neginr commited on
Commit
33e002b
·
verified ·
1 Parent(s): 7eab2d8

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/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: no_pipeline_code_1k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # no_pipeline_code_1k
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: no_pipeline_code_1k
 
16
 
17
  # no_pipeline_code_1k
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/no_pipeline_code_1k dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.666666666666667,
3
+ "total_flos": 8.788556475321549e+16,
4
+ "train_loss": 0.5346557378768921,
5
+ "train_runtime": 2433.5668,
6
+ "train_samples_per_second": 2.876,
7
+ "train_steps_per_second": 0.029
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.666666666666667,
3
+ "total_flos": 8.788556475321549e+16,
4
+ "train_loss": 0.5346557378768921,
5
+ "train_runtime": 2433.5668,
6
+ "train_samples_per_second": 2.876,
7
+ "train_steps_per_second": 0.029
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,532 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.666666666666667,
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": 0.09523809523809523,
13
+ "grad_norm": 7.484724060219609,
14
+ "learning_rate": 2.8571428571428573e-06,
15
+ "loss": 1.1681,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.19047619047619047,
20
+ "grad_norm": 6.829131756518376,
21
+ "learning_rate": 5.7142857142857145e-06,
22
+ "loss": 1.1712,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.2857142857142857,
27
+ "grad_norm": 6.664738586442681,
28
+ "learning_rate": 8.571428571428571e-06,
29
+ "loss": 1.1399,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.38095238095238093,
34
+ "grad_norm": 3.3584066110083803,
35
+ "learning_rate": 1.1428571428571429e-05,
36
+ "loss": 1.0693,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.47619047619047616,
41
+ "grad_norm": 3.442370114366976,
42
+ "learning_rate": 1.4285714285714287e-05,
43
+ "loss": 1.0587,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.5714285714285714,
48
+ "grad_norm": 3.56669601049149,
49
+ "learning_rate": 1.7142857142857142e-05,
50
+ "loss": 1.0467,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.6666666666666666,
55
+ "grad_norm": 3.7867450428586493,
56
+ "learning_rate": 2e-05,
57
+ "loss": 0.9659,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.7619047619047619,
62
+ "grad_norm": 3.335254231811083,
63
+ "learning_rate": 1.9987569212189224e-05,
64
+ "loss": 0.9521,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.8571428571428571,
69
+ "grad_norm": 3.0201486501211114,
70
+ "learning_rate": 1.9950307753654016e-05,
71
+ "loss": 0.9181,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.9523809523809523,
76
+ "grad_norm": 2.1291562708961274,
77
+ "learning_rate": 1.9888308262251286e-05,
78
+ "loss": 0.883,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.0476190476190477,
83
+ "grad_norm": 2.2331674865390463,
84
+ "learning_rate": 1.9801724878485438e-05,
85
+ "loss": 0.8161,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.1428571428571428,
90
+ "grad_norm": 1.5926856923354156,
91
+ "learning_rate": 1.969077286229078e-05,
92
+ "loss": 0.7876,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.2380952380952381,
97
+ "grad_norm": 1.2789248216760856,
98
+ "learning_rate": 1.955572805786141e-05,
99
+ "loss": 0.7916,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.3333333333333333,
104
+ "grad_norm": 1.2902886924531696,
105
+ "learning_rate": 1.9396926207859085e-05,
106
+ "loss": 0.7473,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.4285714285714286,
111
+ "grad_norm": 0.9921992943923053,
112
+ "learning_rate": 1.921476211870408e-05,
113
+ "loss": 0.7337,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.5238095238095237,
118
+ "grad_norm": 1.2564364639133383,
119
+ "learning_rate": 1.900968867902419e-05,
120
+ "loss": 0.7291,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.619047619047619,
125
+ "grad_norm": 0.9308298989088688,
126
+ "learning_rate": 1.8782215733702286e-05,
127
+ "loss": 0.7087,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.7142857142857144,
132
+ "grad_norm": 0.8656622992325634,
133
+ "learning_rate": 1.8532908816321557e-05,
134
+ "loss": 0.7155,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.8095238095238095,
139
+ "grad_norm": 0.8833122782033153,
140
+ "learning_rate": 1.826238774315995e-05,
141
+ "loss": 0.7182,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.9047619047619047,
146
+ "grad_norm": 7.393225273569773,
147
+ "learning_rate": 1.7971325072229227e-05,
148
+ "loss": 0.6887,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.0,
153
