": 5.4800000000000004e-05,
93
+ "loss": 6.3633,
94
+ "step": 1100
95
+ },
96
+ {
97
+ "epoch": 3.22,
98
+ "learning_rate": 5.9800000000000003e-05,
99
+ "loss": 6.364,
100
+ "step": 1200
101
+ },
102
+ {
103
+ "epoch": 3.48,
104
+ "learning_rate": 6.48e-05,
105
+ "loss": 6.2461,
106
+ "step": 1300
107
+ },
108
+ {
109
+ "epoch": 3.75,
110
+ "learning_rate": 6.98e-05,
111
+ "loss": 6.2242,
112
+ "step": 1400
113
+ },
114
+ {
115
+ "epoch": 4.02,
116
+ "learning_rate": 7.48e-05,
117
+ "loss": 6.2419,
118
+ "step": 1500
119
+ },
120
+ {
121
+ "epoch": 4.02,
122
+ "eval_cer": 1.0,
123
+ "eval_loss": 6.290937423706055,
124
+ "eval_runtime": 117.0781,
125
+ "eval_samples_per_second": 19.662,
126
+ "eval_steps_per_second": 2.46,
127
+ "eval_wer": 1.0,
128
+ "step": 1500
129
+ },
130
+ {
131
+ "epoch": 4.29,
132
+ "learning_rate": 7.98e-05,
133
+ "loss": 6.1691,
134
+ "step": 1600
135
+ },
136
+ {
137
+ "epoch": 4.56,
138
+ "learning_rate": 8.48e-05,
139
+ "loss": 6.1668,
140
+ "step": 1700
141
+ },
142
+ {
143
+ "epoch": 4.82,
144
+ "learning_rate": 8.98e-05,
145
+ "loss": 6.1623,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 5.09,
150
+ "learning_rate": 9.48e-05,
151
+ "loss": 6.1884,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 5.36,
156
+ "learning_rate": 9.98e-05,
157
+ "loss": 6.0813,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 5.36,
162
+ "eval_cer": 1.0,
163
+ "eval_loss": 6.115033149719238,
164
+ "eval_runtime": 117.9948,
165
+ "eval_samples_per_second": 19.509,
166
+ "eval_steps_per_second": 2.441,
167
+ "eval_wer": 1.0,
168
+ "step": 2000
169
+ },
170
+ {
171
+ "epoch": 5.63,
172
+ "learning_rate": 9.972804532577904e-05,
173
+ "loss": 6.1027,
174
+ "step": 2100
175
+ },
176
+ {
177
+ "epoch": 5.9,
178
+ "learning_rate": 9.944475920679887e-05,
179
+ "loss": 6.0586,
180
+ "step": 2200
181
+ },
182
+ {
183
+ "epoch": 6.17,
184
+ "learning_rate": 9.91614730878187e-05,
185
+ "loss": 6.0399,
186
+ "step": 2300
187
+ },
188
+ {
189
+ "epoch": 6.43,
190
+ "learning_rate": 9.887818696883852e-05,
191
+ "loss": 6.0035,
192
+ "step": 2400
193
+ },
194
+ {
195
+ "epoch": 6.7,
196
+ "learning_rate": 9.859490084985836e-05,
197
+ "loss": 5.9677,
198
+ "step": 2500
199
+ },
200
+ {
201
+ "epoch": 6.7,
202
+ "eval_cer": 1.002818566168114,
203
+ "eval_loss": 6.030123233795166,
204
+ "eval_runtime": 116.8078,
205
+ "eval_samples_per_second": 19.708,
206
+ "eval_steps_per_second": 2.466,
207
+ "eval_wer": 1.1385881333910783,
208
+ "step": 2500
209
+ },
210
+ {
211
+ "epoch": 6.97,
212
+ "learning_rate": 9.831161473087818e-05,
213
+ "loss": 5.9617,
214
+ "step": 2600
215
+ },
216
+ {
217
+ "epoch": 7.24,
218
+ "learning_rate": 9.802832861189802e-05,
219
+ "loss": 5.9736,
220
+ "step": 2700
221
+ },
222
+ {
223
+ "epoch": 7.51,
224
+ "learning_rate": 9.774504249291784e-05,
225
+ "loss": 5.9098,
226
+ "step": 2800
227
+ },
228
+ {
229
+ "epoch": 7.77,
230
+ "learning_rate": 9.746175637393768e-05,
231
+ "loss": 5.9069,
232
+ "step": 2900
233
+ },
234
+ {
235
+ "epoch": 8.04,
236
+ "learning_rate": 9.717847025495752e-05,
237
+ "loss": 5.9296,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 8.04,
242
+ "eval_cer": 1.0057735145701687,
243
+ "eval_loss": 5.897457599639893,
244
+ "eval_runtime": 116.427,
245
+ "eval_samples_per_second": 19.772,
246
+ "eval_steps_per_second": 2.474,
247
+ "eval_wer": 1.2113469034213946,
248
+ "step": 3000
249
+ },
250
+ {
251
+ "epoch": 8.31,
252
+ "learning_rate": 9.689518413597734e-05,
253
+ "loss": 5.8213,
254
+ "step": 3100
255
+ },
256
+ {
257
+ "epoch": 8.58,
258
+ "learning_rate": 9.661189801699718e-05,
259
+ "loss": 5.8241,
260
+ "step": 3200
261
+ },
262
+ {
263
+ "epoch": 8.85,
264
+ "learning_rate": 9.632861189801701e-05,
265
+ "loss": 5.7787,
266
+ "step": 3300
267
+ },
268
+ {
269
+ "epoch": 9.12,
270
+ "learning_rate": 9.604532577903684e-05,
271
+ "loss": 5.7529,
272
+ "step": 3400
273
+ },
274
+ {
275
+ "epoch": 9.38,
276
+ "learning_rate": 9.576203966005666e-05,
277
+ "loss": 5.6434,
278
+ "step": 3500
279
+ },
280
+ {
281
+ "epoch": 9.38,
282
+ "eval_cer": 1.017093239987271,
283
+ "eval_loss": 5.540365219116211,
284
+ "eval_runtime": 116.7079,
285
+ "eval_samples_per_second": 19.724,
286
+ "eval_steps_per_second": 2.468,
287
+ "eval_wer": 2.16240796881767,
288
+ "step": 3500
289
+ },
290
+ {
291
+ "epoch": 9.65,
292
+ "learning_rate": 9.54787535410765e-05,
293
+ "loss": 5.6259,
294
+ "step": 3600
295
+ },
296
+ {
297
+ "epoch": 9.92,
298
+ "learning_rate": 9.519546742209632e-05,
299
+ "loss": 5.5488,
300
+ "step": 3700
301
+ },
302
+ {
303
+ "epoch": 10.19,
304
+ "learning_rate": 9.491218130311616e-05,
305
+ "loss": 5.5068,
306
+ "step": 3800
307
+ },
308
+ {
309
+ "epoch": 10.46,
310
+ "learning_rate": 9.462889518413598e-05,
311
+ "loss": 5.3439,
312
+ "step": 3900
313
+ },
314
+ {
315
+ "epoch": 10.72,
316
+ "learning_rate": 9.434560906515582e-05,
317
+ "loss": 5.1974,
318
+ "step": 4000
319
+ },
320
+ {
321
+ "epoch": 10.72,
322
+ "eval_cer": 0.9365822612174387,
323
+ "eval_loss": 4.543997287750244,
324
+ "eval_runtime": 115.8257,
325
+ "eval_samples_per_second": 19.875,
326
+ "eval_steps_per_second": 2.486,
327
+ "eval_wer": 2.170203551320918,
328
+ "step": 4000
329
+ },
330
+ {
331
+ "epoch": 10.99,
332
+ "learning_rate": 9.406232294617564e-05,
333
+ "loss": 4.8692,
334
+ "step": 4100
335
+ },
336
+ {
337
+ "epoch": 11.26,
338
+ "learning_rate": 9.377903682719548e-05,
339
+ "loss": 4.7155,
340
+ "step": 4200
341
+ },
342
+ {
343
+ "epoch": 11.53,
344
+ "learning_rate": 9.34957507082153e-05,
345
+ "loss": 4.4978,
346
+ "step": 4300
347
+ },
348
+ {
349
+ "epoch": 11.8,
350
+ "learning_rate": 9.321246458923513e-05,
351
+ "loss": 4.4105,
352
+ "step": 4400
353
+ },
354
+ {
355
+ "epoch": 12.06,
356
+ "learning_rate": 9.292917847025496e-05,
357
+ "loss": 4.3601,
358
+ "step": 4500
359
+ },
360
+ {
361
+ "epoch": 12.06,
362
+ "eval_cer": 0.8998045187980179,
363
+ "eval_loss": 3.383898973464966,
364
+ "eval_runtime": 117.0791,
365
+ "eval_samples_per_second": 19.662,
366
+ "eval_steps_per_second": 2.46,
367
+ "eval_wer": 2.246427024686011,
368
+ "step": 4500
369
+ },
370
+ {
371
+ "epoch": 12.33,
372
+ "learning_rate": 9.264589235127479e-05,
373
+ "loss": 4.1745,
374
+ "step": 4600
375
+ },
376
+ {
377
+ "epoch": 12.6,
378
+ "learning_rate": 9.236260623229462e-05,
379
+ "loss": 4.1194,
380
+ "step": 4700
381
+ },
382
+ {
383
+ "epoch": 12.87,
384
+ "learning_rate": 9.207932011331445e-05,
385
+ "loss": 4.0809,
386
+ "step": 4800
387
+ },
388
+ {
389
+ "epoch": 13.14,
390
+ "learning_rate": 9.179603399433428e-05,
391
+ "loss": 3.9556,
392
+ "step": 4900
393
+ },
394
+ {
395
+ "epoch": 13.4,
396
+ "learning_rate": 9.151558073654392e-05,
397
+ "loss": 3.9321,
398
+ "step": 5000
399
+ },
400
+ {
401
+ "epoch": 13.4,
402
+ "eval_cer": 0.8400236395872165,
403
+ "eval_loss": 2.8784573078155518,
404
+ "eval_runtime": 117.9053,
405
+ "eval_samples_per_second": 19.524,
406
+ "eval_steps_per_second": 2.443,
407
+ "eval_wer": 2.3096578605456908,
408
+ "step": 5000
409
+ },
410
+ {
411
+ "epoch": 13.67,
412
+ "learning_rate": 9.123229461756374e-05,
413
+ "loss": 3.8826,
414
+ "step": 5100
415
+ },
416
+ {
417
+ "epoch": 13.94,
418
+ "learning_rate": 9.094900849858358e-05,
419
+ "loss": 3.7975,
420
+ "step": 5200
421
+ },
422
+ {
423
+ "epoch": 14.21,
424
+ "learning_rate": 9.06657223796034e-05,
425
+ "loss": 3.7704,
426
+ "step": 5300
427
+ },
428
+ {
429
+ "epoch": 14.48,
430
+ "learning_rate": 9.038243626062324e-05,
431
+ "loss": 3.6848,
432
+ "step": 5400
433
+ },
434
+ {
435
+ "epoch": 14.74,
436
+ "learning_rate": 9.009915014164306e-05,
437
+ "loss": 3.6462,
438
+ "step": 5500
439
+ },
440
+ {
441
+ "epoch": 14.74,
442
+ "eval_cer": 0.6663181342910397,
443
+ "eval_loss": 2.510770797729492,
444
+ "eval_runtime": 116.5338,
445
+ "eval_samples_per_second": 19.754,
446
+ "eval_steps_per_second": 2.471,
447
+ "eval_wer": 1.9623213512343005,
448
+ "step": 5500
449
+ },
450
+ {
451
+ "epoch": 15.01,
452
+ "learning_rate": 8.98158640226629e-05,
453
+ "loss": 3.584,
454
+ "step": 5600
455
+ },
456
+ {
457
+ "epoch": 15.28,
458
+ "learning_rate": 8.953257790368272e-05,
459
+ "loss": 3.531,
460
+ "step": 5700
461
+ },
462
+ {
463
+ "epoch": 15.55,
464
+ "learning_rate": 8.925212464589235e-05,
465
+ "loss": 3.5509,
466
+ "step": 5800
467
+ },
468
+ {
469
+ "epoch": 15.82,
470
+ "learning_rate": 8.896883852691219e-05,
471
+ "loss": 3.524,
472
+ "step": 5900
473
+ },
474
+ {
475
+ "epoch": 16.09,
476
+ "learning_rate": 8.868555240793201e-05,
477
+ "loss": 3.5156,
478
+ "step": 6000
