CharlieJi commited on
Commit
b20d652
·
verified ·
1 Parent(s): 51c6fc8

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 +498 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen3-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen3-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
 
16
 
17
  # qwen3-8b-dabstep-reasoning-108-fixed-reasoning-sharegpt-sft
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the eval-ds-dabstep-reasoning-108-fixed-reasoning-sharegpt dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 12383961956352.0,
4
+ "train_loss": 0.45606403878101937,
5
+ "train_runtime": 1434.1495,
6
+ "train_samples_per_second": 0.352,
7
+ "train_steps_per_second": 0.045
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 12383961956352.0,
4
+ "train_loss": 0.45606403878101937,
5
+ "train_runtime": 1434.1495,
6
+ "train_samples_per_second": 0.352,
7
+ "train_steps_per_second": 0.045
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,498 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 65,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.07692307692307693,
14
+ "grad_norm": 6.370218968023409,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.9617,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.15384615384615385,
21
+ "grad_norm": 7.062823048926537,
22
+ "learning_rate": 1e-05,
23
+ "loss": 0.9221,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.23076923076923078,
28
+ "grad_norm": 3.508151848769913,
29
+ "learning_rate": 9.993977281025862e-06,
30
+ "loss": 0.8516,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.3076923076923077,
35
+ "grad_norm": 2.1315111375920908,
36
+ "learning_rate": 9.975923633360985e-06,
37
+ "loss": 0.7455,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.38461538461538464,
42
+ "grad_norm": 2.067690304064468,
43
+ "learning_rate": 9.945882549823906e-06,
44
+ "loss": 0.7818,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.46153846153846156,
49
+ "grad_norm": 2.164959330267267,
50
+ "learning_rate": 9.903926402016153e-06,
51
+ "loss": 0.7056,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.5384615384615384,
56
+ "grad_norm": 1.7114510182271578,
57
+ "learning_rate": 9.850156265972722e-06,
58
+ "loss": 0.6684,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.6153846153846154,
63
+ "grad_norm": 1.4221134607922832,
64
+ "learning_rate": 9.784701678661045e-06,
65
+ "loss": 0.6943,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.6923076923076923,
70
+ "grad_norm": 1.2054367990274877,
71
+ "learning_rate": 9.707720325915105e-06,
72
+ "loss": 0.6606,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.7692307692307693,
77
+ "grad_norm": 1.234597606787108,
78
+ "learning_rate": 9.619397662556434e-06,
79
+ "loss": 0.662,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.8461538461538461,
84
+ "grad_norm": 1.0253610984337118,
85
+ "learning_rate": 9.519946465617217e-06,
86
+ "loss": 0.6118,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.9230769230769231,
91
+ "grad_norm": 0.9531385105738269,
92
+ "learning_rate": 9.409606321741776e-06,
93
+ "loss": 0.6148,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 1.0,
98
+ "grad_norm": 0.8797592723988117,
99
+ "learning_rate": 9.288643050001362e-06,
100
+ "loss": 0.5794,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 1.0769230769230769,
105
+ "grad_norm": 0.8614478397135895,
106
+ "learning_rate": 9.157348061512728e-06,
107
+ "loss": 0.5439,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 1.1538461538461537,
112
+ "grad_norm": 0.8816737566077302,
113
+ "learning_rate": 9.016037657403225e-06,
114
+ "loss": 0.5074,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 1.2307692307692308,
119
+ "grad_norm": 0.8669076102244132,
120
+ "learning_rate": 8.865052266813686e-06,
121
+ "loss": 0.5223,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 1.3076923076923077,
126
+ "grad_norm": 0.8101412038742847,
127
+ "learning_rate": 8.704755626774796e-06,
128
+ "loss": 0.5032,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 1.3846153846153846,
133
+ "grad_norm": 0.8569082435438978,
134
+ "learning_rate": 8.535533905932739e-06,
135
+ "loss": 0.5523,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 1.4615384615384617,
140
+ "grad_norm": 0.7453930156975321,
141
+ "learning_rate": 8.357794774235094e-06,
142
+ "loss": 0.49,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 1.5384615384615383,
147
+ "grad_norm": 0.6283060582206399,
