memepottaboah commited on
Commit
8a518e4
1 Parent(s): dc39050

End of training

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +497 -0
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: peft
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-melody
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: musicgen-POPMUSIC1981-melody
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-POPMUSIC1981-melody
16
 
17
- This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-melody
5
  tags:
6
+ - text-to-audio
7
+ - memepottaboah/POPMUSIC1981
8
  - generated_from_trainer
9
  model-index:
10
  - name: musicgen-POPMUSIC1981-melody
 
16
 
17
  # musicgen-POPMUSIC1981-melody
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the MEMEPOTTABOAH/POPMUSIC1981 - DEFAULT dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.6716417910447765,
3
+ "total_flos": 46267156615872.0,
4
+ "train_loss": 7.157758657748882,
5
+ "train_runtime": 2311.3066,
6
+ "train_samples": 268,
7
+ "train_samples_per_second": 0.58,
8
+ "train_steps_per_second": 0.028
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.6716417910447765,
3
+ "total_flos": 46267156615872.0,
4
+ "train_loss": 7.157758657748882,
5
+ "train_runtime": 2311.3066,
6
+ "train_samples": 268,
7
+ "train_samples_per_second": 0.58,
8
+ "train_steps_per_second": 0.028
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.6716417910447765,
5
+ "eval_steps": 500,
6
+ "global_step": 65,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07462686567164178,
13
+ "grad_norm": 11.831602096557617,
14
+ "learning_rate": 0.00019692307692307696,
15
+ "loss": 9.5753,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14925373134328357,
20
+ "grad_norm": 10.040313720703125,
21
+ "learning_rate": 0.00019384615384615385,
22
+ "loss": 9.3879,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.22388059701492538,
27
+ "grad_norm": 11.504229545593262,
28
+ "learning_rate": 0.0001907692307692308,
29
+ "loss": 9.2222,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.29850746268656714,
34
+ "grad_norm": 13.777145385742188,
35
+ "learning_rate": 0.0001876923076923077,
36
+ "loss": 9.0187,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.373134328358209,
41
+ "grad_norm": 16.53196907043457,
42
+ "learning_rate": 0.00018461538461538463,
43
+ "loss": 8.8251,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.44776119402985076,
48
+ "grad_norm": 23.02943229675293,
49
+ "learning_rate": 0.00018153846153846155,
50
+ "loss": 8.4652,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.5223880597014925,
55
+ "grad_norm": 20.641206741333008,
56
+ "learning_rate": 0.00017846153846153847,
57
+ "loss": 8.1413,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5970149253731343,
62
+ "grad_norm": 16.40256690979004,
63
+ "learning_rate": 0.0001753846153846154,
64
+ "loss": 7.9036,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6716417910447762,
69
+ "grad_norm": 19.79137420654297,
70
+ "learning_rate": 0.00017230769230769234,
71
+ "loss": 7.8958,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.746268656716418,
76
+ "grad_norm": 10.174325942993164,
77
+ "learning_rate": 0.00016923076923076923,
78
+ "loss": 7.6606,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8208955223880597,
83
+ "grad_norm": 11.052704811096191,
84
+ "learning_rate": 0.00016615384615384617,
85
+ "loss": 7.6561,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8955223880597015,
90
+ "grad_norm": 12.233122825622559,
91
+ "learning_rate": 0.0001630769230769231,
92
+ "loss": 7.5328,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9701492537313433,
97
+ "grad_norm": 10.275497436523438,
98
+ "learning_rate": 0.00016,
99
+ "loss": 7.4978,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.0,
104
+ "grad_norm": 7.3966779708862305,
105
+ "learning_rate": 0.00015692307692307693,
106
+ "loss": 3.0154,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0746268656716418,
111
+ "grad_norm": 13.597101211547852,
112
+ "learning_rate": 0.00015384615384615385,
113
+ "loss": 7.3022,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1492537313432836,
118
+ "grad_norm": 12.541572570800781,
119
+ "learning_rate": 0.00015076923076923077,
120
+ "loss": 7.4243,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2238805970149254,
125
+ "grad_norm": 7.609414577484131,
126
+ "learning_rate": 0.00014769230769230772,
127
+ "loss": 7.3352,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.2985074626865671,
132
+ "grad_norm": 8.79019546508789,
133
+ "learning_rate": 0.0001446153846153846,
