Scrya commited on
Commit
f1dc7a1
1 Parent(s): fef9a87

Training in progress, step 600

Browse files
fine-tune-whisper-non-streaming-zh.ipynb → .ipynb_checkpoints/fine-tune-whisper-non-streaming-zh-TW-checkpoint.ipynb RENAMED
@@ -1134,8 +1134,8 @@
1134
  "\n",
1135
  " <div>\n",
1136
  " \n",
1137
- " <progress value='401' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1138
- " [ 401/1000 1:53:27 < 2:50:19, 0.06 it/s, Epoch 1.14/3]\n",
1139
  " </div>\n",
1140
  " <table border=\"1\" class=\"dataframe\">\n",
1141
  " <thead>\n",
@@ -1160,7 +1160,13 @@
1160
  " <td>7.590416</td>\n",
1161
  " </tr>\n",
1162
  " </tbody>\n",
1163
- "</table><p>"
 
 
 
 
 
 
1164
  ],
1165
  "text/plain": [
1166
  "<IPython.core.display.HTML object>"
@@ -1190,7 +1196,11 @@
1190
  "Configuration saved in ./checkpoint-400/config.json\n",
1191
  "Model weights saved in ./checkpoint-400/pytorch_model.bin\n",
1192
  "Feature extractor saved in ./checkpoint-400/preprocessor_config.json\n",
1193
- "Feature extractor saved in ./preprocessor_config.json\n"
 
 
 
 
1194
  ]
1195
  }
1196
  ],
@@ -1221,7 +1231,7 @@
1221
  " \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
1222
  " \"dataset\": \"mozilla-foundation/common_voice_11_0\", # a 'pretty' name for the training dataset\n",
1223
  " \"language\": \"zh-TW\",\n",
1224
- " \"model_name\": \"Whisper Medium MS - Augmented\", # a 'pretty' name for your model\n",
1225
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
1226
  " \"tasks\": \"automatic-speech-recognition\",\n",
1227
  " \"tags\": \"whisper-event\",\n",
 
1134
  "\n",
1135
  " <div>\n",
1136
  " \n",
1137
+ " <progress value='601' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1138
+ " [ 601/1000 3:16:05 < 2:10:37, 0.05 it/s, Epoch 1.70/3]\n",
1139
  " </div>\n",
1140
  " <table border=\"1\" class=\"dataframe\">\n",
1141
  " <thead>\n",
 
1160
  " <td>7.590416</td>\n",
1161
  " </tr>\n",
1162
  " </tbody>\n",
1163
+ "</table><p>\n",
1164
+ " <div>\n",
1165
+ " \n",
1166
+ " <progress value='330' max='2355' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1167
+ " [ 330/2355 07:22 < 45:21, 0.74 it/s]\n",
1168
+ " </div>\n",
1169
+ " "
1170
  ],
1171
  "text/plain": [
1172
  "<IPython.core.display.HTML object>"
 
1196
  "Configuration saved in ./checkpoint-400/config.json\n",
1197
  "Model weights saved in ./checkpoint-400/pytorch_model.bin\n",
1198
  "Feature extractor saved in ./checkpoint-400/preprocessor_config.json\n",
1199
+ "Feature extractor saved in ./preprocessor_config.json\n",
1200
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1201
+ "***** Running Evaluation *****\n",
1202
+ " Num examples = 4709\n",
1203
+ " Batch size = 2\n"
1204
  ]
1205
  }
1206
  ],
 
