ZMC2019 commited on
Commit
e4153c0
·
verified ·
1 Parent(s): 22c1c02

Model save

Browse files
Files changed (4) hide show
  1. README.md +3 -5
  2. all_results.json +6 -6
  3. train_results.json +6 -6
  4. trainer_state.json +46 -354
README.md CHANGED
@@ -1,11 +1,9 @@
1
  ---
2
- base_model: Qwen/Qwen2.5-1.5B-Instruct
3
- datasets: open-r1/OpenR1-Math-220k
4
  library_name: transformers
5
  model_name: Qwen2.5-1.5B-Open-R1-Distill
6
  tags:
7
  - generated_from_trainer
8
- - open-r1
9
  - trl
10
  - sft
11
  licence: license
@@ -13,7 +11,7 @@ licence: license
13
 
14
  # Model Card for Qwen2.5-1.5B-Open-R1-Distill
15
 
16
- This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
17
  It has been trained using [TRL](https://github.com/huggingface/trl).
18
 
19
  ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
29
 
30
  ## Training procedure
31
 
32
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenzhuoming911/huggingface/runs/egmgjjua)
33
 
34
 
35
  This model was trained with SFT.
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
 
3
  library_name: transformers
4
  model_name: Qwen2.5-1.5B-Open-R1-Distill
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - sft
9
  licence: license
 
11
 
12
  # Model Card for Qwen2.5-1.5B-Open-R1-Distill
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/stevenzhou0816100/huggingface/runs/uy7nfosz)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "total_flos": 488621249396736.0,
3
- "train_loss": 0.5791835704846169,
4
- "train_runtime": 3332.7286,
5
- "train_samples": 93733,
6
- "train_samples_per_second": 10.292,
7
- "train_steps_per_second": 0.08
8
  }
 
1
  {
2
+ "total_flos": 1.355802795311104e+16,
3
+ "train_loss": 0.44515162458022434,
4
+ "train_runtime": 298.6439,
5
+ "train_samples": 8221,
6
+ "train_samples_per_second": 0.161,
7
+ "train_steps_per_second": 0.161
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "total_flos": 488621249396736.0,
3
- "train_loss": 0.5791835704846169,
4
- "train_runtime": 3332.7286,
5
- "train_samples": 93733,
6
- "train_samples_per_second": 10.292,
7
- "train_steps_per_second": 0.08
8
  }
 