134
+ "loss": 7.3403,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.373134328358209,
139
+ "grad_norm": 7.513161659240723,
140
+ "learning_rate": 0.00014153846153846156,
141
+ "loss": 7.3048,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4477611940298507,
146
+ "grad_norm": Infinity,
147
+ "learning_rate": 0.00014153846153846156,
148
+ "loss": 7.3934,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5223880597014925,
153
+ "grad_norm": 11.386406898498535,
154
+ "learning_rate": 0.00013846153846153847,
155
+ "loss": 7.2708,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.5970149253731343,
160
+ "grad_norm": NaN,
161
+ "learning_rate": 0.00013846153846153847,
162
+ "loss": 7.2549,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.671641791044776,
167
+ "grad_norm": 9.923229217529297,
168
+ "learning_rate": 0.0001353846153846154,
169
+ "loss": 7.3161,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7462686567164178,
174
+ "grad_norm": 7.624272346496582,
175
+ "learning_rate": 0.0001323076923076923,
176
+ "loss": 7.2844,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8208955223880596,
181
+ "grad_norm": 6.796629905700684,
182
+ "learning_rate": 0.00012923076923076923,
183
+ "loss": 7.2594,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8955223880597014,
188
+ "grad_norm": 5.520105838775635,
189
+ "learning_rate": 0.00012615384615384615,
190
+ "loss": 7.2639,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9701492537313432,
195
+ "grad_norm": 5.706660270690918,
196
+ "learning_rate": 0.0001230769230769231,
197
+ "loss": 7.2271,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.0,
202
+ "grad_norm": 4.667247295379639,
203
+ "learning_rate": 0.00012,
204
+ "loss": 2.942,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.074626865671642,
209
+ "grad_norm": 8.385282516479492,
210
+ "learning_rate": 0.00011692307692307694,
211
+ "loss": 7.1126,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1492537313432836,
216
+ "grad_norm": 4.17704963684082,
217
+ "learning_rate": 0.00011384615384615384,
218
+ "loss": 7.2177,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2238805970149254,
223
+ "grad_norm": 7.29147481918335,
224
+ "learning_rate": 0.00011076923076923077,
225
+ "loss": 7.2731,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.298507462686567,
230
+ "grad_norm": 5.086247444152832,
231
+ "learning_rate": 0.0001076923076923077,
232
+ "loss": 7.1494,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.373134328358209,
237
+ "grad_norm": 4.92710542678833,
238
+ "learning_rate": 0.00010461538461538463,
239
+ "loss": 7.1479,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4477611940298507,
244
+ "grad_norm": 5.310170650482178,
245
+ "learning_rate": 0.00010153846153846153,
246
+ "loss": 7.1172,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5223880597014925,
251
+ "grad_norm": 5.681138515472412,
252
+ "learning_rate": 9.846153846153848e-05,
253
+ "loss": 7.1665,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.5970149253731343,
258
+ "grad_norm": 6.48416805267334,
259
+ "learning_rate": 9.53846153846154e-05,
260
+ "loss": 7.229,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.671641791044776,
265
+ "grad_norm": 7.22155237197876,
266
+ "learning_rate": 9.230769230769232e-05,
267
+ "loss": 7.2443,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.746268656716418,
272
+ "grad_norm": 5.244325160980225,
273
+ "learning_rate": 8.923076923076924e-05,
274
+ "loss": 7.1864,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8208955223880596,
279
+ "grad_norm": 6.491042613983154,
280
+ "learning_rate": 8.615384615384617e-05,
281
+ "loss": 7.1403,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.8955223880597014,
286
+ "grad_norm": 4.748079299926758,
287
+ "learning_rate": 8.307692307692309e-05,
288
+ "loss": 7.2464,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.970149253731343,
293
+ "grad_norm": 4.683705806732178,
294
+ "learning_rate": 8e-05,
295
+ "loss": 7.1566,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 3.0,
300
+ "grad_norm": 8.315367698669434,
301
+ "learning_rate": 7.692307692307693e-05,
302
+ "loss": 2.7335,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 3.074626865671642,
307
+ "grad_norm": 8.71499252319336,
308
+ "learning_rate": 7.384615384615386e-05,
309
+ "loss": 7.0353,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 3.1492537313432836,
314
+ "grad_norm": 4.421390056610107,
315
+ "learning_rate": 7.076923076923078e-05,
316
