xiaosh9527 commited on
Commit
c267850
1 Parent(s): 68d1208

End of training

Browse files
Files changed (2) hide show
  1. README.md +3 -1
  2. trainer_state.json +216 -48
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
 
 
5
  - generated_from_trainer
6
  base_model: facebook/musicgen-melody
7
  model-index:
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-melody-lora-techno-nan-colab
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
 
 
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
5
+ - text-to-audio
6
+ - techno_nan
7
  - generated_from_trainer
8
  base_model: facebook/musicgen-melody
9
  model-index:
 
16
 
17
  # musicgen-melody-lora-techno-nan-colab
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the xiaosh9527/nan_music dataset.
20
 
21
  ## Model description
22
 
trainer_state.json CHANGED
@@ -1,111 +1,279 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.84,
5
  "eval_steps": 500,
6
- "global_step": 24,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.32,
13
- "grad_norm": 0.20171859860420227,
14
- "learning_rate": 9.166666666666667e-05,
15
- "loss": 6.7889,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.64,
20
- "grad_norm": 0.2258663922548294,
21
- "learning_rate": 8.333333333333334e-05,
22
- "loss": 6.8518,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 0.96,
27
- "grad_norm": 0.2266591638326645,
28
- "learning_rate": 7.500000000000001e-05,
29
- "loss": 6.8562,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.28,
34
- "grad_norm": 0.19837072491645813,
35
- "learning_rate": 6.666666666666667e-05,
36
- "loss": 6.8282,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 1.6,
41
- "grad_norm": 0.17619071900844574,
42
- "learning_rate": 5.833333333333334e-05,
43
- "loss": 6.8528,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 1.92,
48
- "grad_norm": 0.12639087438583374,
49
- "learning_rate": 5e-05,
50
- "loss": 6.8231,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 2.24,
55
- "grad_norm": 0.13687172532081604,
56
- "learning_rate": 4.166666666666667e-05,
57
- "loss": 6.7815,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 2.56,
62
- "grad_norm": 0.18898847699165344,
63
- "learning_rate": 3.3333333333333335e-05,
64
- "loss": 6.7792,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 2.88,
69
- "grad_norm": 0.1648869514465332,
70
- "learning_rate": 2.5e-05,
71
- "loss": 6.8046,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 3.2,
76
- "grad_norm": 0.16822992265224457,
77
- "learning_rate": 1.6666666666666667e-05,
78
- "loss": 6.8128,
79
  "step": 20
80
  },
81
  {
82
  "epoch": 3.52,
83
- "grad_norm": 0.16933274269104004,
84
- "learning_rate": 8.333333333333334e-06,
85
- "loss": 6.8081,
86
  "step": 22
87
  },
88
  {
89
  "epoch": 3.84,
90
- "grad_norm": 0.1729530692100525,
91
- "learning_rate": 0.0,
92
- "loss": 6.8425,
93
  "step": 24
94
  },
95
  {
96
- "epoch": 3.84,
97
- "step": 24,
98
- "total_flos": 92571267829680.0,
99
- "train_loss": 6.819143931070964,
100
- "train_runtime": 117.2771,
101
- "train_samples_per_second": 3.411,
102
- "train_steps_per_second": 0.205
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  }
104
  ],
105
  "logging_steps": 2,
106
- "max_steps": 24,
107
  "num_input_tokens_seen": 0,
108
- "num_train_epochs": 4,
109
  "save_steps": 500,
110
  "stateful_callbacks": {
111
  "TrainerControl": {
@@ -119,7 +287,7 @@
119
  "attributes": {}
120
  }
121
  },
122
- "total_flos": 92571267829680.0,
123
  "train_batch_size": 2,
124
  "trial_name": null,
125
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 11.52,
5
  "eval_steps": 500,
6
+ "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.32,
13
+ "grad_norm": 0.9926958680152893,
14
+ "learning_rate": 0.00019444444444444446,
15
+ "loss": 9.5849,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.64,
20
+ "grad_norm": 1.7527631521224976,
21
+ "learning_rate": 0.00018888888888888888,
22
+ "loss": 9.1705,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 0.96,
27
+ "grad_norm": 2.0137224197387695,
28
+ "learning_rate": 0.00018333333333333334,
29
+ "loss": 8.4125,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.28,
34
+ "grad_norm": 1.948047399520874,
35
+ "learning_rate": 0.00017777777777777779,
36
+ "loss": 7.9081,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 1.6,
41
+ "grad_norm": 1.1467063426971436,
42
+ "learning_rate": 0.00017222222222222224,
43
+ "loss": 7.6057,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 1.92,
48
+ "grad_norm": 1.0256859064102173,
49
+ "learning_rate": 0.0001666666666666667,
50
+ "loss": 7.4069,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 2.24,
55
+ "grad_norm": 1.2744684219360352,
56
+ "learning_rate": 0.0001611111111111111,
57
+ "loss": 7.3171,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 2.56,
62
+ "grad_norm": 1.0262680053710938,
63
+ "learning_rate": 0.00015555555555555556,
64
+ "loss": 7.2517,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 2.88,
69
+ "grad_norm": 0.5943800210952759,
70
+ "learning_rate": 0.00015000000000000001,
71
