End of training
Browse files- README.md +3 -1
- trainer_state.json +313 -19
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: music-gen-indian-songs
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# music-gen-indian-songs
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on
|
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 |
+
- tiny-punk
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: music-gen-indian-songs
|
|
|
16 |
|
17 |
# music-gen-indian-songs
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the yav1327/indian_songs dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,39 +1,333 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss":
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss":
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 2,
|
36 |
-
"max_steps":
|
37 |
"num_input_tokens_seen": 0,
|
38 |
"num_train_epochs": 4,
|
39 |
"save_steps": 500,
|
@@ -49,7 +343,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 2,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.853932584269663,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 88,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0898876404494382,
|
13 |
+
"grad_norm": NaN,
|
14 |
+
"learning_rate": 0.00019772727272727273,
|
15 |
+
"loss": 9.4365,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.1797752808988764,
|
20 |
+
"grad_norm": 10.061033248901367,
|
21 |
+
"learning_rate": 0.0001931818181818182,
|
22 |
+
"loss": 9.2158,
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.2696629213483146,
|
27 |
+
"grad_norm": 15.205401420593262,
|
28 |
+
"learning_rate": 0.00018863636363636364,
|
29 |
+
"loss": 8.8062,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.3595505617977528,
|
34 |
+
"grad_norm": 20.087194442749023,
|
35 |
+
"learning_rate": 0.00018409090909090909,
|
36 |
+
"loss": 8.4059,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.449438202247191,
|
41 |
+
"grad_norm": 12.80905818939209,
|
42 |
+
"learning_rate": 0.00017954545454545456,
|
43 |
+
"loss": 7.8943,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.5393258426966292,
|
48 |
+
"grad_norm": 13.147987365722656,
|
49 |
+
"learning_rate": 0.000175,
|
50 |
+
"loss": 7.5915,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.6292134831460674,
|
55 |
+
"grad_norm": 14.075699806213379,
|
56 |
+
"learning_rate": 0.00017045454545454547,
|
57 |
+
"loss": 7.3797,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.7191011235955056,
|
62 |
+
"grad_norm": 6.000680923461914,
|
63 |
+
"learning_rate": 0.00016590909090909094,
|
64 |
+
"loss": 7.3359,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.8089887640449438,
|
69 |
+
"grad_norm": 7.718422889709473,
|
70 |
+
"learning_rate": 0.00016136363636363635,
|
71 |
+
"loss": 7.3118,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.898876404494382,
|
76 |
+
"grad_norm": 6.30356502532959,
|
77 |
+
"learning_rate": 0.00015681818181818182,
|
78 |
+
"loss": 7.2512,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.9887640449438202,
|
83 |
+
"grad_norm": 11.91089153289795,
|
84 |
+
"learning_rate": 0.00015227272727272727,
|
85 |
+
"loss": 7.1725,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.0449438202247192,
|
90 |
+
"grad_norm": 10.328221321105957,
|
91 |
+
"learning_rate": 0.00014772727272727274,
|
92 |
+
"loss": 4.4411,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.1348314606741572,
|
97 |
+
"grad_norm": 11.233499526977539,
|
98 |
+
"learning_rate": 0.0001431818181818182,
|
99 |
+
"loss": 7.1546,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.2247191011235956,
|
104 |
+
"grad_norm": 12.115806579589844,
|
105 |
+
"learning_rate": 0.00013863636363636365,
|
106 |
+
"loss": 7.146,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.3146067415730336,
|
111 |
+
"grad_norm": 8.608111381530762,
|
112 |
+
"learning_rate": 0.0001340909090909091,
|
113 |
+
"loss": 7.1384,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.404494382022472,
|
118 |
+
"grad_norm": 6.332569599151611,
|
119 |
+
"learning_rate": 0.00012954545454545456,
|
120 |
+
"loss": 7.0654,
|
121 |
+
"step": 32
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.49438202247191,
|
125 |
+
"grad_norm": 8.418745994567871,
|
126 |
+
"learning_rate": 0.000125,
|
127 |
+
"loss": 7.025,
|
128 |
+
"step": 34
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.5842696629213484,
|
132 |
+
"grad_norm": 3.712430000305176,
|
133 |
+
"learning_rate": 0.00012045454545454546,
|
134 |
+
"loss": 7.0801,
|
135 |
+
"step": 36
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.6741573033707864,
|
139 |
+
"grad_norm": 10.121654510498047,
|
140 |
+
"learning_rate": 0.00011590909090909093,
|
141 |
+
"loss": 7.1843,
|
142 |
+
"step": 38
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.7640449438202248,
|
146 |
+
"grad_norm": 4.086280345916748,
|
147 |
+
"learning_rate": 0.00011136363636363636,
|
148 |
+
"loss": 7.085,
|
149 |
+
"step": 40
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.8539325842696628,
|
153 |
+
"grad_norm": 6.2060933113098145,
|
154 |
+
"learning_rate": 0.00010681818181818181,
|
155 |
+
"loss": 7.0862,
|
156 |
+
"step": 42
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.9438202247191012,
|
160 |
+
"grad_norm": 3.9082467555999756,
|
161 |
+
"learning_rate": 0.00010227272727272727,
