Hugging Face's logo

YUNTA88
/
rl4phyx-backup

Safetensors
Model card Files
xet
 Community
rl4phyx-backup
File size: 13,567 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
/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/lora_math_f/merged
  Base GPUs:  []
  SFT GPUs:   [0, 1, 2, 3, 4, 5, 6, 7]
============================================================

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

>>> SKIPPING BASE model (BASE_GPUS is empty)

>>> 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(
/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(
/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(
/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 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`.
[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 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`.
[sft][GPU 5] Loading model...
[sft][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`.
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 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`.
[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 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`.
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.
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.
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.
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:   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:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:02<00:02,  2.98s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:02<00:02,  3.00s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.12s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.18s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.12s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.18s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.18s/it]
Loading checkpoint shards:  50%|█████     | 1/2 [00:03<00:03,  3.42s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.70s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.89s/it]
[sft][GPU 2] Model loaded. Processing 192 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.65s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.86s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.71s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.92s/it]
[sft][GPU 5] Model loaded. Processing 192 samples.
[sft][GPU 4] Model loaded. Processing 192 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.72s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.93s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.76s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00,  1.97s/it]
[sft][GPU 1] Model loaded. Processing 192 samples.
[sft][GPU 6] Model loaded. Processing 192 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  1.80s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  2.01s/it]

Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  1.80s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  2.01s/it]
[sft][GPU 3] Model loaded. Processing 192 samples.
[sft][GPU 7] Model loaded. Processing 189 samples.

Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  1.95s/it]
Loading checkpoint shards: 100%|██████████| 2/2 [00:04<00:00,  2.18s/it]
[sft][GPU 0] Model loaded. Processing 192 samples.
[sft][GPU 6] 20/192 done
[sft][GPU 5] 20/192 done
[sft][GPU 7] 20/189 done
[sft][GPU 0] 20/192 done
[sft][GPU 4] 20/192 done
[sft][GPU 3] 20/192 done
[sft][GPU 2] 20/192 done
[sft][GPU 1] 20/192 done
[sft][GPU 6] 40/192 done
[sft][GPU 0] 40/192 done
[sft][GPU 5] 40/192 done
[sft][GPU 4] 40/192 done
[sft][GPU 7] 40/189 done
[sft][GPU 2] 40/192 done
[sft][GPU 3] 40/192 done
[sft][GPU 1] 40/192 done
[sft][GPU 0] 60/192 done
[sft][GPU 6] 60/192 done
[sft][GPU 4] 60/192 done
[sft][GPU 7] 60/189 done
[sft][GPU 5] 60/192 done
[sft][GPU 2] 60/192 done
[sft][GPU 3] 60/192 done
[sft][GPU 0] 80/192 done
[sft][GPU 1] 60/192 done
[sft][GPU 4] 80/192 done
[sft][GPU 5] 80/192 done
[sft][GPU 6] 80/192 done
[sft][GPU 7] 80/189 done
[sft][GPU 2] 80/192 done
[sft][GPU 3] 80/192 done
[sft][GPU 0] 100/192 done
[sft][GPU 1] 80/192 done
[sft][GPU 5] 100/192 done
[sft][GPU 4] 100/192 done
[sft][GPU 6] 100/192 done
[sft][GPU 2] 100/192 done
[sft][GPU 3] 100/192 done
[sft][GPU 7] 100/189 done
[sft][GPU 0] 120/192 done
[sft][GPU 1] 100/192 done
[sft][GPU 5] 120/192 done
[sft][GPU 6] 120/192 done
[sft][GPU 4] 120/192 done
[sft][GPU 3] 120/192 done
[sft][GPU 2] 120/192 done
[sft][GPU 5] 140/192 done
[sft][GPU 1] 120/192 done
[sft][GPU 7] 120/189 done
[sft][GPU 0] 140/192 done
[sft][GPU 6] 140/192 done
[sft][GPU 3] 140/192 done
[sft][GPU 4] 140/192 done
[sft][GPU 2] 140/192 done
[sft][GPU 5] 160/192 done
[sft][GPU 1] 140/192 done
[sft][GPU 0] 160/192 done
[sft][GPU 7] 140/189 done
[sft][GPU 6] 160/192 done
[sft][GPU 4] 160/192 done
[sft][GPU 2] 160/192 done
[sft][GPU 3] 160/192 done
[sft][GPU 5] 180/192 done
[sft][GPU 1] 160/192 done
[sft][GPU 5] 192/192 done
[sft][GPU 5] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu5.jsonl
[sft][GPU 0] 180/192 done
[sft][GPU 4] 180/192 done
[sft][GPU 7] 160/189 done
[sft][GPU 6] 180/192 done
[sft][GPU 2] 180/192 done
[sft][GPU 3] 180/192 done
[sft][GPU 1] 180/192 done
[sft][GPU 0] 192/192 done
[sft][GPU 0] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu0.jsonl
[sft][GPU 4] 192/192 done
[sft][GPU 4] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu4.jsonl
[sft][GPU 2] 192/192 done
[sft][GPU 2] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu2.jsonl
[sft][GPU 3] 192/192 done
[sft][GPU 3] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu3.jsonl
[sft][GPU 6] 192/192 done
[sft][GPU 6] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu6.jsonl
[sft][GPU 1] 192/192 done
[sft][GPU 1] Saved 192 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu1.jsonl
[sft][GPU 7] 180/189 done
[sft][GPU 7] 189/189 done
[sft][GPU 7] Saved 189 results to /workspace/rl4phyx/RL4Phyx/SFT/sft_eval_footprint/inference_results_lora_math_f_gpu7.jsonl

============================================================
  INFERENCE COMPLETE in 84.9 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_lora_math_f.jsonl
============================================================