479
+ },
480
+ {
481
+ "epoch": 16.09,
482
+ "eval_cer": 0.5705778060644633,
483
+ "eval_loss": 2.2789571285247803,
484
+ "eval_runtime": 115.731,
485
+ "eval_samples_per_second": 19.891,
486
+ "eval_steps_per_second": 2.489,
487
+ "eval_wer": 1.6478995236032914,
488
+ "step": 6000
489
+ },
490
+ {
491
+ "epoch": 16.35,
492
+ "learning_rate": 8.840226628895184e-05,
493
+ "loss": 3.4294,
494
+ "step": 6100
495
+ },
496
+ {
497
+ "epoch": 16.62,
498
+ "learning_rate": 8.811898016997168e-05,
499
+ "loss": 3.4156,
500
+ "step": 6200
501
+ },
502
+ {
503
+ "epoch": 16.89,
504
+ "learning_rate": 8.78356940509915e-05,
505
+ "loss": 3.3933,
506
+ "step": 6300
507
+ },
508
+ {
509
+ "epoch": 17.16,
510
+ "learning_rate": 8.755240793201134e-05,
511
+ "loss": 3.3293,
512
+ "step": 6400
513
+ },
514
+ {
515
+ "epoch": 17.43,
516
+ "learning_rate": 8.726912181303116e-05,
517
+ "loss": 3.32,
518
+ "step": 6500
519
+ },
520
+ {
521
+ "epoch": 17.43,
522
+ "eval_cer": 0.6244033277265082,
523
+ "eval_loss": 2.1449646949768066,
524
+ "eval_runtime": 119.2852,
525
+ "eval_samples_per_second": 19.298,
526
+ "eval_steps_per_second": 2.414,
527
+ "eval_wer": 1.833694239930706,
528
+ "step": 6500
529
+ },
530
+ {
531
+ "epoch": 17.69,
532
+ "learning_rate": 8.6985835694051e-05,
533
+ "loss": 3.3019,
534
+ "step": 6600
535
+ },
536
+ {
537
+ "epoch": 17.96,
538
+ "learning_rate": 8.670538243626063e-05,
539
+ "loss": 3.3058,
540
+ "step": 6700
541
+ },
542
+ {
543
+ "epoch": 18.23,
544
+ "learning_rate": 8.642209631728045e-05,
545
+ "loss": 3.289,
546
+ "step": 6800
547
+ },
548
+ {
549
+ "epoch": 18.5,
550
+ "learning_rate": 8.613881019830029e-05,
551
+ "loss": 3.208,
552
+ "step": 6900
553
+ },
554
+ {
555
+ "epoch": 18.77,
556
+ "learning_rate": 8.585552407932011e-05,
557
+ "loss": 3.1918,
558
+ "step": 7000
559
+ },
560
+ {
561
+ "epoch": 18.77,
562
+ "eval_cer": 0.6017184161476565,
563
+ "eval_loss": 1.8536365032196045,
564
+ "eval_runtime": 116.4854,
565
+ "eval_samples_per_second": 19.762,
566
+ "eval_steps_per_second": 2.472,
567
+ "eval_wer": 1.939367691641403,
568
+ "step": 7000
569
+ },
570
+ {
571
+ "epoch": 19.03,
572
+ "learning_rate": 8.557223796033995e-05,
573
+ "loss": 3.1877,
574
+ "step": 7100
575
+ },
576
+ {
577
+ "epoch": 19.3,
578
+ "learning_rate": 8.528895184135977e-05,
579
+ "loss": 3.0893,
580
+ "step": 7200
581
+ },
582
+ {
583
+ "epoch": 19.57,
584
+ "learning_rate": 8.500566572237961e-05,
585
+ "loss": 3.102,
586
+ "step": 7300
587
+ },
588
+ {
589
+ "epoch": 19.84,
590
+ "learning_rate": 8.472521246458924e-05,
591
+ "loss": 3.0536,
592
+ "step": 7400
593
+ },
594
+ {
595
+ "epoch": 20.11,
596
+ "learning_rate": 8.444192634560907e-05,
597
+ "loss": 3.1139,
598
+ "step": 7500
599
+ },
600
+ {
601
+ "epoch": 20.11,
602
+ "eval_cer": 0.5638496158567078,
603
+ "eval_loss": 1.7204933166503906,
604
+ "eval_runtime": 116.1457,
605
+ "eval_samples_per_second": 19.82,
606
+ "eval_steps_per_second": 2.48,
607
+ "eval_wer": 1.9112169770463403,
608
+ "step": 7500
609
+ },
610
+ {
611
+ "epoch": 20.37,
612
+ "learning_rate": 8.41586402266289e-05,
613
+ "loss": 2.9958,
614
+ "step": 7600
615
+ },
616
+ {
617
+ "epoch": 20.64,
618
+ "learning_rate": 8.387535410764873e-05,
619
+ "loss": 3.0055,
620
+ "step": 7700
621
+ },
622
+ {
623
+ "epoch": 20.91,
624
+ "learning_rate": 8.359206798866855e-05,
625
+ "loss": 2.9673,
626
+ "step": 7800
627
+ },
628
+ {
629
+ "epoch": 21.18,
630
+ "learning_rate": 8.330878186968839e-05,
631
+ "loss": 2.9276,
632
+ "step": 7900
633
+ },
634
+ {
635
+ "epoch": 21.45,
636
+ "learning_rate": 8.302549575070821e-05,
637
+ "loss": 2.8995,
638
+ "step": 8000
639
+ },
640
+ {
641
+ "epoch": 21.45,
642
+ "eval_cer": 0.3250443242260308,
643
+ "eval_loss": 1.5478395223617554,
644
+ "eval_runtime": 120.8897,
645
+ "eval_samples_per_second": 19.042,
646
+ "eval_steps_per_second": 2.382,
647
+ "eval_wer": 1.0623646600259853,
648
+ "step": 8000
649
+ },
650
+ {
651
+ "epoch": 21.71,
652
+ "learning_rate": 8.274220963172805e-05,
653
+ "loss": 2.8602,
654
+ "step": 8100
655
+ },
656
+ {
657
+ "epoch": 21.98,
658
+ "learning_rate": 8.245892351274787e-05,
659
+ "loss": 2.877,
660
+ "step": 8200
661
+ },
662
+ {
663
+ "epoch": 22.25,
664
+ "learning_rate": 8.217563739376771e-05,
665
+ "loss": 2.8283,
666
+ "step": 8300
667
+ },
668
+ {
669
+ "epoch": 22.52,
670
+ "learning_rate": 8.189235127478753e-05,
671
+ "loss": 2.7887,
672
+ "step": 8400
673
+ },
674
+ {
675
+ "epoch": 22.79,
676
+ "learning_rate": 8.160906515580737e-05,
677
+ "loss": 2.7572,
678
+ "step": 8500
679
+ },
680
+ {
681
+ "epoch": 22.79,
682
+ "eval_cer": 0.33668227485566216,
683
+ "eval_loss": 1.406813144683838,
684
+ "eval_runtime": 117.2331,
685
+ "eval_samples_per_second": 19.636,
686
+ "eval_steps_per_second": 2.457,
687
+ "eval_wer": 1.141186660892161,
688
+ "step": 8500
689
+ },
690
+ {
691
+ "epoch": 23.06,
692
+ "learning_rate": 8.132577903682719e-05,
693
+ "loss": 2.7576,
694
+ "step": 8600
695
+ },
696
+ {
697
+ "epoch": 23.32,
698
+ "learning_rate": 8.104249291784703e-05,
699
+ "loss": 2.7336,
700
+ "step": 8700
701
+ },
702
+ {
703
+ "epoch": 23.59,
704
+ "learning_rate": 8.075920679886687e-05,
705
+ "loss": 2.6792,
706
+ "step": 8800
707
+ },
708
+ {
709
+ "epoch": 23.86,
710
+ "learning_rate": 8.047592067988669e-05,
711
+ "loss": 2.6983,
712
+ "step": 8900
713
+ },
714
+ {
715
+ "epoch": 24.13,
716
+ "learning_rate": 8.019263456090653e-05,
717
+ "loss": 2.6881,
718
+ "step": 9000
719
+ },
720
+ {
721
+ "epoch": 24.13,
722
+ "eval_cer": 0.5683047688321134,
723
+ "eval_loss": 1.3311798572540283,
724
+ "eval_runtime": 116.7773,
725
+ "eval_samples_per_second": 19.713,
726
+ "eval_steps_per_second": 2.466,
727
+ "eval_wer": 2.009961022087484,
728
+ "step": 9000
729
+ },
730
+ {
731
+ "epoch": 24.4,
732
+ "learning_rate": 7.990934844192635e-05,
733
+ "loss": 2.6439,
734
+ "step": 9100
735
+ },
736
+ {
737
+ "epoch": 24.66,
738
+ "learning_rate": 7.962606232294619e-05,
739
+ "loss": 2.6563,
740
+ "step": 9200
741
+ },
742
+ {
743
+ "epoch": 24.93,
744
+ "learning_rate": 7.934277620396601e-05,
745
+ "loss": 2.6792,
746
+ "step": 9300
747
+ },
748
+ {
749
+ "epoch": 25.2,
750
+ "learning_rate": 7.905949008498585e-05,
751
+ "loss": 2.6905,
752
+ "step": 9400
753
+ },
754
+ {
755
+ "epoch": 25.47,
756
+ "learning_rate": 7.877620396600567e-05,
757
+ "loss": 2.5993,
758
+ "step": 9500
759
+ },
760
+ {
761
+ "epoch": 25.47,
762
+ "eval_cer": 0.6450425057962449,
763
+ "eval_loss": 1.2552706003189087,
764
+ "eval_runtime": 117.844,
765
+ "eval_samples_per_second": 19.534,
766
+ "eval_steps_per_second": 2.444,
767
+ "eval_wer": 2.003897791251624,
768
+ "step": 9500
769
+ },
770
+ {
771
+ "epoch": 25.74,
772
+ "learning_rate": 7.849291784702551e-05,
773
+ "loss": 2.6243,
774
+ "step": 9600
775
+ },
776
+ {
777
+ "epoch": 26.01,
778
+ "learning_rate": 7.820963172804533e-05,
779
+ "loss": 2.5753,
780
+ "step": 9700
781
+ },
782
+ {
783
+ "epoch": 26.27,
784
+ "learning_rate": 7.792634560906516e-05,
785
+ "loss": 2.521,
786
+ "step": 9800
787
+ },
788
+ {
789
+ "epoch": 26.54,
790
+ "learning_rate": 7.76458923512748e-05,
791
+ "loss": 2.5546,
792
+ "step": 9900
793
+ },
794
+ {
795
+ "epoch": 26.81,
796
+ "learning_rate": 7.736260623229463e-05,
797
+ "loss": 2.5304,
798
+ "step": 10000
799
+ },
800
+ {
801
+ "epoch": 26.81,
802
+ "eval_cer": 0.5788971223348638,
803
+ "eval_loss": 1.242166519165039,
804
+ "eval_runtime": 116.3994,
805
+ "eval_samples_per_second": 19.777,
806
+ "eval_steps_per_second": 2.474,
807
+ "eval_wer": 2.039411000433088,
808
+ "step": 10000
809
+ },
810
+ {
811
+ "epoch": 27.08,
812
+ "learning_rate": 7.707932011331445e-05,
813
+ "loss": 2.5599,
814
+ "step": 10100
815
+ },
816
+ {
817
+ "epoch": 27.35,
818
+ "learning_rate": 7.679603399433429e-05,
819
+ "loss": 2.4878,
820
+ "step": 10200
821
+ },
822
+ {
823
+ "epoch": 27.61,
824
+ "learning_rate": 7.651274787535411e-05,
825
+ "loss": 2.4684,
826
+ "step": 10300
827
+ },
828
+ {
829
+ "epoch": 27.88,
830
+ "learning_rate": 7.622946175637395e-05,
831
+ "loss": 2.4647,
832
+ "step": 10400
833
+ },
834
+ {
835
+ "epoch": 28.15,
836
+ "learning_rate": 7.594617563739377e-05,
837
+ "loss": 2.4352,
838
+ "step": 10500
839
+ },
840
+ {
841
+ "epoch": 28.15,
842
+ "eval_cer": 0.5506659999090785,
843
+ "eval_loss": 1.1581844091415405,
844
+ "eval_runtime": 116.2358,
845
+ "eval_samples_per_second": 19.805,
846
+ "eval_steps_per_second": 2.478,
847
+ "eval_wer": 1.9969683845820703,
848
+ "step": 10500
849
+ },
850
+ {
851
+ "epoch": 28.42,
852
+ "learning_rate": 7.56628895184136e-05,
