Hugging Face's logo

baptistecolle
/
Qwen2.5-1.5B-Open-R1-Distill-Agentic-Trace

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Model card Files Community
baptistecolle HF Staff commited on
Commit
69c748f
·
verified ·
1 Parent(s): 407ad6e

Model save

Browse files
Files changed (5) hide show
  1. README.md +58 -0
  2. all_results.json +8 -0
  3. generation_config.json +14 -0
  4. train_results.json +8 -0
  5. trainer_state.json +387 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
3
+ library_name: transformers
4
+ model_name: Qwen2.5-1.5B-Open-R1-Distill-Agentic-Trace
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for Qwen2.5-1.5B-Open-R1-Distill-Agentic-Trace
13
+
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="baptistecolle/Qwen2.5-1.5B-Open-R1-Distill-Agentic-Trace", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
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/baptisecolle/huggingface/runs/leq8aha4)
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.16.0
38
+ - Transformers: 4.50.0
39
+ - Pytorch: 2.5.1
40
+ - Datasets: 3.5.0
41
+ - Tokenizers: 0.21.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 22842265731072.0,
3
+ "train_loss": 0.4351522645284963,
4
+ "train_runtime": 311.5406,
5
+ "train_samples": 207,
6
+ "train_samples_per_second": 5.457,
7
+ "train_steps_per_second": 0.69
8
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.50.0"
14
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 22842265731072.0,
3
+ "train_loss": 0.4351522645284963,
4
+ "train_runtime": 311.5406,
5
+ "train_samples": 207,
6
+ "train_samples_per_second": 5.457,
7
+ "train_steps_per_second": 0.69
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 215,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11627906976744186,
14
+ "grad_norm": 1.426078351046737,
15
+ "learning_rate": 2.272727272727273e-05,
16
+ "loss": 1.0374,
17
+ "num_tokens": 616397.0,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 0.23255813953488372,
22
+ "grad_norm": 1.4337078601293307,
23
+ "learning_rate": 4.545454545454546e-05,
24
+ "loss": 0.8459,
25
+ "num_tokens": 1218796.0,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 0.3488372093023256,
30
+ "grad_norm": 0.9412483454905438,
31
+ "learning_rate": 4.9957324896583496e-05,
32
+ "loss": 0.717,
33
+ "num_tokens": 1836857.0,
34
+ "step": 15
35
+ },
36
+ {
37
+ "epoch": 0.46511627906976744,
38
+ "grad_norm": 1.2421575625153427,
39
+ "learning_rate": 4.9784234694692117e-05,
40
+ "loss": 0.6697,
41
+ "num_tokens": 2480724.0,
42
+ "step": 20
43
+ },
44
+ {
45
+ "epoch": 0.5813953488372093,
46
+ "grad_norm": 1.039756996050679,
47
+ "learning_rate": 4.9479087149591016e-05,
48
+ "loss": 0.6576,
49
+ "num_tokens": 3108504.0,
50
+ "step": 25
51
+ },
52
+ {
53
+ "epoch": 0.6976744186046512,
54
+ "grad_norm": 0.7843538876272397,
55