+ "loss": 7.1684,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 3.2238805970149254,
321
+ "grad_norm": 4.962438106536865,
322
+ "learning_rate": 6.76923076923077e-05,
323
+ "loss": 7.0518,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 3.298507462686567,
328
+ "grad_norm": 4.061994552612305,
329
+ "learning_rate": 6.461538461538462e-05,
330
+ "loss": 7.0753,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 3.373134328358209,
335
+ "grad_norm": 10.23737621307373,
336
+ "learning_rate": 6.153846153846155e-05,
337
+ "loss": 7.2593,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.4477611940298507,
342
+ "grad_norm": 5.402864456176758,
343
+ "learning_rate": 5.846153846153847e-05,
344
+ "loss": 7.1255,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.5223880597014925,
349
+ "grad_norm": 7.442513465881348,
350
+ "learning_rate": 5.538461538461539e-05,
351
+ "loss": 6.9086,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 3.5970149253731343,
356
+ "grad_norm": 12.119452476501465,
357
+ "learning_rate": 5.230769230769231e-05,
358
+ "loss": 7.2655,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 3.671641791044776,
363
+ "grad_norm": 4.1253156661987305,
364
+ "learning_rate": 4.923076923076924e-05,
365
+ "loss": 7.129,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 3.746268656716418,
370
+ "grad_norm": 7.582332611083984,
371
+ "learning_rate": 4.615384615384616e-05,
372
+ "loss": 7.1866,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 3.8208955223880596,
377
+ "grad_norm": 9.213349342346191,
378
+ "learning_rate": 4.3076923076923084e-05,
379
+ "loss": 7.2262,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 3.8955223880597014,
384
+ "grad_norm": 4.230329513549805,
385
+ "learning_rate": 4e-05,
386
+ "loss": 7.0612,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 3.970149253731343,
391
+ "grad_norm": 3.959320545196533,
392
+ "learning_rate": 3.692307692307693e-05,
393
+ "loss": 7.095,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 4.0,
398
+ "grad_norm": 2.782017469406128,
399
+ "learning_rate": 3.384615384615385e-05,
400
+ "loss": 2.8985,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 4.074626865671641,
405
+ "grad_norm": 8.111074447631836,
406
+ "learning_rate": 3.0769230769230774e-05,
407
+ "loss": 7.0008,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 4.149253731343284,
412
+ "grad_norm": 3.9246532917022705,
413
+ "learning_rate": 2.7692307692307694e-05,
414
+ "loss": 7.1253,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 4.223880597014926,
419
+ "grad_norm": 11.857646942138672,
420
+ "learning_rate": 2.461538461538462e-05,
421
+ "loss": 6.9411,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 4.298507462686567,
426
+ "grad_norm": 2.8319931030273438,
427
+ "learning_rate": 2.1538461538461542e-05,
428
+ "loss": 7.1616,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 4.373134328358209,
433
+ "grad_norm": 3.061171293258667,
434
+ "learning_rate": 1.8461538461538465e-05,
435
+ "loss": 7.1291,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 4.447761194029851,
440
+ "grad_norm": 5.19327449798584,
441
+ "learning_rate": 1.5384615384615387e-05,
442
+ "loss": 7.1867,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 4.522388059701493,
447
+ "grad_norm": 3.0203020572662354,
448
+ "learning_rate": 1.230769230769231e-05,
449
+ "loss": 7.1364,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 4.597014925373134,
454
+ "grad_norm": 3.957735300064087,
455
+ "learning_rate": 9.230769230769232e-06,
456
+ "loss": 7.139,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 4.6716417910447765,
461
+ "grad_norm": 4.099056243896484,
462
+ "learning_rate": 6.153846153846155e-06,
463
+ "loss": 7.1104,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 4.6716417910447765,
468
+ "step": 65,
469
+ "total_flos": 46267156615872.0,
470
+ "train_loss": 7.157758657748882,
471
+ "train_runtime": 2311.3066,
472
+ "train_samples_per_second": 0.58,
473
+ "train_steps_per_second": 0.028
474
+ }
475
+ ],
476
+ "logging_steps": 1.0,
477
+ "max_steps": 65,
478
+ "num_input_tokens_seen": 0,
479
+ "num_train_epochs": 5,
480
+ "save_steps": 500,
481
+ "stateful_callbacks": {
482
+ "TrainerControl": {
483
+ "args": {
484
+ "should_epoch_stop": false,
485
+ "should_evaluate": false,
486
+ "should_log": false,
487
+ "should_save": true,
488
+ "should_training_stop": true
489
+ },
490
+ "attributes": {}
491
+ }
492
+ },
493
+ "total_flos": 46267156615872.0,
494
+ "train_batch_size": 2,
495
+ "trial_name": null,
496
+ "trial_params": null
497
+ }