ryanmarten commited on
Commit
183edc0
·
verified ·
1 Parent(s): 0ce217f

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: b2_code_random_1k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # b2_code_random_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: b2_code_random_1k
 
16
 
17
  # b2_code_random_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/b2_code_random_1k dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.72,
3
+ "total_flos": 2.3958341273255936e+17,
4
+ "train_loss": 0.6163317041737693,
5
+ "train_runtime": 8464.3741,
6
+ "train_samples_per_second": 0.827,
7
+ "train_steps_per_second": 0.008
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.72,
3
+ "total_flos": 2.3958341273255936e+17,
4
+ "train_loss": 0.6163317041737693,
5
+ "train_runtime": 8464.3741,
6
+ "train_samples_per_second": 0.827,
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": 6.72,
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": 0.096,
13
+ "grad_norm": 6.561104162339198,
14
+ "learning_rate": 2.8571428571428573e-06,
15
+ "loss": 1.0716,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.192,
20
+ "grad_norm": 6.387912734646695,
21
+ "learning_rate": 5.7142857142857145e-06,
22
+ "loss": 1.0333,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.288,
27
+ "grad_norm": 5.9836285447878055,
28
+ "learning_rate": 8.571428571428571e-06,
29
+ "loss": 1.0256,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.384,
34
+ "grad_norm": 2.9800884023881364,
35
+ "learning_rate": 1.1428571428571429e-05,
36
+ "loss": 0.9827,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.48,
41
+ "grad_norm": 3.9442251407780957,
42
+ "learning_rate": 1.4285714285714287e-05,
43
+ "loss": 0.9239,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.576,
48
+ "grad_norm": 4.08419475313967,
49
+ "learning_rate": 1.7142857142857142e-05,
50
+ "loss": 0.9741,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.672,
55
+ "grad_norm": 4.109925933499094,
56
+ "learning_rate": 2e-05,
57
+ "loss": 0.9141,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.768,
62
+ "grad_norm": 3.0673259525610956,
63
+ "learning_rate": 1.9987569212189224e-05,
64
+ "loss": 0.8904,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.864,
69
+ "grad_norm": 2.3375902380289193,
70
+ "learning_rate": 1.9950307753654016e-05,
71
+ "loss": 0.8498,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.96,
76
+ "grad_norm": 1.6571536728673029,
77
+ "learning_rate": 1.9888308262251286e-05,
78
+ "loss": 0.8233,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.056,
83
+ "grad_norm": 1.3301047327078876,
84
+ "learning_rate": 1.9801724878485438e-05,
85
+ "loss": 0.7883,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.152,
90
+ "grad_norm": 1.211011357001183,
91
+ "learning_rate": 1.969077286229078e-05,
92
+ "loss": 0.7481,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.248,
97
+ "grad_norm": 1.3193538850322144,
98
+ "learning_rate": 1.955572805786141e-05,
99
+ "loss": 0.7535,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.3439999999999999,
104
+ "grad_norm": 0.9080855415027668,
105
+ "learning_rate": 1.9396926207859085e-05,
106
+ "loss": 0.7512,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.44,
111
+ "grad_norm": 1.0512591851739732,
112
+ "learning_rate": 1.921476211870408e-05,
113
+ "loss": 0.7282,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.536,
118
+ "grad_norm": 1.1161230692325639,
119
+ "learning_rate": 1.900968867902419e-05,
120
+ "loss": 0.7459,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.6320000000000001,
125
+ "grad_norm": 0.7835001228910295,
126
+ "learning_rate": 1.8782215733702286e-05,
127
+ "loss": 0.7255,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.728,
132
+ "grad_norm": 0.837107600828801,
133
+ "learning_rate": 1.8532908816321557e-05,
134
+ "loss": 0.7025,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.8239999999999998,
139
+ "grad_norm": 0.7867376905857504,
140
+ "learning_rate": 1.826238774315995e-05,
141
+ "loss": 0.7088,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.92,
146
+ "grad_norm": 0.6609994911085901,
147
+ "learning_rate": 1.7971325072229227e-05,
148
+ "loss": 0.6999,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.016,
153
+ "grad_norm": 0.7070866332623904,
154
+ "learning_rate": 1.766044443118978e-05,
155
