taufiqsyed commited on
Commit
5f7ec59
·
verified ·
1 Parent(s): af26047

End of training

Browse files
Files changed (5) hide show
  1. README.md +5 -3
  2. all_results.json +15 -0
  3. eval_results.json +9 -0
  4. train_results.json +9 -0
  5. trainer_state.json +799 -0
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: peft
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-small
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: salami_truncsplit_dora_model
@@ -14,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # salami_truncsplit_dora_model
16
 
17
- This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.7648
20
- - Clap: 0.2040
21
 
22
  ## Model description
23
 
 
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-small
5
  tags:
6
+ - text-to-audio
7
+ - taufiqsyed/salami_cleaned_sampled
8
  - generated_from_trainer
9
  model-index:
10
  - name: salami_truncsplit_dora_model
 
16
 
17
  # salami_truncsplit_dora_model
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the TAUFIQSYED/SALAMI_CLEANED_SAMPLED - DEFAULT dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.7649
22
+ - Clap: 0.1996
23
 
24
  ## Model description
25
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9915764139590855,
3
+ "eval_clap": 0.1995842158794403,
4
+ "eval_loss": 3.7649130821228027,
5
+ "eval_runtime": 556.0933,
6
+ "eval_samples": 32,
7
+ "eval_samples_per_second": 0.058,
8
+ "eval_steps_per_second": 0.058,
9
+ "total_flos": 168544032748224.0,
10
+ "train_loss": 8.598374061214114,
11
+ "train_runtime": 2970.9735,
12
+ "train_samples": 831,
13
+ "train_samples_per_second": 0.28,
14
+ "train_steps_per_second": 0.035
15
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9915764139590855,
3
+ "eval_clap": 0.1995842158794403,
4
+ "eval_loss": 3.7649130821228027,
5
+ "eval_runtime": 556.0933,
6
+ "eval_samples": 32,
7
+ "eval_samples_per_second": 0.058,
8
+ "eval_steps_per_second": 0.058
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9915764139590855,
3
+ "total_flos": 168544032748224.0,
4
+ "train_loss": 8.598374061214114,
5
+ "train_runtime": 2970.9735,
6
+ "train_samples": 831,
7
+ "train_samples_per_second": 0.28,
8
+ "train_steps_per_second": 0.035
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,799 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9915764139590855,
5
+ "eval_steps": 25,
6
+ "global_step": 103,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009626955475330927,
13
+ "grad_norm": 76.00760650634766,
14
+ "learning_rate": 9.997674418116759e-06,
15
+ "loss": 10.061,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019253910950661854,
20
+ "grad_norm": 68.17976379394531,
21
+ "learning_rate": 9.99069983579947e-06,
22
+ "loss": 9.9795,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02888086642599278,
27
+ "grad_norm": 46.292236328125,
28
+ "learning_rate": 9.979082741033047e-06,
29
+ "loss": 9.5387,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03850782190132371,
34
+ "grad_norm": Infinity,
35
+ "learning_rate": 9.979082741033047e-06,
36
+ "loss": 9.6955,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.048134777376654635,
41
+ "grad_norm": 55.74091720581055,