1231
  " \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
1232
  " \"dataset\": \"mozilla-foundation/common_voice_11_0\", # a 'pretty' name for the training dataset\n",
1233
  " \"language\": \"zh-TW\",\n",
1234
+ " \"model_name\": \"Whisper Medium TW - Augmented\", # a 'pretty' name for your model\n",
1235
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
1236
  " \"tasks\": \"automatic-speech-recognition\",\n",
1237
  " \"tags\": \"whisper-event\",\n",
.ipynb_checkpoints/fine-tune-whisper-non-streaming-zh-checkpoint.ipynb → fine-tune-whisper-non-streaming-zh-TW.ipynb RENAMED
@@ -145,354 +145,11 @@
145
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44"
146
  },
147
  "outputs": [
148
- {
149
- "name": "stdout",
150
- "output_type": "stream",
151
- "text": [
152
- "Downloading and preparing dataset common_voice_11_0/zh-TW to /home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f...\n"
153
- ]
154
- },
155
- {
156
- "data": {
157
- "application/vnd.jupyter.widget-view+json": {
158
- "model_id": "2b102b9d1660420cabb06bfe54c35c25",
159
- "version_major": 2,
160
- "version_minor": 0
161
- },
162
- "text/plain": [
163
- "Downloading data files: 0%| | 0/5 [00:00<?, ?it/s]"
164
- ]
165
- },
166
- "metadata": {},
167
- "output_type": "display_data"
168
- },
169
- {
170
- "data": {
171
- "application/vnd.jupyter.widget-view+json": {
172
- "model_id": "bfd9db96bd5c47fbb8847a7211b71c1b",
173
- "version_major": 2,
174
- "version_minor": 0
175
- },
176
- "text/plain": [
177
- "Downloading data: 0%| | 0.00/152M [00:00<?, ?B/s]"
178
- ]
179
- },
180
- "metadata": {},
181
- "output_type": "display_data"
182
- },
183
- {
184
- "data": {
185
- "application/vnd.jupyter.widget-view+json": {
186
- "model_id": "0f0161d0a1d04428bf295e1ce0bfc7d8",
187
- "version_major": 2,
188
- "version_minor": 0
189
- },
190
- "text/plain": [
191
- "Downloading data: 0%| | 0.00/120M [00:00<?, ?B/s]"
192
- ]
193
- },
194
- "metadata": {},
195
- "output_type": "display_data"
196
- },
197
- {
198
- "data": {
199
- "application/vnd.jupyter.widget-view+json": {
200
- "model_id": "d85a133c5b5c4f8883faada1fcee9ddf",
201
- "version_major": 2,
202
- "version_minor": 0
203
- },
204
- "text/plain": [
205
- "Downloading data: 0%| | 0.00/134M [00:00<?, ?B/s]"
206
- ]
207
- },
208
- "metadata": {},
209
- "output_type": "display_data"
210
- },
211
- {
212
- "data": {
213
- "application/vnd.jupyter.widget-view+json": {
214
- "model_id": "b2b0ecba08154555a3f1940c2d7e3f18",
215
- "version_major": 2,
216
- "version_minor": 0
217
- },
218
- "text/plain": [
219
- "Downloading data: 0%| | 0.00/995M [00:00<?, ?B/s]"
220
- ]
221
- },
222
- "metadata": {},
223
- "output_type": "display_data"
224
- },
225
- {
226
- "data": {
227
- "application/vnd.jupyter.widget-view+json": {
228
- "model_id": "689229ba2edf47bea236f231fdd845b8",
229
- "version_major": 2,
230
- "version_minor": 0
231
- },
232
- "text/plain": [
233
- "Downloading data: 0%| | 0.00/18.6M [00:00<?, ?B/s]"
234
- ]
235
- },
236
- "metadata": {},
237
- "output_type": "display_data"
238
- },
239
- {
240
- "data": {
241
- "application/vnd.jupyter.widget-view+json": {
242
- "model_id": "728521ae7d68422c92c2c29cc9aaff7a",
243
- "version_major": 2,
244
- "version_minor": 0
245
- },
246
- "text/plain": [
247
- "Downloading data: 0%| | 0.00/128M [00:00<?, ?B/s]"
248
- ]
249
- },
250
- "metadata": {},
251
- "output_type": "display_data"
252
- },
253
- {
254
- "data": {
255
- "application/vnd.jupyter.widget-view+json": {
256
- "model_id": "e6c78710e8dd4f00a856ba8c17325ca9",
257
- "version_major": 2,
258
- "version_minor": 0
259
- },
260
- "text/plain": [
261
- "Extracting data files: 0%| | 0/5 [00:00<?, ?it/s]"
262
- ]
263
- },
264
- "metadata": {},
265
- "output_type": "display_data"
266
- },
267
- {
268
- "data": {
269
- "application/vnd.jupyter.widget-view+json": {
270
- "model_id": "cc7cdaf4c35b4784990b949d05f43b47",
271
- "version_major": 2,
272
- "version_minor": 0
273
- },
274
- "text/plain": [
275
- "Downloading data files: 0%| | 0/5 [00:00<?, ?it/s]"
276
- ]
277
- },
278
- "metadata": {},
279
- "output_type": "display_data"
280
- },
281
- {
282
- "data": {
283
- "application/vnd.jupyter.widget-view+json": {
284
- "model_id": "628b00ae5c7a4ac082453b11bd3fb68a",
285
- "version_major": 2,
286
- "version_minor": 0
287
- },
288
- "text/plain": [
289
- "Downloading data: 0%| | 0.00/1.49M [00:00<?, ?B/s]"
290
- ]
291
- },
292
- "metadata": {},
293
- "output_type": "display_data"
294
- },
295
- {
296
- "data": {
297
- "application/vnd.jupyter.widget-view+json": {
298
- "model_id": "34941d3d98554e4dbac5e27e20cc84df",
299
- "version_major": 2,
300
- "version_minor": 0
