Hugging Face's logo

YUNTA88
/
rl4phyx-backup

Safetensors
Model card Files
xet
 Community
rl4phyx-backup
File size: 12,867 Bytes
3eee49d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
============================================================
  OPEN-ENDED EVAL: Base vs SFT (Multi-GPU)
  Base model: /workspace/rl4phyx/models/Qwen2.5-VL-3B-Instruct
  SFT model:  /workspace/rl4phyx/RL4Phyx/SFT/checkpoints/sft_qwen25vl_3b_fullft/final
  Base GPUs:  [0, 1, 2, 3]
  SFT GPUs:   [4, 5, 6, 7]
============================================================

Loaded 1533 test samples
  Mechanics: 276
  Electromagnetism: 275
  Thermodynamics: 255
  Waves/Acoustics: 253
  Optics: 252
  Modern Physics: 222

>>> Starting BASE model inference...
[base][GPU 2] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[base][GPU 0] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[base][GPU 1] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[base][GPU 3] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.64s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.70s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.59s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.71s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.11s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.19s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.11s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.20s/it]
[base][GPU 2] Model loaded. Processing 384 samples.
[base][GPU 0] Model loaded. Processing 384 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.21s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.28s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.17s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.23s/it]
[base][GPU 1] Model loaded. Processing 384 samples.
[base][GPU 3] Model loaded. Processing 381 samples.
[base][GPU 0] 20/384 done
[base][GPU 3] 20/381 done
[base][GPU 2] 20/384 done
[base][GPU 1] 20/384 done
[base][GPU 0] 40/384 done
[base][GPU 3] 40/381 done
[base][GPU 2] 40/384 done
[base][GPU 1] 40/384 done
[base][GPU 0] 60/384 done
[base][GPU 2] 60/384 done
[base][GPU 3] 60/381 done
[base][GPU 1] 60/384 done
[base][GPU 0] 80/384 done
[base][GPU 3] 80/381 done
[base][GPU 1] 80/384 done
[base][GPU 2] 80/384 done
[base][GPU 0] 100/384 done
[base][GPU 3] 100/381 done
[base][GPU 2] 100/384 done
[base][GPU 1] 100/384 done
[base][GPU 0] 120/384 done
[base][GPU 2] 120/384 done
[base][GPU 3] 120/381 done
[base][GPU 1] 120/384 done
[base][GPU 2] 140/384 done
[base][GPU 3] 140/381 done
[base][GPU 1] 140/384 done
[base][GPU 0] 140/384 done
[base][GPU 1] 160/384 done
[base][GPU 2] 160/384 done
[base][GPU 0] 160/384 done
[base][GPU 3] 160/381 done
[base][GPU 1] 180/384 done
[base][GPU 3] 180/381 done
[base][GPU 2] 180/384 done
[base][GPU 0] 180/384 done
[base][GPU 1] 200/384 done
[base][GPU 2] 200/384 done
[base][GPU 0] 200/384 done
[base][GPU 3] 200/381 done
[base][GPU 1] 220/384 done
[base][GPU 2] 220/384 done
[base][GPU 3] 220/381 done
[base][GPU 0] 220/384 done
[base][GPU 1] 240/384 done
[base][GPU 2] 240/384 done
[base][GPU 3] 240/381 done
[base][GPU 0] 240/384 done
[base][GPU 1] 260/384 done
[base][GPU 3] 260/381 done
[base][GPU 2] 260/384 done
[base][GPU 0] 260/384 done
[base][GPU 1] 280/384 done
[base][GPU 2] 280/384 done
[base][GPU 3] 280/381 done
[base][GPU 0] 280/384 done
[base][GPU 1] 300/384 done
[base][GPU 2] 300/384 done
[base][GPU 0] 300/384 done
[base][GPU 3] 300/381 done
[base][GPU 1] 320/384 done
[base][GPU 2] 320/384 done
[base][GPU 0] 320/384 done
[base][GPU 2] 340/384 done
[base][GPU 1] 340/384 done
[base][GPU 3] 320/381 done
[base][GPU 0] 340/384 done
[base][GPU 2] 360/384 done
[base][GPU 1] 360/384 done
[base][GPU 3] 340/381 done
[base][GPU 0] 360/384 done
[base][GPU 2] 380/384 done
[base][GPU 2] 384/384 done
[base][GPU 2] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base_gpu2.jsonl
[base][GPU 1] 380/384 done
[base][GPU 1] 384/384 done
[base][GPU 1] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base_gpu1.jsonl
[base][GPU 3] 360/381 done
[base][GPU 0] 380/384 done
[base][GPU 0] 384/384 done
[base][GPU 0] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base_gpu0.jsonl
[base][GPU 3] 380/381 done
[base][GPU 3] 381/381 done
[base][GPU 3] Saved 381 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base_gpu3.jsonl