+ "learning_rate": 4.9043690578893296e-05,
56
+ "loss": 0.6104,
57
+ "num_tokens": 3730397.0,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.813953488372093,
62
+ "grad_norm": 0.7523189873152597,
63
+ "learning_rate": 4.8480625161598e-05,
64
+ "loss": 0.5963,
65
+ "num_tokens": 4370252.0,
66
+ "step": 35
67
+ },
68
+ {
69
+ "epoch": 0.9302325581395349,
70
+ "grad_norm": 1.861170722861451,
71
+ "learning_rate": 4.779322764783724e-05,
72
+ "loss": 0.7153,
73
+ "num_tokens": 4903914.0,
74
+ "step": 40
75
+ },
76
+ {
77
+ "epoch": 1.0465116279069768,
78
+ "grad_norm": 1.6296026123428795,
79
+ "learning_rate": 4.6985571585149876e-05,
80
+ "loss": 0.5757,
81
+ "num_tokens": 5419349.0,
82
+ "step": 45
83
+ },
84
+ {
85
+ "epoch": 1.1627906976744187,
86
+ "grad_norm": 0.8964132137282615,
87
+ "learning_rate": 4.60624431784618e-05,
88
+ "loss": 0.519,
89
+ "num_tokens": 6028764.0,
90
+ "step": 50
91
+ },
92
+ {
93
+ "epoch": 1.2790697674418605,
94
+ "grad_norm": 0.7192499555698023,
95
+ "learning_rate": 4.502931292682758e-05,
96
+ "loss": 0.4979,
97
+ "num_tokens": 6625180.0,
98
+ "step": 55
99
+ },
100
+ {
101
+ "epoch": 1.3953488372093024,
102
+ "grad_norm": 0.8051552030202953,
103
+ "learning_rate": 4.389230320501529e-05,
104
+ "loss": 0.5165,
105
+ "num_tokens": 7255749.0,
106
+ "step": 60
107
+ },
108
+ {
109
+ "epoch": 1.5116279069767442,
110
+ "grad_norm": 53.24305130149784,
111
+ "learning_rate": 4.2658151982047536e-05,
112
+ "loss": 0.525,
113
+ "num_tokens": 7834089.0,
114
+ "step": 65
115
+ },
116
+ {
117
+ "epoch": 1.627906976744186,
118
+ "grad_norm": 0.6314644559742063,
119
+ "learning_rate": 4.133417289170434e-05,
120
+ "loss": 0.5228,
121
+ "num_tokens": 8481532.0,
122
+ "step": 70
123
+ },
124
+ {
125
+ "epoch": 1.744186046511628,
126
+ "grad_norm": 0.7714043941894847,
127
+ "learning_rate": 3.992821189161138e-05,
128
+ "loss": 0.5209,
129
+ "num_tokens": 9110904.0,
130
+ "step": 75
131
+ },
132
+ {
133
+ "epoch": 1.8604651162790697,
134
+ "grad_norm": 0.793200983051883,
135
+ "learning_rate": 3.8448600767754265e-05,
136
+ "loss": 0.5047,
137
+ "num_tokens": 9725035.0,
138
+ "step": 80
139
+ },
140
+ {
141
+ "epoch": 1.9767441860465116,
142
+ "grad_norm": 0.784007077545182,
143
+ "learning_rate": 3.6904107759952624e-05,
144
+ "loss": 0.485,
145
+ "num_tokens": 10320646.0,
146
+ "step": 85
147
+ },
148
+ {
149
+ "epoch": 2.0930232558139537,
150
+ "grad_norm": 0.7267651662469797,
151
+ "learning_rate": 3.5303885600889935e-05,
152
+ "loss": 0.4358,
153
+ "num_tokens": 10877844.0,
154
+ "step": 90
155
+ },
156
+ {
157
+ "epoch": 2.2093023255813953,
158
+ "grad_norm": 0.7334836153849675,
159
+ "learning_rate": 3.365741727662187e-05,
160
+ "loss": 0.4085,
161
+ "num_tokens": 11472723.0,
162
+ "step": 95
163
+ },
164
+ {
165
+ "epoch": 2.3255813953488373,
166
+ "grad_norm": 0.9638635507157925,
167
