jane102350
commited on
Commit
•
5ee030d
1
Parent(s):
30539e5
End of training
Browse files- README.md +3 -1
- trainer_state.json +41 -531
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-kk-colab
|
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 |
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- text-to-audio
|
6 |
+
- tiny-kk
|
7 |
- generated_from_trainer
|
8 |
base_model: facebook/musicgen-melody
|
9 |
model-index:
|
|
|
16 |
|
17 |
# musicgen-melody-lora-kk-colab
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the jane102350/kk-colab dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,587 +1,97 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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": 0.19047619047619047,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 9.
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.38095238095238093,
|
20 |
-
"grad_norm": 1.
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss": 9.
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5714285714285714,
|
27 |
-
"grad_norm": 1.
|
28 |
-
"learning_rate": 0.
|
29 |
-
"loss": 8.
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7619047619047619,
|
34 |
-
"grad_norm": 2.
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss": 8.
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9523809523809523,
|
41 |
-
"grad_norm": 1.
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss":
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.1428571428571428,
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate":
|
50 |
-
"loss": 7.
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.3333333333333333,
|
55 |
-
"grad_norm": 1.
|
56 |
-
"learning_rate":
|
57 |
-
"loss": 7.
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.5238095238095237,
|
62 |
-
"grad_norm": 1.
|
63 |
-
"learning_rate":
|
64 |
-
"loss": 7.
|
65 |
"step": 16
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.7142857142857144,
|
69 |
-
"grad_norm":
|
70 |
-
"learning_rate":
|
71 |
-
"loss": 7.
|
72 |
"step": 18
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.9047619047619047,
|
76 |
-
"grad_norm":
|
77 |
-
"learning_rate": 0.
|
78 |
-
"loss": 7.
|
79 |
"step": 20
|
80 |
},
|
81 |
{
|
82 |
-
"epoch":
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"
|
87 |
-
|
88 |
-
{
|
89 |
-
"epoch": 2.2857142857142856,
|
90 |
-
"grad_norm": 0.7033187747001648,
|
91 |
-
"learning_rate": 0.00017,
|
92 |
-
"loss": 7.3096,
|
93 |
-
"step": 24
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 2.4761904761904763,
|
97 |
-
"grad_norm": 2.9758119583129883,
|
98 |
-
"learning_rate": 0.0001675,
|
99 |
-
"loss": 7.1991,
|
100 |
-
"step": 26
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 2.6666666666666665,
|
104 |
-
"grad_norm": 0.7531760931015015,
|
105 |
-
"learning_rate": 0.000165,
|
106 |
-
"loss": 7.2661,
|
107 |
-
"step": 28
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"epoch": 2.857142857142857,
|
111 |
-
"grad_norm": 1.3790533542633057,
|
112 |
-
"learning_rate": 0.00016250000000000002,
|
113 |
-
"loss": 7.2782,
|
114 |
-
"step": 30
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 3.0476190476190474,
|
118 |
-
"grad_norm": 0.6538093686103821,
|
119 |
-
"learning_rate": 0.00016,