+ "loss": 0.6979,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.112,
160
+ "grad_norm": 0.8951224417268967,
161
+ "learning_rate": 1.7330518718298263e-05,
162
+ "loss": 0.6508,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.208,
167
+ "grad_norm": 0.7185235221150691,
168
+ "learning_rate": 1.698236818086073e-05,
169
+ "loss": 0.6261,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.304,
174
+ "grad_norm": 0.9374694903200345,
175
+ "learning_rate": 1.6616858375968596e-05,
176
+ "loss": 0.6455,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.4,
181
+ "grad_norm": 0.7468011278611548,
182
+ "learning_rate": 1.6234898018587336e-05,
183
+ "loss": 0.6305,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.496,
188
+ "grad_norm": 0.8806598538095017,
189
+ "learning_rate": 1.5837436722347902e-05,
190
+ "loss": 0.6133,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.592,
195
+ "grad_norm": 0.6587287565394545,
196
+ "learning_rate": 1.5425462638657597e-05,
197
+ "loss": 0.6315,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.6879999999999997,
202
+ "grad_norm": 0.7936517316909375,
203
+ "learning_rate": 1.5000000000000002e-05,
204
+ "loss": 0.6329,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.784,
209
+ "grad_norm": 0.5556624374324638,
210
+ "learning_rate": 1.4562106573531632e-05,
211
+ "loss": 0.615,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.88,
216
+ "grad_norm": 0.5645976671324228,
217
+ "learning_rate": 1.4112871031306118e-05,
218
+ "loss": 0.6014,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.976,
223
+ "grad_norm": 0.5406600060470248,
224
+ "learning_rate": 1.3653410243663953e-05,
225
+ "loss": 0.6091,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 3.072,
230
+ "grad_norm": 0.48509944530499666,
231
+ "learning_rate": 1.3184866502516846e-05,
232
+ "loss": 0.5748,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 3.168,
237
+ "grad_norm": 0.5468192156383544,
238
+ "learning_rate": 1.2708404681430054e-05,
239
+ "loss": 0.5622,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 3.2640000000000002,
244
+ "grad_norm": 0.46164696458342497,
245
+ "learning_rate": 1.2225209339563144e-05,
246
+ "loss": 0.5555,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 3.36,
251
+ "grad_norm": 0.5565314990680137,
252
+ "learning_rate": 1.1736481776669307e-05,
253
+ "loss": 0.5386,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 3.456,
258
+ "grad_norm": 0.5082394365610078,
259
+ "learning_rate": 1.1243437046474854e-05,
260
+ "loss": 0.5682,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 3.552,
265
+ "grad_norm": 0.47372540244322797,
266
+ "learning_rate": 1.0747300935864245e-05,
267
+ "loss": 0.5508,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 3.648,
272
+ "grad_norm": 0.41615288713508297,
273
+ "learning_rate": 1.0249306917380731e-05,
274
+ "loss": 0.5449,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 3.7439999999999998,
279
+ "grad_norm": 0.45704548503040643,
280
+ "learning_rate": 9.750693082619274e-06,
281
+ "loss": 0.538,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 3.84,
286
+ "grad_norm": 0.4365371332944041,
287
+ "learning_rate": 9.252699064135759e-06,
288
+ "loss": 0.5317,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 3.936,
293
+ "grad_norm": 0.4018586903717012,
294
+ "learning_rate": 8.756562953525151e-06,
295
+ "loss": 0.5303,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 4.032,
300
+ "grad_norm": 0.4137162417732452,
301
+ "learning_rate": 8.263518223330698e-06,
302
+ "loss": 0.5406,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 4.128,
307
+ "grad_norm": 0.4324252417717255,
308
+ "learning_rate": 7.774790660436857e-06,
309
+ "loss": 0.4931,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 4.224,
314
+ "grad_norm": 0.36079983507281077,
315
+ "learning_rate": 7.291595318569951e-06,
316
+ "loss": 0.496,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 4.32,
321
+ "grad_norm": 0.39651029766952745,
322
+ "learning_rate": 6.815133497483157e-06,
323
+ "loss": 0.5065,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 4.416,
328
+ "grad_norm": 0.37164149719125644,
329
+ "learning_rate": 6.34658975633605e-06,
330
+ "loss": 0.4968,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 4.5120000000000005,
335
+ "grad_norm": 0.44175971543918185,
336
+ "learning_rate": 5.887128968693887e-06,