|
162 |
+
"loss": 7.034,
|
163 |
+
"step": 44
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.0,
|
167 |
+
"grad_norm": 3.6770272254943848,
|
168 |
+
"learning_rate": 9.772727272727274e-05,
|
169 |
+
"loss": 4.2733,
|
170 |
+
"step": 46
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.0898876404494384,
|
174 |
+
"grad_norm": 3.2819325923919678,
|
175 |
+
"learning_rate": 9.318181818181818e-05,
|
176 |
+
"loss": 7.0196,
|
177 |
+
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.1797752808988764,
|
181 |
+
"grad_norm": 6.796480655670166,
|
182 |
+
"learning_rate": 8.863636363636364e-05,
|
183 |
+
"loss": 7.0643,
|
184 |
+
"step": 50
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.2696629213483144,
|
188 |
+
"grad_norm": 5.090155124664307,
|
189 |
+
"learning_rate": 8.40909090909091e-05,
|
190 |
+
"loss": 6.9201,
|
191 |
+
"step": 52
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.359550561797753,
|
195 |
+
"grad_norm": 9.731218338012695,
|
196 |
+
"learning_rate": 7.954545454545455e-05,
|
197 |
+
"loss": 7.0715,
|
198 |
+
"step": 54
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.449438202247191,
|
202 |
+
"grad_norm": 5.852891445159912,
|
203 |
+
"learning_rate": 7.500000000000001e-05,
|
204 |
+
"loss": 7.1071,
|
205 |
+
"step": 56
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.539325842696629,
|
209 |
+
"grad_norm": 9.918388366699219,
|
210 |
+
"learning_rate": 7.045454545454546e-05,
|
211 |
+
"loss": 7.0041,
|
212 |
+
"step": 58
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.629213483146067,
|
216 |
+
"grad_norm": 5.5014190673828125,
|
217 |
+
"learning_rate": 6.59090909090909e-05,
|
218 |
+
"loss": 6.982,
|
219 |
+
"step": 60
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.7191011235955056,
|
223 |
+
"grad_norm": 7.316319465637207,
|
224 |
+
"learning_rate": 6.136363636363636e-05,
|
225 |
+
"loss": 6.9352,
|
226 |
+
"step": 62
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.808988764044944,
|
230 |
+
"grad_norm": 13.674769401550293,
|
231 |
+
"learning_rate": 5.6818181818181825e-05,
|
232 |
+
"loss": 6.9549,
|
233 |
+
"step": 64
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.898876404494382,
|
237 |
+
"grad_norm": 6.491578102111816,
|
238 |
+
"learning_rate": 5.2272727272727274e-05,
|
239 |
+
"loss": 7.0187,
|
240 |
+
"step": 66
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.98876404494382,
|
244 |
+
"grad_norm": 5.663166522979736,
|
245 |
+
"learning_rate": 4.772727272727273e-05,
|
246 |
+
"loss": 6.9697,
|
247 |
+
"step": 68
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 3.044943820224719,
|
251 |
+
"grad_norm": 5.13517427444458,
|
252 |
+
"learning_rate": 4.318181818181819e-05,
|
253 |
+
"loss": 4.3462,
|
254 |
+
"step": 70
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.134831460674157,
|
258 |
+
"grad_norm": 4.548388957977295,
|
259 |
+
"learning_rate": 3.8636363636363636e-05,
|
260 |
+
"loss": 6.8757,
|
261 |
+
"step": 72
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.2247191011235956,
|
265 |
+
"grad_norm": 7.8548431396484375,
|
266 |
+
"learning_rate": 3.409090909090909e-05,
|
267 |
+
"loss": 6.9019,
|
268 |
+
"step": 74
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 3.3146067415730336,
|
272 |
+
"grad_norm": 18.156105041503906,
|
273 |
+
"learning_rate": 2.954545454545455e-05,
|
274 |
+
"loss": 7.076,
|
275 |
+
"step": 76
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.404494382022472,
|
279 |
+
"grad_norm": 6.122278690338135,
|
280 |
+
"learning_rate": 2.5e-05,
|
281 |
+
"loss": 6.9759,
|
282 |
+
"step": 78
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.49438202247191,
|
286 |
+
"grad_norm": 8.052112579345703,
|
287 |
+
"learning_rate": 2.0454545454545457e-05,
|
288 |
+
"loss": 7.1131,
|
289 |
+
"step": 80
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 3.5842696629213484,
|
293 |
+
"grad_norm": 18.36809730529785,
|
294 |
+
"learning_rate": 1.8181818181818182e-05,
|
295 |
+
"loss": 6.8889,
|
296 |
+
"step": 82
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.6741573033707864,
|
300 |
+
"grad_norm": 3.2839643955230713,
|
301 |
+
"learning_rate": 1.3636363636363637e-05,
|
302 |
+
"loss": 6.9873,
|
303 |
+
"step": 84
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.764044943820225,
|
307 |
+
"grad_norm": 7.564036846160889,
|
308 |
+
"learning_rate": 9.090909090909091e-06,
|
309 |
+
"loss": 6.9841,
|
310 |
+
"step": 86
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 3.853932584269663,
|
314 |
+
"grad_norm": 3.23893404006958,
|
315 |
+
"learning_rate": 4.5454545454545455e-06,
|
316 |
+
"loss": 6.975,
|
317 |
+
"step": 88
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.853932584269663,
|
321 |
+
"step": 88,
|
322 |
+
"total_flos": 343326692124408.0,
|
323 |
+
"train_loss": 7.0837731144645,
|
324 |
+
"train_runtime": 380.6612,
|
325 |
+
"train_samples_per_second": 3.73,
|
326 |
+
"train_steps_per_second": 0.231
|
327 |
}
|
328 |
],
|
329 |
"logging_steps": 2,
|
330 |
+
"max_steps": 88,
|
331 |
"num_input_tokens_seen": 0,
|
332 |
"num_train_epochs": 4,
|
333 |
"save_steps": 500,
|
|
|
343 |
"attributes": {}
|
344 |
}
|
345 |
},
|
346 |
+
"total_flos": 343326692124408.0,
|
347 |
"train_batch_size": 2,
|
348 |
"trial_name": null,
|
349 |
"trial_params": null
|