42
+ "learning_rate": 9.96283394041954e-06,
43
+ "loss": 9.7291,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05776173285198556,
48
+ "grad_norm": Infinity,
49
+ "learning_rate": 9.96283394041954e-06,
50
+ "loss": 9.7559,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06738868832731648,
55
+ "grad_norm": 74.81217956542969,
56
+ "learning_rate": 9.941968549125481e-06,
57
+ "loss": 9.8749,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07701564380264742,
62
+ "grad_norm": 93.73560333251953,
63
+ "learning_rate": 9.916505976821262e-06,
64
+ "loss": 9.9976,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08664259927797834,
69
+ "grad_norm": 66.94046020507812,
70
+ "learning_rate": 9.886469909625624e-06,
71
+ "loss": 9.8316,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09626955475330927,
76
+ "grad_norm": 51.51335144042969,
77
+ "learning_rate": 9.851888288072053e-06,
78
+ "loss": 9.653,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10589651022864019,
83
+ "grad_norm": 58.80746078491211,
84
+ "learning_rate": 9.81279328111758e-06,
85
+ "loss": 9.6294,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.11552346570397112,
90
+ "grad_norm": 49.534664154052734,
91
+ "learning_rate": 9.769221256218165e-06,
92
+ "loss": 9.5226,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.12515042117930206,
97
+ "grad_norm": 50.32096862792969,
98
+ "learning_rate": 9.721212745498493e-06,
99
+ "loss": 9.4886,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.13477737665463296,
104
+ "grad_norm": 72.49077606201172,
105
+ "learning_rate": 9.66881240804768e-06,
106
+ "loss": 9.7044,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1444043321299639,
111
+ "grad_norm": 65.09030151367188,
112
+ "learning_rate": 9.612068988375898e-06,
113
+ "loss": 9.596,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.15403128760529483,
118
+ "grad_norm": 51.388729095458984,
119
+ "learning_rate": 9.551035271070665e-06,
120
+ "loss": 9.4844,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.16365824308062576,
125
+ "grad_norm": 65.17435455322266,
126
+ "learning_rate": 9.485768031694872e-06,
127
+ "loss": 9.5644,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.17328519855595667,
132
+ "grad_norm": 71.97167205810547,
133
+ "learning_rate": 9.416327983972304e-06,
134
+ "loss": 9.574,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.1829121540312876,
139
+ "grad_norm": 61.208251953125,
140
+ "learning_rate": 9.342779723309746e-06,
141
+ "loss": 9.4448,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.19253910950661854,
146
+ "grad_norm": 53.587589263916016,
147
+ "learning_rate": 9.26519166670821e-06,
148
+ "loss": 9.3692,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.20216606498194944,
153
+ "grad_norm": 46.41638946533203,
154
+ "learning_rate": 9.183635989119211e-06,
155
+ "loss": 9.3402,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.21179302045728038,
160
+ "grad_norm": 57.22797393798828,
161
+ "learning_rate": 9.098188556305262e-06,
162
+ "loss": 9.3307,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.2214199759326113,
167
+ "grad_norm": 69.78112030029297,
168
+ "learning_rate": 9.008928854267054e-06,
