sedrickkeh commited on
Commit
2eb9485
·
verified ·
1 Parent(s): 99b5227

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +532 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-32B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: openthoughts2_1k_32B
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # openthoughts2_1k_32B
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-32B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: openthoughts2_1k_32B
 
16
 
17
  # openthoughts2_1k_32B
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the mlfoundations-dev/openthoughts2_1k dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.75,
3
+ "total_flos": 1.0066919896508006e+17,
4
+ "train_loss": 0.3906510761805943,
5
+ "train_runtime": 9044.8257,
6
+ "train_samples_per_second": 0.774,
7
+ "train_steps_per_second": 0.008
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.75,
3
+ "total_flos": 1.0066919896508006e+17,
4
+ "train_loss": 0.3906510761805943,
5
+ "train_runtime": 9044.8257,
6
+ "train_samples_per_second": 0.774,
7
+ "train_steps_per_second": 0.008
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,532 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.75,
5
+ "eval_steps": 500,
6
+ "global_step": 70,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09375,
13
+ "grad_norm": 2.875503705356323,
14
+ "learning_rate": 2.8571428571428573e-06,
15
+ "loss": 0.7458,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.1875,
20
+ "grad_norm": 2.990735042222842,
21
+ "learning_rate": 5.7142857142857145e-06,
22
+ "loss": 0.7602,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.28125,
27
+ "grad_norm": 2.8743554915409346,
28
+ "learning_rate": 8.571428571428571e-06,
29
+ "loss": 0.7519,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.375,
34
+ "grad_norm": 1.4772155527540136,
35
+ "learning_rate": 1.1428571428571429e-05,
36
+ "loss": 0.7153,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.46875,
41
+ "grad_norm": 1.3260714657658668,
42
+ "learning_rate": 1.4285714285714287e-05,
43
+ "loss": 0.6684,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.5625,
48
+ "grad_norm": 1.1210151382840188,
49
+ "learning_rate": 1.7142857142857142e-05,
50
+ "loss": 0.64,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.65625,
55
+ "grad_norm": 1.928672362983636,
56
+ "learning_rate": 2e-05,
57
+ "loss": 0.6327,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.75,
62
+ "grad_norm": 1.3492877961036636,
63
+ "learning_rate": 1.9987569212189224e-05,
64
+ "loss": 0.6231,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.84375,
69
+ "grad_norm": 1.682740189167653,
70
+ "learning_rate": 1.9950307753654016e-05,
71
+ "loss": 0.549,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.9375,
76
+ "grad_norm": 1.3222526769254588,
77
+ "learning_rate": 1.9888308262251286e-05,
78
+ "loss": 0.5613,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.0625,
83
+ "grad_norm": 1.7776044627317216,
84
+ "learning_rate": 1.9801724878485438e-05,
85
+ "loss": 0.9283,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.15625,
90
+ "grad_norm": 0.6787199178640781,
91
+ "learning_rate": 1.969077286229078e-05,
92
+ "loss": 0.5032,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.25,
97
+ "grad_norm": 0.7267722871293905,
98
+ "learning_rate": 1.955572805786141e-05,
99
+ "loss": 0.4411,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.34375,
104
+ "grad_norm": 0.8081353104439796,
105
+ "learning_rate": 1.9396926207859085e-05,
106
+ "loss": 0.5585,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.4375,
111
+ "grad_norm": 0.6320827316278724,
112
+ "learning_rate": 1.921476211870408e-05,
113
+ "loss": 0.5122,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.53125,
118
+ "grad_norm": 0.6454145407007941,
119
+ "learning_rate": 1.900968867902419e-05,
120
+ "loss": 0.472,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.625,
125
+ "grad_norm": 0.7650252540496532,
126
+ "learning_rate": 1.8782215733702286e-05,
127
+ "loss": 0.4393,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.71875,
132
+ "grad_norm": 0.5636187172161755,
133
+ "learning_rate": 1.8532908816321557e-05,
134
+ "loss": 0.5286,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.8125,
139
+ "grad_norm": 0.4876522873094857,
140
+ "learning_rate": 1.826238774315995e-05,
141
+ "loss": 0.446,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.90625,
146
+ "grad_norm": 0.5614039576077123,
147
+ "learning_rate": 1.7971325072229227e-05,
148
+ "loss": 0.4645,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.03125,
153
