PereLluis13 commited on
Commit
2dd76c6
1 Parent(s): eb4c525

End of training

Browse files
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_loss": 0.3033297657966614,
4
- "eval_runtime": 395.7148,
5
  "eval_samples": 4297,
6
- "eval_samples_per_second": 10.859,
7
- "eval_steps_per_second": 0.341,
8
- "eval_wer": 0.19506011201512932,
9
- "train_loss": 0.46717894900821066,
10
- "train_runtime": 42700.8803,
11
  "train_samples": 240334,
12
- "train_samples_per_second": 16.885,
13
- "train_steps_per_second": 0.132
14
  }
 
1
  {
2
+ "epoch": 6.0,
3
+ "eval_loss": 0.27584555745124817,
4
+ "eval_runtime": 371.4251,
5
  "eval_samples": 4297,
6
+ "eval_samples_per_second": 11.569,
7
+ "eval_steps_per_second": 0.363,
8
+ "eval_wer": 0.17918264285046293,
9
+ "train_loss": 0.5975231319014925,
10
+ "train_runtime": 88923.2167,
11
  "train_samples": 240334,
12
+ "train_samples_per_second": 16.216,
13
+ "train_steps_per_second": 0.127
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_loss": 0.3033297657966614,
4
- "eval_runtime": 395.7148,
5
  "eval_samples": 4297,
6
- "eval_samples_per_second": 10.859,
7
- "eval_steps_per_second": 0.341,
8
- "eval_wer": 0.19506011201512932
9
  }
 
1
  {
2
+ "epoch": 6.0,
3
+ "eval_loss": 0.27584555745124817,
4
+ "eval_runtime": 371.4251,
5
  "eval_samples": 4297,
6
+ "eval_samples_per_second": 11.569,
7
+ "eval_steps_per_second": 0.363,
8
+ "eval_wer": 0.17918264285046293
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a05be9118ae044d3c6958be4c34d587836260410070d92f1137dca25860b760
3
  size 1262112241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89ec5de9dd87da4f2a4c2382f07f15a131a2b2c9de36a7ae27f30c07f7e2540
3
  size 1262112241
runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60869ad2db0b6adf88d1fcfa5c0248d385effdf7ebc963a710fb67b170b81db3
3
- size 5695
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247dfe6bd0d58cb74bf4ef78970d1f112256fcf3df6fe455135e580b51f0fe3
3
+ size 10324
runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643549374.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea16ea09e4540e71e147fec1294192500786f27cab5e5cc71cbb8e3a338092a
3
+ size 358
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 0.46717894900821066,
4
- "train_runtime": 42700.8803,
5
  "train_samples": 240334,
6
- "train_samples_per_second": 16.885,
7
- "train_steps_per_second": 0.132
8
  }
 