301
- },
302
- "text/plain": [
303
- "Downloading data: 0%| | 0.00/1.02M [00:00<?, ?B/s]"
304
- ]
305
- },
306
- "metadata": {},
307
- "output_type": "display_data"
308
- },
309
- {
310
- "data": {
311
- "application/vnd.jupyter.widget-view+json": {
312
- "model_id": "5e5886ccc15a497380aae6559f11abd1",
313
- "version_major": 2,
314
- "version_minor": 0
315
- },
316
- "text/plain": [
317
- "Downloading data: 0%| | 0.00/983k [00:00<?, ?B/s]"
318
- ]
319
- },
320
- "metadata": {},
321
- "output_type": "display_data"
322
- },
323
- {
324
- "data": {
325
- "application/vnd.jupyter.widget-view+json": {
326
- "model_id": "830007d441bd44109a015d89d27e0ba9",
327
- "version_major": 2,
328
- "version_minor": 0
329
- },
330
- "text/plain": [
331
- "Downloading data: 0%| | 0.00/8.75M [00:00<?, ?B/s]"
332
- ]
333
- },
334
- "metadata": {},
335
- "output_type": "display_data"
336
- },
337
- {
338
- "data": {
339
- "application/vnd.jupyter.widget-view+json": {
340
- "model_id": "8df8ab2f3cdd4f51bc4f7bdc31f9d2a7",
341
- "version_major": 2,
342
- "version_minor": 0
343
- },
344
- "text/plain": [
345
- "Downloading data: 0%| | 0.00/995k [00:00<?, ?B/s]"
346
- ]
347
- },
348
- "metadata": {},
349
- "output_type": "display_data"
350
- },
351
- {
352
- "data": {
353
- "application/vnd.jupyter.widget-view+json": {
354
- "model_id": "fa78caff99dc442b9612c266eda880f3",
355
- "version_major": 2,
356
- "version_minor": 0
357
- },
358
- "text/plain": [
359
- "Extracting data files: 0%| | 0/5 [00:00<?, ?it/s]"
360
- ]
361
- },
362
- "metadata": {},
363
- "output_type": "display_data"
364
- },
365
- {
366
- "data": {
367
- "application/vnd.jupyter.widget-view+json": {
368
- "model_id": "",
369
- "version_major": 2,
370
- "version_minor": 0
371
- },
372
- "text/plain": [
373
- "Generating train split: 0 examples [00:00, ? examples/s]"
374
- ]
375
- },
376
- "metadata": {},
377
- "output_type": "display_data"
378
- },
379
- {
380
- "name": "stderr",
381
- "output_type": "stream",
382
- "text": [
383
- "\n",
384
- "Reading metadata...: 6568it [00:00, 242101.00it/s]\n"
385
- ]
386
- },
387
- {
388
- "data": {
389
- "application/vnd.jupyter.widget-view+json": {
390
- "model_id": "",
391
- "version_major": 2,
392
- "version_minor": 0
393
- },
394
- "text/plain": [
395
- "Generating validation split: 0 examples [00:00, ? examples/s]"
396
- ]
397
- },
398
- "metadata": {},
399
- "output_type": "display_data"
400
- },
401
- {
402
- "name": "stderr",
403
- "output_type": "stream",
404
- "text": [
405
- "\n",
406
- "\n",
407
- "Reading metadata...: 4709it [00:00, 244282.56it/s]\n"
408
- ]
409
- },
410
- {
411
- "data": {
412
- "application/vnd.jupyter.widget-view+json": {
413
- "model_id": "",
414
- "version_major": 2,
415
- "version_minor": 0
416
- },
417
- "text/plain": [
418
- "Generating test split: 0 examples [00:00, ? examples/s]"
419
- ]
420
- },
421
- "metadata": {},
422
- "output_type": "display_data"
423
- },
424
- {
425
- "name": "stderr",
426
- "output_type": "stream",
427
- "text": [
428
- "\n",
429
- "\n",
430
- "\n",
431
- "Reading metadata...: 4709it [00:00, 253653.42it/s]\n"
432
- ]
433
- },
434
- {
435
- "data": {
436
- "application/vnd.jupyter.widget-view+json": {
437
- "model_id": "",
438
- "version_major": 2,
439
- "version_minor": 0
440
- },
441
- "text/plain": [
442
- "Generating other split: 0 examples [00:00, ? examples/s]"
443
- ]
444
- },
445
- "metadata": {},
446
- "output_type": "display_data"
447
- },
448
- {
449
- "name": "stderr",
450
- "output_type": "stream",
451
- "text": [
452
- "\n",
453
- "\n",
454
- "\n",
455
- "\n",
456
- "Reading metadata...: 0it [00:00, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
457
- "\n",
458
- "\n",
459
- "\n",
460
- "Reading metadata...: 40630it [00:00, 258238.72it/s]\u001b[A\u001b[A\u001b[A\u001b[A\n"
461
- ]
462
- },
463
- {
464
- "data": {
465
- "application/vnd.jupyter.widget-view+json": {
466
- "model_id": "",
467
- "version_major": 2,
468
- "version_minor": 0
469
- },
470
- "text/plain": [
471
- "Generating invalidated split: 0 examples [00:00, ? examples/s]"
472
- ]
473
- },
474
- "metadata": {},
475
- "output_type": "display_data"
476
- },
477
- {
478
- "name": "stderr",
479
- "output_type": "stream",
480
- "text": [
481
- "\n",
482
- "Reading metadata...: 4596it [00:00, 253281.76it/s]\n"
483
- ]
484
- },
485
- {
486
- "name": "stdout",
487
- "output_type": "stream",
488
- "text": [
489
- "Dataset common_voice_11_0 downloaded and prepared to /home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f. Subsequent calls will reuse this data.\n"
490
- ]
491
- },
492
  {
493
  "name": "stderr",
494
  "output_type": "stream",
495
  "text": [
 