853
+ "loss": 2.4437,
854
+ "step": 10600
855
+ },
856
+ {
857
+ "epoch": 28.69,
858
+ "learning_rate": 7.537960339943343e-05,
859
+ "loss": 2.44,
860
+ "step": 10700
861
+ },
862
+ {
863
+ "epoch": 28.95,
864
+ "learning_rate": 7.509631728045327e-05,
865
+ "loss": 2.447,
866
+ "step": 10800
867
+ },
868
+ {
869
+ "epoch": 29.22,
870
+ "learning_rate": 7.481303116147309e-05,
871
+ "loss": 2.4203,
872
+ "step": 10900
873
+ },
874
+ {
875
+ "epoch": 29.49,
876
+ "learning_rate": 7.452974504249293e-05,
877
+ "loss": 2.3795,
878
+ "step": 11000
879
+ },
880
+ {
881
+ "epoch": 29.49,
882
+ "eval_cer": 0.4843842342137564,
883
+ "eval_loss": 1.1159536838531494,
884
+ "eval_runtime": 117.3261,
885
+ "eval_samples_per_second": 19.621,
886
+ "eval_steps_per_second": 2.455,
887
+ "eval_wer": 1.8254655695106106,
888
+ "step": 11000
889
+ },
890
+ {
891
+ "epoch": 29.76,
892
+ "learning_rate": 7.424645892351275e-05,
893
+ "loss": 2.3967,
894
+ "step": 11100
895
+ },
896
+ {
897
+ "epoch": 30.03,
898
+ "learning_rate": 7.396317280453257e-05,
899
+ "loss": 2.3546,
900
+ "step": 11200
901
+ },
902
+ {
903
+ "epoch": 30.29,
904
+ "learning_rate": 7.367988668555241e-05,
905
+ "loss": 2.343,
906
+ "step": 11300
907
+ },
908
+ {
909
+ "epoch": 30.56,
910
+ "learning_rate": 7.339660056657224e-05,
911
+ "loss": 2.3377,
912
+ "step": 11400
913
+ },
914
+ {
915
+ "epoch": 30.83,
916
+ "learning_rate": 7.311331444759207e-05,
917
+ "loss": 2.3287,
918
+ "step": 11500
919
+ },
920
+ {
921
+ "epoch": 30.83,
922
+ "eval_cer": 0.3780060917397827,
923
+ "eval_loss": 1.0775071382522583,
924
+ "eval_runtime": 118.2979,
925
+ "eval_samples_per_second": 19.459,
926
+ "eval_steps_per_second": 2.435,
927
+ "eval_wer": 1.4122996968384582,
928
+ "step": 11500
929
+ },
930
+ {
931
+ "epoch": 31.1,
932
+ "learning_rate": 7.28300283286119e-05,
933
+ "loss": 2.341,
934
+ "step": 11600
935
+ },
936
+ {
937
+ "epoch": 31.37,
938
+ "learning_rate": 7.254674220963173e-05,
939
+ "loss": 2.3039,
940
+ "step": 11700
941
+ },
942
+ {
943
+ "epoch": 31.63,
944
+ "learning_rate": 7.226345609065156e-05,
945
+ "loss": 2.2769,
946
+ "step": 11800
947
+ },
948
+ {
949
+ "epoch": 31.9,
950
+ "learning_rate": 7.198300283286119e-05,
951
+ "loss": 2.323,
952
+ "step": 11900
953
+ },
954
+ {
955
+ "epoch": 32.17,
956
+ "learning_rate": 7.169971671388103e-05,
957
+ "loss": 2.2622,
958
+ "step": 12000
959
+ },
960
+ {
961
+ "epoch": 32.17,
962
+ "eval_cer": 0.48938491612492613,
963
+ "eval_loss": 1.0703905820846558,
964
+ "eval_runtime": 116.0515,
965
+ "eval_samples_per_second": 19.836,
966
+ "eval_steps_per_second": 2.482,
967
+ "eval_wer": 1.7444781290601992,
968
+ "step": 12000
969
+ },
970
+ {
971
+ "epoch": 32.44,
972
+ "learning_rate": 7.141643059490085e-05,
973
+ "loss": 2.2663,
974
+ "step": 12100
975
+ },
976
+ {
977
+ "epoch": 32.71,
978
+ "learning_rate": 7.113314447592069e-05,
979
+ "loss": 2.2797,
980
+ "step": 12200
981
+ },
982
+ {
983
+ "epoch": 32.97,
984
+ "learning_rate": 7.084985835694051e-05,
985
+ "loss": 2.264,
986
+ "step": 12300
987
+ },
988
+ {
989
+ "epoch": 33.24,
990
+ "learning_rate": 7.056657223796033e-05,
991
+ "loss": 2.2497,
992
+ "step": 12400
993
+ },
994
+ {
995
+ "epoch": 33.51,
996
+ "learning_rate": 7.028328611898017e-05,
997
+ "loss": 2.2225,
998
+ "step": 12500
999
+ },
1000
+ {
1001
+ "epoch": 33.51,
1002
+ "eval_cer": 0.5057962449424922,
1003
+ "eval_loss": 1.0272445678710938,
1004
+ "eval_runtime": 118.2938,
1005
+ "eval_samples_per_second": 19.46,
1006
+ "eval_steps_per_second": 2.435,
1007
+ "eval_wer": 1.7236899090515374,
1008
+ "step": 12500
1009
+ },
1010
+ {
1011
+ "epoch": 33.78,
1012
+ "learning_rate": 7e-05,
1013
+ "loss": 2.2025,
1014
+ "step": 12600
1015
+ },
1016
+ {
1017
+ "epoch": 34.05,
1018
+ "learning_rate": 6.971671388101983e-05,
1019
+ "loss": 2.1892,
1020
+ "step": 12700
1021
+ },
1022
+ {
1023
+ "epoch": 34.32,
1024
+ "learning_rate": 6.943342776203965e-05,
1025
+ "loss": 2.1498,
1026
+ "step": 12800
1027
+ },
1028
+ {
1029
+ "epoch": 34.58,
1030
+ "learning_rate": 6.915014164305949e-05,
1031
+ "loss": 2.1819,
1032
+ "step": 12900
1033
+ },
1034
+ {
1035
+ "epoch": 34.85,
1036
+ "learning_rate": 6.886685552407931e-05,
1037
+ "loss": 2.1843,
1038
+ "step": 13000
1039
+ },
1040
+ {
1041
+ "epoch": 34.85,
1042
+ "eval_cer": 0.5028412965404373,
1043
+ "eval_loss": 0.9756352305412292,
1044
+ "eval_runtime": 117.2229,
1045
+ "eval_samples_per_second": 19.638,
1046
+ "eval_steps_per_second": 2.457,
1047
+ "eval_wer": 1.8042442615851018,
1048
+ "step": 13000
1049
+ },
1050
+ {
1051
+ "epoch": 35.12,
1052
+ "learning_rate": 6.858356940509915e-05,
1053
+ "loss": 2.1578,
1054
+ "step": 13100
1055
+ },
1056
+ {
1057
+ "epoch": 35.39,
1058
+ "learning_rate": 6.830028328611899e-05,
1059
+ "loss": 2.1083,
1060
+ "step": 13200
1061
+ },
1062
+ {
1063
+ "epoch": 35.66,
1064
+ "learning_rate": 6.801699716713881e-05,
1065
+ "loss": 2.1531,
1066
+ "step": 13300
1067
+ },
1068
+ {
1069
+ "epoch": 35.92,
1070
+ "learning_rate": 6.773371104815865e-05,
1071
+ "loss": 2.11,
1072
+ "step": 13400
1073
+ },
1074
+ {
1075
+ "epoch": 36.19,
1076
+ "learning_rate": 6.745042492917847e-05,
1077
+ "loss": 2.1,
1078
+ "step": 13500
1079
+ },
1080
+ {
1081
+ "epoch": 36.19,
1082
+ "eval_cer": 0.6055371186980043,
1083
+ "eval_loss": 0.9526697993278503,
1084
+ "eval_runtime": 118.3448,
1085
+ "eval_samples_per_second": 19.452,
1086
+ "eval_steps_per_second": 2.434,
1087
+ "eval_wer": 1.8908618449545258,
1088
+ "step": 13500
1089
+ },
1090
+ {
1091
+ "epoch": 36.46,
1092
+ "learning_rate": 6.716713881019831e-05,
1093
+ "loss": 2.0948,
1094
+ "step": 13600
1095
+ },
1096
+ {
1097
+ "epoch": 36.73,
1098
+ "learning_rate": 6.688385269121813e-05,
1099
+ "loss": 2.071,
1100
+ "step": 13700
1101
+ },
1102
+ {
1103
+ "epoch": 37.0,
1104
+ "learning_rate": 6.660056657223797e-05,
1105
+ "loss": 2.1179,
1106
+ "step": 13800
1107
+ },
1108
+ {
1109
+ "epoch": 37.27,
1110
+ "learning_rate": 6.63172804532578e-05,
1111
+ "loss": 2.0444,
1112
+ "step": 13900
1113
+ },
1114
+ {
1115
+ "epoch": 37.53,
1116
+ "learning_rate": 6.603399433427763e-05,
1117
+ "loss": 2.0741,
1118
+ "step": 14000
1119
+ },
1120
+ {
1121
+ "epoch": 37.53,
1122
+ "eval_cer": 0.5880347320089103,
1123
+ "eval_loss": 0.941799521446228,
1124
+ "eval_runtime": 117.0385,
1125
+ "eval_samples_per_second": 19.669,
1126
+ "eval_steps_per_second": 2.461,
1127
+ "eval_wer": 1.902555218709398,
1128
+ "step": 14000
1129
+ },
1130
+ {
1131
+ "epoch": 37.8,
1132
+ "learning_rate": 6.575070821529745e-05,
1133
+ "loss": 2.0937,
1134
+ "step": 14100
1135
+ },
1136
+ {
1137
+ "epoch": 38.07,
1138
+ "learning_rate": 6.546742209631729e-05,
1139
+ "loss": 2.0848,
1140
+ "step": 14200
1141
+ },
1142
+ {
1143
+ "epoch": 38.34,
1144
+ "learning_rate": 6.518413597733712e-05,
1145
+ "loss": 2.0235,
1146
+ "step": 14300
1147
+ },
1148
+ {
1149
+ "epoch": 38.61,
1150
+ "learning_rate": 6.490084985835695e-05,
1151
+ "loss": 2.0165,
1152
+ "step": 14400
1153
+ },
1154
+ {
1155
+ "epoch": 38.87,
1156
+ "learning_rate": 6.461756373937678e-05,
1157
+ "loss": 2.0179,
1158
+ "step": 14500
1159
+ },
1160
+ {
1161
+ "epoch": 38.87,
1162
+ "eval_cer": 0.5245715324817021,
1163
+ "eval_loss": 0.93625807762146,
1164
+ "eval_runtime": 117.33,
1165
+ "eval_samples_per_second": 19.62,
1166
+ "eval_steps_per_second": 2.455,
1167
+ "eval_wer": 1.797747942832395,
1168
+ "step": 14500
1169
+ },
1170
+ {
1171
+ "epoch": 39.14,
1172
+ "learning_rate": 6.43342776203966e-05,
1173
+ "loss": 1.9771,
1174
+ "step": 14600
1175
+ },
1176
+ {
1177
+ "epoch": 39.41,
1178
+ "learning_rate": 6.405099150141644e-05,
1179
+ "loss": 1.9721,
1180
+ "step": 14700
1181
+ },
1182
+ {
1183
+ "epoch": 39.68,
1184
+ "learning_rate": 6.376770538243626e-05,
1185
+ "loss": 2.0099,
1186
+ "step": 14800
1187
+ },
1188
+ {
1189
+ "epoch": 39.95,
1190
+ "learning_rate": 6.34844192634561e-05,
1191
+ "loss": 2.0237,
1192
+ "step": 14900
1193
+ },
1194
+ {
1195
+ "epoch": 40.21,
1196
+ "learning_rate": 6.320113314447592e-05,
1197
+ "loss": 2.0615,
1198
+ "step": 15000
1199
+ },
1200
+ {
1201
+ "epoch": 40.21,
1202
+ "eval_cer": 0.5598945310724189,
1203
+ "eval_loss": 0.9634870886802673,
1204
+ "eval_runtime": 118.3611,
1205
+ "eval_samples_per_second": 19.449,
1206
+ "eval_steps_per_second": 2.433,
1207
+ "eval_wer": 1.8111736682546558,
1208
+ "step": 15000
1209
+ },
1210
+ {
1211
+ "epoch": 40.48,
1212
+ "learning_rate": 6.291784702549576e-05,
1213
+ "loss": 1.9647,
1214
+ "step": 15100
1215
+ },
1216
+ {
1217
+ "epoch": 40.75,
1218
+ "learning_rate": 6.263456090651558e-05,