+ "loss": 7.1989,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 3.2,
76
+ "grad_norm": 0.7326172590255737,
77
+ "learning_rate": 0.00014444444444444444,
78
+ "loss": 7.1975,
79
  "step": 20
80
  },
81
  {
82
  "epoch": 3.52,
83
+ "grad_norm": 0.5042484998703003,
84
+ "learning_rate": 0.0001388888888888889,
85
+ "loss": 7.1582,
86
  "step": 22
87
  },
88
  {
89
  "epoch": 3.84,
90
+ "grad_norm": 0.512372612953186,
91
+ "learning_rate": 0.00013333333333333334,
92
+ "loss": 7.1793,
93
  "step": 24
94
  },
95
  {
96
+ "epoch": 4.16,
97
+ "grad_norm": 0.5498717427253723,
98
+ "learning_rate": 0.00012777777777777776,
99
+ "loss": 7.1182,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 4.48,
104
+ "grad_norm": 0.5042092800140381,
105
+ "learning_rate": 0.00012222222222222224,
106
+ "loss": 7.1492,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 4.8,
111
+ "grad_norm": 0.4820415675640106,
112
+ "learning_rate": 0.00011666666666666668,
113
+ "loss": 7.0726,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 5.12,
118
+ "grad_norm": 0.5835886597633362,
119
+ "learning_rate": 0.00011111111111111112,
120
+ "loss": 7.1349,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 5.44,
125
+ "grad_norm": 0.35386550426483154,
126
+ "learning_rate": 0.00010555555555555557,
127
+ "loss": 7.0469,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 5.76,
132
+ "grad_norm": 0.5533877015113831,
133
+ "learning_rate": 0.0001,
134
+ "loss": 7.0824,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 6.08,
139
+ "grad_norm": 0.6554893851280212,
140
+ "learning_rate": 9.444444444444444e-05,
141
+ "loss": 7.0484,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 6.4,
146
+ "grad_norm": 0.3372606337070465,
147
+ "learning_rate": 8.888888888888889e-05,
148
+ "loss": 7.0252,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 6.72,
153
+ "grad_norm": 0.299753338098526,
154
+ "learning_rate": 8.333333333333334e-05,
155
+ "loss": 7.0648,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 7.04,
160
+ "grad_norm": 0.35728025436401367,
161
+ "learning_rate": 7.777777777777778e-05,
162
+ "loss": 7.1132,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 7.36,
167
+ "grad_norm": 0.29526084661483765,
168
+ "learning_rate": 7.222222222222222e-05,
169
+ "loss": 7.0196,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 7.68,
174
+ "grad_norm": 0.42963483929634094,
175
+ "learning_rate": 6.666666666666667e-05,
176
+ "loss": 7.0818,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 8.0,
181
+ "grad_norm": 0.2951211929321289,
182
+ "learning_rate": 6.111111111111112e-05,
183
+ "loss": 7.0431,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 8.32,
188
+ "grad_norm": 0.4070325791835785,
189
+ "learning_rate": 5.555555555555556e-05,
190
+ "loss": 6.9709,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 8.64,
195
+ "grad_norm": 0.2796075642108917,
196
+ "learning_rate": 5e-05,
197
+ "loss": 7.0826,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 8.96,
202
+ "grad_norm": 0.37583762407302856,
203
+ "learning_rate": 4.4444444444444447e-05,
204
+ "loss": 7.0513,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 9.28,
209
+ "grad_norm": 0.4634278416633606,
210
+ "learning_rate": 3.888888888888889e-05,
211
+ "loss": 7.0616,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 9.6,
216
+ "grad_norm": 0.45491114258766174,
217
+ "learning_rate": 3.3333333333333335e-05,
218
+ "loss": 7.0114,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 9.92,
223
+ "grad_norm": 0.5008836388587952,
224
+ "learning_rate": 2.777777777777778e-05,
225
+ "loss": 7.058,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 10.24,
230
+ "grad_norm": 0.2694868743419647,
231
+ "learning_rate": 2.2222222222222223e-05,
232
+ "loss": 6.9724,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 10.56,
237
+ "grad_norm": 0.2757045030593872,
238
+ "learning_rate": 1.6666666666666667e-05,
239
+ "loss": 7.0447,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 10.88,
244
+ "grad_norm": 0.336161732673645,
245
+ "learning_rate": 1.1111111111111112e-05,
246
+ "loss": 7.032,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 11.2,
251
+ "grad_norm": 0.2434120923280716,
252
+ "learning_rate": 5.555555555555556e-06,
253
+ "loss": 7.0543,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 11.52,
258
+ "grad_norm": 0.37180185317993164,
259
+ "learning_rate": 0.0,
260
+ "loss": 7.038,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 11.52,
265
+ "step": 72,
266
+ "total_flos": 279672397179648.0,
267
+ "train_loss": 7.299143155415853,
268
+ "train_runtime": 353.7388,
269
+ "train_samples_per_second": 3.392,
270
+ "train_steps_per_second": 0.204
271
  }
272
  ],
273
  "logging_steps": 2,
274
+ "max_steps": 72,
275
  "num_input_tokens_seen": 0,
276
+ "num_train_epochs": 12,
277
  "save_steps": 500,
278
  "stateful_callbacks": {
279
  "TrainerControl": {
 
287
  "attributes": {}
288
  }
289
  },
290
+ "total_flos": 279672397179648.0,
291
  "train_batch_size": 2,
292
  "trial_name": null,
293
  "trial_params": null