yuzhounie commited on
Commit
eaa1805
·
verified ·
1 Parent(s): 03ed6ed

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 +484 -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: gaia_qwen2_32B
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # gaia_qwen2_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 the None 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: gaia_qwen2_32B
 
16
 
17
  # gaia_qwen2_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 claude_gaia_1, the claude_gaia_2 and the claude_gaia_3 datasets.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.8976377952755907,
3
+ "total_flos": 1.2506626070990029e+17,
4
+ "train_loss": 0.2051201125695592,
5
+ "train_runtime": 45189.9744,
6
+ "train_samples_per_second": 0.05,
7
+ "train_steps_per_second": 0.001
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.8976377952755907,
3
+ "total_flos": 1.2506626070990029e+17,
4
+ "train_loss": 0.2051201125695592,
5
+ "train_runtime": 45189.9744,
6
+ "train_samples_per_second": 0.05,
7
+ "train_steps_per_second": 0.001
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.8976377952755907,
6
+ "eval_steps": 500,
7
+ "global_step": 63,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.047244094488188976,
14
+ "grad_norm": 3.6492302417755127,
15
+ "learning_rate": 1.4285714285714286e-06,
16
+ "loss": 0.4012,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.09448818897637795,
21
+ "grad_norm": 2.7150280475616455,
22
+ "learning_rate": 2.8571428571428573e-06,
23
+ "loss": 0.3317,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.14173228346456693,
28
+ "grad_norm": 4.509909629821777,
29
+ "learning_rate": 4.2857142857142855e-06,
30
+ "loss": 0.4663,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.1889763779527559,
35
+ "grad_norm": 3.650169849395752,
36
+ "learning_rate": 5.7142857142857145e-06,
37
+ "loss": 0.4662,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.23622047244094488,
42
+ "grad_norm": 1.761392593383789,
43
+ "learning_rate": 7.1428571428571436e-06,
44
+ "loss": 0.3292,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.28346456692913385,
49
+ "grad_norm": 1.1722800731658936,
50
+ "learning_rate": 8.571428571428571e-06,
51
+ "loss": 0.2505,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.33070866141732286,
56
+ "grad_norm": 1.3030749559402466,
57
+ "learning_rate": 1e-05,
58
+ "loss": 0.2786,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.3779527559055118,
63
+ "grad_norm": 1.4660409688949585,
64
+ "learning_rate": 9.992134075089085e-06,
65
+ "loss": 0.3788,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.4251968503937008,
70
+ "grad_norm": 2.589200735092163,
71
+ "learning_rate": 9.968561049466214e-06,
72
+ "loss": 0.3087,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.47244094488188976,
77
+ "grad_norm": 2.669886827468872,
78
+ "learning_rate": 9.92935509259118e-06,
79
+ "loss": 0.3672,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.5196850393700787,
84
+ "grad_norm": 1.486991286277771,
85
+ "learning_rate": 9.874639560909118e-06,
86
+ "loss": 0.275,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.5669291338582677,
91
+ "grad_norm": 1.572901964187622,
92
+ "learning_rate": 9.804586609725499e-06,
93
+ "loss": 0.309,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.6141732283464567,
98
+ "grad_norm": 1.242970585823059,
99
+ "learning_rate": 9.719416651541839e-06,
100
+ "loss": 0.2988,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.6614173228346457,
105
+ "grad_norm": 1.272771954536438,
106
+ "learning_rate": 9.619397662556434e-06,
107
+ "loss": 0.3199,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.7086614173228346,
112
+ "grad_norm": 1.215131163597107,
113
+ "learning_rate": 9.504844339512096e-06,
114
+ "loss": 0.2371,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.7559055118110236,
119
+ "grad_norm": 1.2442128658294678,
120
+ "learning_rate": 9.376117109543769e-06,
121
+ "loss": 0.2661,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.8031496062992126,
126
+ "grad_norm": 1.0294448137283325,
127
+ "learning_rate": 9.233620996141421e-06,
128
+ "loss": 0.2356,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.8503937007874016,
133
+ "grad_norm": 1.2284340858459473,
134
+ "learning_rate": 9.077804344796302e-06,
135
+ "loss": 0.2911,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.8976377952755905,