1219
+ "loss": 1.9683,
1220
+ "step": 15200
1221
+ },
1222
+ {
1223
+ "epoch": 41.02,
1224
+ "learning_rate": 6.235127478753542e-05,
1225
+ "loss": 1.9311,
1226
+ "step": 15300
1227
+ },
1228
+ {
1229
+ "epoch": 41.29,
1230
+ "learning_rate": 6.206798866855524e-05,
1231
+ "loss": 1.9126,
1232
+ "step": 15400
1233
+ },
1234
+ {
1235
+ "epoch": 41.55,
1236
+ "learning_rate": 6.178470254957506e-05,
1237
+ "loss": 1.9448,
1238
+ "step": 15500
1239
+ },
1240
+ {
1241
+ "epoch": 41.55,
1242
+ "eval_cer": 0.491430649634041,
1243
+ "eval_loss": 0.9248816967010498,
1244
+ "eval_runtime": 116.7415,
1245
+ "eval_samples_per_second": 19.719,
1246
+ "eval_steps_per_second": 2.467,
1247
+ "eval_wer": 1.7249891728020788,
1248
+ "step": 15500
1249
+ },
1250
+ {
1251
+ "epoch": 41.82,
1252
+ "learning_rate": 6.15014164305949e-05,
1253
+ "loss": 1.934,
1254
+ "step": 15600
1255
+ },
1256
+ {
1257
+ "epoch": 42.09,
1258
+ "learning_rate": 6.121813031161473e-05,
1259
+ "loss": 2.0163,
1260
+ "step": 15700
1261
+ },
1262
+ {
1263
+ "epoch": 42.36,
1264
+ "learning_rate": 6.093484419263457e-05,
1265
+ "loss": 1.8725,
1266
+ "step": 15800
1267
+ },
1268
+ {
1269
+ "epoch": 42.63,
1270
+ "learning_rate": 6.065155807365439e-05,
1271
+ "loss": 1.9246,
1272
+ "step": 15900
1273
+ },
1274
+ {
1275
+ "epoch": 42.89,
1276
+ "learning_rate": 6.036827195467423e-05,
1277
+ "loss": 1.8966,
1278
+ "step": 16000
1279
+ },
1280
+ {
1281
+ "epoch": 42.89,
1282
+ "eval_cer": 0.4318770741464745,
1283
+ "eval_loss": 0.9022775888442993,
1284
+ "eval_runtime": 116.8996,
1285
+ "eval_samples_per_second": 19.692,
1286
+ "eval_steps_per_second": 2.464,
1287
+ "eval_wer": 1.5829363360762234,
1288
+ "step": 16000
1289
+ },
1290
+ {
1291
+ "epoch": 43.16,
1292
+ "learning_rate": 6.008498583569405e-05,
1293
+ "loss": 1.8316,
1294
+ "step": 16100
1295
+ },
1296
+ {
1297
+ "epoch": 43.43,
1298
+ "learning_rate": 5.9804532577903686e-05,
1299
+ "loss": 1.8786,
1300
+ "step": 16200
1301
+ },
1302
+ {
1303
+ "epoch": 43.7,
1304
+ "learning_rate": 5.9521246458923516e-05,
1305
+ "loss": 1.84,
1306
+ "step": 16300
1307
+ },
1308
+ {
1309
+ "epoch": 43.97,
1310
+ "learning_rate": 5.9237960339943346e-05,
1311
+ "loss": 1.875,
1312
+ "step": 16400
1313
+ },
1314
+ {
1315
+ "epoch": 44.24,
1316
+ "learning_rate": 5.895750708215297e-05,
1317
+ "loss": 1.8662,
1318
+ "step": 16500
1319
+ },
1320
+ {
1321
+ "epoch": 44.24,
1322
+ "eval_cer": 0.42301222894031004,
1323
+ "eval_loss": 0.9001737236976624,
1324
+ "eval_runtime": 118.0444,
1325
+ "eval_samples_per_second": 19.501,
1326
+ "eval_steps_per_second": 2.44,
1327
+ "eval_wer": 1.483326115201386,
1328
+ "step": 16500
1329
+ },
1330
+ {
1331
+ "epoch": 44.5,
1332
+ "learning_rate": 5.867422096317281e-05,
1333
+ "loss": 1.8645,
1334
+ "step": 16600
1335
+ },
1336
+ {
1337
+ "epoch": 44.77,
1338
+ "learning_rate": 5.839093484419263e-05,
1339
+ "loss": 1.8243,
1340
+ "step": 16700
1341
+ },
1342
+ {
1343
+ "epoch": 45.04,
1344
+ "learning_rate": 5.810764872521247e-05,
1345
+ "loss": 1.7991,
1346
+ "step": 16800
1347
+ },
1348
+ {
1349
+ "epoch": 45.31,
1350
+ "learning_rate": 5.78243626062323e-05,
1351
+ "loss": 1.7956,
1352
+ "step": 16900
1353
+ },
1354
+ {
1355
+ "epoch": 45.58,
1356
+ "learning_rate": 5.754107648725213e-05,
1357
+ "loss": 1.8136,
1358
+ "step": 17000
1359
+ },
1360
+ {
1361
+ "epoch": 45.58,
1362
+ "eval_cer": 0.2986770923307724,
1363
+ "eval_loss": 0.9075531959533691,
1364
+ "eval_runtime": 118.7643,
1365
+ "eval_samples_per_second": 19.383,
1366
+ "eval_steps_per_second": 2.425,
1367
+ "eval_wer": 1.1827631009094846,
1368
+ "step": 17000
1369
+ },
1370
+ {
1371
+ "epoch": 45.84,
1372
+ "learning_rate": 5.725779036827196e-05,
1373
+ "loss": 1.8,
1374
+ "step": 17100
1375
+ },
1376
+ {
1377
+ "epoch": 46.11,
1378
+ "learning_rate": 5.6974504249291784e-05,
1379
+ "loss": 1.8339,
1380
+ "step": 17200
1381
+ },
1382
+ {
1383
+ "epoch": 46.38,
1384
+ "learning_rate": 5.669121813031162e-05,
1385
+ "loss": 1.7869,
1386
+ "step": 17300
1387
+ },
1388
+ {
1389
+ "epoch": 46.65,
1390
+ "learning_rate": 5.6407932011331444e-05,
1391
+ "loss": 1.8145,
1392
+ "step": 17400
1393
+ },
1394
+ {
1395
+ "epoch": 46.92,
1396
+ "learning_rate": 5.612464589235128e-05,
1397
+ "loss": 1.7908,
1398
+ "step": 17500
1399
+ },
1400
+ {
1401
+ "epoch": 46.92,
1402
+ "eval_cer": 0.42578533436377686,
1403
+ "eval_loss": 0.8774313926696777,
1404
+ "eval_runtime": 118.9119,
1405
+ "eval_samples_per_second": 19.359,
1406
+ "eval_steps_per_second": 2.422,
1407
+ "eval_wer": 1.577306193157211,
1408
+ "step": 17500
1409
+ },
1410
+ {
1411
+ "epoch": 47.18,
1412
+ "learning_rate": 5.5841359773371105e-05,
1413
+ "loss": 1.7488,
1414
+ "step": 17600
1415
+ },
1416
+ {
1417
+ "epoch": 47.45,
1418
+ "learning_rate": 5.555807365439094e-05,
1419
+ "loss": 1.7289,
1420
+ "step": 17700
1421
+ },
1422
+ {
1423
+ "epoch": 47.72,
1424
+ "learning_rate": 5.5274787535410765e-05,
1425
+ "loss": 1.7722,
1426
+ "step": 17800
1427
+ },
1428
+ {
1429
+ "epoch": 47.99,
1430
+ "learning_rate": 5.49915014164306e-05,
1431
+ "loss": 1.7659,
1432
+ "step": 17900
1433
+ },
1434
+ {
1435
+ "epoch": 48.26,
1436
+ "learning_rate": 5.4708215297450426e-05,
1437
+ "loss": 1.7354,
1438
+ "step": 18000
1439
+ },
1440
+ {
1441
+ "epoch": 48.26,
1442
+ "eval_cer": 0.40241851161522024,
1443
+ "eval_loss": 0.8727295398712158,
1444
+ "eval_runtime": 117.7378,
1445
+ "eval_samples_per_second": 19.552,
1446
+ "eval_steps_per_second": 2.446,
1447
+ "eval_wer": 1.5036812472932006,
1448
+ "step": 18000
1449
+ },
1450
+ {
1451
+ "epoch": 48.52,
1452
+ "learning_rate": 5.442492917847026e-05,
1453
+ "loss": 1.7538,
1454
+ "step": 18100
1455
+ },
1456
+ {
1457
+ "epoch": 48.79,
1458
+ "learning_rate": 5.4141643059490086e-05,
1459
+ "loss": 1.7304,
1460
+ "step": 18200
1461
+ },
1462
+ {
1463
+ "epoch": 49.06,
1464
+ "learning_rate": 5.385835694050991e-05,
1465
+ "loss": 1.7194,
1466
+ "step": 18300
1467
+ },
1468
+ {
1469
+ "epoch": 49.33,
1470
+ "learning_rate": 5.357507082152975e-05,
1471
+ "loss": 1.6824,
1472
+ "step": 18400
1473
+ },
1474
+ {
1475
+ "epoch": 49.6,
1476
+ "learning_rate": 5.329178470254958e-05,
1477
+ "loss": 1.6739,
1478
+ "step": 18500
1479
+ },
1480
+ {
1481
+ "epoch": 49.6,
1482
+ "eval_cer": 0.27890166840932856,
1483
+ "eval_loss": 0.8635693788528442,
1484
+ "eval_runtime": 118.5578,
1485
+ "eval_samples_per_second": 19.417,
1486
+ "eval_steps_per_second": 2.429,
1487
+ "eval_wer": 1.1238631442182763,
1488
+ "step": 18500
1489
+ },
1490
+ {
1491
+ "epoch": 49.86,
1492
+ "learning_rate": 5.300849858356941e-05,
1493
+ "loss": 1.6807,
1494
+ "step": 18600
1495
+ },
1496
+ {
1497
+ "epoch": 50.13,
1498
+ "learning_rate": 5.272521246458924e-05,
1499
+ "loss": 1.6651,
1500
+ "step": 18700
1501
+ },
1502
+ {
1503
+ "epoch": 50.4,
1504
+ "learning_rate": 5.2441926345609075e-05,
1505
+ "loss": 1.7008,
1506
+ "step": 18800
1507
+ },
1508
+ {
1509
+ "epoch": 50.67,
1510
+ "learning_rate": 5.21586402266289e-05,
1511
+ "loss": 1.6183,
1512
+ "step": 18900
1513
+ },
1514
+ {
1515
+ "epoch": 50.94,
1516
+ "learning_rate": 5.1875354107648735e-05,
1517
+ "loss": 1.6457,
1518
+ "step": 19000
1519
+ },
1520
+ {
1521
+ "epoch": 50.94,
1522
+ "eval_cer": 0.3103605037050507,
1523
+ "eval_loss": 0.8516315221786499,
1524
+ "eval_runtime": 117.1957,
1525
+ "eval_samples_per_second": 19.642,
1526
+ "eval_steps_per_second": 2.457,
1527
+ "eval_wer": 1.2269380684278908,
1528
+ "step": 19000
1529
+ },
1530
+ {
1531
+ "epoch": 51.21,
1532
+ "learning_rate": 5.159206798866856e-05,
1533
+ "loss": 1.6506,
1534
+ "step": 19100
1535
+ },
1536
+ {
1537
+ "epoch": 51.47,
1538
+ "learning_rate": 5.130878186968838e-05,
1539
+ "loss": 1.6612,
1540
+ "step": 19200
1541
+ },
1542
+ {
1543
+ "epoch": 51.74,
1544
+ "learning_rate": 5.102549575070822e-05,
1545
+ "loss": 1.6339,
1546
+ "step": 19300
1547
+ },
1548
+ {
1549
+ "epoch": 52.01,
1550
+ "learning_rate": 5.074220963172804e-05,
1551
+ "loss": 1.6134,
1552
+ "step": 19400
1553
+ },
1554
+ {
1555
+ "epoch": 52.28,
1556
+ "learning_rate": 5.045892351274788e-05,
1557
+ "loss": 1.5847,
1558
+ "step": 19500
1559
+ },
1560
+ {
1561
+ "epoch": 52.28,
1562
+ "eval_cer": 0.33600036368595715,
1563
+ "eval_loss": 0.8398524522781372,
1564
+ "eval_runtime": 116.7512,
1565
+ "eval_samples_per_second": 19.717,
1566
+ "eval_steps_per_second": 2.467,
1567
+ "eval_wer": 1.3308791684711996,
1568
+ "step": 19500
1569
+ },
1570
+ {
1571
+ "epoch": 52.55,
1572
+ "learning_rate": 5.01756373937677e-05,
1573
+ "loss": 1.5839,
1574
+ "step": 19600
1575
+ },
1576
+ {