+ "learning_rate": 3.1974459829988826e-05,
168
+ "loss": 0.411,
169
+ "num_tokens": 12095224.0,
170
+ "step": 100
171
+ },
172
+ {
173
+ "epoch": 2.441860465116279,
174
+ "grad_norm": 0.566412620058458,
175
+ "learning_rate": 3.026498653995607e-05,
176
+ "loss": 0.3724,
177
+ "num_tokens": 12706666.0,
178
+ "step": 105
179
+ },
180
+ {
181
+ "epoch": 2.558139534883721,
182
+ "grad_norm": 0.7503759786149439,
183
+ "learning_rate": 2.8539127819529143e-05,
184
+ "loss": 0.3938,
185
+ "num_tokens": 13319481.0,
186
+ "step": 110
187
+ },
188
+ {
189
+ "epoch": 2.6744186046511627,
190
+ "grad_norm": 0.6009758378668209,
191
+ "learning_rate": 2.6807111182486174e-05,
192
+ "loss": 0.3838,
193
+ "num_tokens": 13929481.0,
194
+ "step": 115
195
+ },
196
+ {
197
+ "epoch": 2.7906976744186047,
198
+ "grad_norm": 0.7071770345433811,
199
+ "learning_rate": 2.507920063468675e-05,
200
+ "loss": 0.3704,
201
+ "num_tokens": 14531032.0,
202
+ "step": 120
203
+ },
204
+ {
205
+ "epoch": 2.9069767441860463,
206
+ "grad_norm": 0.6933855131506369,
207
+ "learning_rate": 2.3365635849127166e-05,
208
+ "loss": 0.3946,
209
+ "num_tokens": 15156384.0,
210
+ "step": 125
211
+ },
212
+ {
213
+ "epoch": 3.0232558139534884,
214
+ "grad_norm": 0.657092893175657,
215
+ "learning_rate": 2.1676571485193282e-05,
216
+ "loss": 0.3853,
217
+ "num_tokens": 15707749.0,
218
+ "step": 130
219
+ },
220
+ {
221
+ "epoch": 3.13953488372093,
222
+ "grad_norm": 0.7324356510004003,
223
+ "learning_rate": 2.002201701170766e-05,
224
+ "loss": 0.3217,
225
+ "num_tokens": 16340606.0,
226
+ "step": 135
227
+ },
228
+ {
229
+ "epoch": 3.255813953488372,
230
+ "grad_norm": 0.6246116853697837,
231
+ "learning_rate": 1.8411777390382367e-05,
232
+ "loss": 0.2979,
233
+ "num_tokens": 16944484.0,
234
+ "step": 140
235
+ },
236
+ {
237
+ "epoch": 3.3720930232558137,
238
+ "grad_norm": 0.6458581868017114,
239
+ "learning_rate": 1.6855394971189778e-05,
240
+ "loss": 0.3229,
241
+ "num_tokens": 17553663.0,
242
+ "step": 145
243
+ },
244
+ {
245
+ "epoch": 3.488372093023256,
246
+ "grad_norm": 0.563906679313201,
247
+ "learning_rate": 1.5362092943981944e-05,
248
+ "loss": 0.3026,
249
+ "num_tokens": 18188173.0,
250
+ "step": 150
251
+ },
252
+ {
253
+ "epoch": 3.604651162790698,
254
+ "grad_norm": 0.5655342559997661,
255
+ "learning_rate": 1.3940720681466734e-05,
256
+ "loss": 0.2997,
257
+ "num_tokens": 18819640.0,
258
+ "step": 155
259
+ },
260
+ {
261
+ "epoch": 3.7209302325581395,
262
+ "grad_norm": 0.6061135438357336,
263
+ "learning_rate": 1.2599701297440578e-05,
264
+ "loss": 0.3158,
265
+ "num_tokens": 19430442.0,
266
+ "step": 160
267
+ },
268
+ {
269
+ "epoch": 3.8372093023255816,
270
+ "grad_norm": 0.5589360223860185,
271
+ "learning_rate": 1.1346981731050059e-05,
272
+ "loss": 0.2665,
273
+ "num_tokens": 20003957.0,
274
+ "step": 165
275
+ },
276
+ {