|
120 |
-
"loss": 7.2109,
|
121 |
-
"step": 32
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 3.238095238095238,
|
125 |
-
"grad_norm": 0.6145215630531311,
|
126 |
-
"learning_rate": 0.0001575,
|
127 |
-
"loss": 7.2192,
|
128 |
-
"step": 34
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 3.4285714285714284,
|
132 |
-
"grad_norm": 0.4128475785255432,
|
133 |
-
"learning_rate": 0.000155,
|
134 |
-
"loss": 7.2892,
|
135 |
-
"step": 36
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"epoch": 3.619047619047619,
|
139 |
-
"grad_norm": 1.0160013437271118,
|
140 |
-
"learning_rate": 0.0001525,
|
141 |
-
"loss": 7.2049,
|
142 |
-
"step": 38
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 3.8095238095238093,
|
146 |
-
"grad_norm": 0.5834835171699524,
|
147 |
-
"learning_rate": 0.00015000000000000001,
|
148 |
-
"loss": 7.1672,
|
149 |
-
"step": 40
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 4.0,
|
153 |
-
"grad_norm": 0.4894554615020752,
|
154 |
-
"learning_rate": 0.0001475,
|
155 |
-
"loss": 7.1269,
|
156 |
-
"step": 42
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 4.190476190476191,
|
160 |
-
"grad_norm": 0.593618631362915,
|
161 |
-
"learning_rate": 0.000145,
|
162 |
-
"loss": 7.0175,
|
163 |
-
"step": 44
|
164 |
-
},
|
165 |
-
{
|
166 |
-
"epoch": 4.380952380952381,
|
167 |
-
"grad_norm": 1.6190487146377563,
|
168 |
-
"learning_rate": 0.00014250000000000002,
|
169 |
-
"loss": 7.2919,
|
170 |
-
"step": 46
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 4.571428571428571,
|
174 |
-
"grad_norm": 0.755859911441803,
|
175 |
-
"learning_rate": 0.00014,
|
176 |
-
"loss": 7.1624,
|
177 |
-
"step": 48
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 4.761904761904762,
|
181 |
-
"grad_norm": 0.46613645553588867,
|
182 |
-
"learning_rate": 0.0001375,
|
183 |
-
"loss": 7.2233,
|
184 |
-
"step": 50
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 4.9523809523809526,
|
188 |
-
"grad_norm": 0.5973020792007446,
|
189 |
-
"learning_rate": 0.00013500000000000003,
|
190 |
-
"loss": 7.1642,
|
191 |
-
"step": 52
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 5.142857142857143,
|
195 |
-
"grad_norm": 0.97837233543396,
|
196 |
-
"learning_rate": 0.0001325,
|
197 |
-
"loss": 7.1172,
|
198 |
-
"step": 54
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"epoch": 5.333333333333333,
|
202 |
-
"grad_norm": 0.9348046183586121,
|
203 |
-
"learning_rate": 0.00013000000000000002,
|
204 |
-
"loss": 7.1564,
|
205 |
-
"step": 56
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 5.523809523809524,
|
209 |
-
"grad_norm": 0.6632198691368103,
|
210 |
-
"learning_rate": 0.0001275,
|
211 |
-
"loss": 7.0821,
|
212 |
-
"step": 58
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 5.714285714285714,
|
216 |
-
"grad_norm": 0.7776179909706116,
|
217 |
-
"learning_rate": 0.000125,
|
218 |
-
"loss": 7.2272,
|
219 |
-
"step": 60
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 5.904761904761905,
|
223 |
-
"grad_norm": 0.6282438039779663,
|
224 |
-
"learning_rate": 0.00012250000000000002,
|
225 |
-
"loss": 7.0926,
|
226 |
-
"step": 62
|
227 |
-
},
|
228 |
-
{
|
229 |
-
"epoch": 6.095238095238095,
|
230 |
-
"grad_norm": 0.6008353233337402,
|
231 |
-
"learning_rate": 0.00012,