+ "grad_norm": 1.3701068669512917,
154
+ "learning_rate": 1.766044443118978e-05,
155
+ "loss": 0.6928,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.0952380952380953,
160
+ "grad_norm": 0.9300509606319867,
161
+ "learning_rate": 1.7330518718298263e-05,
162
+ "loss": 0.5924,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.1904761904761907,
167
+ "grad_norm": 1.0080266962573095,
168
+ "learning_rate": 1.698236818086073e-05,
169
+ "loss": 0.5783,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.2857142857142856,
174
+ "grad_norm": 1.0171300238506318,
175
+ "learning_rate": 1.6616858375968596e-05,
176
+ "loss": 0.5365,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.380952380952381,
181
+ "grad_norm": 1.0869352839148714,
182
+ "learning_rate": 1.6234898018587336e-05,
183
+ "loss": 0.5672,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.4761904761904763,
188
+ "grad_norm": 0.9352917707943944,
189
+ "learning_rate": 1.5837436722347902e-05,
190
+ "loss": 0.5471,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.571428571428571,
195
+ "grad_norm": 0.993521936112931,
196
+ "learning_rate": 1.5425462638657597e-05,
197
+ "loss": 0.5512,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.6666666666666665,
202
+ "grad_norm": 0.9930650263586331,
203
+ "learning_rate": 1.5000000000000002e-05,
204
+ "loss": 0.5206,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.761904761904762,
209
+ "grad_norm": 0.974105528692108,
210
+ "learning_rate": 1.4562106573531632e-05,
211
+ "loss": 0.5612,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.857142857142857,
216
+ "grad_norm": 0.7181078494690534,
217
+ "learning_rate": 1.4112871031306118e-05,
218
+ "loss": 0.5221,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.9523809523809526,
223
+ "grad_norm": 1.103522827508161,
224
+ "learning_rate": 1.3653410243663953e-05,
225
+ "loss": 0.5776,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 3.0476190476190474,
230
+ "grad_norm": 0.8303489757452878,
231
+ "learning_rate": 1.3184866502516846e-05,
232
+ "loss": 0.5098,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 3.142857142857143,
237
+ "grad_norm": 0.8903290470299019,
238
+ "learning_rate": 1.2708404681430054e-05,
239
+ "loss": 0.4652,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 3.238095238095238,
244
+ "grad_norm": 0.7691679182805314,
245
+ "learning_rate": 1.2225209339563144e-05,
246
+ "loss": 0.4647,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 3.3333333333333335,
251
+ "grad_norm": 0.8793575084895185,
252
+ "learning_rate": 1.1736481776669307e-05,
253
+ "loss": 0.3883,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 3.4285714285714284,
258
+ "grad_norm": 0.7939936564361072,
259
+ "learning_rate": 1.1243437046474854e-05,
260
+ "loss": 0.4612,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 3.5238095238095237,
265
+ "grad_norm": 0.7197516044980385,
266
+ "learning_rate": 1.0747300935864245e-05,
267
+ "loss": 0.416,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 3.619047619047619,
272
+ "grad_norm": 0.6671406349191635,
273
+ "learning_rate": 1.0249306917380731e-05,
274
+ "loss": 0.3956,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 3.7142857142857144,
279
+ "grad_norm": 0.7440093237406595,
280
+ "learning_rate": 9.750693082619274e-06,
281
+ "loss": 0.4029,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 3.8095238095238093,
286
+ "grad_norm": 0.7753199974148295,
287
+ "learning_rate": 9.252699064135759e-06,
288
+ "loss": 0.4192,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 3.9047619047619047,
293
+ "grad_norm": 0.8295304396639599,
294
+ "learning_rate": 8.756562953525151e-06,
295
+ "loss": 0.4103,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 4.0,
300
+ "grad_norm": 0.6905026252396183,
301
+ "learning_rate": 8.263518223330698e-06,
302
+ "loss": 0.3936,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 4.095238095238095,
307
+ "grad_norm": 0.6460976497116867,
308
+ "learning_rate": 7.774790660436857e-06,
309
+ "loss": 0.36,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 4.190476190476191,
314
+ "grad_norm": 0.5661215485831413,
315
+ "learning_rate": 7.291595318569951e-06,
316
+ "loss": 0.3508,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 4.285714285714286,
321
+ "grad_norm": 0.6575394619885413,
322
+ "learning_rate": 6.815133497483157e-06,
323
+ "loss": 0.3752,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 4.380952380952381,
328
+ "grad_norm": 0.5600906657273061,
329
+ "learning_rate": 6.34658975633605e-06,
330
+ "loss": 0.3458,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 4.476190476190476,
335
+ "grad_norm": 0.5345328508008275,
336