169
+ "loss": 9.344,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.23104693140794225,
174
+ "grad_norm": 98.2169418334961,
175
+ "learning_rate": 8.91593991530297e-06,
176
+ "loss": 9.3648,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.24067388688327315,
181
+ "grad_norm": 62.788787841796875,
182
+ "learning_rate": 8.819308240769726e-06,
183
+ "loss": 9.2964,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.24067388688327315,
188
+ "eval_clap": 0.2401558756828308,
189
+ "eval_loss": 3.682433843612671,
190
+ "eval_runtime": 555.3456,
191
+ "eval_samples_per_second": 0.058,
192
+ "eval_steps_per_second": 0.058,
193
+ "step": 25
194
+ },
195
+ {
196
+ "epoch": 0.2503008423586041,
197
+ "grad_norm": 67.70946502685547,
198
+ "learning_rate": 8.71912372061598e-06,
199
+ "loss": 9.2203,
200
+ "step": 26
201
+ },
202
+ {
203
+ "epoch": 0.259927797833935,
204
+ "grad_norm": 55.66056442260742,
205
+ "learning_rate": 8.615479549763756e-06,
206
+ "loss": 9.1849,
207
+ "step": 27
208
+ },
209
+ {
210
+ "epoch": 0.2695547533092659,
211
+ "grad_norm": 50.55543518066406,
212
+ "learning_rate": 8.508472141415468e-06,
213
+ "loss": 9.1337,
214
+ "step": 28
215
+ },
216
+ {
217
+ "epoch": 0.27918170878459686,
218
+ "grad_norm": 44.69493103027344,
219
+ "learning_rate": 8.398201037367202e-06,
220
+ "loss": 9.1279,
221
+ "step": 29
222
+ },
223
+ {
224
+ "epoch": 0.2888086642599278,
225
+ "grad_norm": 45.56080627441406,
226
+ "learning_rate": 8.284768815411693e-06,
227
+ "loss": 9.1314,
228
+ "step": 30
229
+ },
230
+ {
231
+ "epoch": 0.29843561973525873,
232
+ "grad_norm": 49.1536979675293,
233
+ "learning_rate": 8.168280993917078e-06,
234
+ "loss": 9.0014,
235
+ "step": 31
236
+ },
237
+ {
238
+ "epoch": 0.30806257521058966,
239
+ "grad_norm": 80.88127136230469,
240
+ "learning_rate": 8.048845933670274e-06,
241
+ "loss": 9.0433,
242
+ "step": 32
243
+ },
244
+ {
245
+ "epoch": 0.3176895306859206,
246
+ "grad_norm": 56.1622200012207,
247
+ "learning_rate": 7.92657473707621e-06,
248
+ "loss": 8.9263,
249
+ "step": 33
250
+ },
251
+ {
252
+ "epoch": 0.32731648616125153,
253
+ "grad_norm": 90.87548828125,
254
+ "learning_rate": 7.801581144806752e-06,
255
+ "loss": 8.9342,
256
+ "step": 34
257
+ },
258
+ {
259
+ "epoch": 0.3369434416365824,
260
+ "grad_norm": 71.51224517822266,
261
+ "learning_rate": 7.673981429995372e-06,
262
+ "loss": 8.9876,
263
+ "step": 35
264
+ },
265
+ {
266
+ "epoch": 0.34657039711191334,
267
+ "grad_norm": 74.96617889404297,
268
+ "learning_rate": 7.5438942900761035e-06,
269
+ "loss": 8.9411,
270
+ "step": 36
271
+ },
272
+ {
273
+ "epoch": 0.3561973525872443,
274
+ "grad_norm": 65.20315551757812,
275
+ "learning_rate": 7.411440736367281e-06,
276
+ "loss": 8.8483,
277
+ "step": 37
278
+ },
279
+ {
280
+ "epoch": 0.3658243080625752,
281
+ "grad_norm": 88.80438232421875,
282
+ "learning_rate": 7.276743981502856e-06,
283
+ "loss": 8.854,
284
+ "step": 38
285
+ },
286
+ {
287
+ "epoch": 0.37545126353790614,
288
+ "grad_norm": 57.63005065917969,
289
+ "learning_rate": 7.139929324815965e-06,
290
+ "loss": 8.7488,
291
+ "step": 39
292
+ },
293
+ {
294
+ "epoch": 0.3850782190132371,
295