|
232 |
-
"loss": 7.1073,
|
233 |
-
"step": 64
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 6.285714285714286,
|
237 |
-
"grad_norm": 0.8796420097351074,
|
238 |
-
"learning_rate": 0.00011750000000000001,
|
239 |
-
"loss": 7.1737,
|
240 |
-
"step": 66
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 6.476190476190476,
|
244 |
-
"grad_norm": 0.6400454640388489,
|
245 |
-
"learning_rate": 0.00011499999999999999,
|
246 |
-
"loss": 7.0924,
|
247 |
-
"step": 68
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 6.666666666666667,
|
251 |
-
"grad_norm": 0.5479526519775391,
|
252 |
-
"learning_rate": 0.00011250000000000001,
|
253 |
-
"loss": 7.1275,
|
254 |
-
"step": 70
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 6.857142857142857,
|
258 |
-
"grad_norm": 0.5992618203163147,
|
259 |
-
"learning_rate": 0.00011000000000000002,
|
260 |
-
"loss": 7.0599,
|
261 |
-
"step": 72
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 7.0476190476190474,
|
265 |
-
"grad_norm": 0.5336684584617615,
|
266 |
-
"learning_rate": 0.0001075,
|
267 |
-
"loss": 7.0206,
|
268 |
-
"step": 74
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 7.238095238095238,
|
272 |
-
"grad_norm": 0.3991040289402008,
|
273 |
-
"learning_rate": 0.000105,
|
274 |
-
"loss": 7.0123,
|
275 |
-
"step": 76
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 7.428571428571429,
|
279 |
-
"grad_norm": 1.032917857170105,
|
280 |
-
"learning_rate": 0.0001025,
|
281 |
-
"loss": 7.0267,
|
282 |
-
"step": 78
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 7.619047619047619,
|
286 |
-
"grad_norm": 0.5554404854774475,
|
287 |
-
"learning_rate": 0.0001,
|
288 |
-
"loss": 7.0203,
|
289 |
-
"step": 80
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 7.809523809523809,
|
293 |
-
"grad_norm": 0.7755109667778015,
|
294 |
-
"learning_rate": 9.75e-05,
|
295 |
-
"loss": 7.1445,
|
296 |
-
"step": 82
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 8.0,
|
300 |
-
"grad_norm": 1.8295842409133911,
|
301 |
-
"learning_rate": 9.5e-05,
|
302 |
-
"loss": 7.0002,
|
303 |
-
"step": 84
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 8.19047619047619,
|
307 |
-
"grad_norm": 1.4985620975494385,
|
308 |
-
"learning_rate": 9.250000000000001e-05,
|
309 |
-
"loss": 7.0613,
|
310 |
-
"step": 86
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 8.380952380952381,
|
314 |
-
"grad_norm": 1.0733778476715088,
|
315 |
-
"learning_rate": 9e-05,
|
316 |
-
"loss": 7.0594,
|
317 |
-
"step": 88
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 8.571428571428571,
|
321 |
-
"grad_norm": 0.7009026408195496,
|
322 |
-
"learning_rate": 8.75e-05,
|
323 |
-
"loss": 6.9432,
|
324 |
-
"step": 90
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"epoch": 8.761904761904763,
|
328 |
-
"grad_norm": 1.195196509361267,
|
329 |
-
"learning_rate": 8.5e-05,
|
330 |
-
"loss": 6.9266,
|
331 |
-
"step": 92
|
332 |
-
},
|
333 |
-
{
|
334 |
-
"epoch": 8.952380952380953,
|
335 |
-
"grad_norm": 2.6835684776306152,
|
336 |
-
"learning_rate": 8.25e-05,
|
337 |
-
"loss": 6.9855,
|
338 |
-
"step": 94
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 9.142857142857142,
|
342 |
-
"grad_norm": 0.7434377670288086,
|
343 |
-
"learning_rate": 8e-05,
|
344 |