1577
+ "epoch": 52.81,
1578
+ "learning_rate": 4.9892351274787533e-05,
1579
+ "loss": 1.5887,
1580
+ "step": 19700
1581
+ },
1582
+ {
1583
+ "epoch": 53.08,
1584
+ "learning_rate": 4.9609065155807364e-05,
1585
+ "loss": 1.6578,
1586
+ "step": 19800
1587
+ },
1588
+ {
1589
+ "epoch": 53.35,
1590
+ "learning_rate": 4.9325779036827194e-05,
1591
+ "loss": 1.5896,
1592
+ "step": 19900
1593
+ },
1594
+ {
1595
+ "epoch": 53.62,
1596
+ "learning_rate": 4.9042492917847024e-05,
1597
+ "loss": 1.5971,
1598
+ "step": 20000
1599
+ },
1600
+ {
1601
+ "epoch": 53.62,
1602
+ "eval_cer": 0.3334545619857253,
1603
+ "eval_loss": 0.844145655632019,
1604
+ "eval_runtime": 117.5266,
1605
+ "eval_samples_per_second": 19.587,
1606
+ "eval_steps_per_second": 2.451,
1607
+ "eval_wer": 1.3152880034647034,
1608
+ "step": 20000
1609
+ },
1610
+ {
1611
+ "epoch": 53.89,
1612
+ "learning_rate": 4.8759206798866854e-05,
1613
+ "loss": 1.5645,
1614
+ "step": 20100
1615
+ },
1616
+ {
1617
+ "epoch": 54.16,
1618
+ "learning_rate": 4.847592067988669e-05,
1619
+ "loss": 1.481,
1620
+ "step": 20200
1621
+ },
1622
+ {
1623
+ "epoch": 54.42,
1624
+ "learning_rate": 4.819263456090652e-05,
1625
+ "loss": 1.5474,
1626
+ "step": 20300
1627
+ },
1628
+ {
1629
+ "epoch": 54.69,
1630
+ "learning_rate": 4.790934844192635e-05,
1631
+ "loss": 1.576,
1632
+ "step": 20400
1633
+ },
1634
+ {
1635
+ "epoch": 54.96,
1636
+ "learning_rate": 4.762606232294618e-05,
1637
+ "loss": 1.602,
1638
+ "step": 20500
1639
+ },
1640
+ {
1641
+ "epoch": 54.96,
1642
+ "eval_cer": 0.34331954357412375,
1643
+ "eval_loss": 0.8589980602264404,
1644
+ "eval_runtime": 117.5211,
1645
+ "eval_samples_per_second": 19.588,
1646
+ "eval_steps_per_second": 2.451,
1647
+ "eval_wer": 1.2932005197055003,
1648
+ "step": 20500
1649
+ },
1650
+ {
1651
+ "epoch": 55.23,
1652
+ "learning_rate": 4.734277620396601e-05,
1653
+ "loss": 1.6106,
1654
+ "step": 20600
1655
+ },
1656
+ {
1657
+ "epoch": 55.5,
1658
+ "learning_rate": 4.7059490084985836e-05,
1659
+ "loss": 1.551,
1660
+ "step": 20700
1661
+ },
1662
+ {
1663
+ "epoch": 55.76,
1664
+ "learning_rate": 4.6776203966005666e-05,
1665
+ "loss": 1.5118,
1666
+ "step": 20800
1667
+ },
1668
+ {
1669
+ "epoch": 56.03,
1670
+ "learning_rate": 4.64957507082153e-05,
1671
+ "loss": 1.5028,
1672
+ "step": 20900
1673
+ },
1674
+ {
1675
+ "epoch": 56.3,
1676
+ "learning_rate": 4.621246458923513e-05,
1677
+ "loss": 1.5063,
1678
+ "step": 21000
1679
+ },
1680
+ {
1681
+ "epoch": 56.3,
1682
+ "eval_cer": 0.28749374914761106,
1683
+ "eval_loss": 0.8333584070205688,
1684
+ "eval_runtime": 116.6165,
1685
+ "eval_samples_per_second": 19.74,
1686
+ "eval_steps_per_second": 2.47,
1687
+ "eval_wer": 1.1312256388046773,
1688
+ "step": 21000
1689
+ },
1690
+ {
1691
+ "epoch": 56.57,
1692
+ "learning_rate": 4.592917847025496e-05,
1693
+ "loss": 1.5195,
1694
+ "step": 21100
1695
+ },
1696
+ {
1697
+ "epoch": 56.84,
1698
+ "learning_rate": 4.564589235127479e-05,
1699
+ "loss": 1.549,
1700
+ "step": 21200
1701
+ },
1702
+ {
1703
+ "epoch": 57.1,
1704
+ "learning_rate": 4.536260623229462e-05,
1705
+ "loss": 1.5636,
1706
+ "step": 21300
1707
+ },
1708
+ {
1709
+ "epoch": 57.37,
1710
+ "learning_rate": 4.507932011331445e-05,
1711
+ "loss": 1.482,
1712
+ "step": 21400
1713
+ },
1714
+ {
1715
+ "epoch": 57.64,
1716
+ "learning_rate": 4.479603399433428e-05,
1717
+ "loss": 1.4631,
1718
+ "step": 21500
1719
+ },
1720
+ {
1721
+ "epoch": 57.64,
1722
+ "eval_cer": 0.2999045324362413,
1723
+ "eval_loss": 0.8474038243293762,
1724
+ "eval_runtime": 118.5932,
1725
+ "eval_samples_per_second": 19.411,
1726
+ "eval_steps_per_second": 2.428,
1727
+ "eval_wer": 1.169770463404071,
1728
+ "step": 21500
1729
+ },
1730
+ {
1731
+ "epoch": 57.91,
1732
+ "learning_rate": 4.451274787535411e-05,
1733
+ "loss": 1.4869,
1734
+ "step": 21600
1735
+ },
1736
+ {
1737
+ "epoch": 58.18,
1738
+ "learning_rate": 4.422946175637394e-05,
1739
+ "loss": 1.4692,
1740
+ "step": 21700
1741
+ },
1742
+ {
1743
+ "epoch": 58.44,
1744
+ "learning_rate": 4.394617563739377e-05,
1745
+ "loss": 1.4673,
1746
+ "step": 21800
1747
+ },
1748
+ {
1749
+ "epoch": 58.71,
1750
+ "learning_rate": 4.36628895184136e-05,
1751
+ "loss": 1.501,
1752
+ "step": 21900
1753
+ },
1754
+ {
1755
+ "epoch": 58.98,
1756
+ "learning_rate": 4.3379603399433425e-05,
1757
+ "loss": 1.4997,
1758
+ "step": 22000
1759
+ },
1760
+ {
1761
+ "epoch": 58.98,
1762
+ "eval_cer": 0.38541619311724323,
1763
+ "eval_loss": 0.8637779355049133,
1764
+ "eval_runtime": 116.453,
1765
+ "eval_samples_per_second": 19.768,
1766
+ "eval_steps_per_second": 2.473,
1767
+ "eval_wer": 1.4278908618449546,
1768
+ "step": 22000
1769
+ },
1770
+ {
1771
+ "epoch": 59.25,
1772
+ "learning_rate": 4.3096317280453255e-05,
1773
+ "loss": 1.4404,
1774
+ "step": 22100
1775
+ },
1776
+ {
1777
+ "epoch": 59.52,
1778
+ "learning_rate": 4.2815864022662894e-05,
1779
+ "loss": 1.4639,
1780
+ "step": 22200
1781
+ },
1782
+ {
1783
+ "epoch": 59.78,
1784
+ "learning_rate": 4.2532577903682725e-05,
1785
+ "loss": 1.4724,
1786
+ "step": 22300
1787
+ },
1788
+ {
1789
+ "epoch": 60.05,
1790
+ "learning_rate": 4.224929178470255e-05,
1791
+ "loss": 1.4146,
1792
+ "step": 22400
1793
+ },
1794
+ {
1795
+ "epoch": 60.32,
1796
+ "learning_rate": 4.196600566572238e-05,
1797
+ "loss": 1.4301,
1798
+ "step": 22500
1799
+ },
1800
+ {
1801
+ "epoch": 60.32,
1802
+ "eval_cer": 0.32995408464790654,
1803
+ "eval_loss": 0.8549993634223938,
1804
+ "eval_runtime": 118.194,
1805
+ "eval_samples_per_second": 19.476,
1806
+ "eval_steps_per_second": 2.437,
1807
+ "eval_wer": 1.27371156344738,
1808
+ "step": 22500
1809
+ },
1810
+ {
1811
+ "epoch": 60.59,
1812
+ "learning_rate": 4.168271954674221e-05,
1813
+ "loss": 1.4288,
1814
+ "step": 22600
1815
+ },
1816
+ {
1817
+ "epoch": 60.86,
1818
+ "learning_rate": 4.139943342776204e-05,
1819
+ "loss": 1.4183,
1820
+ "step": 22700
1821
+ },
1822
+ {
1823
+ "epoch": 61.13,
1824
+ "learning_rate": 4.111614730878187e-05,
1825
+ "loss": 1.3995,
1826
+ "step": 22800
1827
+ },
1828
+ {
1829
+ "epoch": 61.39,
1830
+ "learning_rate": 4.08328611898017e-05,
1831
+ "loss": 1.3967,
1832
+ "step": 22900
1833
+ },
1834
+ {
1835
+ "epoch": 61.66,
1836
+ "learning_rate": 4.054957507082153e-05,
1837
+ "loss": 1.3798,
1838
+ "step": 23000
1839
+ },
1840
+ {
1841
+ "epoch": 61.66,
1842
+ "eval_cer": 0.2934491066963677,
1843
+ "eval_loss": 0.8265963792800903,
1844
+ "eval_runtime": 118.5302,
1845
+ "eval_samples_per_second": 19.421,
1846
+ "eval_steps_per_second": 2.43,
1847
+ "eval_wer": 1.1801645734084019,
1848
+ "step": 23000
1849
+ },
1850
+ {
1851
+ "epoch": 61.93,
1852
+ "learning_rate": 4.026628895184136e-05,
1853
+ "loss": 1.3781,
1854
+ "step": 23100
1855
+ },
1856
+ {
1857
+ "epoch": 62.2,
1858
+ "learning_rate": 3.99830028328612e-05,
1859
+ "loss": 1.412,
1860
+ "step": 23200
1861
+ },
1862
+ {
1863
+ "epoch": 62.47,
1864
+ "learning_rate": 3.969971671388103e-05,
1865
+ "loss": 1.3643,
1866
+ "step": 23300
1867
+ },
1868
+ {
1869
+ "epoch": 62.73,
1870
+ "learning_rate": 3.941643059490085e-05,
1871
+ "loss": 1.3848,
1872
+ "step": 23400
1873
+ },
1874
+ {
1875
+ "epoch": 63.0,
1876
+ "learning_rate": 3.913314447592068e-05,
1877
+ "loss": 1.3454,
1878
+ "step": 23500
1879
+ },
1880
+ {
1881
+ "epoch": 63.0,
1882
+ "eval_cer": 0.3711415192980861,
1883
+ "eval_loss": 0.8234531879425049,
1884
+ "eval_runtime": 118.9878,
1885
+ "eval_samples_per_second": 19.347,
1886
+ "eval_steps_per_second": 2.42,
1887
+ "eval_wer": 1.3815504547423128,
1888
+ "step": 23500
1889
+ },
1890
+ {
1891
+ "epoch": 63.27,
1892
+ "learning_rate": 3.884985835694051e-05,
1893
+ "loss": 1.3549,
1894
+ "step": 23600
1895
+ },
1896
+ {
1897
+ "epoch": 63.54,
1898
+ "learning_rate": 3.856657223796034e-05,
1899
+ "loss": 1.3746,
1900
+ "step": 23700
1901
+ },
1902
+ {
1903
+ "epoch": 63.81,
1904
+ "learning_rate": 3.828328611898017e-05,
1905
+ "loss": 1.3619,
1906
+ "step": 23800
1907
+ },
1908
+ {
1909
+ "epoch": 64.07,
1910
+ "learning_rate": 3.8e-05,
1911
+ "loss": 1.4683,
1912
+ "step": 23900
1913
+ },
1914
+ {
1915
+ "epoch": 64.34,
1916
+ "learning_rate": 3.771671388101983e-05,
1917
+ "loss": 1.3678,
1918
+ "step": 24000
1919
+ },
1920
+ {
1921
+ "epoch": 64.34,
1922
+ "eval_cer": 0.5034777469654953,
1923
+ "eval_loss": 0.8549569249153137,
1924
+ "eval_runtime": 117.2623,
1925
+ "eval_samples_per_second": 19.631,
1926
+ "eval_steps_per_second": 2.456,
1927
+ "eval_wer": 1.642702468601126,
1928
+ "step": 24000
1929
+ },
1930
+ {
1931
+ "epoch": 64.61,
1932
+ "learning_rate": 3.743342776203966e-05,
1933
+ "loss": 1.3534,
1934