277
+ "epoch": 3.953488372093023,
278
+ "grad_norm": 0.5770875534708484,
279
+ "learning_rate": 1.0189985652885225e-05,
280
+ "loss": 0.3215,
281
+ "num_tokens": 20589734.0,
282
+ "step": 170
283
+ },
284
+ {
285
+ "epoch": 4.069767441860465,
286
+ "grad_norm": 0.501582071030718,
287
+ "learning_rate": 9.135569471985015e-06,
288
+ "loss": 0.2683,
289
+ "num_tokens": 21131356.0,
290
+ "step": 175
291
+ },
292
+ {
293
+ "epoch": 4.186046511627907,
294
+ "grad_norm": 0.6129991511301848,
295
+ "learning_rate": 8.189981704459338e-06,
296
+ "loss": 0.2346,
297
+ "num_tokens": 21741947.0,
298
+ "step": 180
299
+ },
300
+ {
301
+ "epoch": 4.3023255813953485,
302
+ "grad_norm": 0.5871856744225346,
303
+ "learning_rate": 7.358825944511101e-06,
304
+ "loss": 0.2473,
305
+ "num_tokens": 22338072.0,
306
+ "step": 185
307
+ },
308
+ {
309
+ "epoch": 4.4186046511627906,
310
+ "grad_norm": 0.5101346511723733,
311
+ "learning_rate": 6.647027657293392e-06,
312
+ "loss": 0.2479,
313
+ "num_tokens": 22958505.0,
314
+ "step": 190
315
+ },
316
+ {
317
+ "epoch": 4.534883720930233,
318
+ "grad_norm": 0.6244435714805572,
319
+ "learning_rate": 6.0588049903889796e-06,
320
+ "loss": 0.2544,
321
+ "num_tokens": 23589480.0,
322
+ "step": 195
323
+ },
324
+ {
325
+ "epoch": 4.651162790697675,
326
+ "grad_norm": 0.5334908287870592,
327
+ "learning_rate": 5.597643776884412e-06,
328
+ "loss": 0.2294,
329
+ "num_tokens": 24195388.0,
330
+ "step": 200
331
+ },
332
+ {
333
+ "epoch": 4.767441860465116,
334
+ "grad_norm": 0.5107011201150088,
335
+ "learning_rate": 5.266276878171664e-06,
336
+ "loss": 0.2345,
337
+ "num_tokens": 24813280.0,
338
+ "step": 205
339
+ },
340
+ {
341
+ "epoch": 4.883720930232558,
342
+ "grad_norm": 0.5467832269520996,
343
+ "learning_rate": 5.0666679888927605e-06,
344
+ "loss": 0.2326,
345
+ "num_tokens": 25383723.0,
346
+ "step": 210
347
+ },
348
+ {
349
+ "epoch": 5.0,
350
+ "grad_norm": 0.5165825558969128,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.2413,
353
+ "num_tokens": 25965455.0,
354
+ "step": 215
355
+ },
356
+ {
357
+ "epoch": 5.0,
358
+ "step": 215,
359
+ "total_flos": 22842265731072.0,
360
+ "train_loss": 0.4351522645284963,
361
+ "train_runtime": 311.5406,
362
+ "train_samples_per_second": 5.457,
363
+ "train_steps_per_second": 0.69
364
+ }
365
+ ],
366
+ "logging_steps": 5,
367
+ "max_steps": 215,
368
+ "num_input_tokens_seen": 0,
369
+ "num_train_epochs": 5,
370
+ "save_steps": 100,
371
+ "stateful_callbacks": {
372
+ "TrainerControl": {
373
+ "args": {
374
+ "should_epoch_stop": false,
375
+ "should_evaluate": false,
376
+ "should_log": false,
377
+ "should_save": true,
378
+ "should_training_stop": true
379
+ },
380
+ "attributes": {}
381
+ }
382
+ },
383
+ "total_flos": 22842265731072.0,
384
+ "train_batch_size": 1,
385
+ "trial_name": null,
386
+ "trial_params": null
387
+ }