Hugging Face's logo

reasoning-project
/
Q25M-1.5B-MR1-50k-SFT-v0.2-3epoch

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files Metrics Community
JW17 commited on
Commit
d6ab4e2
·
verified ·
1 Parent(s): a23516e

Add files using upload-large-folder tool

Browse files
Files changed (40) hide show
  1. .gitattributes +9 -0
  2. checkpoint-112/model.safetensors +3 -0
  3. checkpoint-112/tokenizer.json +3 -0
  4. checkpoint-112/training_args.bin +3 -0
  5. checkpoint-168/model.safetensors +3 -0
  6. checkpoint-168/tokenizer.json +3 -0
  7. checkpoint-168/training_args.bin +3 -0
  8. checkpoint-224/model.safetensors +3 -0
  9. checkpoint-224/tokenizer.json +3 -0
  10. checkpoint-224/training_args.bin +3 -0
  11. checkpoint-280/model.safetensors +3 -0
  12. checkpoint-280/special_tokens_map.json +19 -0
  13. checkpoint-280/tokenizer.json +3 -0
  14. checkpoint-280/training_args.bin +3 -0
  15. checkpoint-336/model.safetensors +3 -0
  16. checkpoint-336/tokenizer.json +3 -0
  17. checkpoint-336/training_args.bin +3 -0
  18. checkpoint-392/generation_config.json +6 -0
  19. checkpoint-392/model.safetensors +3 -0
  20. checkpoint-392/tokenizer.json +3 -0
  21. checkpoint-392/trainer_state.json +306 -0
  22. checkpoint-392/training_args.bin +3 -0
  23. checkpoint-448/model.safetensors +3 -0
  24. checkpoint-448/tokenizer.json +3 -0
  25. checkpoint-448/tokenizer_config.json +208 -0
  26. checkpoint-448/training_args.bin +3 -0
  27. checkpoint-501/model.safetensors +3 -0
  28. checkpoint-501/special_tokens_map.json +19 -0
  29. checkpoint-501/tokenizer.json +3 -0
  30. checkpoint-501/training_args.bin +3 -0
  31. checkpoint-56/model.safetensors +3 -0
  32. checkpoint-56/tokenizer.json +3 -0
  33. checkpoint-56/training_args.bin +3 -0
  34. model.safetensors +3 -0
  35. runs/Feb15_19-22-58_4c5ca18e0017/events.out.tfevents.1739648015.4c5ca18e0017 +3 -0
  36. runs/Feb15_19-34-39_4c5ca18e0017/events.out.tfevents.1739648086.4c5ca18e0017 +3 -0
  37. runs/Feb15_19-35-57_4c5ca18e0017/events.out.tfevents.1739648164.4c5ca18e0017 +3 -0
  38. runs/Feb16_01-00-56_044e936b01ce/events.out.tfevents.1739667669.044e936b01ce +3 -0
  39. tokenizer.json +3 -0
  40. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-448/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-336/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-168/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-112/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-501/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-224/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-112/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b023410ba9b5e57005073e2cd484d69387424f8247747a3d964d5cc3730c7809
3
+ size 3087467144
checkpoint-112/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-112/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-168/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9344ada2606b1aef5b19007eeb54ee0a9f303cbd5d6aee59f3d7292d66b85b
3
+ size 3087467144
checkpoint-168/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-224/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7be3143f2a37ce45278a1450833901e4d55ae9b0cad408c70965924597a7ac
3
+ size 3087467144
checkpoint-224/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-224/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-280/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de90b09db6ea8c91037e7c66d01f652d57928f4dc36e318ff0e709d353d9fa66
3
+ size 3087467144
checkpoint-280/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|endoftext|>",
18
+ "pad_token": "<|endoftext|>"
19
+ }
checkpoint-280/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-280/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-336/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0303800568f1f52358c8d552e78491d1b55845410b700a0160599f8f840444
3
+ size 3087467144
checkpoint-336/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-336/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-392/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.48.3"
6
+ }
checkpoint-392/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ca41b098c05b669ddda7efce8aaab86c95ac08d2d138361acbde2afe61620d
3
+ size 3087467144
checkpoint-392/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-392/trainer_state.json ADDED
@@ -0,0 +1,306 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.3473053892215567,
5
+ "eval_steps": 500,
6
+ "global_step": 392,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.059880239520958084,
13
+ "grad_norm": 6.566332162525977,
14
+ "learning_rate": 7.692307692307694e-06,
15
+ "loss": 4.3864,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11976047904191617,