140
+ "grad_norm": 0.817711353302002,
141
+ "learning_rate": 8.90915741234015e-06,
142
+ "loss": 0.238,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.9448818897637795,
147
+ "grad_norm": 1.085610032081604,
148
+ "learning_rate": 8.728210824415829e-06,
149
+ "loss": 0.2162,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.9921259842519685,
154
+ "grad_norm": 0.7799460887908936,
155
+ "learning_rate": 8.535533905932739e-06,
156
+ "loss": 0.2419,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 1.0,
161
+ "grad_norm": 0.7799460887908936,
162
+ "learning_rate": 8.331732889760021e-06,
163
+ "loss": 0.271,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 1.047244094488189,
168
+ "grad_norm": 5.261403560638428,
169
+ "learning_rate": 8.117449009293668e-06,
170
+ "loss": 0.1911,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 1.094488188976378,
175
+ "grad_norm": 0.7940455675125122,
176
+ "learning_rate": 7.89335648089903e-06,
177
+ "loss": 0.2041,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 1.141732283464567,
182
+ "grad_norm": 1.4895520210266113,
183
+ "learning_rate": 7.660160382576683e-06,
184
+ "loss": 0.1895,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 1.188976377952756,
189
+ "grad_norm": 0.8921546936035156,
190
+ "learning_rate": 7.4185944355261996e-06,
191
+ "loss": 0.1575,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 1.236220472440945,
196
+ "grad_norm": 0.9935773611068726,
197
+ "learning_rate": 7.169418695587791e-06,
198
+ "loss": 0.194,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 1.2834645669291338,
203
+ "grad_norm": 0.9794341921806335,
204
+ "learning_rate": 6.913417161825449e-06,
205
+ "loss": 0.2202,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 1.330708661417323,
210
+ "grad_norm": 0.8670676946640015,
211
+ "learning_rate": 6.651395309775837e-06,
212
+ "loss": 0.1789,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 1.3779527559055118,
217
+ "grad_norm": 1.1269317865371704,
218
+ "learning_rate": 6.384177557124247e-06,
219
+ "loss": 0.2017,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 1.425196850393701,
224
+ "grad_norm": 1.1137402057647705,
225
+ "learning_rate": 6.112604669781572e-06,
226
+ "loss": 0.1751,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 1.4724409448818898,
231
+ "grad_norm": 0.9292981624603271,
232
+ "learning_rate": 5.837531116523683e-06,
233
+ "loss": 0.1893,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 1.5196850393700787,
238
+ "grad_norm": 0.8478426933288574,
239
+ "learning_rate": 5.559822380516539e-06,
240
+ "loss": 0.1381,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 1.5669291338582676,
245
+ "grad_norm": 0.759232223033905,
246
+ "learning_rate": 5.2803522361859596e-06,
247
+ "loss": 0.1584,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 1.6141732283464567,
252
+ "grad_norm": 1.4674817323684692,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.1839,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 1.6614173228346458,
259
+ "grad_norm": 0.900875985622406,
260
+ "learning_rate": 4.719647763814041e-06,
261
+ "loss": 0.1776,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 1.7086614173228347,
266
+ "grad_norm": 0.7754679322242737,
267
+ "learning_rate": 4.4401776194834615e-06,
268
+ "loss": 0.1667,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.7559055118110236,
273
+ "grad_norm": 0.8453861474990845,
274
+ "learning_rate": 4.162468883476319e-06,
275
+ "loss": 0.1421,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.8031496062992125,
280
+ "grad_norm": 0.7882893085479736,
281
+ "learning_rate": 3.887395330218429e-06,
282
+ "loss": 0.1543,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.8503937007874016,
287
+ "grad_norm": 1.541914701461792,
288
+ "learning_rate": 3.6158224428757538e-06,
289
+ "loss": 0.1796,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.8976377952755905,
294
+ "grad_norm": 0.989794909954071,
295
+ "learning_rate": 3.3486046902241663e-06,
296
+ "loss": 0.1771,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.9448818897637796,
301
+ "grad_norm": 1.0352776050567627,
302
+ "learning_rate": 3.0865828381745515e-06,
303
+ "loss": 0.163,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.9921259842519685,
308
+ "grad_norm": 1.0325061082839966,
309
+ "learning_rate": 2.83058130441221e-06,
310
+ "loss": 0.1518,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 2.0,
