Hugging Face's logo

YUNTA88
/
rl4phyx-backup

Safetensors
Model card Files
xet
 Community
rl4phyx-backup
File size: 8,459 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
/opt/conda/lib/python3.11/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.
  warnings.warn(
============================================================
  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_phyx/final
  Base GPUs:  [0, 1, 2, 3]
  SFT GPUs:   [0, 1, 2, 3]
============================================================

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

>>> Starting SFT model inference...
/opt/conda/lib/python3.11/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.
  warnings.warn(
/opt/conda/lib/python3.11/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.
  warnings.warn(
[sft][GPU 0] Loading model...
/opt/conda/lib/python3.11/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.
  warnings.warn(
The tokenizer you are loading from '/workspace/rl4phyx/RL4Phyx/SFT/checkpoints/sft_qwen25vl_3b_fullft_phyx/final' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
`torch_dtype` is deprecated! Use `dtype` instead!
/opt/conda/lib/python3.11/site-packages/torch/utils/_pytree.py:185: FutureWarning: optree is installed but the version is too old to support PyTorch Dynamo in C++ pytree. C++ pytree support is disabled. Please consider upgrading optree using `python3 -m pip install --upgrade 'optree>=0.13.0'`.
  warnings.warn(
[sft][GPU 1] Loading model...
The tokenizer you are loading from '/workspace/rl4phyx/RL4Phyx/SFT/checkpoints/sft_qwen25vl_3b_fullft_phyx/final' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
`torch_dtype` is deprecated! Use `dtype` instead!
[sft][GPU 2] Loading model...
The tokenizer you are loading from '/workspace/rl4phyx/RL4Phyx/SFT/checkpoints/sft_qwen25vl_3b_fullft_phyx/final' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
`torch_dtype` is deprecated! Use `dtype` instead!
[sft][GPU 3] Loading model...
The tokenizer you are loading from '/workspace/rl4phyx/RL4Phyx/SFT/checkpoints/sft_qwen25vl_3b_fullft_phyx/final' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
`torch_dtype` is deprecated! Use `dtype` instead!

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
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,  1.54s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.24s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.10s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.01it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.07s/it]
[sft][GPU 0] Model loaded. Processing 384 samples.

Loading checkpoint shards:  50%|█████     | 1/2 [00:01<00:01,  1.28s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.28it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.20it/s]

Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.12it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00,  1.06it/s]
[sft][GPU 1] Model loaded. Processing 384 samples.
[sft][GPU 2] Model loaded. Processing 384 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.05it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.01s/it]
[sft][GPU 3] Model loaded. Processing 381 samples.
[sft][GPU 0] 20/384 done
[sft][GPU 3] 20/381 done
[sft][GPU 2] 20/384 done
[sft][GPU 1] 20/384 done
[sft][GPU 0] 40/384 done
[sft][GPU 3] 40/381 done
[sft][GPU 2] 40/384 done
[sft][GPU 1] 40/384 done
[sft][GPU 0] 60/384 done
[sft][GPU 2] 60/384 done
[sft][GPU 3] 60/381 done
[sft][GPU 0] 80/384 done
[sft][GPU 1] 60/384 done
[sft][GPU 2] 80/384 done
[sft][GPU 0] 100/384 done
[sft][GPU 1] 80/384 done
[sft][GPU 3] 80/381 done
[sft][GPU 2] 100/384 done
[sft][GPU 3] 100/381 done
[sft][GPU 0] 120/384 done
[sft][GPU 1] 100/384 done
[sft][GPU 2] 120/384 done
[sft][GPU 3] 120/381 done
[sft][GPU 0] 140/384 done
[sft][GPU 1] 120/384 done
[sft][GPU 2] 140/384 done
[sft][GPU 0] 160/384 done
[sft][GPU 3] 140/381 done
[sft][GPU 1] 140/384 done
[sft][GPU 2] 160/384 done
[sft][GPU 0] 180/384 done
[sft][GPU 1] 160/384 done
[sft][GPU 3] 160/381 done
[sft][GPU 2] 180/384 done
[sft][GPU 0] 200/384 done
[sft][GPU 3] 180/381 done
[sft][GPU 1] 180/384 done
[sft][GPU 2] 200/384 done
[sft][GPU 1] 200/384 done
[sft][GPU 3] 200/381 done
[sft][GPU 0] 220/384 done
[sft][GPU 2] 220/384 done
[sft][GPU 3] 220/381 done
[sft][GPU 1] 220/384 done
[sft][GPU 0] 240/384 done
[sft][GPU 2] 240/384 done
[sft][GPU 3] 240/381 done
[sft][GPU 1] 240/384 done
[sft][GPU 3] 260/381 done
[sft][GPU 0] 260/384 done
[sft][GPU 2] 260/384 done
[sft][GPU 1] 260/384 done
[sft][GPU 0] 280/384 done
[sft][GPU 3] 280/381 done
[sft][GPU 2] 280/384 done
[sft][GPU 0] 300/384 done
[sft][GPU 1] 280/384 done
[sft][GPU 2] 300/384 done
[sft][GPU 1] 300/384 done
[sft][GPU 3] 300/381 done
[sft][GPU 0] 320/384 done
[sft][GPU 2] 320/384 done
[sft][GPU 1] 320/384 done
[sft][GPU 0] 340/384 done
[sft][GPU 2] 340/384 done
[sft][GPU 3] 320/381 done
[sft][GPU 1] 340/384 done
[sft][GPU 0] 360/384 done
[sft][GPU 2] 360/384 done
[sft][GPU 1] 360/384 done
[sft][GPU 2] 380/384 done
[sft][GPU 3] 340/381 done
[sft][GPU 0] 380/384 done
[sft][GPU 2] 384/384 done
[sft][GPU 2] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_phyx_gpu2.jsonl
[sft][GPU 0] 384/384 done
[sft][GPU 0] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_phyx_gpu0.jsonl
[sft][GPU 3] 360/381 done
[sft][GPU 1] 380/384 done
[sft][GPU 1] 384/384 done
[sft][GPU 1] Saved 384 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_phyx_gpu1.jsonl
[sft][GPU 3] 380/381 done
[sft][GPU 3] 381/381 done
[sft][GPU 3] Saved 381 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_phyx_gpu3.jsonl

============================================================
  INFERENCE COMPLETE in 94.1 min
  Base results: 0 → /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_base.jsonl
  SFT results:  1533 → /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_phyx.jsonl
============================================================