1
  {
2
+ "total_flos": 1.355802795311104e+16,
3
+ "train_loss": 0.44515162458022434,
4
+ "train_runtime": 298.6439,
5
+ "train_samples": 8221,
6
+ "train_samples_per_second": 0.161,
7
+ "train_steps_per_second": 0.161
8
  }
trainer_state.json CHANGED
@@ -3,394 +3,86 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 268,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.018656716417910446,
13
- "grad_norm": 1.8343927439827759,
14
- "learning_rate": 1.785714285714286e-05,
15
- "loss": 0.8456,
16
  "step": 5
17
  },
18
  {
19
- "epoch": 0.03731343283582089,
20
- "grad_norm": 0.7815495842773689,
21
- "learning_rate": 3.571428571428572e-05,
22
- "loss": 0.7682,
23
  "step": 10
24
  },
25
  {
26
- "epoch": 0.055970149253731345,
27
- "grad_norm": 0.5015268609367467,
28
- "learning_rate": 4.999827900623038e-05,
29
- "loss": 0.7026,
30
  "step": 15
31
  },
32
  {
33
- "epoch": 0.07462686567164178,
34
- "grad_norm": 0.3826502871869476,
35
- "learning_rate": 4.993807186343243e-05,
36
- "loss": 0.6746,
37
  "step": 20
38
  },
39
  {
40
- "epoch": 0.09328358208955224,
41
- "grad_norm": 0.3545092052686732,
42
- "learning_rate": 4.979207812402531e-05,
43
- "loss": 0.6436,
44
  "step": 25
45
  },
46
  {
47
- "epoch": 0.11194029850746269,
48
- "grad_norm": 0.2701627334187389,
49
- "learning_rate": 4.956085596012407e-05,
50
- "loss": 0.6362,
51
  "step": 30
52
  },
53
  {
54
- "epoch": 0.13059701492537312,
55
- "grad_norm": 0.24403347290033586,
56
- "learning_rate": 4.924528939432311e-05,
57
- "loss": 0.6199,
58
  "step": 35
59
  },
60
  {
61
- "epoch": 0.14925373134328357,
62
- "grad_norm": 0.23580774948158992,
63
- "learning_rate": 4.884658491984735e-05,
64
- "loss": 0.6106,
65
  "step": 40
66
  },
67
  {
68
- "epoch": 0.16791044776119404,
69
- "grad_norm": 0.20719592888977728,
70
- "learning_rate": 4.8366266887814235e-05,
71
- "loss": 0.6112,
72
  "step": 45
73
  },
74
- {
75
- "epoch": 0.1865671641791045,
76
- "grad_norm": 0.22380542974606113,
77
- "learning_rate": 4.780617167924209e-05,
78
- "loss": 0.5938,
79
- "step": 50
80
- },
81
- {
82
- "epoch": 0.20522388059701493,
83
- "grad_norm": 0.22842463830159124,
84
- "learning_rate": 4.716844068408693e-05,
85
- "loss": 0.5965,
86
- "step": 55
87
- },
88
- {
89
- "epoch": 0.22388059701492538,
90
- "grad_norm": 0.2472281149897854,
91
- "learning_rate": 4.6455512114150546e-05,
92
- "loss": 0.5918,
93
- "step": 60
94
- },
95
- {
96
- "epoch": 0.24253731343283583,
97
- "grad_norm": 0.4696997844524139,
98
- "learning_rate": 4.5670111681161296e-05,
99
- "loss": 0.5828,
100
- "step": 65
101
- },
102
- {
103
- "epoch": 0.26119402985074625,
104
- "grad_norm": 0.3601208448021653,
105
- "learning_rate": 4.481524217566783e-05,
106
- "loss": 0.5797,
107
- "step": 70
108
- },
109
- {
110
- "epoch": 0.2798507462686567,
111
- "grad_norm": 0.4470058024970664,
112
- "learning_rate": 4.3894171986588217e-05,
113
- "loss": 0.5785,
114
- "step": 75
115
- },
116
- {
117
- "epoch": 0.29850746268656714,
118
- "grad_norm": 0.3818035550378131,
119
- "learning_rate": 4.29104226053073e-05,
120
- "loss": 0.5773,
121
- "step": 80
122
- },
123
- {
124
- "epoch": 0.31716417910447764,
125
- "grad_norm": 0.2970537633505199,
126
- "learning_rate": 4.186775516209732e-05,
127
- "loss": 0.5727,
128
- "step": 85
129
- },
130
- {
131
- "epoch": 0.3358208955223881,
132
- "grad_norm": 0.29663024827578144,
133
- "learning_rate": 4.077015604633669e-05,
134
- "loss": 0.5752,
135
- "step": 90
136
- },
137
- {
138
- "epoch": 0.35447761194029853,
139
- "grad_norm": 0.29881953809988826,
140
- "learning_rate": 3.962182166550441e-05,
141
- "loss": 0.5736,
142
- "step": 95
143
- },
144
- {
145
- "epoch": 0.373134328358209,
146
- "grad_norm": 0.26921847718817626,
147
- "learning_rate": 3.8427142401220634e-05,
148
- "loss": 0.5695,
149
- "step": 100
150
- },
151
- {
152
- "epoch": 0.3917910447761194,
153
- "grad_norm": 0.23743210548629676,
154
- "learning_rate": 3.71906858236735e-05,
155
- "loss": 0.5659,
156
- "step": 105
157
- },
158
- {
159
- "epoch": 0.41044776119402987,
160
- "grad_norm": 0.24355534227876938,
161
- "learning_rate": 3.591717922860785e-05,
162
- "loss": 0.5731,
163
- "step": 110
164
- },
165
- {
166
- "epoch": 0.4291044776119403,
167
- "grad_norm": 0.21539403564797405,
168
- "learning_rate": 3.46114915636416e-05,
169
- "loss": 0.564,
170
- "step": 115
171
- },
172
- {
173
- "epoch": 0.44776119402985076,
174
- "grad_norm": 0.21006239470343735,
175
- "learning_rate": 3.3278614813010034e-05,
176
- "loss": 0.565,
177
- "step": 120
178
- },
179
- {
180
- "epoch": 0.4664179104477612,
181
- "grad_norm": 0.22904886863828847,
182
- "learning_rate": 3.1923644911909e-05,
183
- "loss": 0.5618,
184
- "step": 125
185
- },
186
- {
187
- "epoch": 0.48507462686567165,
188
- "grad_norm": 0.21290253924535837,
189
- "learning_rate": 3.0551762263406576e-05,
190
- "loss": 0.5605,
191
- "step": 130
192
- },
193
- {
194
- "epoch": 0.503731343283582,
195
- "grad_norm": 0.21115276011060066,
196
- "learning_rate": 2.9168211932412042e-05,
197
- "loss": 0.5577,
198
- "step": 135
199
- },
200
- {
201
- "epoch": 0.5223880597014925,
202
- "grad_norm": 0.19494831752949845,
