Hugging Face's logo

shawnzzzzz
/
Qwen2.5-VL-7B-Open-R1-Distill

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Model card Files Community
shawnzzzzz commited on
Commit
4d86664
·
verified ·
1 Parent(s): eb2399e

Model save

Browse files
Files changed (5) hide show
  1. README.md +58 -0
  2. all_results.json +8 -0
  3. generation_config.json +16 -0
  4. train_results.json +8 -0
  5. trainer_state.json +467 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-VL-7B-Instruct
3
+ library_name: transformers
4
+ model_name: Qwen2.5-VL-7B-Open-R1-Distill
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for Qwen2.5-VL-7B-Open-R1-Distill
13
+
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-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="shawnzzzzz/Qwen2.5-VL-7B-Open-R1-Distill", 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/shawnzzz/huggingface/runs/81a3m1bk)
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.16.0.dev0
38
+ - Transformers: 4.49.0
39
+ - Pytorch: 2.5.1
40
+ - Datasets: 3.3.2
41
+ - Tokenizers: 0.21.0
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": 2841831180075008.0,
3
+ "train_loss": 0.4941176689519418,
4
+ "train_runtime": 26749.4727,
5
+ "train_samples": 93733,
6
+ "train_samples_per_second": 1.28,
7
+ "train_steps_per_second": 0.01
8
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.1,
12
+ "top_k": 1,
13
+ "top_p": 0.001,
14
+ "transformers_version": "4.49.0",
15
+ "use_cache": false
16
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_flos": 2841831180075008.0,
3
+ "train_loss": 0.4941176689519418,
4
+ "train_runtime": 26749.4727,
5
+ "train_samples": 93733,
6
+ "train_samples_per_second": 1.28,
7
+ "train_steps_per_second": 0.01
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9978976874562018,
5
+ "eval_steps": 500,
6
+ "global_step": 267,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01868722261153936,
13
+ "grad_norm": 3.5830482905634797,
14
+ "learning_rate": 1.785714285714286e-05,
15
+ "loss": 0.8152,
16
+ "mean_token_accuracy": 0.7747266553342342,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.03737444522307872,
21
+ "grad_norm": 1.6625011834876648,
22
+ "learning_rate": 3.571428571428572e-05,
23
+ "loss": 0.7025,
24
+ "mean_token_accuracy": 0.7917468748986721,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 0.05606166783461808,
29
+ "grad_norm": 1.5899441749058187,
30
+ "learning_rate": 4.9998265374824964e-05,
31
+ "loss": 0.629,
32
+ "mean_token_accuracy": 0.8071001760661602,
33
+ "step": 15
34
+ },
35
+ {
36
+ "epoch": 0.07474889044615744,
37
+ "grad_norm": 1.5979853248536116,
38
+ "learning_rate": 4.993758157237536e-05,
39
+ "loss": 0.5972,
40
+ "mean_token_accuracy": 0.8143526442348957,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 0.09343611305769679,
45
+ "grad_norm": 1.2674965103641067,
46
+ "learning_rate": 4.979043378581744e-05,
47
+ "loss": 0.5727,
48
+ "mean_token_accuracy": 0.8199357651174068,
49
+ "step": 25
50
+ },
51
+ {
52
+ "epoch": 0.11212333566923616,
53
+ "grad_norm": 1.3685254142570102,
54
+ "learning_rate": 4.9557389054153965e-05,
55
+ "loss": 0.5555,
56
+ "mean_token_accuracy": 0.8241050921380519,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 0.1308105582807755,
61
+ "grad_norm": 0.9457691254500147,
62
+ "learning_rate": 4.923934542318854e-05,
63
+ "loss": 0.5409,
64
+ "mean_token_accuracy": 0.8273717932403087,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.14949778089231489,
69
+ "grad_norm": 0.9189569415750541,
70
+ "learning_rate": 4.883752848487571e-05,
71
+ "loss": 0.5272,
72
+ "mean_token_accuracy": 0.8308477029204369,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 0.16818500350385424,
