justin1983 commited on
Commit
7f4b768
1 Parent(s): 28b643f

Training in progress, epoch 2

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59b64f7735551bd057d4824a7eb20408627d9e880594a25ea3da58fdfa13d750
3
  size 756676997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d9b410a83e288f9e29281fdab9516934fddf282e4650fd952f5a6bbc852a11
3
  size 756676997
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b30c75792e62f2dcfc9627e890f06989430395b3e7114124c88f2620a022c2d9
3
  size 378349481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe6005ae34709190bbb6221e7f2d78dd48218e4439610fec95a5e5629156fd1
3
  size 378349481
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cd61c5500e338981b11c949c83fb219725b2eba846fe69f1847ef82bc2d76ce
3
  size 13617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3afdb7355532adb7b578d661b009de91be436e733677a897fb5f1d2628cc96
3
  size 13617
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f444185c3e228ee6138ca7334fba6706bbb1da32fc13357fe5c32dffd6ee429b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b9fa9ec6f49466f7adb473ab8162797c4ceaba994da2e5fd138284cf868e72
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 0.9154545454545454,
3
  "best_model_checkpoint": "wav2vec2-base-finetuned-amd/checkpoint-290",
4
- "epoch": 1.0,
5
- "global_step": 290,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -189,11 +189,194 @@
189
  "eval_samples_per_second": 4.977,
190
  "eval_steps_per_second": 0.156,
191
  "step": 290
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "max_steps": 580,
195
  "num_train_epochs": 2,
196
- "total_flos": 2.52423673883136e+17,
197
  "trial_name": null,
198
  "trial_params": null
199
  }
 