203
- "learning_rate": 2.777828359242567e-05,
204
- "loss": 0.5631,
205
- "step": 140
206
- },
207
- {
208
- "epoch": 0.5410447761194029,
209
- "grad_norm": 0.22951585851679665,
210
- "learning_rate": 2.6387291301738377e-05,
211
- "loss": 0.5557,
212
- "step": 145
213
- },
214
- {
215
- "epoch": 0.5597014925373134,
216
- "grad_norm": 0.19810923061547167,
217
- "learning_rate": 2.50005531864019e-05,
218
- "loss": 0.5536,
219
- "step": 150
220
- },
221
- {
222
- "epoch": 0.5783582089552238,
223
- "grad_norm": 0.18718418228217987,
224
- "learning_rate": 2.362337110764688e-05,
225
- "loss": 0.5539,
226
- "step": 155
227
- },
228
- {
229
- "epoch": 0.5970149253731343,
230
- "grad_norm": 0.19650724426746513,
231
- "learning_rate": 2.226101039148557e-05,
232
- "loss": 0.5521,
233
- "step": 160
234
- },
235
- {
236
- "epoch": 0.6156716417910447,
237
- "grad_norm": 0.20908234372877013,
238
- "learning_rate": 2.0918679697998252e-05,
239
- "loss": 0.551,
240
- "step": 165
241
- },
242
- {
243
- "epoch": 0.6343283582089553,
244
- "grad_norm": 0.19226552097090244,
245
- "learning_rate": 1.9601511107268255e-05,
246
- "loss": 0.5514,
247
- "step": 170
248
- },
249
- {
250
- "epoch": 0.6529850746268657,
251
- "grad_norm": 0.18543518094959596,
252
- "learning_rate": 1.8314540498102216e-05,
253
- "loss": 0.551,
254
- "step": 175
255
- },
256
- {
257
- "epoch": 0.6716417910447762,
258
- "grad_norm": 0.16607605774831136,
259
- "learning_rate": 1.7062688294552992e-05,
260
- "loss": 0.5431,
261
- "step": 180
262
- },
263
- {
264
- "epoch": 0.6902985074626866,
265
- "grad_norm": 0.18289191933087842,
266
- "learning_rate": 1.5850740653856096e-05,
267
- "loss": 0.5465,
268
- "step": 185
269
- },
270
- {
271
- "epoch": 0.7089552238805971,
272
- "grad_norm": 0.16298717661946557,
273
- "learning_rate": 1.4683331167703218e-05,
274
- "loss": 0.5501,
275
- "step": 190
276
- },
277
- {
278
- "epoch": 0.7276119402985075,
279
- "grad_norm": 0.165024427295752,
280
- "learning_rate": 1.356492314681356e-05,
281
- "loss": 0.5528,
282
- "step": 195
283
- },
284
- {
285
- "epoch": 0.746268656716418,
286
- "grad_norm": 0.15102046043252118,
287
- "learning_rate": 1.2499792556533716e-05,
288
- "loss": 0.5473,
289
- "step": 200
290
- },
291
- {
292
- "epoch": 0.7649253731343284,
293
- "grad_norm": 0.1663197393117164,
294
- "learning_rate": 1.1492011668707753e-05,
295
- "loss": 0.5448,
296
- "step": 205
297
- },
298
- {
299
- "epoch": 0.7835820895522388,
300
- "grad_norm": 0.16404505929138055,
301
- "learning_rate": 1.0545433492320603e-05,
302
- "loss": 0.5499,
303
- "step": 210
304
- },
305
- {
306
- "epoch": 0.8022388059701493,
307
- "grad_norm": 0.1516324807248961,
308
- "learning_rate": 9.663677042440537e-06,
309
- "loss": 0.5443,
310
- "step": 215
311
- },
312
- {
313
- "epoch": 0.8208955223880597,
314
- "grad_norm": 0.15568509701819017,
315
- "learning_rate": 8.850113503781367e-06,
316
- "loss": 0.5441,
317
- "step": 220
318
- },
319
- {
320
- "epoch": 0.8395522388059702,
321
- "grad_norm": 0.13899753855441885,
322
- "learning_rate": 8.107853341784671e-06,
323
- "loss": 0.5505,
324
- "step": 225
325
- },
326
- {
327
- "epoch": 0.8582089552238806,
328
- "grad_norm": 0.1504041608633977,
329
- "learning_rate": 7.439734410499752e-06,
330
- "loss": 0.5469,
331
- "step": 230
332
- },
333
- {
334
- "epoch": 0.8768656716417911,
335
- "grad_norm": 0.1724320545374918,
336
- "learning_rate": 6.848311102728011e-06,
337
- "loss": 0.547,
338
- "step": 235
339
- },
340
- {
341
- "epoch": 0.8955223880597015,
342
- "grad_norm": 0.1751468100979065,
343
- "learning_rate": 6.335844583913515e-06,
344
- "loss": 0.5432,
345
- "step": 240
346
- },
347
- {
348
- "epoch": 0.914179104477612,
349
- "grad_norm": 0.13796859493374333,
350
- "learning_rate": 5.904294147118193e-06,
351
- "loss": 0.5469,
352
- "step": 245
353
- },
354
- {
355
- "epoch": 0.9328358208955224,
356
- "grad_norm": 0.1442761998642154,
357
- "learning_rate": 5.555309722133842e-06,
358
- "loss": 0.5434,
359
- "step": 250
360
- },
361
- {
362
- "epoch": 0.9514925373134329,
363
- "grad_norm": 0.13635376165657714,
364
- "learning_rate": 5.290225567370509e-06,
365
- "loss": 0.5394,
366
- "step": 255
367
- },
368
- {
369
- "epoch": 0.9701492537313433,
370
- "grad_norm": 0.1407502462221505,
371
- "learning_rate": 5.110055168638854e-06,
372
- "loss": 0.5431,
373
- "step": 260
374
- },
375
- {
376
- "epoch": 0.9888059701492538,
377
- "grad_norm": 0.1371738538237689,
378
- "learning_rate": 5.0154873643297575e-06,
379
- "loss": 0.5469,
380
- "step": 265
381
- },
382
  {
383
  "epoch": 1.0,
384
- "step": 268,
385
- "total_flos": 488621249396736.0,
386
- "train_loss": 0.5791835704846169,
387
- "train_runtime": 3332.7286,
388
- "train_samples_per_second": 10.292,
389
- "train_steps_per_second": 0.08
390
  }
391
  ],
392
  "logging_steps": 5,
393
- "max_steps": 268,
394
  "num_input_tokens_seen": 0,
395
  "num_train_epochs": 1,
396
  "save_steps": 100,
@@ -406,8 +98,8 @@
406
  "attributes": {}
407
  }
408
  },
409
- "total_flos": 488621249396736.0,
410
- "train_batch_size": 16,
411
  "trial_name": null,
412
  "trial_params": null
413
  }
 