315
+ "grad_norm": 1.0325061082839966,
316
+ "learning_rate": 2.5814055644738013e-06,
317
+ "loss": 0.1685,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 2.047244094488189,
322
+ "grad_norm": 2.2215065956115723,
323
+ "learning_rate": 2.339839617423318e-06,
324
+ "loss": 0.135,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 2.094488188976378,
329
+ "grad_norm": 0.8818472027778625,
330
+ "learning_rate": 2.1066435191009717e-06,
331
+ "loss": 0.1472,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 2.141732283464567,
336
+ "grad_norm": 1.6831822395324707,
337
+ "learning_rate": 1.8825509907063328e-06,
338
+ "loss": 0.1161,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 2.188976377952756,
343
+ "grad_norm": 0.5498701930046082,
344
+ "learning_rate": 1.6682671102399806e-06,
345
+ "loss": 0.0941,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 2.236220472440945,
350
+ "grad_norm": 0.9785574078559875,
351
+ "learning_rate": 1.4644660940672628e-06,
352
+ "loss": 0.1614,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 2.283464566929134,
357
+ "grad_norm": 0.9736632704734802,
358
+ "learning_rate": 1.2717891755841722e-06,
359
+ "loss": 0.1533,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 2.3307086614173227,
364
+ "grad_norm": 1.1105008125305176,
365
+ "learning_rate": 1.0908425876598512e-06,
366
+ "loss": 0.1051,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 2.377952755905512,
371
+ "grad_norm": 0.4693005383014679,
372
+ "learning_rate": 9.221956552036992e-07,
373
+ "loss": 0.0923,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 2.425196850393701,
378
+ "grad_norm": 0.9733160138130188,
379
+ "learning_rate": 7.663790038585794e-07,
380
+ "loss": 0.0977,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 2.47244094488189,
385
+ "grad_norm": 0.7047190070152283,
386
+ "learning_rate": 6.238828904562316e-07,
387
+ "loss": 0.1154,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 2.5196850393700787,
392
+ "grad_norm": 1.1957942247390747,
393
+ "learning_rate": 4.951556604879049e-07,
394
+ "loss": 0.1237,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 2.5669291338582676,
399
+ "grad_norm": 0.6617165207862854,
400
+ "learning_rate": 3.8060233744356634e-07,
401
+ "loss": 0.1042,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 2.6141732283464565,
406
+ "grad_norm": 0.8499227166175842,
407
+ "learning_rate": 2.8058334845816214e-07,
408
+ "loss": 0.1259,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 2.661417322834646,
413
+ "grad_norm": 0.8625606298446655,
414
+ "learning_rate": 1.9541339027450256e-07,
415
+ "loss": 0.1105,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 2.7086614173228347,
420
+ "grad_norm": 0.6735402941703796,
421
+ "learning_rate": 1.253604390908819e-07,
422
+ "loss": 0.1063,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 2.7559055118110236,
427
+ "grad_norm": 0.753610372543335,
428
+ "learning_rate": 7.064490740882057e-08,
429
+ "loss": 0.1343,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 2.8031496062992125,
434
+ "grad_norm": 0.7327992916107178,
435
+ "learning_rate": 3.143895053378698e-08,
436
+ "loss": 0.1197,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 2.850393700787402,
441
+ "grad_norm": 0.829689621925354,
442
+ "learning_rate": 7.865924910916977e-09,
443
+ "loss": 0.1359,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 2.8976377952755907,
448
+ "grad_norm": 0.7220540046691895,
449
+ "learning_rate": 0.0,
450
+ "loss": 0.1042,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 2.8976377952755907,
455
+ "step": 63,
456
+ "total_flos": 1.2506626070990029e+17,
457
+ "train_loss": 0.2051201125695592,
458
+ "train_runtime": 45189.9744,
459
+ "train_samples_per_second": 0.05,
460
+ "train_steps_per_second": 0.001
461
+ }
462
+ ],
463
+ "logging_steps": 1,
464
+ "max_steps": 63,
465
+ "num_input_tokens_seen": 0,
466
+ "num_train_epochs": 3,
467
+ "save_steps": 20,
468
+ "stateful_callbacks": {
469
+ "TrainerControl": {
470
+ "args": {
471
+ "should_epoch_stop": false,
472
+ "should_evaluate": false,
473
+ "should_log": false,
474
+ "should_save": true,
475
+ "should_training_stop": true
476
+ },
477
+ "attributes": {}
478
+ }
479
+ },
480
+ "total_flos": 1.2506626070990029e+17,
481
+ "train_batch_size": 1,
482
+ "trial_name": null,
483
+ "trial_params": null
484
+ }
training_loss.png ADDED