+ "learning_rate": 5.887128968693887e-06,
337
+ "loss": 0.3336,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 4.571428571428571,
342
+ "grad_norm": 0.5062595557522536,
343
+ "learning_rate": 5.43789342646837e-06,
344
+ "loss": 0.3038,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 4.666666666666667,
349
+ "grad_norm": 0.5400689758849032,
350
+ "learning_rate": 5.000000000000003e-06,
351
+ "loss": 0.3211,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 4.761904761904762,
356
+ "grad_norm": 0.5310247032056505,
357
+ "learning_rate": 4.5745373613424075e-06,
358
+ "loss": 0.3365,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 4.857142857142857,
363
+ "grad_norm": 0.518898644519975,
364
+ "learning_rate": 4.162563277652104e-06,
365
+ "loss": 0.3369,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 4.9523809523809526,
370
+ "grad_norm": 0.5254824086989422,
371
+ "learning_rate": 3.7651019814126656e-06,
372
+ "loss": 0.3433,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 5.0476190476190474,
377
+ "grad_norm": 0.5021916764888207,
378
+ "learning_rate": 3.3831416240314085e-06,
379
+ "loss": 0.3293,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 5.142857142857143,
384
+ "grad_norm": 0.4669975382305803,
385
+ "learning_rate": 3.017631819139273e-06,
386
+ "loss": 0.3245,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 5.238095238095238,
391
+ "grad_norm": 0.4577103294748289,
392
+ "learning_rate": 2.669481281701739e-06,
393
+ "loss": 0.3289,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 5.333333333333333,
398
+ "grad_norm": 0.3976260825196007,
399
+ "learning_rate": 2.339555568810221e-06,
400
+ "loss": 0.2791,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 5.428571428571429,
405
+ "grad_norm": 0.42070433621682796,
406
+ "learning_rate": 2.0286749277707783e-06,
407
+ "loss": 0.2922,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 5.523809523809524,
412
+ "grad_norm": 0.38740869241789666,
413
+ "learning_rate": 1.7376122568400533e-06,
414
+ "loss": 0.2699,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 5.619047619047619,
419
+ "grad_norm": 0.39143917552785173,
420
+ "learning_rate": 1.467091183678444e-06,
421
+ "loss": 0.3225,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 5.714285714285714,
426
+ "grad_norm": 0.3655735116880477,
427
+ "learning_rate": 1.2177842662977136e-06,
428
+ "loss": 0.2777,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 5.809523809523809,
433
+ "grad_norm": 0.39040760721698864,
434
+ "learning_rate": 9.903113209758098e-07,
435
+ "loss": 0.2655,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 5.904761904761905,
440
+ "grad_norm": 0.3709207628693518,
441
+ "learning_rate": 7.852378812959227e-07,
442
+ "loss": 0.2869,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 6.0,
447
+ "grad_norm": 0.34592781426824,
448
+ "learning_rate": 6.030737921409169e-07,
449
+ "loss": 0.3139,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 6.095238095238095,
454
+ "grad_norm": 0.36905837602390407,
455
+ "learning_rate": 4.4427194213859216e-07,
456
+ "loss": 0.2995,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 6.190476190476191,
461
+ "grad_norm": 0.33021532282471866,
462
+ "learning_rate": 3.0922713770922155e-07,
463
+ "loss": 0.2728,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 6.285714285714286,
468
+ "grad_norm": 0.3412788352995484,
469
+ "learning_rate": 1.9827512151456175e-07,
470
+ "loss": 0.2758,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 6.380952380952381,
475
+ "grad_norm": 0.38759192979056284,
476
+ "learning_rate": 1.1169173774871478e-07,
477
+ "loss": 0.2703,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 6.476190476190476,
482
+ "grad_norm": 0.3156250948411893,
483
+ "learning_rate": 4.9692246345985905e-08,
484
+ "loss": 0.2773,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 6.571428571428571,
489
+ "grad_norm": 0.3281474911839613,
490
+ "learning_rate": 1.2430787810776556e-08,
491
+ "loss": 0.2819,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 6.666666666666667,
496
+ "grad_norm": 0.3391994826898966,
497
+ "learning_rate": 0.0,
498
+ "loss": 0.2673,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 6.666666666666667,
503
+ "step": 70,
504
+ "total_flos": 8.788556475321549e+16,
505
+ "train_loss": 0.5346557378768921,
506
+ "train_runtime": 2433.5668,
507
+ "train_samples_per_second": 2.876,
508
+ "train_steps_per_second": 0.029
509
+ }
510
+ ],
511
+ "logging_steps": 1,
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": 8.788556475321549e+16,
529
+ "train_batch_size": 1,
530
+ "trial_name": null,
531
+ "trial_params": null
532
+ }
training_loss.png ADDED