77
+ "grad_norm": 0.7752642460093544,
78
+ "learning_rate": 4.835348665446049e-05,
79
+ "loss": 0.5213,
80
+ "mean_token_accuracy": 0.8322811633348465,
81
+ "step": 45
82
+ },
83
+ {
84
+ "epoch": 0.18687222611539359,
85
+ "grad_norm": 0.8083941553455664,
86
+ "learning_rate": 4.7789085203607664e-05,
87
+ "loss": 0.5118,
88
+ "mean_token_accuracy": 0.8346851594746113,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 0.20555944872693296,
93
+ "grad_norm": 0.9161612194082712,
94
+ "learning_rate": 4.714649907251388e-05,
95
+ "loss": 0.5088,
96
+ "mean_token_accuracy": 0.8352511122822761,
97
+ "step": 55
98
+ },
99
+ {
100
+ "epoch": 0.22424667133847231,
101
+ "grad_norm": 0.6723034421711911,
102
+ "learning_rate": 4.6428204488701576e-05,
103
+ "loss": 0.5018,
104
+ "mean_token_accuracy": 0.837028643488884,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 0.2429338939500117,
109
+ "grad_norm": 0.7871127694104725,
110
+ "learning_rate": 4.563696942479205e-05,
111
+ "loss": 0.5061,
112
+ "mean_token_accuracy": 0.8351837247610092,
113
+ "step": 65
114
+ },
115
+ {
116
+ "epoch": 0.261621116561551,
117
+ "grad_norm": 0.761272463434446,
118
+ "learning_rate": 4.477584293202868e-05,
119
+ "loss": 0.4939,
120
+ "mean_token_accuracy": 0.8390413090586663,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 0.2803083391730904,
125
+ "grad_norm": 0.5083377211370889,
126
+ "learning_rate": 4.384814339065424e-05,
127
+ "loss": 0.4914,
128
+ "mean_token_accuracy": 0.8395063504576683,
129
+ "step": 75
130
+ },
131
+ {
132
+ "epoch": 0.29899556178462977,
133
+ "grad_norm": 0.908648503032802,
134
+ "learning_rate": 4.285744572241972e-05,
135
+ "loss": 0.4972,
136
+ "mean_token_accuracy": 0.8376469679176808,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 0.3176827843961691,
141
+ "grad_norm": 0.5938541774391267,
142
+ "learning_rate": 4.180756761450171e-05,
143
+ "loss": 0.4816,
144
+ "mean_token_accuracy": 0.8424232035875321,
145
+ "step": 85
146
+ },
147
+ {
148
+ "epoch": 0.33637000700770847,
149
+ "grad_norm": 0.4849394515949123,
150
+ "learning_rate": 4.070255480791492e-05,
151
+ "loss": 0.491,
152
+ "mean_token_accuracy": 0.8394017495214939,
153
+ "step": 90
154
+ },
155
+ {
156
+ "epoch": 0.35505722961924785,
157
+ "grad_norm": 0.5718927262308711,
158
+ "learning_rate": 3.954666550711159e-05,
159
+ "loss": 0.4851,
160
+ "mean_token_accuracy": 0.8409382797777653,
161
+ "step": 95
162
+ },
163
+ {
164
+ "epoch": 0.37374445223078717,
165
+ "grad_norm": 0.5859959003534665,
166
+ "learning_rate": 3.8344353970845606e-05,
167
+ "loss": 0.4862,
168
+ "mean_token_accuracy": 0.8411718301475049,
169
+ "step": 100
170
+ },
171
+ {
172
+ "epoch": 0.39243167484232655,
173
+ "grad_norm": 0.3782337735273932,
174
+ "learning_rate": 3.710025334753495e-05,
175
+ "loss": 0.4834,
176
+ "mean_token_accuracy": 0.8412449143826961,
177
+ "step": 105
178
+ },
179
+ {
180
+ "epoch": 0.41111889745386593,
181
+ "grad_norm": 0.41111283052381054,
182
+ "learning_rate": 3.581915782126652e-05,
183
+ "loss": 0.476,
184
+ "mean_token_accuracy": 0.8432458408176899,
185
+ "step": 110
186
+ },
187
+ {
188
+ "epoch": 0.4298061200654053,
189
+ "grad_norm": 0.3851706170856147,
190
+ "learning_rate": 3.4506004137244676e-05,
191
+ "loss": 0.4851,
192
+ "mean_token_accuracy": 0.8405788190662861,
193
+ "step": 115
194
+ },
195
+ {
196
+ "epoch": 0.44849334267694463,
197
+ "grad_norm": 0.5062426249148336,
198
+ "learning_rate": 3.3165852577875546e-05,
199
+ "loss": 0.4785,
200
+ "mean_token_accuracy": 0.8426314078271389,
201
+ "step": 120
202
+ },
203
+ {
204
+ "epoch": 0.467180565288484,
205
+ "grad_norm": 0.40499027788768055,