337
+ "loss": 0.5167,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 4.608,
342
+ "grad_norm": 0.43066151889582394,
343
+ "learning_rate": 5.43789342646837e-06,
344
+ "loss": 0.478,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 4.704,
349
+ "grad_norm": 0.43747108772437127,
350
+ "learning_rate": 5.000000000000003e-06,
351
+ "loss": 0.5054,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 4.8,
356
+ "grad_norm": 0.37307042597663015,
357
+ "learning_rate": 4.5745373613424075e-06,
358
+ "loss": 0.5036,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 4.896,
363
+ "grad_norm": 0.36725795450264026,
364
+ "learning_rate": 4.162563277652104e-06,
365
+ "loss": 0.481,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 4.992,
370
+ "grad_norm": 0.35962626797899955,
371
+ "learning_rate": 3.7651019814126656e-06,
372
+ "loss": 0.4931,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 5.088,
377
+ "grad_norm": 0.40183445913049437,
378
+ "learning_rate": 3.3831416240314085e-06,
379
+ "loss": 0.4508,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 5.184,
384
+ "grad_norm": 0.39120770284598194,
385
+ "learning_rate": 3.017631819139273e-06,
386
+ "loss": 0.4842,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 5.28,
391
+ "grad_norm": 0.3068995631376283,
392
+ "learning_rate": 2.669481281701739e-06,
393
+ "loss": 0.4532,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 5.376,
398
+ "grad_norm": 0.3090845491159116,
399
+ "learning_rate": 2.339555568810221e-06,
400
+ "loss": 0.45,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 5.4719999999999995,
405
+ "grad_norm": 0.34761836291617715,
406
+ "learning_rate": 2.0286749277707783e-06,
407
+ "loss": 0.4759,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 5.568,
412
+ "grad_norm": 0.3309196033174949,
413
+ "learning_rate": 1.7376122568400533e-06,
414
+ "loss": 0.4821,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 5.664,
419
+ "grad_norm": 0.33063742119211254,
420
+ "learning_rate": 1.467091183678444e-06,
421
+ "loss": 0.4722,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 5.76,
426
+ "grad_norm": 0.3153825652124885,
427
+ "learning_rate": 1.2177842662977136e-06,
428
+ "loss": 0.4434,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 5.856,
433
+ "grad_norm": 0.3041050883727483,
434
+ "learning_rate": 9.903113209758098e-07,
435
+ "loss": 0.487,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 5.952,
440
+ "grad_norm": 0.30797227976594754,
441
+ "learning_rate": 7.852378812959227e-07,
442
+ "loss": 0.4655,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 6.048,
447
+ "grad_norm": 0.3315394099214905,
448
+ "learning_rate": 6.030737921409169e-07,
449
+ "loss": 0.4747,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 6.144,
454
+ "grad_norm": 0.304933301231908,
455
+ "learning_rate": 4.4427194213859216e-07,
456
+ "loss": 0.4624,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 6.24,
461
+ "grad_norm": 0.28896065611928046,
462
+ "learning_rate": 3.0922713770922155e-07,
463
+ "loss": 0.4664,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 6.336,
468
+ "grad_norm": 0.2883682511546891,
469
+ "learning_rate": 1.9827512151456175e-07,
470
+ "loss": 0.4517,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 6.432,
475
+ "grad_norm": 0.3081527797067212,
476
+ "learning_rate": 1.1169173774871478e-07,
477
+ "loss": 0.453,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 6.5280000000000005,
482
+ "grad_norm": 0.28225362394511627,
483
+ "learning_rate": 4.9692246345985905e-08,
484
+ "loss": 0.4606,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 6.624,
489
+ "grad_norm": 0.2691175677873696,
490
+ "learning_rate": 1.2430787810776556e-08,
491
+ "loss": 0.466,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 6.72,
496
+ "grad_norm": 0.27657233615825566,
497
+ "learning_rate": 0.0,
498
+ "loss": 0.4437,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 6.72,
503
+ "step": 70,
504
+ "total_flos": 2.3958341273255936e+17,
505
+ "train_loss": 0.6163317041737693,
506
+ "train_runtime": 8464.3741,
507
+ "train_samples_per_second": 0.827,
508
+ "train_steps_per_second": 0.008
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": 2.3958341273255936e+17,
529
+ "train_batch_size": 1,
530
+ "trial_name": null,
531
+ "trial_params": null
532
+ }
training_loss.png ADDED