496
  "Found cached dataset common_voice_11_0 (/home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
497
  ]
498
  },
@@ -526,20 +183,20 @@
526
  },
527
  {
528
  "cell_type": "code",
529
- "execution_count": 20,
530
  "id": "79731fc3",
531
  "metadata": {},
532
  "outputs": [
533
  {
534
  "data": {
535
  "text/plain": [
536
- "{'audio': {'path': None,\n",
537
- " 'array': array([0., 0., 0., ..., 0., 0., 0.]),\n",
538
- " 'sampling_rate': 16000},\n",
539
  " 'sentence': '爸爸們父親節快樂!'}"
540
  ]
541
  },
542
- "execution_count": 20,
543
  "metadata": {},
544
  "output_type": "execute_result"
545
  }
@@ -759,7 +416,7 @@
759
  },
760
  {
761
  "cell_type": "code",
762
- "execution_count": 17,
763
  "id": "b27e4720",
764
  "metadata": {},
765
  "outputs": [],
@@ -784,7 +441,7 @@
784
  },
785
  {
786
  "cell_type": "code",
787
- "execution_count": 18,
788
  "id": "b459b0c5",
789
  "metadata": {},
790
  "outputs": [
@@ -798,7 +455,7 @@
798
  {
799
  "data": {
800
  "application/vnd.jupyter.widget-view+json": {
801
- "model_id": "2db072c14c9a419d87f37e6747e62703",
802
  "version_major": 2,
803
  "version_minor": 0
804
  },
@@ -827,7 +484,7 @@
827
  },
828
  {
829
  "cell_type": "code",
830
- "execution_count": 21,
831
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
832
  "metadata": {},
833
  "outputs": [],
@@ -838,7 +495,7 @@
838
  },
839
  {
840
  "cell_type": "code",
841
- "execution_count": 24,
842
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
843
  "metadata": {},
844
  "outputs": [],
@@ -865,7 +522,7 @@
865
  },
866
  {
867
  "cell_type": "code",
868
- "execution_count": 25,
869
  "id": "90965caa",
870
  "metadata": {},
871
  "outputs": [
@@ -879,7 +536,7 @@
879
  {
880
  "data": {
881
  "application/vnd.jupyter.widget-view+json": {
882
- "model_id": "ee8d88c2e3ef46039c2db32818ab08d7",
883
  "version_major": 2,
884
  "version_minor": 0
885
  },
@@ -891,18 +548,11 @@
891
  "output_type": "display_data"
892
  },
893
  {
894
- "data": {
895
- "application/vnd.jupyter.widget-view+json": {
896
- "model_id": "48fce3473f7a42a29723b4148fb549c4",
897
- "version_major": 2,
898
- "version_minor": 0
899
- },
900
- "text/plain": [
901
- " 0%| | 0/4709 [00:00<?, ?ex/s]"
902
- ]
903
- },
904
- "metadata": {},
905
- "output_type": "display_data"
906
  }
907
  ],
908
  "source": [
@@ -912,7 +562,7 @@
912
  },
913
  {
914
  "cell_type": "code",
915
- "execution_count": 26,
916
  "id": "bde2118b",
917
  "metadata": {},
918
  "outputs": [
@@ -931,7 +581,7 @@
931
  " 34131, 220, 42117, 220, 27694, 42598, 220, 34043, 220, 50257])}"
932
  ]
933
  },
934
- "execution_count": 26,
935
  "metadata": {},
936
  "output_type": "execute_result"
937
  }
@@ -950,7 +600,7 @@
950
  },
951
  {
952
  "cell_type": "code",
953
- "execution_count": 27,
954
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
955
  "metadata": {},
956
  "outputs": [],
@@ -971,14 +621,14 @@
971
  },
972
  {
973
  "cell_type": "code",
974
- "execution_count": 28,
975
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
976
  "metadata": {},
977
  "outputs": [
978
  {
979
  "data": {
980
  "application/vnd.jupyter.widget-view+json": {
981
- "model_id": "cbb3a2b5bb1a43a6a9acf13fa6ddf6b9",
982
  "version_major": 2,
983
  "version_minor": 0
984
  },
@@ -999,7 +649,7 @@
999
  },
1000
  {
1001
  "cell_type": "code",
1002
- "execution_count": 29,
1003
  "id": "53945dcb",
1004
  "metadata": {},
1005
  "outputs": [],
@@ -1077,7 +727,7 @@
1077
  },
1078
  {
1079
  "cell_type": "code",
1080
- "execution_count": 30,
1081
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
1082
  "metadata": {
1083
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
@@ -1129,7 +779,7 @@
1129
  },
1130
  {
1131
  "cell_type": "code",
1132
- "execution_count": 31,
1133
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
1134
  "metadata": {
1135
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
@@ -1162,7 +812,7 @@
1162
  },
1163
  {
1164
  "cell_type": "code",
1165
- "execution_count": 32,
1166
  "id": "b22b4011-f31f-4b57-b684-c52332f92890",
1167
  "metadata": {
1168
  "id": "b22b4011-f31f-4b57-b684-c52332f92890"
@@ -1195,7 +845,7 @@
1195
  },
1196
  {
1197
  "cell_type": "code",
1198
- "execution_count": 33,
1199
  "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52",
1200
  "metadata": {
1201
  "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52"
@@ -1248,7 +898,7 @@
1248
  },
1249
  {
1250
  "cell_type": "code",
1251
- "execution_count": 34,
1252
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
1253
  "metadata": {
1254
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f"
@@ -1272,7 +922,7 @@
1272
  },
1273
  {
1274
  "cell_type": "code",
1275
- "execution_count": 35,
1276
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
1277
  "metadata": {
1278
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
@@ -1306,7 +956,7 @@
1306
  },
1307
  {
1308
  "cell_type": "code",
1309
- "execution_count": 36,
1310
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
1311
  "metadata": {
1312
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a"
@@ -1364,7 +1014,7 @@
1364
  },
1365
  {
1366
  "cell_type": "code",
1367
- "execution_count": 37,
1368
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
1369
  "metadata": {
1370
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
@@ -1407,7 +1057,7 @@
1407
  },
1408
  {
1409
  "cell_type": "code",
1410
- "execution_count": 38,
1411
  "id": "-2zQwMfEOBJq",
1412
  "metadata": {
1413
  "id": "-2zQwMfEOBJq"
@@ -1456,7 +1106,7 @@
1456
  },
1457
  {
1458
  "cell_type": "code",
1459
- "execution_count": 39,
1460
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
1461
  "metadata": {
1462
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
@@ -1468,8 +1118,6 @@
1468
  "output_type": "stream",
1469
  "text": [
1470
  "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1471
- "/home/daniel/whisper/lib/python3.8/site-packages/bitsandbytes/cextension.py:127: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers and GPU quantization are unavailable.\n",
1472
- " warn(\"The installed version of bitsandbytes was compiled without GPU support. \"\n",
1473
  "***** Running training *****\n",
1474
  " Num examples = 11277\n",
1475
  " Num Epochs = 3\n",
@@ -1481,25 +1129,83 @@
1481
  ]
1482
  },
1483
  {
1484
- "ename": "NameError",
1485
- "evalue": "name 'str2optimizer8bit_blockwise' is not defined",
1486
- "output_type": "error",
1487
- "traceback": [
1488
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
1489
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
1490
- "Cell \u001b[0;32mIn[39], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
1491
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/transformers/trainer.py:1535\u001b[0m, in \u001b[0;36mTrainer.train\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 1530\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_wrapped \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\n\u001b[1;32m 1532\u001b[0m inner_training_loop \u001b[38;5;241m=\u001b[39m find_executable_batch_size(\n\u001b[1;32m 1533\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_training_loop, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_train_batch_size, args\u001b[38;5;241m.\u001b[39mauto_find_batch_size\n\u001b[1;32m 1534\u001b[0m )\n\u001b[0;32m-> 1535\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43minner_training_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1536\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1537\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1538\u001b[0m \u001b[43m \u001b[49m\u001b[43mtrial\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1539\u001b[0m \u001b[43m \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1540\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
1492
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/transformers/trainer.py:1845\u001b[0m, in \u001b[0;36mTrainer._inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m 1843\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdo_grad_scaling:\n\u001b[1;32m 1844\u001b[0m scale_before \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscaler\u001b[38;5;241m.\u001b[39mget_scale()\n\u001b[0;32m-> 1845\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscaler\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstep\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptimizer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1846\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscaler\u001b[38;5;241m.\u001b[39mupdate()\n\u001b[1;32m 1847\u001b[0m scale_after \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mscaler\u001b[38;5;241m.\u001b[39mget_scale()\n",
1493
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/cuda/amp/grad_scaler.py:341\u001b[0m, in \u001b[0;36mGradScaler.step\u001b[0;34m(self, optimizer, *args, **kwargs)\u001b[0m\n\u001b[1;32m 337\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39munscale_(optimizer)\n\u001b[1;32m 339\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(optimizer_state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfound_inf_per_device\u001b[39m\u001b[38;5;124m\"\u001b[39m]) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo inf checks were recorded for this optimizer.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 341\u001b[0m retval \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_maybe_opt_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43moptimizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moptimizer_state\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 343\u001b[0m optimizer_state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstage\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m OptState\u001b[38;5;241m.\u001b[39mSTEPPED\n\u001b[1;32m 345\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m retval\n",
1494