206
+ "learning_rate": 3.180386746279663e-05,
207
+ "loss": 0.4747,
208
+ "mean_token_accuracy": 0.843725374341011,
209
+ "step": 125
210
+ },
211
+ {
212
+ "epoch": 0.4858677879000234,
213
+ "grad_norm": 0.47044740848341193,
214
+ "learning_rate": 3.04252972479953e-05,
215
+ "loss": 0.472,
216
+ "mean_token_accuracy": 0.8443724811077118,
217
+ "step": 130
218
+ },
219
+ {
220
+ "epoch": 0.5045550105115627,
221
+ "grad_norm": 0.4272272972180237,
222
+ "learning_rate": 2.90354543007051e-05,
223
+ "loss": 0.4725,
224
+ "mean_token_accuracy": 0.8439367160201072,
225
+ "step": 135
226
+ },
227
+ {
228
+ "epoch": 0.523242233123102,
229
+ "grad_norm": 0.4584455682048115,
230
+ "learning_rate": 2.7639694428017792e-05,
231
+ "loss": 0.4777,
232
+ "mean_token_accuracy": 0.842538620531559,
233
+ "step": 140
234
+ },
235
+ {
236
+ "epoch": 0.5419294557346415,
237
+ "grad_norm": 0.4589522708203329,
238
+ "learning_rate": 2.6243396238098518e-05,
239
+ "loss": 0.4693,
240
+ "mean_token_accuracy": 0.8448904320597649,
241
+ "step": 145
242
+ },
243
+ {
244
+ "epoch": 0.5606166783461808,
245
+ "grad_norm": 0.5239037802900407,
246
+ "learning_rate": 2.4851940413536174e-05,
247
+ "loss": 0.4697,
248
+ "mean_token_accuracy": 0.8447436839342117,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 0.5793039009577201,
253
+ "grad_norm": 0.4866344062046232,
254
+ "learning_rate": 2.347068897669999e-05,
255
+ "loss": 0.4687,
256
+ "mean_token_accuracy": 0.8448469452559948,
257
+ "step": 155
258
+ },
259
+ {
260
+ "epoch": 0.5979911235692595,
261
+ "grad_norm": 0.3163374085877721,
262
+ "learning_rate": 2.2104964627003848e-05,
263
+ "loss": 0.4629,
264
+ "mean_token_accuracy": 0.846843034029007,
265
+ "step": 160
266
+ },
267
+ {
268
+ "epoch": 0.6166783461807989,
269
+ "grad_norm": 0.2747336073106856,
270
+ "learning_rate": 2.0760030229702972e-05,
271
+ "loss": 0.4612,
272
+ "mean_token_accuracy": 0.8469885870814323,
273
+ "step": 165
274
+ },
275
+ {
276
+ "epoch": 0.6353655687923382,
277
+ "grad_norm": 0.24722982457005138,
278
+ "learning_rate": 1.9441068535263564e-05,
279
+ "loss": 0.4596,
280
+ "mean_token_accuracy": 0.8476050347089767,
281
+ "step": 170
282
+ },
283
+ {
284
+ "epoch": 0.6540527914038776,
285
+ "grad_norm": 0.23852151209010736,
286
+ "learning_rate": 1.815316220745756e-05,
287
+ "loss": 0.4636,
288
+ "mean_token_accuracy": 0.8460029393434525,
289
+ "step": 175
290
+ },
291
+ {
292
+ "epoch": 0.6727400140154169,
293
+ "grad_norm": 0.2597676847867842,
294
+ "learning_rate": 1.6901274237144782e-05,
295
+ "loss": 0.4669,
296
+ "mean_token_accuracy": 0.8451244607567787,
297
+ "step": 180
298
+ },
299
+ {
300
+ "epoch": 0.6914272366269563,
301
+ "grad_norm": 0.8605153163863832,
302
+ "learning_rate": 1.5690228817218815e-05,
303
+ "loss": 0.4668,
304
+ "mean_token_accuracy": 0.8468827910721302,
305
+ "step": 185
306
+ },
307
+ {
308
+ "epoch": 0.7101144592384957,
309
+ "grad_norm": 0.24915841679008277,
310
+ "learning_rate": 1.4524692752415493e-05,
311
+ "loss": 0.4591,
312
+ "mean_token_accuracy": 0.8473225735127926,
313
+ "step": 190
314
+ },
315
+ {
316
+ "epoch": 0.728801681850035,
317
+ "grad_norm": 0.29798920762515824,
318
+ "learning_rate": 1.3409157475622094e-05,
319
+ "loss": 0.4576,
320
+ "mean_token_accuracy": 0.847739252448082,
321
+ "step": 195
322
+ },
323
+ {
324
+ "epoch": 0.7474889044615743,
325
+ "grad_norm": 0.26110601129292016,
326
+ "learning_rate": 1.2347921739987815e-05,
327
+ "loss": 0.4611,
328
+ "mean_token_accuracy": 0.8468295410275459,
329
+ "step": 200
330
+ },
331
+ {
332
+ "epoch": 0.7661761270731138,
333
+ "grad_norm": 0.2785413649007615,
334
+ "learning_rate": 1.1345075053532287e-05,