148
+ "learning_rate": 8.171966420818227e-06,
149
+ "loss": 0.4874,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 1.6153846153846154,
154
+ "grad_norm": 0.8023986095300789,
155
+ "learning_rate": 7.978496522462167e-06,
156
+ "loss": 0.4622,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 1.6923076923076923,
161
+ "grad_norm": 0.7122469220028385,
162
+ "learning_rate": 7.777851165098012e-06,
163
+ "loss": 0.4828,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 1.7692307692307692,
168
+ "grad_norm": 0.5943006237807561,
169
+ "learning_rate": 7.570513720966108e-06,
170
+ "loss": 0.4552,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 1.8461538461538463,
175
+ "grad_norm": 0.7102435889730987,
176
+ "learning_rate": 7.3569836841299905e-06,
177
+ "loss": 0.4797,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 1.9230769230769231,
182
+ "grad_norm": 0.7244490320083123,
183
+ "learning_rate": 7.137775467151411e-06,
184
+ "loss": 0.4787,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 2.0,
189
+ "grad_norm": 0.6176632029398068,
190
+ "learning_rate": 6.913417161825449e-06,
191
+ "loss": 0.4329,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 2.076923076923077,
196
+ "grad_norm": 0.8216799021152335,
197
+ "learning_rate": 6.684449266961101e-06,
198
+ "loss": 0.3743,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 2.1538461538461537,
203
+ "grad_norm": 0.6005917289643109,
204
+ "learning_rate": 6.451423386272312e-06,
205
+ "loss": 0.4369,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 2.230769230769231,
210
+ "grad_norm": 0.624537941070379,
211
+ "learning_rate": 6.21490089951632e-06,
212
+ "loss": 0.4317,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 2.3076923076923075,
217
+ "grad_norm": 0.6577500844311218,
218
+ "learning_rate": 5.975451610080643e-06,
219
+ "loss": 0.4278,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 2.3846153846153846,
224
+ "grad_norm": 0.5918326665297654,
225
+ "learning_rate": 5.733652372276809e-06,
226
+ "loss": 0.444,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 2.4615384615384617,
231
+ "grad_norm": 0.7154936597726321,
232
+ "learning_rate": 5.490085701647805e-06,
233
+ "loss": 0.3575,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 2.5384615384615383,
238
+ "grad_norm": 0.7058375820227064,
239
+ "learning_rate": 5.245338371637091e-06,
240
+ "loss": 0.3927,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 2.6153846153846154,
245
+ "grad_norm": 0.624999538418926,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.4115,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 2.6923076923076925,
252
+ "grad_norm": 0.6189527167900223,
253
+ "learning_rate": 4.75466162836291e-06,
254
+ "loss": 0.393,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 2.769230769230769,
259
+ "grad_norm": 0.6581614058929585,
260
+ "learning_rate": 4.509914298352197e-06,
261
+ "loss": 0.3589,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 2.8461538461538463,
266
+ "grad_norm": 0.5968832668044702,
267
+ "learning_rate": 4.266347627723192e-06,
268
+ "loss": 0.4319,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 2.9230769230769234,
273
+ "grad_norm": 0.6829725248958235,
274
+ "learning_rate": 4.02454838991936e-06,
275
+ "loss": 0.3402,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 3.0,
280
+ "grad_norm": 0.6835108217400175,
281
+ "learning_rate": 3.7850991004836813e-06,
282
+ "loss": 0.3331,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 3.076923076923077,
287
+ "grad_norm": 0.7315492211655491,
288
+ "learning_rate": 3.5485766137276894e-06,
289
+ "loss": 0.3531,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 3.1538461538461537,
294
+ "grad_norm": 0.6375294587624502,
295
+ "learning_rate": 3.3155507330389004e-06,
296
+ "loss": 0.3531,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 3.230769230769231,
301
+ "grad_norm": 0.618128196978316,
302
+ "learning_rate": 3.0865828381745515e-06,
303
+ "loss": 0.3411,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 3.3076923076923075,
308
+ "grad_norm": 0.6384871969000007,
309
+ "learning_rate": 2.862224532848591e-06,
310
+ "loss": 0.3315,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 3.3846153846153846,
315
+ "grad_norm": 0.561255153854599,
316
+ "learning_rate": 2.6430163158700116e-06,
317
+ "loss": 0.3666,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 3.4615384615384617,
322
+ "grad_norm": 0.5408489944687312,
323
