Baselhany commited on
Commit
e0d7657
·
verified ·
1 Parent(s): ae4353c

Training in progress, step 8400, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51d5619c459155c47bd01aa5955aeaeb352a6ec1ae09efde7465df43001603d7
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5bb063a3184a1ee06d2a005f868382df57ecbe893a611919f2268e407868ce
3
  size 151061672
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:423a50ab52b674fd9e4f747477f47789594de775982c5d8aab3045683afe82c7
3
  size 297616186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f5b1a7c7f8ae2a2c5b75f5dcaa1a5c7f49942782fc234acaf394e7ad4bbd5e
3
  size 297616186
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c95e1a461be3f7576b26df8bd8ff963fbbe816fd5fe47de86343853964a00c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f14f32dfc7ca77432756f9215cfce2984eed32a406197351b5f81222f88949
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee8e101806051a5471b6da8d97d90136d368b9e20f5708864cf5bedf200343a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b42c9151a92fc141b81f4c111bdd6ed21be543f9f1ff87540b8275dbaeeb5d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 13.366213870443335,
3
  "best_model_checkpoint": "./Whisper_tiny_fine_tune_Quran/checkpoint-8000",
4
- "epoch": 2.8168295044450313,
5
  "eval_steps": 400,
6
- "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1327,6 +1327,72 @@
1327
  "eval_steps_per_second": 0.218,
1328
  "eval_wer": 13.366213870443335,
1329
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1330
  }
1331
  ],
1332
  "logging_steps": 50,
@@ -1346,7 +1412,7 @@
1346
  "attributes": {}
1347
  }
1348
  },
1349
- "total_flos": 1.260486918144e+19,
1350
  "train_batch_size": 16,
1351
  "trial_name": null,
1352
  "trial_params": null
 
1
  {
2
  "best_metric": 13.366213870443335,
3
  "best_model_checkpoint": "./Whisper_tiny_fine_tune_Quran/checkpoint-8000",
4
+ "epoch": 2.9576621776252088,
5
  "eval_steps": 400,
6
+ "global_step": 8400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1327
  "eval_steps_per_second": 0.218,
1328
  "eval_wer": 13.366213870443335,
1329
  "step": 8000
1330
+ },
1331
+ {
1332
+ "epoch": 2.8344335885925536,
1333
+ "grad_norm": 21345.421875,
1334
+ "learning_rate": 8.450057309301873e-07,
1335
+ "loss": 0.003,
1336
+ "step": 8050
1337
+ },
1338
+ {
1339
+ "epoch": 2.852037672740076,
1340
+ "grad_norm": 21389.115234375,
1341
+ "learning_rate": 6.751647633076952e-07,
1342
+ "loss": 0.0027,
1343
+ "step": 8100
1344
+ },
1345
+ {
1346
+ "epoch": 2.869641756887598,
1347
+ "grad_norm": 40714.12890625,
1348
+ "learning_rate": 5.242447386824833e-07,
1349
+ "loss": 0.0032,
1350
+ "step": 8150
1351
+ },
1352
+ {
1353
+ "epoch": 2.8872458410351203,
1354
+ "grad_norm": 13599.498046875,
1355
+ "learning_rate": 3.9230354978077586e-07,
1356
+ "loss": 0.0024,
1357
+ "step": 8200
1358
+ },
1359
+ {
1360
+ "epoch": 2.9048499251826425,
1361
+ "grad_norm": 18847.646484375,
1362
+ "learning_rate": 2.7939180907197717e-07,
1363
+ "loss": 0.0029,
1364
+ "step": 8250
1365
+ },
1366
+ {
1367
+ "epoch": 2.9224540093301647,
1368
+ "grad_norm": 25907.548828125,
1369
+ "learning_rate": 1.855528293537856e-07,
1370
+ "loss": 0.0031,
1371
+ "step": 8300
1372
+ },
1373
+ {
1374
+ "epoch": 2.940058093477687,
1375
+ "grad_norm": 36510.4765625,
1376
+ "learning_rate": 1.108226071374452e-07,
1377
+ "loss": 0.0027,
1378
+ "step": 8350
1379
+ },
1380
+ {
1381
+ "epoch": 2.9576621776252088,
1382
+ "grad_norm": 34380.96875,
1383
+ "learning_rate": 5.522980883952422e-08,
1384
+ "loss": 0.0028,
1385
+ "step": 8400
1386
+ },
1387
+ {
1388
+ "epoch": 2.9576621776252088,
1389
+ "eval_cer": 4.579377261089553,
1390
+ "eval_loss": 0.0121904406696558,
1391
+ "eval_runtime": 1111.3761,
1392
+ "eval_samples_per_second": 3.479,
1393
+ "eval_steps_per_second": 0.218,
1394
+ "eval_wer": 13.553577824924917,
1395
+ "step": 8400
1396
  }
1397
  ],
1398
  "logging_steps": 50,
 
1412
  "attributes": {}
1413
  }
1414
  },
1415
+ "total_flos": 1.3235112640512e+19,
1416
  "train_batch_size": 16,
1417
  "trial_name": null,
1418
  "trial_params": null