+ "step": 24100
1935
+ },
1936
+ {
1937
+ "epoch": 64.88,
1938
+ "learning_rate": 3.715014164305949e-05,
1939
+ "loss": 1.341,
1940
+ "step": 24200
1941
+ },
1942
+ {
1943
+ "epoch": 65.15,
1944
+ "learning_rate": 3.686685552407932e-05,
1945
+ "loss": 1.2738,
1946
+ "step": 24300
1947
+ },
1948
+ {
1949
+ "epoch": 65.41,
1950
+ "learning_rate": 3.658356940509915e-05,
1951
+ "loss": 1.3237,
1952
+ "step": 24400
1953
+ },
1954
+ {
1955
+ "epoch": 65.68,
1956
+ "learning_rate": 3.630028328611898e-05,
1957
+ "loss": 1.3761,
1958
+ "step": 24500
1959
+ },
1960
+ {
1961
+ "epoch": 65.68,
1962
+ "eval_cer": 0.490703277719689,
1963
+ "eval_loss": 0.8510046601295471,
1964
+ "eval_runtime": 120.5712,
1965
+ "eval_samples_per_second": 19.092,
1966
+ "eval_steps_per_second": 2.389,
1967
+ "eval_wer": 1.6708531831961888,
1968
+ "step": 24500
1969
+ },
1970
+ {
1971
+ "epoch": 65.95,
1972
+ "learning_rate": 3.6016997167138814e-05,
1973
+ "loss": 1.3209,
1974
+ "step": 24600
1975
+ },
1976
+ {
1977
+ "epoch": 66.22,
1978
+ "learning_rate": 3.5733711048158644e-05,
1979
+ "loss": 1.4141,
1980
+ "step": 24700
1981
+ },
1982
+ {
1983
+ "epoch": 66.49,
1984
+ "learning_rate": 3.5450424929178474e-05,
1985
+ "loss": 1.3229,
1986
+ "step": 24800
1987
+ },
1988
+ {
1989
+ "epoch": 66.76,
1990
+ "learning_rate": 3.5167138810198305e-05,
1991
+ "loss": 1.3413,
1992
+ "step": 24900
1993
+ },
1994
+ {
1995
+ "epoch": 67.02,
1996
+ "learning_rate": 3.4883852691218135e-05,
1997
+ "loss": 1.2668,
1998
+ "step": 25000
1999
+ },
2000
+ {
2001
+ "epoch": 67.02,
2002
+ "eval_cer": 0.45051597945174343,
2003
+ "eval_loss": 0.8514528274536133,
2004
+ "eval_runtime": 118.6832,
2005
+ "eval_samples_per_second": 19.396,
2006
+ "eval_steps_per_second": 2.427,
2007
+ "eval_wer": 1.5842355998267648,
2008
+ "step": 25000
2009
+ },
2010
+ {
2011
+ "epoch": 67.29,
2012
+ "learning_rate": 3.4600566572237965e-05,
2013
+ "loss": 1.3151,
2014
+ "step": 25100
2015
+ },
2016
+ {
2017
+ "epoch": 67.56,
2018
+ "learning_rate": 3.4317280453257796e-05,
2019
+ "loss": 1.3491,
2020
+ "step": 25200
2021
+ },
2022
+ {
2023
+ "epoch": 67.83,
2024
+ "learning_rate": 3.4033994334277626e-05,
2025
+ "loss": 1.3392,
2026
+ "step": 25300
2027
+ },
2028
+ {
2029
+ "epoch": 68.1,
2030
+ "learning_rate": 3.375070821529745e-05,
2031
+ "loss": 1.3551,
2032
+ "step": 25400
2033
+ },
2034
+ {
2035
+ "epoch": 68.36,
2036
+ "learning_rate": 3.346742209631728e-05,
2037
+ "loss": 1.2835,
2038
+ "step": 25500
2039
+ },
2040
+ {
2041
+ "epoch": 68.36,
2042
+ "eval_cer": 0.4221030140473701,
2043
+ "eval_loss": 0.8283268213272095,
2044
+ "eval_runtime": 118.4861,
2045
+ "eval_samples_per_second": 19.428,
2046
+ "eval_steps_per_second": 2.431,
2047
+ "eval_wer": 1.5352966652230402,
2048
+ "step": 25500
2049
+ },
2050
+ {
2051
+ "epoch": 68.63,
2052
+ "learning_rate": 3.318413597733711e-05,
2053
+ "loss": 1.2847,
2054
+ "step": 25600
2055
+ },
2056
+ {
2057
+ "epoch": 68.9,
2058
+ "learning_rate": 3.290084985835694e-05,
2059
+ "loss": 1.3164,
2060
+ "step": 25700
2061
+ },
2062
+ {
2063
+ "epoch": 69.17,
2064
+ "learning_rate": 3.261756373937677e-05,
2065
+ "loss": 1.2624,
2066
+ "step": 25800
2067
+ },
2068
+ {
2069
+ "epoch": 69.44,
2070
+ "learning_rate": 3.23342776203966e-05,
2071
+ "loss": 1.3301,
2072
+ "step": 25900
2073
+ },
2074
+ {
2075
+ "epoch": 69.7,
2076
+ "learning_rate": 3.205099150141643e-05,
2077
+ "loss": 1.2961,
2078
+ "step": 26000
2079
+ },
2080
+ {
2081
+ "epoch": 69.7,
2082
+ "eval_cer": 0.43692321680229124,
2083
+ "eval_loss": 0.8339292407035828,
2084
+ "eval_runtime": 119.6696,
2085
+ "eval_samples_per_second": 19.236,
2086
+ "eval_steps_per_second": 2.407,
2087
+ "eval_wer": 1.574274577739281,
2088
+ "step": 26000
2089
+ },
2090
+ {
2091
+ "epoch": 69.97,
2092
+ "learning_rate": 3.176770538243626e-05,
2093
+ "loss": 1.2716,
2094
+ "step": 26100
2095
+ },
2096
+ {
2097
+ "epoch": 70.24,
2098
+ "learning_rate": 3.148441926345609e-05,
2099
+ "loss": 1.2832,
2100
+ "step": 26200
2101
+ },
2102
+ {
2103
+ "epoch": 70.51,
2104
+ "learning_rate": 3.120113314447592e-05,
2105
+ "loss": 1.2607,
2106
+ "step": 26300
2107
+ },
2108
+ {
2109
+ "epoch": 70.78,
2110
+ "learning_rate": 3.091784702549575e-05,
2111
+ "loss": 1.2774,
2112
+ "step": 26400
2113
+ },
2114
+ {
2115
+ "epoch": 71.05,
2116
+ "learning_rate": 3.0637393767705384e-05,
2117
+ "loss": 1.2656,
2118
+ "step": 26500
2119
+ },
2120
+ {
2121
+ "epoch": 71.05,
2122
+ "eval_cer": 0.42169386734554715,
2123
+ "eval_loss": 0.8330555558204651,
2124
+ "eval_runtime": 120.4651,
2125
+ "eval_samples_per_second": 19.109,
2126
+ "eval_steps_per_second": 2.391,
2127
+ "eval_wer": 1.5331312256388048,
2128
+ "step": 26500
2129
+ },
2130
+ {
2131
+ "epoch": 71.31,
2132
+ "learning_rate": 3.0354107648725215e-05,
2133
+ "loss": 1.2885,
2134
+ "step": 26600
2135
+ },
2136
+ {
2137
+ "epoch": 71.58,
2138
+ "learning_rate": 3.007082152974504e-05,
2139
+ "loss": 1.2552,
2140
+ "step": 26700
2141
+ },
2142
+ {
2143
+ "epoch": 71.85,
2144
+ "learning_rate": 2.9787535410764872e-05,
2145
+ "loss": 1.2682,
2146
+ "step": 26800
2147
+ },
2148
+ {
2149
+ "epoch": 72.12,
2150
+ "learning_rate": 2.9504249291784702e-05,
2151
+ "loss": 1.2665,
2152
+ "step": 26900
2153
+ },
2154
+ {
2155
+ "epoch": 72.39,
2156
+ "learning_rate": 2.9220963172804532e-05,
2157
+ "loss": 1.2556,
2158
+ "step": 27000
2159
+ },
2160
+ {
2161
+ "epoch": 72.39,
2162
+ "eval_cer": 0.4109196708642088,
2163
+ "eval_loss": 0.8242233991622925,
2164
+ "eval_runtime": 118.9857,
2165
+ "eval_samples_per_second": 19.347,
2166
+ "eval_steps_per_second": 2.42,
2167
+ "eval_wer": 1.4707665656128195,
2168
+ "step": 27000
2169
+ },
2170
+ {
2171
+ "epoch": 72.65,
2172
+ "learning_rate": 2.8937677053824363e-05,
2173
+ "loss": 1.2125,
2174
+ "step": 27100
2175
+ },
2176
+ {
2177
+ "epoch": 72.92,
2178
+ "learning_rate": 2.8654390934844193e-05,
2179
+ "loss": 1.2157,
2180
+ "step": 27200
2181
+ },
2182
+ {
2183
+ "epoch": 73.19,
2184
+ "learning_rate": 2.8371104815864023e-05,
2185
+ "loss": 1.2664,
2186
+ "step": 27300
2187
+ },
2188
+ {
2189
+ "epoch": 73.46,
2190
+ "learning_rate": 2.8087818696883857e-05,
2191
+ "loss": 1.2075,
2192
+ "step": 27400
2193
+ },
2194
+ {
2195
+ "epoch": 73.73,
2196
+ "learning_rate": 2.7804532577903687e-05,
2197
+ "loss": 1.2043,
2198
+ "step": 27500
2199
+ },
2200
+ {
2201
+ "epoch": 73.73,
2202
+ "eval_cer": 0.40305496204027824,
2203
+ "eval_loss": 0.8244912624359131,
2204
+ "eval_runtime": 118.8221,
2205
+ "eval_samples_per_second": 19.373,
2206
+ "eval_steps_per_second": 2.424,
2207
+ "eval_wer": 1.4469467301862278,
2208
+ "step": 27500
2209
+ },
2210
+ {
2211
+ "epoch": 73.99,
2212
+ "learning_rate": 2.7521246458923517e-05,
2213
+ "loss": 1.2218,
2214
+ "step": 27600
2215
+ },
2216
+ {
2217
+ "epoch": 74.26,
2218
+ "learning_rate": 2.723796033994334e-05,
2219
+ "loss": 1.2257,
2220
+ "step": 27700
2221
+ },
2222
+ {
2223
+ "epoch": 74.53,
2224
+ "learning_rate": 2.695467422096317e-05,
2225
+ "loss": 1.1943,
2226
+ "step": 27800
2227
+ },
2228
+ {
2229
+ "epoch": 74.8,
2230
+ "learning_rate": 2.6671388101983e-05,
2231
+ "loss": 1.2292,
2232
+ "step": 27900
2233
+ },
2234
+ {
2235
+ "epoch": 75.07,
2236
+ "learning_rate": 2.638810198300283e-05,
2237
+ "loss": 1.2722,
2238
+ "step": 28000
2239
+ },
2240
+ {
2241
+ "epoch": 75.07,
2242
+ "eval_cer": 0.4095558485247988,
2243
+ "eval_loss": 0.8202398419380188,
2244
+ "eval_runtime": 118.3165,
2245
+ "eval_samples_per_second": 19.456,
2246
+ "eval_steps_per_second": 2.434,
2247
+ "eval_wer": 1.4924209614551753,
2248
+ "step": 28000
2249
+ },
2250
+ {
2251
+ "epoch": 75.33,
2252
+ "learning_rate": 2.6104815864022665e-05,
2253
+ "loss": 1.2,
2254
+ "step": 28100
2255
+ },
2256
+ {
2257
+ "epoch": 75.6,
2258
+ "learning_rate": 2.5821529745042495e-05,
2259
+ "loss": 1.1984,
2260
+ "step": 28200
2261
+ },
2262
+ {
2263
+ "epoch": 75.87,
2264
+ "learning_rate": 2.5538243626062326e-05,
2265
+ "loss": 1.204,
2266
+ "step": 28300
2267
+ },
2268
+ {
2269
+ "epoch": 76.14,
2270
+ "learning_rate": 2.5254957507082156e-05,
2271
+ "loss": 1.103,
2272
+ "step": 28400
2273
+ },
2274
+ {
2275
+ "epoch": 76.41,
2276
+ "learning_rate": 2.4971671388101983e-05,
2277
+ "loss": 1.202,
2278
+ "step": 28500
2279
+ },
2280
+ {
2281
+ "epoch": 76.41,
2282
+ "eval_cer": 0.37186889121243805,
2283
+ "eval_loss": 0.8290452361106873,
2284
+ "eval_runtime": 117.9552,
2285
+ "eval_samples_per_second": 19.516,
2286
+ "eval_steps_per_second": 2.442,
2287
+ "eval_wer": 1.3806842789086184,
2288
+ "step": 28500
2289
+ },
2290
+ {
2291
+ "epoch": 76.67,