>>> Starting SFT model inference...
[sft][GPU 6] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[sft][GPU 4] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[sft][GPU 5] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
[sft][GPU 7] Loading model...
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.89s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.90s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.83s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.84s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.24s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.34s/it]
[sft][GPU 6] Model loaded. Processing 384 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.34s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.42s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.44s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.51s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.33s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.41s/it]
[sft][GPU 7] Model loaded. Processing 381 samples.
[sft][GPU 5] Model loaded. Processing 384 samples.
[sft][GPU 4] Model loaded. Processing 384 samples.
[sft][GPU 7] 20/381 done
[sft][GPU 4] 20/384 done
[sft][GPU 5] 20/384 done
[sft][GPU 6] 20/384 done
[sft][GPU 4] 40/384 done
[sft][GPU 7] 40/381 done
[sft][GPU 5] 40/384 done
[sft][GPU 6] 40/384 done
[sft][GPU 4] 60/384 done
[sft][GPU 7] 60/381 done
[sft][GPU 6] 60/384 done
[sft][GPU 5] 60/384 done
[sft][GPU 4] 80/384 done
[sft][GPU 5] 80/384 done
[sft][GPU 6] 80/384 done
[sft][GPU 7] 80/381 done
[sft][GPU 4] 100/384 done
[sft][GPU 7] 100/381 done
[sft][GPU 6] 100/384 done
[sft][GPU 5] 100/384 done
[sft][GPU 7] 120/381 done
[sft][GPU 4] 120/384 done
[sft][GPU 6] 120/384 done
[sft][GPU 5] 120/384 done
[sft][GPU 7] 140/381 done
[sft][GPU 5] 140/384 done
[sft][GPU 6] 140/384 done
[sft][GPU 4] 140/384 done
[sft][GPU 7] 160/381 done
[sft][GPU 5] 160/384 done
[sft][GPU 6] 160/384 done
[sft][GPU 4] 160/384 done
[sft][GPU 7] 180/381 done
[sft][GPU 5] 180/384 done
[sft][GPU 6] 180/384 done
[sft][GPU 4] 180/384 done
[sft][GPU 5] 200/384 done
[sft][GPU 7] 200/381 done
[sft][GPU 6] 200/384 done
[sft][GPU 4] 200/384 done
[sft][GPU 5] 220/384 done
[sft][GPU 7] 220/381 done
[sft][GPU 6] 220/384 done
[sft][GPU 4] 220/384 done
[sft][GPU 5] 240/384 done
[sft][GPU 7] 240/381 done
[sft][GPU 6] 240/384 done
[sft][GPU 5] 260/384 done
[sft][GPU 4] 240/384 done
[sft][GPU 7] 260/381 done
[sft][GPU 6] 260/384 done
[sft][GPU 5] 280/384 done
[sft][GPU 4] 260/384 done
[sft][GPU 7] 280/381 done
[sft][GPU 6] 280/384 done
[sft][GPU 5] 300/384 done
[sft][GPU 4] 280/384 done
[sft][GPU 6] 300/384 done
[sft][GPU 7] 300/381 done
[sft][GPU 5] 320/384 done
[sft][GPU 4] 300/384 done
[sft][GPU 6] 320/384 done
[sft][GPU 5] 340/384 done
[sft][GPU 7] 320/381 done
[sft][GPU 4] 320/384 done
[sft][GPU 6] 340/384 done
[sft][GPU 5] 360/384 done
[sft][GPU 6] 360/384 done
[sft][GPU 4] 340/384 done
[sft][GPU 7] 340/381 done
[sft][GPU 6] 380/384 done
[sft][GPU 5] 380/384 done
[sft][GPU 4] 360/384 done
[sft][GPU 6] 384/384 done
[sft][GPU 6] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_sft_gpu6.jsonl
[sft][GPU 5] 384/384 done
[sft][GPU 5] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_sft_gpu5.jsonl
[sft][GPU 7] 360/381 done
[sft][GPU 4] 380/384 done
[sft][GPU 7] 380/381 done
[sft][GPU 7] 381/381 done
[sft][GPU 7] Saved 381 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_sft_gpu7.jsonl
[sft][GPU 4] 384/384 done
[sft][GPU 4] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_sft_gpu4.jsonl

============================================================
  INFERENCE COMPLETE in 252.6 min
  Base results: 1533 → /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base.jsonl
  SFT results:  1533 → /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_sft.jsonl
============================================================