20
+ "grad_norm": 2.0437379261117132,
21
+ "learning_rate": 1.5384615384615387e-05,
22
+ "loss": 3.4794,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.17964071856287425,
27
+ "grad_norm": 0.8566260346858398,
28
+ "learning_rate": 1.9996500732179695e-05,
29
+ "loss": 2.5375,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.23952095808383234,
34
+ "grad_norm": 0.6117118904297301,
35
+ "learning_rate": 1.995716208873644e-05,
36
+ "loss": 1.8752,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2994011976047904,
41
+ "grad_norm": 0.3923875723199884,
42
+ "learning_rate": 1.9874283308955058e-05,
43
+ "loss": 1.4434,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.3592814371257485,
48
+ "grad_norm": 0.2726465509781607,
49
+ "learning_rate": 1.9748226800652062e-05,
50
+ "loss": 1.2232,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.41916167664670656,
55
+ "grad_norm": 0.22048277219015358,
56
+ "learning_rate": 1.957954377686475e-05,
57
+ "loss": 1.1031,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.47904191616766467,
62
+ "grad_norm": 0.19131964365908752,
63
+ "learning_rate": 1.9368971845536844e-05,
64
+ "loss": 1.0318,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.5389221556886228,
69
+ "grad_norm": 0.19325047947069812,
70
+ "learning_rate": 1.911743178414665e-05,
71
+ "loss": 0.9724,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.5988023952095808,
76
+ "grad_norm": 0.18220999359482376,
77
+ "learning_rate": 1.8826023513381372e-05,
78
+ "loss": 0.942,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.6586826347305389,
83
+ "grad_norm": 0.17750272843534337,
84
+ "learning_rate": 1.849602128746387e-05,
85
+ "loss": 0.9106,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.718562874251497,
90
+ "grad_norm": 0.16658108783370879,
91
+ "learning_rate": 1.8128868122163125e-05,
92
+ "loss": 0.8876,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.7784431137724551,
97
+ "grad_norm": 0.1461861518555333,
98
+ "learning_rate": 1.7726169484853438e-05,
99
+ "loss": 0.872,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.8383233532934131,
104
+ "grad_norm": 0.14457472093324725,
105
+ "learning_rate": 1.7289686274214116e-05,
106
+ "loss": 0.8576,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.8982035928143712,
111
+ "grad_norm": 0.1544690749108873,
112
+ "learning_rate": 1.6821327120267567e-05,
113
+ "loss": 0.8467,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.9580838323353293,
118
+ "grad_norm": 0.1429893393640351,
119
+ "learning_rate": 1.6323140038425842e-05,
120
+ "loss": 0.8252,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.0179640718562875,
125
+ "grad_norm": 0.11444623635062835,
126
+ "learning_rate": 1.5797303474040332e-05,
127
+ "loss": 0.8209,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.0778443113772456,
132
+ "grad_norm": 0.12105393067348605,
133
+ "learning_rate": 1.524611677661454e-05,
134
+ "loss": 0.8064,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.1377245508982037,
139
+ "grad_norm": 0.11410840909819214,
140
+ "learning_rate": 1.4671990145333697e-05,
141
+ "loss": 0.7997,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.1976047904191618,
146
+ "grad_norm": 0.1145244272492734,
147
+ "learning_rate": 1.4077434089877038e-05,
148
+ "loss": 0.7938,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 1.2574850299401197,
153
+ "grad_norm": 0.12645762812759187,
154
+ "learning_rate": 1.3465048452597682e-05,
155
+ "loss": 0.7775,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 1.3173652694610778,
160
+ "grad_norm": 0.11488140079430814,
161
+ "learning_rate": 1.283751104007355e-05,
162
+ "loss": 0.7767,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.377245508982036,
167
+ "grad_norm": 0.13144847588925945,
168
+ "learning_rate": 1.2197565913740531e-05,
169
+ "loss": 0.7754,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.437125748502994,
174
+ "grad_norm": 0.10603932803573335,
175
+ "learning_rate": 1.1548011390810016e-05,
176
+ "loss": 0.7644,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.4970059880239521,
181
+ "grad_norm": 0.12250644964069578,
182
+ "learning_rate": 1.0891687807939707e-05,
183
+ "loss": 0.7735,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.55688622754491,
188
+ "grad_norm": 0.1092716735846818,
189
+ "learning_rate": 1.023146510116414e-05,
190
+ "loss": 0.7646,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.6167664670658684,
195
+ "grad_norm": 0.10437029986936892,
196
+ "learning_rate": 9.570230256394595e-06,
197
+ "loss": 0.7589,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.6766467065868262,
202