2292
+ "learning_rate": 2.4691218130311615e-05,
2293
+ "loss": 1.1915,
2294
+ "step": 28600
2295
+ },
2296
+ {
2297
+ "epoch": 76.94,
2298
+ "learning_rate": 2.4407932011331446e-05,
2299
+ "loss": 1.1898,
2300
+ "step": 28700
2301
+ },
2302
+ {
2303
+ "epoch": 77.21,
2304
+ "learning_rate": 2.4124645892351276e-05,
2305
+ "loss": 1.2433,
2306
+ "step": 28800
2307
+ },
2308
+ {
2309
+ "epoch": 77.48,
2310
+ "learning_rate": 2.3841359773371106e-05,
2311
+ "loss": 1.1887,
2312
+ "step": 28900
2313
+ },
2314
+ {
2315
+ "epoch": 77.75,
2316
+ "learning_rate": 2.3558073654390936e-05,
2317
+ "loss": 1.1679,
2318
+ "step": 29000
2319
+ },
2320
+ {
2321
+ "epoch": 77.75,
2322
+ "eval_cer": 0.3748693003591399,
2323
+ "eval_loss": 0.8194963335990906,
2324
+ "eval_runtime": 117.7002,
2325
+ "eval_samples_per_second": 19.558,
2326
+ "eval_steps_per_second": 2.447,
2327
+ "eval_wer": 1.4097011693373755,
2328
+ "step": 29000
2329
+ },
2330
+ {
2331
+ "epoch": 78.02,
2332
+ "learning_rate": 2.3274787535410767e-05,
2333
+ "loss": 1.1151,
2334
+ "step": 29100
2335
+ },
2336
+ {
2337
+ "epoch": 78.28,
2338
+ "learning_rate": 2.2991501416430597e-05,
2339
+ "loss": 1.1638,
2340
+ "step": 29200
2341
+ },
2342
+ {
2343
+ "epoch": 78.55,
2344
+ "learning_rate": 2.2708215297450424e-05,
2345
+ "loss": 1.1516,
2346
+ "step": 29300
2347
+ },
2348
+ {
2349
+ "epoch": 78.82,
2350
+ "learning_rate": 2.2424929178470254e-05,
2351
+ "loss": 1.1652,
2352
+ "step": 29400
2353
+ },
2354
+ {
2355
+ "epoch": 79.09,
2356
+ "learning_rate": 2.2141643059490084e-05,
2357
+ "loss": 1.1967,
2358
+ "step": 29500
2359
+ },
2360
+ {
2361
+ "epoch": 79.09,
2362
+ "eval_cer": 0.30767831977087784,
2363
+ "eval_loss": 0.8058642148971558,
2364
+ "eval_runtime": 118.6259,
2365
+ "eval_samples_per_second": 19.406,
2366
+ "eval_steps_per_second": 2.428,
2367
+ "eval_wer": 1.2074491121697704,
2368
+ "step": 29500
2369
+ },
2370
+ {
2371
+ "epoch": 79.36,
2372
+ "learning_rate": 2.1858356940509918e-05,
2373
+ "loss": 1.1425,
2374
+ "step": 29600
2375
+ },
2376
+ {
2377
+ "epoch": 79.62,
2378
+ "learning_rate": 2.1575070821529748e-05,
2379
+ "loss": 1.1489,
2380
+ "step": 29700
2381
+ },
2382
+ {
2383
+ "epoch": 79.89,
2384
+ "learning_rate": 2.1291784702549575e-05,
2385
+ "loss": 1.136,
2386
+ "step": 29800
2387
+ },
2388
+ {
2389
+ "epoch": 80.16,
2390
+ "learning_rate": 2.1008498583569405e-05,
2391
+ "loss": 1.0913,
2392
+ "step": 29900
2393
+ },
2394
+ {
2395
+ "epoch": 80.43,
2396
+ "learning_rate": 2.0725212464589236e-05,
2397
+ "loss": 1.1241,
2398
+ "step": 30000
2399
+ },
2400
+ {
2401
+ "epoch": 80.43,
2402
+ "eval_cer": 0.3270445969904987,
2403
+ "eval_loss": 0.8137025833129883,
2404
+ "eval_runtime": 117.4298,
2405
+ "eval_samples_per_second": 19.603,
2406
+ "eval_steps_per_second": 2.453,
2407
+ "eval_wer": 1.2451277609354698,
2408
+ "step": 30000
2409
+ },
2410
+ {
2411
+ "epoch": 80.7,
2412
+ "learning_rate": 2.0441926345609066e-05,
2413
+ "loss": 1.1314,
2414
+ "step": 30100
2415
+ },
2416
+ {
2417
+ "epoch": 80.96,
2418
+ "learning_rate": 2.0158640226628896e-05,
2419
+ "loss": 1.1315,
2420
+ "step": 30200
2421
+ },
2422
+ {
2423
+ "epoch": 81.23,
2424
+ "learning_rate": 1.9875354107648726e-05,
2425
+ "loss": 1.1535,
2426
+ "step": 30300
2427
+ },
2428
+ {
2429
+ "epoch": 81.5,
2430
+ "learning_rate": 1.9592067988668557e-05,
2431
+ "loss": 1.1567,
2432
+ "step": 30400
2433
+ },
2434
+ {
2435
+ "epoch": 81.77,
2436
+ "learning_rate": 1.931161473087819e-05,
2437
+ "loss": 1.1414,
2438
+ "step": 30500
2439
+ },
2440
+ {
2441
+ "epoch": 81.77,
2442
+ "eval_cer": 0.3120880120016366,
2443
+ "eval_loss": 0.8117419481277466,
2444
+ "eval_runtime": 116.2752,
2445
+ "eval_samples_per_second": 19.798,
2446
+ "eval_steps_per_second": 2.477,
2447
+ "eval_wer": 1.2031182330012993,
2448
+ "step": 30500
2449
+ },
2450
+ {
2451
+ "epoch": 82.04,
2452
+ "learning_rate": 1.902832861189802e-05,
2453
+ "loss": 1.0878,
2454
+ "step": 30600
2455
+ },
2456
+ {
2457
+ "epoch": 82.31,
2458
+ "learning_rate": 1.8745042492917846e-05,
2459
+ "loss": 1.0806,
2460
+ "step": 30700
2461
+ },
2462
+ {
2463
+ "epoch": 82.57,
2464
+ "learning_rate": 1.8461756373937677e-05,
2465
+ "loss": 1.0914,
2466
+ "step": 30800
2467
+ },
2468
+ {
2469
+ "epoch": 82.84,
2470
+ "learning_rate": 1.8178470254957507e-05,
2471
+ "loss": 1.1274,
2472
+ "step": 30900
2473
+ },
2474
+ {
2475
+ "epoch": 83.11,
2476
+ "learning_rate": 1.7895184135977337e-05,
2477
+ "loss": 1.132,
2478
+ "step": 31000
2479
+ },
2480
+ {
2481
+ "epoch": 83.11,
2482
+ "eval_cer": 0.390053189071237,
2483
+ "eval_loss": 0.823433518409729,
2484
+ "eval_runtime": 118.2321,
2485
+ "eval_samples_per_second": 19.47,
2486
+ "eval_steps_per_second": 2.436,
2487
+ "eval_wer": 1.4265915980944133,
2488
+ "step": 31000
2489
+ },
2490
+ {
2491
+ "epoch": 83.38,
2492
+ "learning_rate": 1.761189801699717e-05,
2493
+ "loss": 1.0891,
2494
+ "step": 31100
2495
+ },
2496
+ {
2497
+ "epoch": 83.65,
2498
+ "learning_rate": 1.7328611898016998e-05,
2499
+ "loss": 1.1041,
2500
+ "step": 31200
2501
+ },
2502
+ {
2503
+ "epoch": 83.91,
2504
+ "learning_rate": 1.7045325779036828e-05,
2505
+ "loss": 1.0895,
2506
+ "step": 31300
2507
+ },
2508
+ {
2509
+ "epoch": 84.18,
2510
+ "learning_rate": 1.6762039660056658e-05,
2511
+ "loss": 1.0966,
2512
+ "step": 31400
2513
+ },
2514
+ {
2515
+ "epoch": 84.45,
2516
+ "learning_rate": 1.647875354107649e-05,
2517
+ "loss": 1.0982,
2518
+ "step": 31500
2519
+ },
2520
+ {
2521
+ "epoch": 84.45,
2522
+ "eval_cer": 0.3606855480292767,
2523
+ "eval_loss": 0.8063952326774597,
2524
+ "eval_runtime": 119.0446,
2525
+ "eval_samples_per_second": 19.337,
2526
+ "eval_steps_per_second": 2.419,
2527
+ "eval_wer": 1.3711563447379818,
2528
+ "step": 31500
2529
+ },
2530
+ {
2531
+ "epoch": 84.72,
2532
+ "learning_rate": 1.619546742209632e-05,
2533
+ "loss": 1.0969,
2534
+ "step": 31600
2535
+ },
2536
+ {
2537
+ "epoch": 84.99,
2538
+ "learning_rate": 1.5912181303116146e-05,
2539
+ "loss": 1.0552,
2540
+ "step": 31700
2541
+ },
2542
+ {
2543
+ "epoch": 85.25,
2544
+ "learning_rate": 1.562889518413598e-05,
2545
+ "loss": 1.079,
2546
+ "step": 31800
2547
+ },
2548
+ {
2549
+ "epoch": 85.52,
2550
+ "learning_rate": 1.534560906515581e-05,
2551
+ "loss": 1.0959,
2552
+ "step": 31900
2553
+ },
2554
+ {
2555
+ "epoch": 85.79,
2556
+ "learning_rate": 1.5062322946175638e-05,
2557
+ "loss": 1.0797,
2558
+ "step": 32000
2559
+ },
2560
+ {
2561
+ "epoch": 85.79,
2562
+ "eval_cer": 0.356184934309224,
2563
+ "eval_loss": 0.8166823983192444,
2564
+ "eval_runtime": 117.1158,
2565
+ "eval_samples_per_second": 19.656,
2566
+ "eval_steps_per_second": 2.459,
2567
+ "eval_wer": 1.335643135556518,
2568
+ "step": 32000
2569
+ },
2570
+ {
2571
+ "epoch": 86.06,
2572
+ "learning_rate": 1.477903682719547e-05,
2573
+ "loss": 1.1358,
2574
+ "step": 32100
2575
+ },
2576
+ {
2577
+ "epoch": 86.33,
2578
+ "learning_rate": 1.4495750708215297e-05,
2579
+ "loss": 1.0718,
2580
+ "step": 32200
2581
+ },
2582
+ {
2583
+ "epoch": 86.59,
2584
+ "learning_rate": 1.4212464589235127e-05,
2585
+ "loss": 1.0725,
2586
+ "step": 32300
2587
+ },
2588
+ {
2589
+ "epoch": 86.86,
2590
+ "learning_rate": 1.3929178470254959e-05,
2591
+ "loss": 1.0705,
2592
+ "step": 32400
2593
+ },
2594
+ {
2595
+ "epoch": 87.13,
2596
+ "learning_rate": 1.364589235127479e-05,
2597
+ "loss": 1.0119,
2598
+ "step": 32500
2599
+ },
2600
+ {
2601
+ "epoch": 87.13,
2602
+ "eval_cer": 0.3267718325226167,
2603
+ "eval_loss": 0.8214733600616455,
2604
+ "eval_runtime": 118.8447,
2605
+ "eval_samples_per_second": 19.37,
2606
+ "eval_steps_per_second": 2.423,
2607
+ "eval_wer": 1.2754439151147683,
2608
+ "step": 32500
2609
+ },
2610
+ {
2611
+ "epoch": 87.4,
2612
+ "learning_rate": 1.336260623229462e-05,
2613
+ "loss": 1.0571,
2614
+ "step": 32600
2615
+ },
2616
+ {
2617
+ "epoch": 87.67,
2618
+ "learning_rate": 1.3079320113314446e-05,
2619
+ "loss": 1.0636,
2620
+ "step": 32700
2621
+ },
2622
+ {
2623
+ "epoch": 87.93,
2624
+ "learning_rate": 1.2796033994334278e-05,
2625
+ "loss": 1.0892,
2626
+ "step": 32800
2627
+ },
2628
+ {
2629
+ "epoch": 88.2,
2630
+ "learning_rate": 1.2512747875354109e-05,
2631
+ "loss": 1.1356,
2632
+ "step": 32900
2633
+ },
2634
+ {
2635
+ "epoch": 88.47,
2636
+ "learning_rate": 1.2229461756373939e-05,
2637
+ "loss": 1.0216,
2638
+ "step": 33000
2639
+ },
2640
+ {
2641
+ "epoch": 88.47,
2642
+ "eval_cer": 0.3183615947629222,
2643
+ "eval_loss": 0.816307008266449,
2644
+ "eval_runtime": 118.8553,
2645
+ "eval_samples_per_second": 19.368,
2646
+ "eval_steps_per_second": 2.423,
2647
