sedrickkeh commited on
Commit
25d28e1
·
verified ·
1 Parent(s): 33ba132

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 +378 -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: multiple_samples_ground_truth_numina_aime
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # multiple_samples_ground_truth_numina_aime
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: multiple_samples_ground_truth_numina_aime
 
16
 
17
  # multiple_samples_ground_truth_numina_aime
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/multiple_samples_ground_truth_numina_aime dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 41283677585408.0,
4
+ "train_loss": 0.8019564437369505,
5
+ "train_runtime": 1597.112,
6
+ "train_samples_per_second": 2.859,
7
+ "train_steps_per_second": 0.03
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 41283677585408.0,
4
+ "train_loss": 0.8019564437369505,
5
+ "train_runtime": 1597.112,
6
+ "train_samples_per_second": 2.859,
7
+ "train_steps_per_second": 0.03
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,378 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 6.530343055725098,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.101,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.125,
20
+ "grad_norm": 6.764411926269531,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.0766,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 6.143789768218994,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.0221,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.25,
34
+ "grad_norm": 4.986618518829346,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.045,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.3125,
41
+ "grad_norm": 2.9099574089050293,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.9587,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.375,
48
+ "grad_norm": 5.138437271118164,
49
+ "learning_rate": 9.986661418317759e-06,
50
+ "loss": 0.9389,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.4375,
55
+ "grad_norm": 5.72763204574585,
56
+ "learning_rate": 9.946716840375552e-06,
57
+ "loss": 0.9971,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5,
62
+ "grad_norm": 6.512542247772217,
63
+ "learning_rate": 9.880379387779637e-06,
64
+ "loss": 0.9481,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.5625,
69
+ "grad_norm": 4.968111991882324,
70
+ "learning_rate": 9.78800299954203e-06,
71
+ "loss": 0.9156,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.625,
76
+ "grad_norm": 2.9014463424682617,
77
+ "learning_rate": 9.670080543662742e-06,
78
+ "loss": 0.8799,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.6875,
83
+ "grad_norm": 2.4352829456329346,
84
+ "learning_rate": 9.527241187465735e-06,
85
+ "loss": 0.9048,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.75,
90
+ "grad_norm": 2.237089157104492,
91
+ "learning_rate": 9.36024704071904e-06,
92
+ "loss": 0.8642,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.8125,
97
+ "grad_norm": 1.9950438737869263,
98
+ "learning_rate": 9.16998908944939e-06,
99
+ "loss": 0.849,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.875,
104
+ "grad_norm": 1.2918341159820557,
105
+ "learning_rate": 8.957482442146271e-06,
106
+ "loss": 0.8796,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.9375,
111
+ "grad_norm": 1.4066290855407715,
112
+ "learning_rate": 8.72386091371891e-06,
113
+ "loss": 0.7775,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.0,
118
+ "grad_norm": 1.3670933246612549,
119
+ "learning_rate": 8.470370976103171e-06,
120
+ "loss": 0.7598,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.0625,
125
+ "grad_norm": 1.154747486114502,
126
+ "learning_rate": 8.198365107794457e-06,
127
+ "loss": 0.8226,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.125,
132
+ "grad_norm": 0.9220020771026611,
133
+ "learning_rate": 7.909294577789765e-06,
134
+ "loss": 0.7433,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.1875,
139
+ "grad_norm": 1.0542454719543457,
140
+ "learning_rate": 7.604701702439652e-06,
141
+ "loss": 0.7302,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.25,
146
+ "grad_norm": 0.983396589756012,
147
+ "learning_rate": 7.286211616523193e-06,
148
+ "loss": 0.8066,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.3125,
153
+ "grad_norm": 0.8708000779151917,
154
+ "learning_rate": 6.95552360245078e-06,
155
+ "loss": 0.7155,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.375,
160
+ "grad_norm": 0.8514654040336609,
161
+ "learning_rate": 6.614402023857231e-06,
162
+ "loss": 0.7416,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.4375,
167
+ "grad_norm": 0.7727275490760803,
168
+ "learning_rate": 6.264666911958404e-06,
169
+ "loss": 0.7355,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.5,
174
+ "grad_norm": 0.7927507162094116,
175
+ "learning_rate": 5.908184254897183e-06,