1
  {
2
+ "epoch": 6.0,
3
+ "train_loss": 0.5975231319014925,
4
+ "train_runtime": 88923.2167,
5
  "train_samples": 240334,
6
+ "train_samples_per_second": 16.216,
7
+ "train_steps_per_second": 0.127
8
  }
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.9996005858074826,
5
- "global_step": 5631,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -173,18 +173,183 @@
173
  "step": 5500
174
  },
175
  {
176
- "epoch": 3.0,
177
- "step": 5631,
178
- "total_flos": 1.4549289807228204e+20,
179
- "train_loss": 0.46717894900821066,
180
- "train_runtime": 42700.8803,
181
- "train_samples_per_second": 16.885,
182
- "train_steps_per_second": 0.132
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  }
184
  ],
185
- "max_steps": 5631,
186
- "num_train_epochs": 3,
187
- "total_flos": 1.4549289807228204e+20,
188
  "trial_name": null,
189
  "trial_params": null
190
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.999600585807483,
5
+ "global_step": 11262,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
173
  "step": 5500
174
  },
175
  {
176
+ "epoch": 3.2,
177
+ "learning_rate": 4.263388037141005e-05,
178
+ "loss": 1.213,
179
+ "step": 6000
180
+ },
181
+ {
182
+ "epoch": 3.2,
183
+ "eval_loss": 0.3051116168498993,
184
+ "eval_runtime": 371.5477,
185
+ "eval_samples_per_second": 11.565,
186
+ "eval_steps_per_second": 0.363,
187
+ "eval_wer": 0.19797998690732255,
188
+ "step": 6000
189
+ },
190
+ {
191
+ "epoch": 3.46,
192
+ "learning_rate": 3.8585078816670256e-05,
193
+ "loss": 1.2074,
194
+ "step": 6500
195
+ },
196
+ {
197
+ "epoch": 3.46,
198
+ "eval_loss": 0.3011966645717621,
199
+ "eval_runtime": 372.0587,
200
+ "eval_samples_per_second": 11.549,
201
+ "eval_steps_per_second": 0.363,
202
+ "eval_wer": 0.18792148549934018,
203
+ "step": 6500
204
+ },
205
+ {
206
+ "epoch": 3.73,
207
+ "learning_rate": 3.4536277261930465e-05,
208
+ "loss": 1.1918,
209
+ "step": 7000
210
+ },
211
+ {
212
+ "epoch": 3.73,
213
+ "eval_loss": 0.29471954703330994,
214
+ "eval_runtime": 372.8767,
215
+ "eval_samples_per_second": 11.524,
216
+ "eval_steps_per_second": 0.362,
217
+ "eval_wer": 0.18287145276764655,
218
+ "step": 7000
219
+ },
220
+ {
221
+ "epoch": 4.0,
222
+ "learning_rate": 3.0487475707190668e-05,
223
+ "loss": 1.1893,
224
+ "step": 7500
225
+ },
226
+ {
227
+ "epoch": 4.0,
228
+ "eval_loss": 0.28953900933265686,
229
+ "eval_runtime": 372.4558,
230
+ "eval_samples_per_second": 11.537,
231
+ "eval_steps_per_second": 0.362,
232
+ "eval_wer": 0.1807205129004437,
233
+ "step": 7500
234
+ },
235
+ {
236
+ "epoch": 4.26,
237
+ "learning_rate": 2.643867415245087e-05,
238
+ "loss": 1.1751,
239
+ "step": 8000
240
+ },
241
+ {
242
+ "epoch": 4.26,
243
+ "eval_loss": 0.2877567410469055,
244
+ "eval_runtime": 371.9244,
245
+ "eval_samples_per_second": 11.553,
246
+ "eval_steps_per_second": 0.363,
247
+ "eval_wer": 0.17759281773122604,
248
+ "step": 8000
249
+ },
250
+ {
251
+ "epoch": 4.53,
252
+ "learning_rate": 2.2389872597711073e-05,
253
+ "loss": 1.1628,
254
+ "step": 8500
255
+ },
256
+ {
257
+ "epoch": 4.53,
258
+ "eval_loss": 0.28352275490760803,
259
+ "eval_runtime": 373.4388,
260
+ "eval_samples_per_second": 11.507,
261
+ "eval_steps_per_second": 0.362,
262
+ "eval_wer": 0.1730727267059447,
263
+ "step": 8500
264
+ },
265
+ {
266
+ "epoch": 4.79,
267
+ "learning_rate": 1.834107104297128e-05,
268
+ "loss": 1.1577,
269
+ "step": 9000
270
+ },
271
+ {
272
+ "epoch": 4.79,
273
+ "eval_loss": 0.28156954050064087,
274
+ "eval_runtime": 371.5997,
275
+ "eval_samples_per_second": 11.564,
276
+ "eval_steps_per_second": 0.363,
277
+ "eval_wer": 0.17605494768124527,
278
+ "step": 9000
279
+ },
280
+ {
281
+ "epoch": 5.06,
282
+ "learning_rate": 1.4300367091340963e-05,
283
+ "loss": 1.1448,
284
+ "step": 9500
285
+ },
286
+ {
287
+ "epoch": 5.06,
288
+ "eval_loss": 0.2757455110549927,
289
+ "eval_runtime": 373.7148,
290
+ "eval_samples_per_second": 11.498,
291
+ "eval_steps_per_second": 0.361,
292
+ "eval_wer": 0.17397674491100096,
293
+ "step": 9500
294
+ },
295
+ {
296
+ "epoch": 5.33,
297
+ "learning_rate": 1.0251565536601165e-05,
298
+ "loss": 1.1407,
299
+ "step": 10000
300
+ },
301
+ {
302
+ "epoch": 5.33,
303
+ "eval_loss": 0.2768358588218689,
304
+ "eval_runtime": 373.2273,
305
+ "eval_samples_per_second": 11.513,
306
+ "eval_steps_per_second": 0.362,
307
+ "eval_wer": 0.17976453962613131,
308
+ "step": 10000
309
+ },
310
+ {
311
+ "epoch": 5.59,
312
+ "learning_rate": 6.202763981861369e-06,
313
+ "loss": 1.1401,
314
+ "step": 10500
315
+ },
316
+ {
317
+ "epoch": 5.59,
318
+ "eval_loss": 0.2780420780181885,
319
+ "eval_runtime": 375.3753,
320
+ "eval_samples_per_second": 11.447,
321
+ "eval_steps_per_second": 0.36,
322
+ "eval_wer": 0.18160374907779753,
323
+ "step": 10500
324
+ },
325
+ {
326
+ "epoch": 5.86,
327
+ "learning_rate": 2.153962427121572e-06,
328
+ "loss": 1.1333,
329
+ "step": 11000
330
+ },
331
+ {
332
+ "epoch": 5.86,
333
+ "eval_loss": 0.2748132646083832,
334
+ "eval_runtime": 371.6352,
335
+ "eval_samples_per_second": 11.562,
336
+ "eval_steps_per_second": 0.363,
337
+ "eval_wer": 0.17495350021301578,
338
+ "step": 11000
339
+ },
340
+ {
341
+ "epoch": 6.0,
342
+ "step": 11262,
343
+ "total_flos": 3.063803468240281e+20,
344
+ "train_loss": 0.5975231319014925,
345
+ "train_runtime": 88923.2167,
346
+ "train_samples_per_second": 16.216,
347
+ "train_steps_per_second": 0.127
348
  }
349
  ],
350
+ "max_steps": 11262,
351
+ "num_train_epochs": 6,
352
+ "total_flos": 3.063803468240281e+20,
353
  "trial_name": null,
354
  "trial_params": null
355
  }