-
"loss": 6.7975,
|
345 |
-
"step": 96
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 9.333333333333334,
|
349 |
-
"grad_norm": 0.5993837118148804,
|
350 |
-
"learning_rate": 7.75e-05,
|
351 |
-
"loss": 7.0476,
|
352 |
-
"step": 98
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 9.523809523809524,
|
356 |
-
"grad_norm": 0.4656153619289398,
|
357 |
-
"learning_rate": 7.500000000000001e-05,
|
358 |
-
"loss": 6.9894,
|
359 |
-
"step": 100
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 9.714285714285714,
|
363 |
-
"grad_norm": 0.7926774621009827,
|
364 |
-
"learning_rate": 7.25e-05,
|
365 |
-
"loss": 6.9854,
|
366 |
-
"step": 102
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 9.904761904761905,
|
370 |
-
"grad_norm": 1.0828678607940674,
|
371 |
-
"learning_rate": 7e-05,
|
372 |
-
"loss": 6.9185,
|
373 |
-
"step": 104
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 10.095238095238095,
|
377 |
-
"grad_norm": 0.6923830509185791,
|
378 |
-
"learning_rate": 6.750000000000001e-05,
|
379 |
-
"loss": 6.9804,
|
380 |
-
"step": 106
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 10.285714285714286,
|
384 |
-
"grad_norm": 0.5546735525131226,
|
385 |
-
"learning_rate": 6.500000000000001e-05,
|
386 |
-
"loss": 6.9273,
|
387 |
-
"step": 108
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"epoch": 10.476190476190476,
|
391 |
-
"grad_norm": 0.8265076875686646,
|
392 |
-
"learning_rate": 6.25e-05,
|
393 |
-
"loss": 6.9087,
|
394 |
-
"step": 110
|
395 |
-
},
|
396 |
-
{
|
397 |
-
"epoch": 10.666666666666666,
|
398 |
-
"grad_norm": 0.3945198655128479,
|
399 |
-
"learning_rate": 6e-05,
|
400 |
-
"loss": 6.9375,
|
401 |
-
"step": 112
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 10.857142857142858,
|
405 |
-
"grad_norm": 0.5948878526687622,
|
406 |
-
"learning_rate": 5.7499999999999995e-05,
|
407 |
-
"loss": 6.8764,
|
408 |
-
"step": 114
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 11.047619047619047,
|
412 |
-
"grad_norm": 0.7741471529006958,
|
413 |
-
"learning_rate": 5.500000000000001e-05,
|
414 |
-
"loss": 6.7551,
|
415 |
-
"step": 116
|
416 |
-
},
|
417 |
-
{
|
418 |
-
"epoch": 11.238095238095237,
|
419 |
-
"grad_norm": 0.32554784417152405,
|
420 |
-
"learning_rate": 5.25e-05,
|
421 |
-
"loss": 6.8862,
|
422 |
-
"step": 118
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 11.428571428571429,
|
426 |
-
"grad_norm": 0.5033702850341797,
|
427 |
-
"learning_rate": 5e-05,
|
428 |
-
"loss": 6.7297,
|
429 |
-
"step": 120
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 11.619047619047619,
|
433 |
-
"grad_norm": 0.5291158556938171,
|
434 |
-
"learning_rate": 4.75e-05,
|
435 |
-
"loss": 6.9826,
|
436 |
-
"step": 122
|
437 |
-
},
|
438 |
-
{
|
439 |
-
"epoch": 11.80952380952381,
|
440 |
-
"grad_norm": 0.39498385787010193,
|
441 |
-
"learning_rate": 4.5e-05,
|
442 |
-
"loss": 6.837,
|
443 |
-
"step": 124
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 12.0,
|
447 |
-
"grad_norm": 0.4402136206626892,
|
448 |
-
"learning_rate": 4.25e-05,
|
449 |
-
"loss": 7.0434,
|
450 |
-
"step": 126
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 12.19047619047619,
|
454 |
-
"grad_norm": 0.6476764678955078,
|
455 |
-
"learning_rate": 4e-05,
|
456 |
-
"loss": 6.8524,