+ "grad_norm": 68.39657592773438,
296
+ "learning_rate": 7.00112403578139e-06,
297
+ "loss": 8.6557,
298
+ "step": 40
299
+ },
300
+ {
301
+ "epoch": 0.394705174488568,
302
+ "grad_norm": Infinity,
303
+ "learning_rate": 7.00112403578139e-06,
304
+ "loss": 8.6279,
305
+ "step": 41
306
+ },
307
+ {
308
+ "epoch": 0.4043321299638989,
309
+ "grad_norm": 60.18503189086914,
310
+ "learning_rate": 6.860457235625322e-06,
311
+ "loss": 8.7681,
312
+ "step": 42
313
+ },
314
+ {
315
+ "epoch": 0.4139590854392298,
316
+ "grad_norm": 47.89727020263672,
317
+ "learning_rate": 6.7180597772125665e-06,
318
+ "loss": 8.6985,
319
+ "step": 43
320
+ },
321
+ {
322
+ "epoch": 0.42358604091456076,
323
+ "grad_norm": 67.0323486328125,
324
+ "learning_rate": 6.574064123322925e-06,
325
+ "loss": 8.8191,
326
+ "step": 44
327
+ },
328
+ {
329
+ "epoch": 0.4332129963898917,
330
+ "grad_norm": 81.16446685791016,
331
+ "learning_rate": 6.42860422342998e-06,
332
+ "loss": 8.4126,
333
+ "step": 45
334
+ },
335
+ {
336
+ "epoch": 0.4428399518652226,
337
+ "grad_norm": 60.89363479614258,
338
+ "learning_rate": 6.281815389096903e-06,
339
+ "loss": 8.5561,
340
+ "step": 46
341
+ },
342
+ {
343
+ "epoch": 0.45246690734055356,
344
+ "grad_norm": 65.52593994140625,
345
+ "learning_rate": 6.133834168105206e-06,
346
+ "loss": 8.4911,
347
+ "step": 47
348
+ },
349
+ {
350
+ "epoch": 0.4620938628158845,
351
+ "grad_norm": 51.18860626220703,
352
+ "learning_rate": 5.9847982174335314e-06,
353
+ "loss": 8.5119,
354
+ "step": 48
355
+ },
356
+ {
357
+ "epoch": 0.4717208182912154,
358
+ "grad_norm": 82.5036392211914,
359
+ "learning_rate": 5.834846175204612e-06,
360
+ "loss": 8.416,
361
+ "step": 49
362
+ },
363
+ {
364
+ "epoch": 0.4813477737665463,
365
+ "grad_norm": 51.89071273803711,
366
+ "learning_rate": 5.684117531719552e-06,
367
+ "loss": 8.4519,
368
+ "step": 50
369
+ },
370
+ {
371
+ "epoch": 0.4813477737665463,
372
+ "eval_clap": 0.22033847868442535,
373
+ "eval_loss": 3.708993673324585,
374
+ "eval_runtime": 557.8096,
375
+ "eval_samples_per_second": 0.057,
376
+ "eval_steps_per_second": 0.057,
377
+ "step": 50
378
+ },
379
+ {
380
+ "epoch": 0.49097472924187724,
381
+ "grad_norm": 52.55020523071289,
382
+ "learning_rate": 5.532752499699381e-06,
383
+ "loss": 8.4129,
384
+ "step": 51
385
+ },
386
+ {
387
+ "epoch": 0.5006016847172082,
388
+ "grad_norm": 51.49772644042969,
389
+ "learning_rate": 5.380891883854591e-06,
390
+ "loss": 8.4629,
391
+ "step": 52
392
+ },
393
+ {
394
+ "epoch": 0.5102286401925391,
395
+ "grad_norm": 61.926124572753906,
396
+ "learning_rate": 5.228676949903974e-06,
397
+ "loss": 8.3679,
398
+ "step": 53
399
+ },
400
+ {
401
+ "epoch": 0.51985559566787,
402
+ "grad_norm": 52.0053825378418,
403
+ "learning_rate": 5.07624929316463e-06,
404
+ "loss": 8.4213,
405
+ "step": 54
406
+ },
407
+ {
408
+ "epoch": 0.529482551143201,
409
+ "grad_norm": 57.23885726928711,
410
+ "learning_rate": 4.923750706835371e-06,
411
+ "loss": 8.436,
412
+ "step": 55
413
+ },
414
+ {
415
+ "epoch": 0.5391095066185319,
416
+ "grad_norm": 42.909393310546875,
417
+ "learning_rate": 4.771323050096028e-06,
418
+ "loss": 8.4824,
419
+ "step": 56
420
+ },
421
+ {
422