+ "grad_norm": 1.011631880110753,
154
+ "learning_rate": 1.766044443118978e-05,
155
+ "loss": 0.7493,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.125,
160
+ "grad_norm": 0.48981037970039826,
161
+ "learning_rate": 1.7330518718298263e-05,
162
+ "loss": 0.4312,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.21875,
167
+ "grad_norm": 0.5824671327559001,
168
+ "learning_rate": 1.698236818086073e-05,
169
+ "loss": 0.3837,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.3125,
174
+ "grad_norm": 0.4951836648461806,
175
+ "learning_rate": 1.6616858375968596e-05,
176
+ "loss": 0.3636,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.40625,
181
+ "grad_norm": 0.40746509032687167,
182
+ "learning_rate": 1.6234898018587336e-05,
183
+ "loss": 0.3929,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.5,
188
+ "grad_norm": 0.47270781275959445,
189
+ "learning_rate": 1.5837436722347902e-05,
190
+ "loss": 0.4309,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.59375,
195
+ "grad_norm": 0.4139970793315771,
196
+ "learning_rate": 1.5425462638657597e-05,
197
+ "loss": 0.347,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.6875,
202
+ "grad_norm": 0.4094525531542567,
203
+ "learning_rate": 1.5000000000000002e-05,
204
+ "loss": 0.3898,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.78125,
209
+ "grad_norm": 0.3609227071911589,
210
+ "learning_rate": 1.4562106573531632e-05,
211
+ "loss": 0.3793,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.875,
216
+ "grad_norm": 0.3475046450366041,
217
+ "learning_rate": 1.4112871031306118e-05,
218
+ "loss": 0.3784,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.96875,
223
+ "grad_norm": 0.6690800228387159,
224
+ "learning_rate": 1.3653410243663953e-05,
225
+ "loss": 0.652,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 3.09375,
230
+ "grad_norm": 0.44950641151876647,
231
+ "learning_rate": 1.3184866502516846e-05,
232
+ "loss": 0.3481,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 3.1875,
237
+ "grad_norm": 0.3848478424704702,
238
+ "learning_rate": 1.2708404681430054e-05,
239
+ "loss": 0.3106,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 3.28125,
244
+ "grad_norm": 0.5347567465033009,
245
+ "learning_rate": 1.2225209339563144e-05,
246
+ "loss": 0.3268,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 3.375,
251
+ "grad_norm": 0.4072495441359064,
252
+ "learning_rate": 1.1736481776669307e-05,
253
+ "loss": 0.3324,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 3.46875,
258
+ "grad_norm": 0.38962221521765955,
259
+ "learning_rate": 1.1243437046474854e-05,
260
+ "loss": 0.3175,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 3.5625,
265
+ "grad_norm": 0.3788865699519135,
266
+ "learning_rate": 1.0747300935864245e-05,
267
+ "loss": 0.3257,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 3.65625,
272
+ "grad_norm": 0.395721175839029,
273
+ "learning_rate": 1.0249306917380731e-05,
274
+ "loss": 0.306,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 3.75,
279
+ "grad_norm": 0.33584385177429055,
280
+ "learning_rate": 9.750693082619274e-06,
281
+ "loss": 0.2622,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 3.84375,
286
+ "grad_norm": 0.39573379970895023,
287
+ "learning_rate": 9.252699064135759e-06,
288
+ "loss": 0.3478,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 3.9375,
293
+ "grad_norm": 0.35397292743924824,
294
+ "learning_rate": 8.756562953525151e-06,
295
+ "loss": 0.3309,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 4.0625,
300
+ "grad_norm": 0.6876995002147458,
301
+ "learning_rate": 8.263518223330698e-06,
302
+ "loss": 0.4723,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 4.15625,
307
+ "grad_norm": 0.4197974469543892,
308
+ "learning_rate": 7.774790660436857e-06,
309
+ "loss": 0.2464,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 4.25,
314
+ "grad_norm": 0.38253306452841973,
315
+ "learning_rate": 7.291595318569951e-06,
316
+ "loss": 0.228,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 4.34375,
321
+ "grad_norm": 0.3901250987784833,
322
+ "learning_rate": 6.815133497483157e-06,
323
+ "loss": 0.2946,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 4.4375,
328
+ "grad_norm": 0.36777969276301314,
329
+ "learning_rate": 6.34658975633605e-06,
330
+ "loss": 0.2977,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 4.53125,
335
+ "grad_norm": 0.3425452852047255,
336
+ "learning_rate": 5.887128968693887e-06,
337
+ "loss": 0.2405,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 4.625,
342
+ "grad_norm": 0.34222956283167716,
343
+ "learning_rate": 5.43789342646837e-06,