|
457 |
-
"step": 128
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 12.380952380952381,
|
461 |
-
"grad_norm": 0.330609530210495,
|
462 |
-
"learning_rate": 3.7500000000000003e-05,
|
463 |
-
"loss": 6.8742,
|
464 |
-
"step": 130
|
465 |
-
},
|
466 |
-
{
|
467 |
-
"epoch": 12.571428571428571,
|
468 |
-
"grad_norm": 0.5420040488243103,
|
469 |
-
"learning_rate": 3.5e-05,
|
470 |
-
"loss": 6.7931,
|
471 |
-
"step": 132
|
472 |
-
},
|
473 |
-
{
|
474 |
-
"epoch": 12.761904761904763,
|
475 |
-
"grad_norm": 0.3482373356819153,
|
476 |
-
"learning_rate": 3.2500000000000004e-05,
|
477 |
-
"loss": 6.883,
|
478 |
-
"step": 134
|
479 |
-
},
|
480 |
-
{
|
481 |
-
"epoch": 12.952380952380953,
|
482 |
-
"grad_norm": 0.3476051092147827,
|
483 |
-
"learning_rate": 3e-05,
|
484 |
-
"loss": 6.9857,
|
485 |
-
"step": 136
|
486 |
-
},
|
487 |
-
{
|
488 |
-
"epoch": 13.142857142857142,
|
489 |
-
"grad_norm": 0.43590274453163147,
|
490 |
-
"learning_rate": 2.8749999999999997e-05,
|
491 |
-
"loss": 8.116,
|
492 |
-
"step": 138
|
493 |
-
},
|
494 |
-
{
|
495 |
-
"epoch": 13.333333333333334,
|
496 |
-
"grad_norm": 0.2993098497390747,
|
497 |
-
"learning_rate": 2.625e-05,
|
498 |
-
"loss": 6.657,
|
499 |
-
"step": 140
|
500 |
-
},
|
501 |
-
{
|
502 |
-
"epoch": 13.523809523809524,
|
503 |
-
"grad_norm": 0.3477262556552887,
|
504 |
-
"learning_rate": 2.375e-05,
|
505 |
-
"loss": 6.9781,
|
506 |
-
"step": 142
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 13.714285714285714,
|
510 |
-
"grad_norm": 0.47370073199272156,
|
511 |
-
"learning_rate": 2.125e-05,
|
512 |
-
"loss": 6.9277,
|
513 |
-
"step": 144
|
514 |
-
},
|
515 |
-
{
|
516 |
-
"epoch": 13.904761904761905,
|
517 |
-
"grad_norm": 0.3924289345741272,
|
518 |
-
"learning_rate": 1.8750000000000002e-05,
|
519 |
-
"loss": 6.8967,
|
520 |
-
"step": 146
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 14.095238095238095,
|
524 |
-
"grad_norm": 0.5621922612190247,
|
525 |
-
"learning_rate": 1.6250000000000002e-05,
|
526 |
-
"loss": 6.7197,
|
527 |
-
"step": 148
|
528 |
-
},
|
529 |
-
{
|
530 |
-
"epoch": 14.285714285714286,
|
531 |
-
"grad_norm": 0.3454875349998474,
|
532 |
-
"learning_rate": 1.3750000000000002e-05,
|
533 |
-
"loss": 6.9314,
|
534 |
-
"step": 150
|
535 |
-
},
|
536 |
-
{
|
537 |
-
"epoch": 14.476190476190476,
|
538 |
-
"grad_norm": 0.3146642744541168,
|
539 |
-
"learning_rate": 1.125e-05,
|
540 |
-
"loss": 6.9142,
|
541 |
-
"step": 152
|
542 |
-
},
|
543 |
-
{
|
544 |
-
"epoch": 14.666666666666666,
|
545 |
-
"grad_norm": 0.3762160837650299,
|
546 |
-
"learning_rate": 8.75e-06,
|
547 |
-
"loss": 6.8759,
|
548 |
-
"step": 154
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 14.857142857142858,
|
552 |
-
"grad_norm": 0.33906954526901245,
|
553 |
-
"learning_rate": 6.25e-06,
|
554 |
-
"loss": 6.8712,
|
555 |
-
"step": 156
|
556 |
-
},
|
557 |
-
{
|
558 |
-
"epoch": 15.047619047619047,
|
559 |
-
"grad_norm": 0.3414846360683441,
|
560 |
-
"learning_rate": 3.75e-06,
|
561 |
-
"loss": 6.737,
|
562 |
-
"step": 158
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 15.238095238095237,
|
566 |
-
"grad_norm": 0.4463809132575989,
|
567 |
-
"learning_rate": 1.25e-06,
|
568 |
-
"loss": 6.9144,
|
569 |
-
"step": 160