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/cuda/amp/grad_scaler.py:288\u001b[0m, in \u001b[0;36mGradScaler._maybe_opt_step\u001b[0;34m(self, optimizer, optimizer_state, *args, **kwargs)\u001b[0m\n\u001b[1;32m 286\u001b[0m retval \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 287\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28msum\u001b[39m(v\u001b[38;5;241m.\u001b[39mitem() \u001b[38;5;28;01mfor\u001b[39;00m v \u001b[38;5;129;01min\u001b[39;00m optimizer_state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfound_inf_per_device\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mvalues()):\n\u001b[0;32m--> 288\u001b[0m retval \u001b[38;5;241m=\u001b[39m \u001b[43moptimizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstep\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 289\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m retval\n",
1495
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/optim/lr_scheduler.py:68\u001b[0m, in \u001b[0;36m_LRScheduler.__init__.<locals>.with_counter.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 66\u001b[0m instance\u001b[38;5;241m.\u001b[39m_step_count \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 67\u001b[0m wrapped \u001b[38;5;241m=\u001b[39m func\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__get__\u001b[39m(instance, \u001b[38;5;28mcls\u001b[39m)\n\u001b[0;32m---> 68\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
1496
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/optim/optimizer.py:140\u001b[0m, in \u001b[0;36mOptimizer._hook_for_profile.<locals>.profile_hook_step.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 138\u001b[0m profile_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOptimizer.step#\u001b[39m\u001b[38;5;132;01m{}\u001b[39;00m\u001b[38;5;124m.step\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(obj\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m 139\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mautograd\u001b[38;5;241m.\u001b[39mprofiler\u001b[38;5;241m.\u001b[39mrecord_function(profile_name):\n\u001b[0;32m--> 140\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 141\u001b[0m obj\u001b[38;5;241m.\u001b[39m_optimizer_step_code()\n\u001b[1;32m 142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m out\n",
1497
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
1498
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/bitsandbytes/optim/optimizer.py:265\u001b[0m, in \u001b[0;36mOptimizer8bit.step\u001b[0;34m(self, closure)\u001b[0m\n\u001b[1;32m 262\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(state) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m 263\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minit_state(group, p, gindex, pindex)\n\u001b[0;32m--> 265\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupdate_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgroup\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgindex\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpindex\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 267\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m loss\n",
1499
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
1500
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/bitsandbytes/optim/optimizer.py:506\u001b[0m, in \u001b[0;36mOptimizer2State.update_step\u001b[0;34m(self, group, p, gindex, pindex)\u001b[0m\n\u001b[1;32m 504\u001b[0m state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax2\u001b[39m\u001b[38;5;124m\"\u001b[39m], state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnew_max2\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnew_max2\u001b[39m\u001b[38;5;124m\"\u001b[39m], state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmax2\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 505\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m state[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstate1\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m torch\u001b[38;5;241m.\u001b[39muint8 \u001b[38;5;129;01mand\u001b[39;00m config[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mblock_wise\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[0;32m--> 506\u001b[0m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptimizer_update_8bit_blockwise\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 507\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptimizer_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 508\u001b[0m \u001b[43m \u001b[49m\u001b[43mgrad\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 509\u001b[0m \u001b[43m \u001b[49m\u001b[43mp\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 510\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstate1\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 511\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstate2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 512\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbetas\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 513\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbetas\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 514\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43meps\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 515\u001b[0m \u001b[43m \u001b[49m\u001b[43mstep\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 516\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 517\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mqmap1\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 518\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mqmap2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 519\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mabsmax1\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 520\u001b[0m \u001b[43m \u001b[49m\u001b[43mstate\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mabsmax2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 521\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mweight_decay\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 522\u001b[0m \u001b[43m \u001b[49m\u001b[43mgnorm_scale\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgnorm_scale\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 523\u001b[0m \u001b[43m \u001b[49m\u001b[43mskip_zeros\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mskip_zeros\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 524\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
1501
- "File \u001b[0;32m~/whisper/lib/python3.8/site-packages/bitsandbytes/functional.py:858\u001b[0m, in \u001b[0;36moptimizer_update_8bit_blockwise\u001b[0;34m(optimizer_name, g, p, state1, state2, beta1, beta2, eps, step, lr, qmap1, qmap2, absmax1, absmax2, weight_decay, gnorm_scale, skip_zeros)\u001b[0m\n\u001b[1;32m 837\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21moptimizer_update_8bit_blockwise\u001b[39m(\n\u001b[1;32m 838\u001b[0m optimizer_name: \u001b[38;5;28mstr\u001b[39m,\n\u001b[1;32m 839\u001b[0m g: Tensor,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 854\u001b[0m skip_zeros\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 855\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 857\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m g\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m torch\u001b[38;5;241m.\u001b[39mfloat32 \u001b[38;5;129;01mand\u001b[39;00m state1\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m torch\u001b[38;5;241m.\u001b[39muint8:\n\u001b[0;32m--> 858\u001b[0m \u001b[43mstr2optimizer8bit_blockwise\u001b[49m[optimizer_name][\u001b[38;5;241m0\u001b[39m](\n\u001b[1;32m 859\u001b[0m get_ptr(p),\n\u001b[1;32m 860\u001b[0m get_ptr(g),\n\u001b[1;32m 861\u001b[0m get_ptr(state1),\n\u001b[1;32m 862\u001b[0m get_ptr(state2),\n\u001b[1;32m 863\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(beta1),\n\u001b[1;32m 864\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(beta2),\n\u001b[1;32m 865\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(eps),\n\u001b[1;32m 866\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_int32(step),\n\u001b[1;32m 867\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(lr),\n\u001b[1;32m 868\u001b[0m get_ptr(qmap1),\n\u001b[1;32m 869\u001b[0m get_ptr(qmap2),\n\u001b[1;32m 870\u001b[0m get_ptr(absmax1),\n\u001b[1;32m 871\u001b[0m get_ptr(absmax2),\n\u001b[1;32m 872\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(weight_decay),\n\u001b[1;32m 873\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_float(gnorm_scale),\n\u001b[1;32m 874\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_bool(skip_zeros),\n\u001b[1;32m 875\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_int32(g\u001b[38;5;241m.\u001b[39mnumel()),\n\u001b[1;32m 876\u001b[0m )\n\u001b[1;32m 877\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m g\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m torch\u001b[38;5;241m.\u001b[39mfloat16 \u001b[38;5;129;01mand\u001b[39;00m state1\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m torch\u001b[38;5;241m.\u001b[39muint8:\n\u001b[1;32m 878\u001b[0m str2optimizer8bit_blockwise[optimizer_name][\u001b[38;5;241m1\u001b[39m](\n\u001b[1;32m 879\u001b[0m get_ptr(p),\n\u001b[1;32m 880\u001b[0m get_ptr(g),\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 895\u001b[0m ct\u001b[38;5;241m.\u001b[39mc_int32(g\u001b[38;5;241m.\u001b[39mnumel()),\n\u001b[1;32m 896\u001b[0m )\n",
1502
- "\u001b[0;31mNameError\u001b[0m: name 'str2optimizer8bit_blockwise' is not defined"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1503
  ]
1504
  }
1505
  ],
@@ -1530,7 +1236,7 @@
1530
  " \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
1531
  " \"dataset\": \"mozilla-foundation/common_voice_11_0\", # a 'pretty' name for the training dataset\n",
1532
  " \"language\": \"zh-TW\",\n",
1533
- " \"model_name\": \"Whisper Medium MS - Augmented\", # a 'pretty' name for your model\n",
1534
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
1535
  " \"tasks\": \"automatic-speech-recognition\",\n",
1536
  " \"tags\": \"whisper-event\",\n",
 