344
+ "loss": 0.2637,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 4.71875,
349
+ "grad_norm": 0.3010985646978744,
350
+ "learning_rate": 5.000000000000003e-06,
351
+ "loss": 0.2559,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 4.8125,
356
+ "grad_norm": 0.3204500290045904,
357
+ "learning_rate": 4.5745373613424075e-06,
358
+ "loss": 0.2402,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 4.90625,
363
+ "grad_norm": 0.43376115329479936,
364
+ "learning_rate": 4.162563277652104e-06,
365
+ "loss": 0.2634,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 5.03125,
370
+ "grad_norm": 0.5277252915121167,
371
+ "learning_rate": 3.7651019814126656e-06,
372
+ "loss": 0.3428,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 5.125,
377
+ "grad_norm": 0.3242694914181531,
378
+ "learning_rate": 3.3831416240314085e-06,
379
+ "loss": 0.2751,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 5.21875,
384
+ "grad_norm": 0.2629237100248874,
385
+ "learning_rate": 3.017631819139273e-06,
386
+ "loss": 0.206,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 5.3125,
391
+ "grad_norm": 0.26869870078975083,
392
+ "learning_rate": 2.669481281701739e-06,
393
+ "loss": 0.208,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 5.40625,
398
+ "grad_norm": 0.2946292151795919,
399
+ "learning_rate": 2.339555568810221e-06,
400
+ "loss": 0.176,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 5.5,
405
+ "grad_norm": 0.35978658604512964,
406
+ "learning_rate": 2.0286749277707783e-06,
407
+ "loss": 0.247,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 5.59375,
412
+ "grad_norm": 0.2694338117234328,
413
+ "learning_rate": 1.7376122568400533e-06,
414
+ "loss": 0.2397,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 5.6875,
419
+ "grad_norm": 0.23603362724985336,
420
+ "learning_rate": 1.467091183678444e-06,
421
+ "loss": 0.2557,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 5.78125,
426
+ "grad_norm": 0.22274653612755244,
427
+ "learning_rate": 1.2177842662977136e-06,
428
+ "loss": 0.2265,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 5.875,
433
+ "grad_norm": 0.24217335349194297,
434
+ "learning_rate": 9.903113209758098e-07,
435
+ "loss": 0.2466,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 5.96875,
440
+ "grad_norm": 0.48048696089483417,
441
+ "learning_rate": 7.852378812959227e-07,
442
+ "loss": 0.3496,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 6.09375,
447
+ "grad_norm": 0.2936135705752043,
448
+ "learning_rate": 6.030737921409169e-07,
449
+ "loss": 0.1815,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 6.1875,
454
+ "grad_norm": 0.2767171386917678,
455
+ "learning_rate": 4.4427194213859216e-07,
456
+ "loss": 0.2077,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 6.28125,
461
+ "grad_norm": 0.2345675305906572,
462
+ "learning_rate": 3.0922713770922155e-07,
463
+ "loss": 0.2032,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 6.375,
468
+ "grad_norm": 0.23553355433831719,
469
+ "learning_rate": 1.9827512151456175e-07,
470
+ "loss": 0.2458,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 6.46875,
475
+ "grad_norm": 0.20099324393208673,
476
+ "learning_rate": 1.1169173774871478e-07,
477
+ "loss": 0.2298,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 6.5625,
482
+ "grad_norm": 0.21234850892293564,
483
+ "learning_rate": 4.9692246345985905e-08,
484
+ "loss": 0.2243,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 6.65625,
489
+ "grad_norm": 0.2120148750108375,
490
+ "learning_rate": 1.2430787810776556e-08,
491
+ "loss": 0.2301,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 6.75,
496
+ "grad_norm": 0.2753841782457882,
497
+ "learning_rate": 0.0,
498
+ "loss": 0.2001,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 6.75,
503
+ "step": 70,
504
+ "total_flos": 1.0066919896508006e+17,
505
+ "train_loss": 0.3906510761805943,
506
+ "train_runtime": 9044.8257,
507
+ "train_samples_per_second": 0.774,
508
+ "train_steps_per_second": 0.008
509
+ }
510
+ ],
511
+ "logging_steps": 1.0,
512
+ "max_steps": 70,
513
+ "num_input_tokens_seen": 0,
514
+ "num_train_epochs": 7,
515
+ "save_steps": 500,
516
+ "stateful_callbacks": {
517
+ "TrainerControl": {
518
+ "args": {
519
+ "should_epoch_stop": false,
520
+ "should_evaluate": false,
521
+ "should_log": false,
522
+ "should_save": true,
523
+ "should_training_stop": true
524
+ },
525
+ "attributes": {}
526
+ }
527
+ },
528
+ "total_flos": 1.0066919896508006e+17,
529
+ "train_batch_size": 1,
530
+ "trial_name": null,
531
+ "trial_params": null
532
+ }
training_loss.png ADDED