+ "learning_rate": 2.429486279033892e-06,
324
+ "loss": 0.3705,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 3.5384615384615383,
329
+ "grad_norm": 0.5671728055194564,
330
+ "learning_rate": 2.2221488349019903e-06,
331
+ "loss": 0.3648,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 3.6153846153846154,
336
+ "grad_norm": 0.5700975153063862,
337
+ "learning_rate": 2.0215034775378336e-06,
338
+ "loss": 0.3223,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 3.6923076923076925,
343
+ "grad_norm": 0.664767908088173,
344
+ "learning_rate": 1.8280335791817733e-06,
345
+ "loss": 0.3183,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 3.769230769230769,
350
+ "grad_norm": 0.6330871629952953,
351
+ "learning_rate": 1.642205225764908e-06,
352
+ "loss": 0.3209,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 3.8461538461538463,
357
+ "grad_norm": 0.6309153488529204,
358
+ "learning_rate": 1.4644660940672628e-06,
359
+ "loss": 0.3199,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 3.9230769230769234,
364
+ "grad_norm": 0.55827785835018,
365
+ "learning_rate": 1.2952443732252058e-06,
366
+ "loss": 0.3426,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 4.0,
371
+ "grad_norm": 0.5523594386231,
372
+ "learning_rate": 1.134947733186315e-06,
373
+ "loss": 0.3742,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 4.076923076923077,
378
+ "grad_norm": 0.5458600271870175,
379
+ "learning_rate": 9.83962342596776e-07,
380
+ "loss": 0.3534,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 4.153846153846154,
385
+ "grad_norm": 0.6854362784340675,
386
+ "learning_rate": 8.426519384872733e-07,
387
+ "loss": 0.3497,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 4.230769230769231,
392
+ "grad_norm": 0.6032529402232379,
393
+ "learning_rate": 7.113569499986401e-07,
394
+ "loss": 0.2484,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 4.3076923076923075,
399
+ "grad_norm": 0.7477132723449166,
400
+ "learning_rate": 5.903936782582253e-07,
401
+ "loss": 0.244,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 4.384615384615385,
406
+ "grad_norm": 0.5868192979660759,
407
+ "learning_rate": 4.800535343827834e-07,
408
+ "loss": 0.3561,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 4.461538461538462,
413
+ "grad_norm": 0.5590511625666816,
414
+ "learning_rate": 3.8060233744356634e-07,
415
+ "loss": 0.3018,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 4.538461538461538,
420
+ "grad_norm": 0.573822252707526,
421
+ "learning_rate": 2.9227967408489653e-07,
422
+ "loss": 0.3274,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 4.615384615384615,
427
+ "grad_norm": 0.5539473518142963,
428
+ "learning_rate": 2.152983213389559e-07,
429
+ "loss": 0.329,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 4.6923076923076925,
434
+ "grad_norm": 0.5602498609734554,
435
+ "learning_rate": 1.4984373402728014e-07,
436
+ "loss": 0.3235,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 4.769230769230769,
441
+ "grad_norm": 0.5088498618342225,
442
+ "learning_rate": 9.607359798384785e-08,
443
+ "loss": 0.357,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 4.846153846153846,
448
+ "grad_norm": 0.5487703200660301,
449
+ "learning_rate": 5.411745017609493e-08,
450
+ "loss": 0.2892,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 4.923076923076923,
455
+ "grad_norm": 0.5219657252094004,
456
+ "learning_rate": 2.4076366639015914e-08,
457
+ "loss": 0.349,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 5.0,
462
+ "grad_norm": 0.5380803859588003,
463
+ "learning_rate": 6.022718974137976e-09,
464
+ "loss": 0.3456,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 5.0,
469
+ "step": 65,
470
+ "total_flos": 12383961956352.0,
471
+ "train_loss": 0.45606403878101937,
472
+ "train_runtime": 1434.1495,
473
+ "train_samples_per_second": 0.352,
474
+ "train_steps_per_second": 0.045
475
+ }
476
+ ],
477
+ "logging_steps": 1,
478
+ "max_steps": 65,
479
+ "num_input_tokens_seen": 0,
480
+ "num_train_epochs": 5,
481
+ "save_steps": 42,
482
+ "stateful_callbacks": {
483
+ "TrainerControl": {
484
+ "args": {
485
+ "should_epoch_stop": false,
486
+ "should_evaluate": false,
487
+ "should_log": false,
488
+ "should_save": true,
489
+ "should_training_stop": true
490
+ },
491
+ "attributes": {}
492
+ }
493
+ },
494
+ "total_flos": 12383961956352.0,
495
+ "train_batch_size": 1,
496
+ "trial_name": null,
497
+ "trial_params": null
498
+ }
training_loss.png ADDED