145
  "id": "a2787582-554f-44ce-9f38-4180a5ed6b44"
146
  },
147
  "outputs": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
148
  {
149
  "name": "stderr",
150
  "output_type": "stream",
151
  "text": [
152
+ "Found cached dataset common_voice_11_0 (/home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
153
  "Found cached dataset common_voice_11_0 (/home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
154
  ]
155
  },
 
183
  },
184
  {
185
  "cell_type": "code",
186
+ "execution_count": 2,
187
  "id": "79731fc3",
188
  "metadata": {},
189
  "outputs": [
190
  {
191
  "data": {
192
  "text/plain": [
193
+ "{'audio': {'path': '/home/daniel/.cache/huggingface/datasets/downloads/extracted/8d1722ebe07713de78ba2ed06286baa9fb33c24f19cb47ef1a3d6cb0774ad391/common_voice_zh-TW_18013265.mp3',\n",
194
+ " 'array': array([0., 0., 0., ..., 0., 0., 0.], dtype=float32),\n",
195
+ " 'sampling_rate': 48000},\n",
196
  " 'sentence': '爸爸們父親節快樂!'}"
197
  ]
198
  },
199
+ "execution_count": 2,
200
  "metadata": {},
201
  "output_type": "execute_result"
202
  }
 
416
  },
417
  {
418
  "cell_type": "code",
419
+ "execution_count": 6,
420
  "id": "b27e4720",
421
  "metadata": {},
422
  "outputs": [],
 