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 15.238095238095237,
|
573 |
-
"step": 160,
|
574 |
-
"total_flos": 800861569170024.0,
|
575 |
-
"train_loss": 7.170098584890366,
|
576 |
-
"train_runtime": 677.1666,
|
577 |
-
"train_samples_per_second": 3.969,
|
578 |
"train_steps_per_second": 0.236
|
579 |
}
|
580 |
],
|
581 |
"logging_steps": 2,
|
582 |
-
"max_steps":
|
583 |
"num_input_tokens_seen": 0,
|
584 |
-
"num_train_epochs":
|
585 |
"save_steps": 500,
|
586 |
"stateful_callbacks": {
|
587 |
"TrainerControl": {
|
@@ -595,7 +105,7 @@
|
|
595 |
"attributes": {}
|
596 |
}
|
597 |
},
|
598 |
-
"total_flos":
|
599 |
"train_batch_size": 2,
|
600 |
"trial_name": null,
|
601 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9047619047619047,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.19047619047619047,
|
13 |
+
"grad_norm": 2.075279951095581,
|
14 |
+
"learning_rate": 0.00018,
|
15 |
+
"loss": 9.5584,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.38095238095238093,
|
20 |
+
"grad_norm": 1.2216403484344482,
|
21 |
+
"learning_rate": 0.00016,
|
22 |
+
"loss": 9.2621,
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.5714285714285714,
|
27 |
+
"grad_norm": 1.9454573392868042,
|
28 |
+
"learning_rate": 0.00014,
|
29 |
+
"loss": 8.8941,
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.7619047619047619,
|
34 |
+
"grad_norm": 2.4250237941741943,
|
35 |
+
"learning_rate": 0.00012,
|
36 |
+
"loss": 8.4539,
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.9523809523809523,
|
41 |
+
"grad_norm": 1.720076560974121,
|
42 |
+
"learning_rate": 0.0001,
|
43 |
+
"loss": 8.1194,
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.1428571428571428,
|
48 |
+
"grad_norm": 1.4687391519546509,
|
49 |
+
"learning_rate": 8e-05,
|
50 |
+
"loss": 7.9072,
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.3333333333333333,
|
55 |
+
"grad_norm": 1.1075403690338135,
|
56 |
+
"learning_rate": 6e-05,
|
57 |
+
"loss": 7.7305,
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.5238095238095237,
|
62 |
+
"grad_norm": 1.532745361328125,
|
63 |
+
"learning_rate": 4e-05,
|
64 |
+
"loss": 7.6572,
|
65 |
"step": 16
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.7142857142857144,
|
69 |
+
"grad_norm": 1.2055246829986572,
|
70 |
+
"learning_rate": 2e-05,
|
71 |
+
"loss": 7.6057,
|
72 |
"step": 18
|
73 |
},
|
74 |
{
|
75 |
"epoch": 1.9047619047619047,
|
76 |
+
"grad_norm": 0.9867807030677795,
|
77 |
+
"learning_rate": 0.0,
|
78 |
+
"loss": 7.5695,
|
79 |
"step": 20
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 1.9047619047619047,
|
83 |
+
"step": 20,
|
84 |
+
"total_flos": 99814369025136.0,
|
85 |
+
"train_loss": 8.27579402923584,
|
86 |
+
"train_runtime": 84.8689,
|
87 |
+
"train_samples_per_second": 3.959,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
"train_steps_per_second": 0.236
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 2,
|
92 |
+
"max_steps": 20,
|
93 |
"num_input_tokens_seen": 0,
|
94 |
+
"num_train_epochs": 2,
|
95 |
"save_steps": 500,
|
96 |
"stateful_callbacks": {
|
97 |
"TrainerControl": {
|
|
|
105 |
"attributes": {}
|
106 |
}
|
107 |
},
|
108 |
+
"total_flos": 99814369025136.0,
|
109 |
"train_batch_size": 2,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|