+ "epoch": 0.5487364620938628,
423
+ "grad_norm": 66.2441635131836,
424
+ "learning_rate": 4.619108116145411e-06,
425
+ "loss": 8.1536,
426
+ "step": 57
427
+ },
428
+ {
429
+ "epoch": 0.5583634175691937,
430
+ "grad_norm": 40.68450927734375,
431
+ "learning_rate": 4.467247500300621e-06,
432
+ "loss": 8.437,
433
+ "step": 58
434
+ },
435
+ {
436
+ "epoch": 0.5679903730445247,
437
+ "grad_norm": 42.75899887084961,
438
+ "learning_rate": 4.31588246828045e-06,
439
+ "loss": 8.3363,
440
+ "step": 59
441
+ },
442
+ {
443
+ "epoch": 0.5776173285198556,
444
+ "grad_norm": 57.25278091430664,
445
+ "learning_rate": 4.165153824795391e-06,
446
+ "loss": 8.0644,
447
+ "step": 60
448
+ },
449
+ {
450
+ "epoch": 0.5872442839951865,
451
+ "grad_norm": 67.98326873779297,
452
+ "learning_rate": 4.015201782566471e-06,
453
+ "loss": 8.0196,
454
+ "step": 61
455
+ },
456
+ {
457
+ "epoch": 0.5968712394705175,
458
+ "grad_norm": 52.99440383911133,
459
+ "learning_rate": 3.866165831894796e-06,
460
+ "loss": 8.2462,
461
+ "step": 62
462
+ },
463
+ {
464
+ "epoch": 0.6064981949458483,
465
+ "grad_norm": 52.595184326171875,
466
+ "learning_rate": 3.7181846109031007e-06,
467
+ "loss": 8.1063,
468
+ "step": 63
469
+ },
470
+ {
471
+ "epoch": 0.6161251504211793,
472
+ "grad_norm": 49.23164749145508,
473
+ "learning_rate": 3.5713957765700224e-06,
474
+ "loss": 8.1307,
475
+ "step": 64
476
+ },
477
+ {
478
+ "epoch": 0.6257521058965102,
479
+ "grad_norm": 88.22976684570312,
480
+ "learning_rate": 3.425935876677077e-06,
481
+ "loss": 7.6549,
482
+ "step": 65
483
+ },
484
+ {
485
+ "epoch": 0.6353790613718412,
486
+ "grad_norm": 38.58320236206055,
487
+ "learning_rate": 3.2819402227874364e-06,
488
+ "loss": 8.2685,
489
+ "step": 66
490
+ },
491
+ {
492
+ "epoch": 0.6450060168471721,
493
+ "grad_norm": 44.78543472290039,
494
+ "learning_rate": 3.1395427643746802e-06,
495
+ "loss": 8.1257,
496
+ "step": 67
497
+ },
498
+ {
499
+ "epoch": 0.6546329723225031,
500
+ "grad_norm": 53.79373550415039,
501
+ "learning_rate": 2.99887596421861e-06,
502
+ "loss": 8.0466,
503
+ "step": 68
504
+ },
505
+ {
506
+ "epoch": 0.6642599277978339,
507
+ "grad_norm": 54.07878875732422,
508
+ "learning_rate": 2.860070675184036e-06,
509
+ "loss": 7.8841,
510
+ "step": 69
511
+ },
512
+ {
513
+ "epoch": 0.6738868832731648,
514
+ "grad_norm": 59.090728759765625,
515
+ "learning_rate": 2.7232560184971437e-06,
516
+ "loss": 7.8315,
517
+ "step": 70
518
+ },
519
+ {
520
+ "epoch": 0.6835138387484958,
521
+ "grad_norm": 60.55500030517578,
522
+ "learning_rate": 2.588559263632719e-06,
523
+ "loss": 7.9892,
524
+ "step": 71
525
+ },
526
+ {
527
+ "epoch": 0.6931407942238267,
528
+ "grad_norm": 29.40604591369629,
529
+ "learning_rate": 2.4561057099238973e-06,
530
+ "loss": 8.3634,
531
+ "step": 72
532
+ },
533
+ {
534
+ "epoch": 0.7027677496991577,
535
+ "grad_norm": 53.2240104675293,
536
+ "learning_rate": 2.3260185700046295e-06,
537
+ "loss": 7.921,
538
+ "step": 73
539
+ },
540
+ {
541
+ "epoch": 0.7123947051744886,
542
+ "grad_norm": 33.78420639038086,
543
+ "learning_rate": 2.1984188551932513e-06,
544
+ "loss": 8.2299,
545
+ "step": 74
546
+ },
547
+ {
548
+ "epoch": 0.7220216606498195,
549