441
  },
442
  {
443
  "cell_type": "code",
444
+ "execution_count": 7,
445
  "id": "b459b0c5",
446
  "metadata": {},
447
  "outputs": [
 
455
  {
456
  "data": {
457
  "application/vnd.jupyter.widget-view+json": {
458
+ "model_id": "e7f849f56879427995d5de3d75585606",
459
  "version_major": 2,
460
  "version_minor": 0
461
  },
 
484
  },
485
  {
486
  "cell_type": "code",
487
+ "execution_count": 8,
488
  "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
489
  "metadata": {},
490
  "outputs": [],
 
495
  },
496
  {
497
  "cell_type": "code",
498
+ "execution_count": 9,
499
  "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
500
  "metadata": {},
501
  "outputs": [],
 
522
  },
523
  {
524
  "cell_type": "code",
525
+ "execution_count": 10,
526
  "id": "90965caa",
527
  "metadata": {},
528
  "outputs": [
 
536
  {
537
  "data": {
538
  "application/vnd.jupyter.widget-view+json": {
539
+ "model_id": "91de26e5528241e895f883a394bdab2a",
540
  "version_major": 2,
541
  "version_minor": 0
542
  },
 
548
  "output_type": "display_data"
549
  },
550
  {
551
+ "name": "stderr",
552
+ "output_type": "stream",
553
+ "text": [
554
+ "Loading cached processed dataset at /home/daniel/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/zh-TW/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-e493134b08029cc3.arrow\n"
555
+ ]
 
 
 
 
 
 
 
556
  }
557
  ],
558
  "source": [
 
562
  },
563
  {
564
  "cell_type": "code",
565
+ "execution_count": 11,
566
  "id": "bde2118b",
567
  "metadata": {},
568
  "outputs": [
 
581
  " 34131, 220, 42117, 220, 27694, 42598, 220, 34043, 220, 50257])}"
582
  ]
583
  },
584
+ "execution_count": 11,
585
  "metadata": {},
586
  "output_type": "execute_result"
587
  }
 
600
  },
601
  {
602
  "cell_type": "code",
603
+ "execution_count": 12,
604
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
605
  "metadata": {},
606
  "outputs": [],
 
621
  },
622
  {
623
  "cell_type": "code",
624
+ "execution_count": 13,
625
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
626
  "metadata": {},
627
  "outputs": [
628
  {
629
  "data": {
630
  "application/vnd.jupyter.widget-view+json": {
631
+ "model_id": "bcef97571c7548c081de85f242931b21",
632
  "version_major": 2,
633
  "version_minor": 0
634
  },
 
649
  },
650
  {
651
  "cell_type": "code",
652
+ "execution_count": 14,
653
  "id": "53945dcb",
654
  "metadata": {},
655
  "outputs": [],
 
727
  },
728
  {
729
  "cell_type": "code",
730
+ "execution_count": 15,
731
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
732
  "metadata": {
733
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
 
779
  },
780
  {
781
  "cell_type": "code",
782
+ "execution_count": 16,
783
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
784
  "metadata": {
785
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
 
812
  },
813
  {
814
  "cell_type": "code",
815
+ "execution_count": 17,
816
  "id": "b22b4011-f31f-4b57-b684-c52332f92890",
817
  "metadata": {
818
  "id": "b22b4011-f31f-4b57-b684-c52332f92890"
 
845
  },
846
  {
847
  "cell_type": "code",
848
+ "execution_count": 18,
849
  "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52",
850
  "metadata": {
851
  "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52"
 
898
  },
899
  {
900
  "cell_type": "code",
901
+ "execution_count": 19,
902
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
903
  "metadata": {
904
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f"
 
922
  },
923
  {
924
  "cell_type": "code",
925
+ "execution_count": 20,
926
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
927
  "metadata": {
928
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
 
956
  },
957
  {
958
  "cell_type": "code",
959
+ "execution_count": 21,
960
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
961
  "metadata": {
962
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a"
 
1014
  },
1015
  {
1016
  "cell_type": "code",
1017
+ "execution_count": 22,
1018
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
1019
  "metadata": {
1020
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
 
1057
  },
1058
  {
1059
  "cell_type": "code",
1060
+ "execution_count": 23,
1061
  "id": "-2zQwMfEOBJq",
1062
  "metadata": {
1063
  "id": "-2zQwMfEOBJq"
 