1
  {
2
  "best_metric": 0.9154545454545454,
3
  "best_model_checkpoint": "wav2vec2-base-finetuned-amd/checkpoint-290",
4
+ "epoch": 2.0,
5
+ "global_step": 580,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 4.977,
190
  "eval_steps_per_second": 0.156,
191
  "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.03,
195
+ "learning_rate": 2.413793103448276e-05,
196
+ "loss": 0.2694,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.07,
201
+ "learning_rate": 2.327586206896552e-05,
202
+ "loss": 0.247,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.1,
207
+ "learning_rate": 2.2413793103448276e-05,
208
+ "loss": 0.3238,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.14,
213
+ "learning_rate": 2.1551724137931033e-05,
214
+ "loss": 0.2553,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.17,
219
+ "learning_rate": 2.0689655172413793e-05,
220
+ "loss": 0.2761,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 1.21,
225
+ "learning_rate": 1.9827586206896554e-05,
226
+ "loss": 0.2304,
227
+ "step": 350
228
+ },
229
+ {
230
+ "epoch": 1.24,
231
+ "learning_rate": 1.896551724137931e-05,
232
+ "loss": 0.2309,
233
+ "step": 360
234
+ },
235
+ {
236
+ "epoch": 1.28,
237
+ "learning_rate": 1.810344827586207e-05,
238
+ "loss": 0.2566,
239
+ "step": 370
240
+ },
241
+ {
242
+ "epoch": 1.31,
243
+ "learning_rate": 1.7241379310344828e-05,
244
+ "loss": 0.2529,
245
+ "step": 380
246
+ },
247
+ {
248
+ "epoch": 1.34,
249
+ "learning_rate": 1.6379310344827585e-05,
250
+ "loss": 0.2176,
251
+ "step": 390
252
+ },
253
+ {
254
+ "epoch": 1.38,
255
+ "learning_rate": 1.5517241379310346e-05,
256
+ "loss": 0.2097,
257
+ "step": 400
258
+ },
259
+ {
260
+ "epoch": 1.41,
261
+ "learning_rate": 1.4655172413793103e-05,
262
+ "loss": 0.303,
263
+ "step": 410
264
+ },
265
+ {
266
+ "epoch": 1.45,
267
+ "learning_rate": 1.3793103448275863e-05,
268
+ "loss": 0.2871,
269
+ "step": 420
270
+ },
271
+ {
272
+ "epoch": 1.48,
273
+ "learning_rate": 1.2931034482758622e-05,
274
+ "loss": 0.2247,
275
+ "step": 430
276
+ },
277
+ {
278
+ "epoch": 1.52,
279
+ "learning_rate": 1.206896551724138e-05,
280
+ "loss": 0.3443,
281
+ "step": 440
282
+ },
283
+ {
284
+ "epoch": 1.55,
285
+ "learning_rate": 1.1206896551724138e-05,
286
+ "loss": 0.2057,
287
+ "step": 450
288
+ },
289
+ {
290
+ "epoch": 1.59,
291
+ "learning_rate": 1.0344827586206897e-05,
292
+ "loss": 0.2815,
293
+ "step": 460
294
+ },
295
+ {
296
+ "epoch": 1.62,
297
+ "learning_rate": 9.482758620689655e-06,
298
+ "loss": 0.2639,
299
+ "step": 470
300
+ },
301
+ {
302
+ "epoch": 1.66,
303
+ "learning_rate": 8.620689655172414e-06,
304
+ "loss": 0.2257,
305
+ "step": 480
306
+ },
307
+ {
308
+ "epoch": 1.69,
309
+ "learning_rate": 7.758620689655173e-06,
310
+ "loss": 0.2836,
311
+ "step": 490
312
+ },
313
+ {
314
+ "epoch": 1.72,
315
+ "learning_rate": 6.896551724137932e-06,
316
+ "loss": 0.2213,
317
+ "step": 500
318
+ },
319
+ {
320
+ "epoch": 1.76,
321
+ "learning_rate": 6.03448275862069e-06,
322
+ "loss": 0.2649,
323
+ "step": 510
324
+ },
325
+ {
326
+ "epoch": 1.79,
327
+ "learning_rate": 5.172413793103448e-06,
328
+ "loss": 0.1916,
329
+ "step": 520
330
+ },
331
+ {
332
+ "epoch": 1.83,
333
+ "learning_rate": 4.310344827586207e-06,
334
+ "loss": 0.2386,
335
+ "step": 530
336
+ },
337
+ {
338
+ "epoch": 1.86,
339
+ "learning_rate": 3.448275862068966e-06,
340
+ "loss": 0.2954,
341
+ "step": 540
342
+ },
343
+ {
344
+ "epoch": 1.9,
345
+ "learning_rate": 2.586206896551724e-06,
346
+ "loss": 0.2116,
347
+ "step": 550
348
+ },
349
+ {
350
+ "epoch": 1.93,
351
+ "learning_rate": 1.724137931034483e-06,
352
+ "loss": 0.2265,
353
+ "step": 560
354
+ },
355
+ {
356
+ "epoch": 1.97,
357
+ "learning_rate": 8.620689655172415e-07,
358
+ "loss": 0.2434,
359
+ "step": 570
360
+ },
361
+ {
362
+ "epoch": 2.0,
363
+ "learning_rate": 0.0,
364
+ "loss": 0.2864,
365
+ "step": 580
366
+ },
367
+ {
368
+ "epoch": 2.0,
369
+ "eval_accuracy": 0.8983636363636364,
370
+ "eval_loss": 0.25890666246414185,
371
+ "eval_runtime": 1202.4276,
372
+ "eval_samples_per_second": 4.574,
373
+ "eval_steps_per_second": 0.143,
374
+ "step": 580
375
  }
376
  ],
377
  "max_steps": 580,
378
  "num_train_epochs": 2,
379
+ "total_flos": 5.04847347766272e+17,
380
  "trial_name": null,
381
  "trial_params": null
382
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b30c75792e62f2dcfc9627e890f06989430395b3e7114124c88f2620a022c2d9
3
  size 378349481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe6005ae34709190bbb6221e7f2d78dd48218e4439610fec95a5e5629156fd1
3
  size 378349481