+ "grad_norm": 34.38809585571289,
550
+ "learning_rate": 2.0734252629237892e-06,
551
+ "loss": 8.2681,
552
+ "step": 75
553
+ },
554
+ {
555
+ "epoch": 0.7220216606498195,
556
+ "eval_clap": 0.19331718981266022,
557
+ "eval_loss": 3.7505130767822266,
558
+ "eval_runtime": 558.4399,
559
+ "eval_samples_per_second": 0.057,
560
+ "eval_steps_per_second": 0.057,
561
+ "step": 75
562
+ },
563
+ {
564
+ "epoch": 0.7316486161251504,
565
+ "grad_norm": 60.09890365600586,
566
+ "learning_rate": 1.9511540663297284e-06,
567
+ "loss": 7.715,
568
+ "step": 76
569
+ },
570
+ {
571
+ "epoch": 0.7412755716004813,
572
+ "grad_norm": 37.1711540222168,
573
+ "learning_rate": 1.8317190060829242e-06,
574
+ "loss": 8.0466,
575
+ "step": 77
576
+ },
577
+ {
578
+ "epoch": 0.7509025270758123,
579
+ "grad_norm": 38.487030029296875,
580
+ "learning_rate": 1.7152311845883096e-06,
581
+ "loss": 8.0262,
582
+ "step": 78
583
+ },
584
+ {
585
+ "epoch": 0.7605294825511432,
586
+ "grad_norm": 41.10578918457031,
587
+ "learning_rate": 1.601798962632799e-06,
588
+ "loss": 7.9379,
589
+ "step": 79
590
+ },
591
+ {
592
+ "epoch": 0.7701564380264742,
593
+ "grad_norm": 53.3963737487793,
594
+ "learning_rate": 1.491527858584535e-06,
595
+ "loss": 7.7086,
596
+ "step": 80
597
+ },
598
+ {
599
+ "epoch": 0.779783393501805,
600
+ "grad_norm": 40.814266204833984,
601
+ "learning_rate": 1.3845204502362442e-06,
602
+ "loss": 7.9538,
603
+ "step": 81
604
+ },
605
+ {
606
+ "epoch": 0.789410348977136,
607
+ "grad_norm": 35.338104248046875,
608
+ "learning_rate": 1.28087627938402e-06,
609
+ "loss": 8.1487,
610
+ "step": 82
611
+ },
612
+ {
613
+ "epoch": 0.7990373044524669,
614
+ "grad_norm": 49.323917388916016,
615
+ "learning_rate": 1.1806917592302763e-06,
616
+ "loss": 7.9905,
617
+ "step": 83
618
+ },
619
+ {
620
+ "epoch": 0.8086642599277978,
621
+ "grad_norm": 53.45624542236328,
622
+ "learning_rate": 1.0840600846970333e-06,
623
+ "loss": 7.7256,
624
+ "step": 84
625
+ },
626
+ {
627
+ "epoch": 0.8182912154031288,
628
+ "grad_norm": 59.274879455566406,
629
+ "learning_rate": 9.91071145732948e-07,
630
+ "loss": 7.8195,
631
+ "step": 85
632
+ },
633
+ {
634
+ "epoch": 0.8279181708784596,
635
+ "grad_norm": 39.876834869384766,
636
+ "learning_rate": 9.018114436947373e-07,
637
+ "loss": 7.9528,
638
+ "step": 86
639
+ },
640
+ {
641
+ "epoch": 0.8375451263537906,
642
+ "grad_norm": 74.85022735595703,
643
+ "learning_rate": 8.163640108807897e-07,
644
+ "loss": 7.593,
645
+ "step": 87
646
+ },
647
+ {
648
+ "epoch": 0.8471720818291215,
649
+ "grad_norm": 36.163230895996094,
650
+ "learning_rate": 7.348083332917927e-07,
651
+ "loss": 8.0817,
652
+ "step": 88
653
+ },
654
+ {
655
+ "epoch": 0.8567990373044525,
656
+ "grad_norm": 75.65898895263672,
657
+ "learning_rate": 6.572202766902569e-07,
658
+ "loss": 7.7246,
659
+ "step": 89
660
+ },
661
+ {
662
+ "epoch": 0.8664259927797834,
663
+ "grad_norm": 34.32077407836914,
664
+ "learning_rate": 5.836720160276971e-07,
665
+ "loss": 8.0978,
666
+ "step": 90
667
+ },
668
+ {
669
+ "epoch": 0.8760529482551144,
670
+ "grad_norm": 47.713619232177734,
671
+ "learning_rate": 5.1423196830513e-07,
672
+ "loss": 7.9117,
673
+ "step": 91
674