+ "grad_norm": 0.10262505227638254,
203
+ "learning_rate": 8.910874685364275e-06,
204
+ "loss": 0.7579,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.7365269461077846,
209
+ "grad_norm": 0.10634904902257739,
210
+ "learning_rate": 8.256281582220486e-06,
211
+ "loss": 0.7563,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.7964071856287425,
216
+ "grad_norm": 0.10308159473170038,
217
+ "learning_rate": 7.6093133160502e-06,
218
+ "loss": 0.7541,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 1.8562874251497006,
223
+ "grad_norm": 0.11967986382799979,
224
+ "learning_rate": 6.972798914468369e-06,
225
+ "loss": 0.7535,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.9161676646706587,
230
+ "grad_norm": 0.09790252223897214,
231
+ "learning_rate": 6.349521692999945e-06,
232
+ "loss": 0.7521,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.9760479041916168,
237
+ "grad_norm": 0.09917905729981547,
238
+ "learning_rate": 5.742207084349274e-06,
239
+ "loss": 0.748,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 2.035928143712575,
244
+ "grad_norm": 0.09219293703087832,
245
+ "learning_rate": 5.153510720776354e-06,
246
+ "loss": 0.7458,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 2.095808383233533,
251
+ "grad_norm": 0.09531637506680916,
252
+ "learning_rate": 4.58600682169262e-06,
253
+ "loss": 0.7417,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 2.155688622754491,
258
+ "grad_norm": 0.099401468944997,
259
+ "learning_rate": 4.042176937254474e-06,
260
+ "loss": 0.7381,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 2.215568862275449,
265
+ "grad_norm": 0.09333850738653798,
266
+ "learning_rate": 3.5243990971758124e-06,
267
+ "loss": 0.7368,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 2.2754491017964074,
272
+ "grad_norm": 0.10118930739249864,
273
+ "learning_rate": 3.034937412209178e-06,
274
+ "loss": 0.7407,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 2.3353293413173652,
279
+ "grad_norm": 0.09991557691778238,
280
+ "learning_rate": 2.5759321737655017e-06,
281
+ "loss": 0.7348,
282
+ "step": 390
283
+ }
284
+ ],
285
+ "logging_steps": 10,
286
+ "max_steps": 501,
287
+ "num_input_tokens_seen": 0,
288
+ "num_train_epochs": 3,
289
+ "save_steps": 56,
290
+ "stateful_callbacks": {
291
+ "TrainerControl": {
292
+ "args": {
293
+ "should_epoch_stop": false,
294
+ "should_evaluate": false,
295
+ "should_log": false,
296
+ "should_save": true,
297
+ "should_training_stop": false
298
+ },
299
+ "attributes": {}
300
+ }
301
+ },
302
+ "total_flos": 714699737923584.0,
303
+ "train_batch_size": 32,
304
+ "trial_name": null,
305
+ "trial_params": null
306
+ }
checkpoint-392/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-448/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d496f3eadfcc5d59b9f86e7516bd7b378964d04a8712455394a4232874fe0d0
3
+ size 3087467144
checkpoint-448/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-448/tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
checkpoint-448/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-501/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07586f7497d7b113f603e7bc91bcebff27a408cfe26d0faf144ccf7b95183099
3
+ size 3087467144
checkpoint-501/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|endoftext|>",
18
+ "pad_token": "<|endoftext|>"
19
+ }
checkpoint-501/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-501/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8f6e7804f3a840a4161690b37ce0fd44d23414301e916175c2b9b03fdf932b
3
+ size 3087467144
checkpoint-56/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07586f7497d7b113f603e7bc91bcebff27a408cfe26d0faf144ccf7b95183099
3
+ size 3087467144
runs/Feb15_19-22-58_4c5ca18e0017/events.out.tfevents.1739648015.4c5ca18e0017 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763e1af1f5c7a7a9c74969443a761862577ffc03ba55d59b1b4ce53cdd4ed5be
3
+ size 5545
runs/Feb15_19-34-39_4c5ca18e0017/events.out.tfevents.1739648086.4c5ca18e0017 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29256023a625bc1be93e9960b53208225233fe782a73eae67f0036aedfb47d21
3
+ size 5545
runs/Feb15_19-35-57_4c5ca18e0017/events.out.tfevents.1739648164.4c5ca18e0017 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562b54d072752d094e9eaaf53a6bf3637fc37055e244f3522e040d59848249ca
3
+ size 10139
runs/Feb16_01-00-56_044e936b01ce/events.out.tfevents.1739667669.044e936b01ce ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b4227afe35b487d1ca4ad0b07dbdd8536a4f3df92d3e8c7faff80042ae6d8e
3
+ size 16401
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928b4f12fd04ea31b06d20c711eaba74babe41da2d5bba03acd16f48c50e7e2f
3
+ size 6840