+ "eval_wer": 1.2511909917713295,
2648
+ "step": 33000
2649
+ },
2650
+ {
2651
+ "epoch": 88.74,
2652
+ "learning_rate": 1.1946175637393768e-05,
2653
+ "loss": 1.0226,
2654
+ "step": 33100
2655
+ },
2656
+ {
2657
+ "epoch": 89.01,
2658
+ "learning_rate": 1.1662889518413598e-05,
2659
+ "loss": 1.0002,
2660
+ "step": 33200
2661
+ },
2662
+ {
2663
+ "epoch": 89.28,
2664
+ "learning_rate": 1.1379603399433428e-05,
2665
+ "loss": 1.0296,
2666
+ "step": 33300
2667
+ },
2668
+ {
2669
+ "epoch": 89.54,
2670
+ "learning_rate": 1.1096317280453258e-05,
2671
+ "loss": 1.0635,
2672
+ "step": 33400
2673
+ },
2674
+ {
2675
+ "epoch": 89.81,
2676
+ "learning_rate": 1.0813031161473089e-05,
2677
+ "loss": 1.0375,
2678
+ "step": 33500
2679
+ },
2680
+ {
2681
+ "epoch": 89.81,
2682
+ "eval_cer": 0.3290448697549666,
2683
+ "eval_loss": 0.8136931657791138,
2684
+ "eval_runtime": 119.3202,
2685
+ "eval_samples_per_second": 19.293,
2686
+ "eval_steps_per_second": 2.414,
2687
+ "eval_wer": 1.2685145084452143,
2688
+ "step": 33500
2689
+ },
2690
+ {
2691
+ "epoch": 90.08,
2692
+ "learning_rate": 1.0529745042492919e-05,
2693
+ "loss": 1.096,
2694
+ "step": 33600
2695
+ },
2696
+ {
2697
+ "epoch": 90.35,
2698
+ "learning_rate": 1.0246458923512749e-05,
2699
+ "loss": 1.0465,
2700
+ "step": 33700
2701
+ },
2702
+ {
2703
+ "epoch": 90.62,
2704
+ "learning_rate": 9.963172804532578e-06,
2705
+ "loss": 1.0637,
2706
+ "step": 33800
2707
+ },
2708
+ {
2709
+ "epoch": 90.88,
2710
+ "learning_rate": 9.679886685552408e-06,
2711
+ "loss": 1.0514,
2712
+ "step": 33900
2713
+ },
2714
+ {
2715
+ "epoch": 91.15,
2716
+ "learning_rate": 9.396600566572238e-06,
2717
+ "loss": 0.9794,
2718
+ "step": 34000
2719
+ },
2720
+ {
2721
+ "epoch": 91.15,
2722
+ "eval_cer": 0.32549893167250077,
2723
+ "eval_loss": 0.8219542503356934,
2724
+ "eval_runtime": 117.5416,
2725
+ "eval_samples_per_second": 19.585,
2726
+ "eval_steps_per_second": 2.45,
2727
+ "eval_wer": 1.2724122996968386,
2728
+ "step": 34000
2729
+ },
2730
+ {
2731
+ "epoch": 91.42,
2732
+ "learning_rate": 9.113314447592068e-06,
2733
+ "loss": 1.0268,
2734
+ "step": 34100
2735
+ },
2736
+ {
2737
+ "epoch": 91.69,
2738
+ "learning_rate": 8.830028328611899e-06,
2739
+ "loss": 1.0211,
2740
+ "step": 34200
2741
+ },
2742
+ {
2743
+ "epoch": 91.96,
2744
+ "learning_rate": 8.546742209631727e-06,
2745
+ "loss": 1.0557,
2746
+ "step": 34300
2747
+ },
2748
+ {
2749
+ "epoch": 92.22,
2750
+ "learning_rate": 8.26345609065156e-06,
2751
+ "loss": 1.0814,
2752
+ "step": 34400
2753
+ },
2754
+ {
2755
+ "epoch": 92.49,
2756
+ "learning_rate": 7.98016997167139e-06,
2757
+ "loss": 1.0207,
2758
+ "step": 34500
2759
+ },
2760
+ {
2761
+ "epoch": 92.49,
2762
+ "eval_cer": 0.33609128517525116,
2763
+ "eval_loss": 0.8165063261985779,
2764
+ "eval_runtime": 117.4538,
2765
+ "eval_samples_per_second": 19.599,
2766
+ "eval_steps_per_second": 2.452,
2767
+ "eval_wer": 1.2906019922044174,
2768
+ "step": 34500
2769
+ },
2770
+ {
2771
+ "epoch": 92.76,
2772
+ "learning_rate": 7.696883852691218e-06,
2773
+ "loss": 1.0183,
2774
+ "step": 34600
2775
+ },
2776
+ {
2777
+ "epoch": 93.03,
2778
+ "learning_rate": 7.413597733711048e-06,
2779
+ "loss": 0.9889,
2780
+ "step": 34700
2781
+ },
2782
+ {
2783
+ "epoch": 93.3,
2784
+ "learning_rate": 7.130311614730878e-06,
2785
+ "loss": 1.0047,
2786
+ "step": 34800
2787
+ },
2788
+ {
2789
+ "epoch": 93.56,
2790
+ "learning_rate": 6.847025495750709e-06,
2791
+ "loss": 1.0318,
2792
+ "step": 34900
2793
+ },
2794
+ {
2795
+ "epoch": 93.83,
2796
+ "learning_rate": 6.563739376770539e-06,
2797
+ "loss": 1.0169,
2798
+ "step": 35000
2799
+ },
2800
+ {
2801
+ "epoch": 93.83,
2802
+ "eval_cer": 0.3305450743283175,
2803
+ "eval_loss": 0.8153378367424011,
2804
+ "eval_runtime": 118.1425,
2805
+ "eval_samples_per_second": 19.485,
2806
+ "eval_steps_per_second": 2.438,
2807
+ "eval_wer": 1.281940233867475,
2808
+ "step": 35000
2809
+ },
2810
+ {
2811
+ "epoch": 94.1,
2812
+ "learning_rate": 6.2804532577903686e-06,
2813
+ "loss": 1.0584,
2814
+ "step": 35100
2815
+ },
2816
+ {
2817
+ "epoch": 94.37,
2818
+ "learning_rate": 5.997167138810199e-06,
2819
+ "loss": 1.0074,
2820
+ "step": 35200
2821
+ },
2822
+ {
2823
+ "epoch": 94.64,
2824
+ "learning_rate": 5.71671388101983e-06,
2825
+ "loss": 1.0278,
2826
+ "step": 35300
2827
+ },
2828
+ {
2829
+ "epoch": 94.9,
2830
+ "learning_rate": 5.433427762039661e-06,
2831
+ "loss": 1.0251,
2832
+ "step": 35400
2833
+ },
2834
+ {
2835
+ "epoch": 95.17,
2836
+ "learning_rate": 5.15014164305949e-06,
2837
+ "loss": 1.0127,
2838
+ "step": 35500
2839
+ },
2840
+ {
2841
+ "epoch": 95.17,
2842
+ "eval_cer": 0.3251807064599718,
2843
+ "eval_loss": 0.8187472224235535,
2844
+ "eval_runtime": 117.413,
2845
+ "eval_samples_per_second": 19.606,
2846
+ "eval_steps_per_second": 2.453,
2847
+ "eval_wer": 1.2832394976180164,
2848
+ "step": 35500
2849
+ },
2850
+ {
2851
+ "epoch": 95.44,
2852
+ "learning_rate": 4.86685552407932e-06,
2853
+ "loss": 1.0153,
2854
+ "step": 35600
2855
+ },
2856
+ {
2857
+ "epoch": 95.71,
2858
+ "learning_rate": 4.58356940509915e-06,
2859
+ "loss": 1.0098,
2860
+ "step": 35700
2861
+ },
2862
+ {
2863
+ "epoch": 95.98,
2864
+ "learning_rate": 4.300283286118981e-06,
2865
+ "loss": 1.0034,
2866
+ "step": 35800
2867
+ },
2868
+ {
2869
+ "epoch": 96.25,
2870
+ "learning_rate": 4.01699716713881e-06,
2871
+ "loss": 1.017,
2872
+ "step": 35900
2873
+ },
2874
+ {
2875
+ "epoch": 96.51,
2876
+ "learning_rate": 3.7337110481586406e-06,
2877
+ "loss": 0.9978,
2878
+ "step": 36000
2879
+ },
2880
+ {
2881
+ "epoch": 96.51,
2882
+ "eval_cer": 0.3209528572078011,
2883
+ "eval_loss": 0.811066746711731,
2884
+ "eval_runtime": 117.24,
2885
+ "eval_samples_per_second": 19.635,
2886
+ "eval_steps_per_second": 2.456,
2887
+ "eval_wer": 1.2611520138588133,
2888
+ "step": 36000
2889
+ },
2890
+ {
2891
+ "epoch": 96.78,
2892
+ "learning_rate": 3.4504249291784704e-06,
2893
+ "loss": 1.0111,
2894
+ "step": 36100
2895
+ },
2896
+ {
2897
+ "epoch": 97.05,
2898
+ "learning_rate": 3.1671388101983003e-06,
2899
+ "loss": 1.0185,
2900
+ "step": 36200
2901
+ },
2902
+ {
2903
+ "epoch": 97.32,
2904
+ "learning_rate": 2.8838526912181305e-06,
2905
+ "loss": 0.9678,
2906
+ "step": 36300
2907
+ },
2908
+ {
2909
+ "epoch": 97.59,
2910
+ "learning_rate": 2.6005665722379608e-06,
2911
+ "loss": 1.0271,
2912
+ "step": 36400
2913
+ },
2914
+ {
2915
+ "epoch": 97.85,
2916
+ "learning_rate": 2.3172804532577906e-06,
2917
+ "loss": 0.9923,
2918
+ "step": 36500
2919
+ },
2920
+ {
2921
+ "epoch": 97.85,
2922
+ "eval_cer": 0.3122243942355776,
2923
+ "eval_loss": 0.8076378703117371,
2924
+ "eval_runtime": 116.5522,
2925
+ "eval_samples_per_second": 19.751,
2926
+ "eval_steps_per_second": 2.471,
2927
+ "eval_wer": 1.227804244261585,
2928
+ "step": 36500
2929
+ },
2930
+ {
2931
+ "epoch": 98.12,
2932
+ "learning_rate": 2.0339943342776205e-06,
2933
+ "loss": 0.9955,
2934
+ "step": 36600
2935
+ },
2936
+ {
2937
+ "epoch": 98.39,
2938
+ "learning_rate": 1.7507082152974505e-06,
2939
+ "loss": 1.0009,
2940
+ "step": 36700
2941
+ },
2942
+ {
2943
+ "epoch": 98.66,
2944
+ "learning_rate": 1.4674220963172806e-06,
2945
+ "loss": 0.9855,
2946
+ "step": 36800
2947
+ },
2948
+ {
2949
+ "epoch": 98.93,
2950
+ "learning_rate": 1.1869688385269122e-06,
2951
+ "loss": 1.0056,
2952
+ "step": 36900
2953
+ },
2954
+ {
2955
+ "epoch": 99.2,
2956
+ "learning_rate": 9.036827195467423e-07,
2957
+ "loss": 1.0451,
2958
+ "step": 37000
2959
+ },
2960
+ {
2961
+ "epoch": 99.2,
2962
+ "eval_cer": 0.3155884893394554,
2963
+ "eval_loss": 0.8086187243461609,
2964
+ "eval_runtime": 119.7199,
2965
+ "eval_samples_per_second": 19.228,
2966
+ "eval_steps_per_second": 2.406,
2967
+ "eval_wer": 1.2451277609354698,
2968
+ "step": 37000
2969
+ },
2970
+ {
2971
+ "epoch": 99.46,
2972
+ "learning_rate": 6.203966005665723e-07,
2973
+ "loss": 1.0189,
2974
+ "step": 37100
2975
+ },
2976
+ {
2977
+ "epoch": 99.73,
2978
+ "learning_rate": 3.371104815864023e-07,
2979
+ "loss": 0.9878,
2980
+ "step": 37200
2981
+ },
2982
+ {
2983
+ "epoch": 100.0,
2984
+ "learning_rate": 5.3824362606232296e-08,
2985
+ "loss": 0.96,
2986
+ "step": 37300
2987
+ },
2988
+ {
2989
+ "epoch": 100.0,
2990
+ "step": 37300,
2991
+ "total_flos": 1.39626030021533e+20,
2992
+ "train_loss": 3.7852419735087786,
2993
+ "train_runtime": 72640.1075,
2994
+ "train_samples_per_second": 16.45,
2995
+ "train_steps_per_second": 0.513
2996
+ }
2997
+ ],
2998
+ "max_steps": 37300,
2999
+ "num_train_epochs": 100,
3000
+ "total_flos": 1.39626030021533e+20,
3001
+ "trial_name": null,
3002
+ "trial_params": null
3003
+ }