+ },
675
+ {
676
+ "epoch": 0.8856799037304453,
677
+ "grad_norm": 60.309242248535156,
678
+ "learning_rate": 4.4896472892933693e-07,
679
+ "loss": 7.5789,
680
+ "step": 92
681
+ },
682
+ {
683
+ "epoch": 0.8953068592057761,
684
+ "grad_norm": 32.33110809326172,
685
+ "learning_rate": 3.8793101162410417e-07,
686
+ "loss": 8.0885,
687
+ "step": 93
688
+ },
689
+ {
690
+ "epoch": 0.9049338146811071,
691
+ "grad_norm": 66.57474517822266,
692
+ "learning_rate": 3.3118759195232273e-07,
693
+ "loss": 7.4854,
694
+ "step": 94
695
+ },
696
+ {
697
+ "epoch": 0.914560770156438,
698
+ "grad_norm": 35.20654296875,
699
+ "learning_rate": 2.787872545015069e-07,
700
+ "loss": 8.0212,
701
+ "step": 95
702
+ },
703
+ {
704
+ "epoch": 0.924187725631769,
705
+ "grad_norm": 37.926116943359375,
706
+ "learning_rate": 2.307787437818365e-07,
707
+ "loss": 8.1619,
708
+ "step": 96
709
+ },
710
+ {
711
+ "epoch": 0.9338146811070999,
712
+ "grad_norm": 61.7646484375,
713
+ "learning_rate": 1.8720671888242058e-07,
714
+ "loss": 7.7689,
715
+ "step": 97
716
+ },
717
+ {
718
+ "epoch": 0.9434416365824309,
719
+ "grad_norm": 42.409461975097656,
720
+ "learning_rate": 1.4811171192794628e-07,
721
+ "loss": 8.0395,
722
+ "step": 98
723
+ },
724
+ {
725
+ "epoch": 0.9530685920577617,
726
+ "grad_norm": 53.46702575683594,
727
+ "learning_rate": 1.1353009037437523e-07,
728
+ "loss": 7.6451,
729
+ "step": 99
730
+ },
731
+ {
732
+ "epoch": 0.9626955475330926,
733
+ "grad_norm": 34.210060119628906,
734
+ "learning_rate": 8.34940231787379e-08,
735
+ "loss": 8.0758,
736
+ "step": 100
737
+ },
738
+ {
739
+ "epoch": 0.9626955475330926,
740
+ "eval_clap": 0.2040124535560608,
741
+ "eval_loss": 3.7648072242736816,
742
+ "eval_runtime": 556.6846,
743
+ "eval_samples_per_second": 0.057,
744
+ "eval_steps_per_second": 0.057,
745
+ "step": 100
746
+ },
747
+ {
748
+ "epoch": 0.9723225030084236,
749
+ "grad_norm": 63.23333740234375,
750
+ "learning_rate": 5.803145087451945e-08,
751
+ "loss": 7.5566,
752
+ "step": 101
753
+ },
754
+ {
755
+ "epoch": 0.9819494584837545,
756
+ "grad_norm": 52.794490814208984,
757
+ "learning_rate": 3.716605958046071e-08,
758
+ "loss": 7.7234,
759
+ "step": 102
760
+ },
761
+ {
762
+ "epoch": 0.9915764139590855,
763
+ "grad_norm": 46.992191314697266,
764
+ "learning_rate": 2.0917258966953735e-08,
765
+ "loss": 7.7302,
766
+ "step": 103
767
+ },
768
+ {
769
+ "epoch": 0.9915764139590855,
770
+ "step": 103,
771
+ "total_flos": 168544032748224.0,
772
+ "train_loss": 8.598374061214114,
773
+ "train_runtime": 2970.9735,
774
+ "train_samples_per_second": 0.28,
775
+ "train_steps_per_second": 0.035
776
+ }
777
+ ],
778
+ "logging_steps": 1.0,
779
+ "max_steps": 103,
780
+ "num_input_tokens_seen": 0,
781
+ "num_train_epochs": 1,
782
+ "save_steps": 500,
783
+ "stateful_callbacks": {
784
+ "TrainerControl": {
785
+ "args": {
786
+ "should_epoch_stop": false,
787
+ "should_evaluate": false,
788
+ "should_log": false,
789
+ "should_save": true,
790
+ "should_training_stop": true
791
+ },
792
+ "attributes": {}
793
+ }
794
+ },
795
+ "total_flos": 168544032748224.0,
796
+ "train_batch_size": 1,
797
+ "trial_name": null,
798
+ "trial_params": null
799
+ }