335
+ "loss": 0.4615,
336
+ "mean_token_accuracy": 0.846584790199995,
337
+ "step": 205
338
+ },
339
+ {
340
+ "epoch": 0.7848633496846531,
341
+ "grad_norm": 0.281588896295376,
342
+ "learning_rate": 1.0404481920087206e-05,
343
+ "loss": 0.4532,
344
+ "mean_token_accuracy": 0.8491566374897956,
345
+ "step": 210
346
+ },
347
+ {
348
+ "epoch": 0.8035505722961925,
349
+ "grad_norm": 0.26784943568942043,
350
+ "learning_rate": 9.529766947299371e-06,
351
+ "loss": 0.4555,
352
+ "mean_token_accuracy": 0.8485622465610504,
353
+ "step": 215
354
+ },
355
+ {
356
+ "epoch": 0.8222377949077319,
357
+ "grad_norm": 0.22085700610769077,
358
+ "learning_rate": 8.724300879081718e-06,
359
+ "loss": 0.4584,
360
+ "mean_token_accuracy": 0.8476461283862591,
361
+ "step": 220
362
+ },
363
+ {
364
+ "epoch": 0.8409250175192712,
365
+ "grad_norm": 0.1833370072353519,
366
+ "learning_rate": 7.991187606337009e-06,
367
+ "loss": 0.452,
368
+ "mean_token_accuracy": 0.8494263976812363,
369
+ "step": 225
370
+ },
371
+ {
372
+ "epoch": 0.8596122401308106,
373
+ "grad_norm": 0.20272051001866034,
374
+ "learning_rate": 7.333252206008559e-06,
375
+ "loss": 0.4538,
376
+ "mean_token_accuracy": 0.8487676382064819,
377
+ "step": 230
378
+ },
379
+ {
380
+ "epoch": 0.8782994627423499,
381
+ "grad_norm": 0.19595652872474512,
382
+ "learning_rate": 6.753030054550158e-06,
383
+ "loss": 0.4506,
384
+ "mean_token_accuracy": 0.8496683083474637,
385
+ "step": 235
386
+ },
387
+ {
388
+ "epoch": 0.8969866853538893,
389
+ "grad_norm": 0.19319039281954486,
390
+ "learning_rate": 6.25275705776658e-06,
391
+ "loss": 0.4519,
392
+ "mean_token_accuracy": 0.8493411011993885,
393
+ "step": 240
394
+ },
395
+ {
396
+ "epoch": 0.9156739079654287,
397
+ "grad_norm": 0.20035376740680347,
398
+ "learning_rate": 5.834361034674521e-06,
399
+ "loss": 0.4557,
400
+ "mean_token_accuracy": 0.8482660032808781,
401
+ "step": 245
402
+ },
403
+ {
404
+ "epoch": 0.934361130576968,
405
+ "grad_norm": 0.2010469617138832,
406
+ "learning_rate": 5.499454288586379e-06,
407
+ "loss": 0.453,
408
+ "mean_token_accuracy": 0.8490205124020577,
409
+ "step": 250
410
+ },
411
+ {
412
+ "epoch": 0.9530483531885073,
413
+ "grad_norm": 0.2001591137777418,
414
+ "learning_rate": 5.24932739404462e-06,
415
+ "loss": 0.4488,
416
+ "mean_token_accuracy": 0.8502446681261062,
417
+ "step": 255
418
+ },
419
+ {
420
+ "epoch": 0.9717355758000468,
421
+ "grad_norm": 0.18321355893669744,
422
+ "learning_rate": 5.08494422354882e-06,
423
+ "loss": 0.4518,
424
+ "mean_token_accuracy": 0.849391470849514,
425
+ "step": 260
426
+ },
427
+ {
428
+ "epoch": 0.9904227984115861,
429
+ "grad_norm": 0.18951844466307075,
430
+ "learning_rate": 5.006938233240212e-06,
431
+ "loss": 0.4554,
432
+ "mean_token_accuracy": 0.8482832841575145,
433
+ "step": 265
434
+ },
435
+ {
436
+ "epoch": 0.9978976874562018,
437
+ "mean_token_accuracy": 0.8498711809515953,
438
+ "step": 267,
439
+ "total_flos": 2841831180075008.0,
440
+ "train_loss": 0.4941176689519418,
441
+ "train_runtime": 26749.4727,
442
+ "train_samples_per_second": 1.28,
443
+ "train_steps_per_second": 0.01
444
+ }
445
+ ],
446
+ "logging_steps": 5,
447
+ "max_steps": 267,
448
+ "num_input_tokens_seen": 0,
449
+ "num_train_epochs": 1,
450
+ "save_steps": 100,
451
+ "stateful_callbacks": {
452
+ "TrainerControl": {
453
+ "args": {
454
+ "should_epoch_stop": false,
455
+ "should_evaluate": false,
456
+ "should_log": false,
457
+ "should_save": true,
458
+ "should_training_stop": true
459
+ },
460
+ "attributes": {}
461
+ }
462
+ },
463
+ "total_flos": 2841831180075008.0,
464
+ "train_batch_size": 1,
465
+ "trial_name": null,
466
+ "trial_params": null
467
+ }