1106
  },
1107
  {
1108
  "cell_type": "code",
1109
+ "execution_count": null,
1110
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
1111
  "metadata": {
1112
  "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
 
1118
  "output_type": "stream",
1119
  "text": [
1120
  "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
 
 
1121
  "***** Running training *****\n",
1122
  " Num examples = 11277\n",
1123
  " Num Epochs = 3\n",
 
1129
  ]
1130
  },
1131
  {
1132
+ "data": {
1133
+ "text/html": [
1134
+ "\n",
1135
+ " <div>\n",
1136
+ " \n",
1137
+ " <progress value='601' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1138
+ " [ 601/1000 3:16:05 < 2:10:37, 0.05 it/s, Epoch 1.70/3]\n",
1139
+ " </div>\n",
1140
+ " <table border=\"1\" class=\"dataframe\">\n",
1141
+ " <thead>\n",
1142
+ " <tr style=\"text-align: left;\">\n",
1143
+ " <th>Step</th>\n",
1144
+ " <th>Training Loss</th>\n",
1145
+ " <th>Validation Loss</th>\n",
1146
+ " <th>Wer</th>\n",
1147
+ " </tr>\n",
1148
+ " </thead>\n",
1149
+ " <tbody>\n",
1150
+ " <tr>\n",
1151
+ " <td>200</td>\n",
1152
+ " <td>0.216900</td>\n",
1153
+ " <td>0.119112</td>\n",
1154
+ " <td>9.333440</td>\n",
1155
+ " </tr>\n",
1156
+ " <tr>\n",
1157
+ " <td>400</td>\n",
1158
+ " <td>0.082300</td>\n",
1159
+ " <td>0.101187</td>\n",
1160
+ " <td>7.590416</td>\n",
1161
+ " </tr>\n",
1162
+ " <tr>\n",
1163
+ " <td>600</td>\n",
1164
+ " <td>0.078400</td>\n",
1165
+ " <td>0.095110</td>\n",
1166
+ " <td>7.486474</td>\n",
1167
+ " </tr>\n",
1168
+ " </tbody>\n",
1169
+ "</table><p>"
1170
+ ],
1171
+ "text/plain": [
1172
+ "<IPython.core.display.HTML object>"
1173
+ ]
1174
+ },
1175
+ "metadata": {},
1176
+ "output_type": "display_data"
1177
+ },
1178
+ {
1179
+ "name": "stderr",
1180
+ "output_type": "stream",
1181
+ "text": [
1182
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1183
+ "***** Running Evaluation *****\n",
1184
+ " Num examples = 4709\n",
1185
+ " Batch size = 2\n",
1186
+ "Saving model checkpoint to ./checkpoint-200\n",
1187
+ "Configuration saved in ./checkpoint-200/config.json\n",
1188
+ "Model weights saved in ./checkpoint-200/pytorch_model.bin\n",
1189
+ "Feature extractor saved in ./checkpoint-200/preprocessor_config.json\n",
1190
+ "Feature extractor saved in ./preprocessor_config.json\n",
1191
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1192
+ "***** Running Evaluation *****\n",
1193
+ " Num examples = 4709\n",
1194
+ " Batch size = 2\n",
1195
+ "Saving model checkpoint to ./checkpoint-400\n",
1196
+ "Configuration saved in ./checkpoint-400/config.json\n",
1197
+ "Model weights saved in ./checkpoint-400/pytorch_model.bin\n",
1198
+ "Feature extractor saved in ./checkpoint-400/preprocessor_config.json\n",
1199
+ "Feature extractor saved in ./preprocessor_config.json\n",
1200
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
1201
+ "***** Running Evaluation *****\n",
1202
+ " Num examples = 4709\n",
1203
+ " Batch size = 2\n",
1204
+ "Saving model checkpoint to ./checkpoint-600\n",
1205
+ "Configuration saved in ./checkpoint-600/config.json\n",
1206
+ "Model weights saved in ./checkpoint-600/pytorch_model.bin\n",
1207
+ "Feature extractor saved in ./checkpoint-600/preprocessor_config.json\n",
1208
+ "Feature extractor saved in ./preprocessor_config.json\n"
1209
  ]
1210
  }
1211
  ],
 
1236
  " \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
1237
  " \"dataset\": \"mozilla-foundation/common_voice_11_0\", # a 'pretty' name for the training dataset\n",
1238
  " \"language\": \"zh-TW\",\n",
1239
+ " \"model_name\": \"Whisper Medium TW - Augmented\", # a 'pretty' name for your model\n",
1240
  " \"finetuned_from\": \"openai/whisper-medium\",\n",
1241
  " \"tasks\": \"automatic-speech-recognition\",\n",
1242
  " \"tags\": \"whisper-event\",\n",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c59231bec50bf7e63c665d3feb4951821ecb964b915a1be521482c50b1e826e8
3
  size 3055754841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6411d501e4303ddf9b86289a5d217422eb9512dbcc64a08c30ef1eb0eacffd82
3
  size 3055754841
runs/Dec20_16-48-49_DANDAN/events.out.tfevents.1671526137.DANDAN.29004.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdd159d93587e66eb3149250140df4f3a7bf7e881249d76236bd2e9630445a9d
3
- size 7418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79731c0e98643c8665dadac50b68886f182f977725bc91193254b8e577a064f0
3
+ size 8992