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
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": 0.10416666666666667,
13
+ "grad_norm": 10.75,
14
+ "learning_rate": 4.978103154668534e-05,
15
+ "loss": 0.9914,
16
  "step": 5
17
  },
18
  {
19
+ "epoch": 0.20833333333333334,
20
+ "grad_norm": 4.28125,
21
+ "learning_rate": 4.7366320839325864e-05,
22
+ "loss": 0.55,
23
  "step": 10
24
  },
25
  {
26
+ "epoch": 0.3125,
27
+ "grad_norm": 1.984375,
28
+ "learning_rate": 4.255543864307431e-05,
29
+ "loss": 0.4382,
30
  "step": 15
31
  },
32
  {
33
+ "epoch": 0.4166666666666667,
34
+ "grad_norm": 1.2578125,
35
+ "learning_rate": 3.5928648351858027e-05,
36
+ "loss": 0.3833,
37
  "step": 20
38
  },
39
  {
40
+ "epoch": 0.5208333333333334,
41
+ "grad_norm": 1.3515625,
42
+ "learning_rate": 2.828523867580628e-05,
43
+ "loss": 0.3536,
44
  "step": 25
45
  },
46
  {
47
+ "epoch": 0.625,
48
+ "grad_norm": 1.2734375,
49
+ "learning_rate": 2.054711762656369e-05,
50
+ "loss": 0.3548,
51
  "step": 30
52
  },
53
  {
54
+ "epoch": 0.7291666666666666,
55
+ "grad_norm": 1.1171875,
56
+ "learning_rate": 1.364761680517269e-05,
57
+ "loss": 0.3445,
58
  "step": 35
59
  },
60
  {
61
+ "epoch": 0.8333333333333334,
62
+ "grad_norm": 1.0078125,
63
+ "learning_rate": 8.418917836480417e-06,
64
+ "loss": 0.3189,
65
  "step": 40
66
  },
67
  {
68
+ "epoch": 0.9375,
69
+ "grad_norm": 0.8203125,
70
+ "learning_rate": 5.491678983489372e-06,
71
+ "loss": 0.3172,
72
  "step": 45
73
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
  {
75
  "epoch": 1.0,
76
+ "step": 48,
77
+ "total_flos": 1.355802795311104e+16,
78
+ "train_loss": 0.44515162458022434,
79
+ "train_runtime": 298.6439,
80
+ "train_samples_per_second": 0.161,
81
+ "train_steps_per_second": 0.161
82
  }
83
  ],
84
  "logging_steps": 5,
85
+ "max_steps": 48,
86
  "num_input_tokens_seen": 0,
87
  "num_train_epochs": 1,
88
  "save_steps": 100,
 
98
  "attributes": {}
99
  }
100
  },
101
+ "total_flos": 1.355802795311104e+16,
102
+ "train_batch_size": 1,
103
  "trial_name": null,
104
  "trial_params": null
105
  }