176
+ "loss": 0.7514,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.5625,
181
+ "grad_norm": 0.8321970105171204,
182
+ "learning_rate": 5.546856041889374e-06,
183
+ "loss": 0.7772,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.625,
188
+ "grad_norm": 0.749494731426239,
189
+ "learning_rate": 5.182610115288296e-06,
190
+ "loss": 0.7391,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.6875,
195
+ "grad_norm": 0.680793821811676,
196
+ "learning_rate": 4.817389884711706e-06,
197
+ "loss": 0.7486,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.75,
202
+ "grad_norm": 0.6702898144721985,
203
+ "learning_rate": 4.4531439581106295e-06,
204
+ "loss": 0.7909,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.8125,
209
+ "grad_norm": 0.5399229526519775,
210
+ "learning_rate": 4.091815745102818e-06,
211
+ "loss": 0.7535,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.875,
216
+ "grad_norm": 0.5391576290130615,
217
+ "learning_rate": 3.7353330880415963e-06,
218
+ "loss": 0.7276,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.9375,
223
+ "grad_norm": 0.6090447306632996,
224
+ "learning_rate": 3.3855979761427705e-06,
225
+ "loss": 0.7982,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.0,
230
+ "grad_norm": 0.571646511554718,
231
+ "learning_rate": 3.044476397549221e-06,
232
+ "loss": 0.7689,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.0625,
237
+ "grad_norm": 0.5187521576881409,
238
+ "learning_rate": 2.7137883834768076e-06,
239
+ "loss": 0.735,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.125,
244
+ "grad_norm": 0.5552323460578918,
245
+ "learning_rate": 2.3952982975603494e-06,
246
+ "loss": 0.772,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.1875,
251
+ "grad_norm": 0.4510865807533264,
252
+ "learning_rate": 2.0907054222102367e-06,
253
+ "loss": 0.7111,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.25,
258
+ "grad_norm": 0.46868014335632324,
259
+ "learning_rate": 1.8016348922055448e-06,
260
+ "loss": 0.6825,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.3125,
265
+ "grad_norm": 0.49473336338996887,
266
+ "learning_rate": 1.5296290238968303e-06,
267
+ "loss": 0.6869,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.375,
272
+ "grad_norm": 0.43930625915527344,
273
+ "learning_rate": 1.2761390862810907e-06,
274
+ "loss": 0.6477,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.4375,
279
+ "grad_norm": 0.43224358558654785,
280
+ "learning_rate": 1.04251755785373e-06,
281
+ "loss": 0.7017,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.5,
286
+ "grad_norm": 0.4535328447818756,
287
+ "learning_rate": 8.30010910550611e-07,
288
+ "loss": 0.6958,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.5625,
293
+ "grad_norm": 0.44307926297187805,
294
+ "learning_rate": 6.397529592809615e-07,
295
+ "loss": 0.6983,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 2.625,
300
+ "grad_norm": 0.44362759590148926,
301
+ "learning_rate": 4.727588125342669e-07,
302
+ "loss": 0.6935,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 2.6875,
307
+ "grad_norm": 0.38771650195121765,
308
+ "learning_rate": 3.299194563372604e-07,
309
+ "loss": 0.7581,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 2.75,
314
+ "grad_norm": 0.45481687784194946,
315
+ "learning_rate": 2.1199700045797077e-07,
316
+ "loss": 0.7712,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 2.8125,
321
+ "grad_norm": 0.42201128602027893,
322
+ "learning_rate": 1.196206122203647e-07,
323
+ "loss": 0.7006,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 2.875,
328
+ "grad_norm": 0.47298797965049744,
329
+ "learning_rate": 5.3283159624448745e-08,
330
+ "loss": 0.7299,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 2.9375,
335
+ "grad_norm": 0.4228404462337494,
336
+ "learning_rate": 1.333858168224178e-08,
337
+ "loss": 0.7749,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.0,
342
+ "grad_norm": 0.40613028407096863,
343
+ "learning_rate": 0.0,
344
+ "loss": 0.666,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.0,
349
+ "step": 48,
350
+ "total_flos": 41283677585408.0,
351
+ "train_loss": 0.8019564437369505,
352
+ "train_runtime": 1597.112,
353
+ "train_samples_per_second": 2.859,
354
+ "train_steps_per_second": 0.03
355
+ }
356
+ ],
357
+ "logging_steps": 1.0,
358
+ "max_steps": 48,
359
+ "num_input_tokens_seen": 0,
360
+ "num_train_epochs": 3,
361
+ "save_steps": 500,
362
+ "stateful_callbacks": {
363
+ "TrainerControl": {
364
+ "args": {
365
+ "should_epoch_stop": false,
366
+ "should_evaluate": false,
367
+ "should_log": false,
368
+ "should_save": true,
369
+ "should_training_stop": true
370
+ },
371
+ "attributes": {}
372
+ }
373
+ },
374
+ "total_flos": 41283677585408.0,
375
+ "train_batch_size": 1,
376
+ "trial_name": null,
377
+ "trial_params": null
378
+ }
training_loss.png ADDED