Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- chat_template.json +3 -0
- git_hash.txt +1 -0
- merges.txt +0 -0
- preprocessor_config.json +29 -0
- results.json +588 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- training_config.yml +72 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vidore/colqwen2.5-base
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "vidore/colqwen2.5-base",
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": "gaussian",
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 32,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.1,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
26 |
+
"task_type": "FEATURE_EXTRACTION",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8a0a2aa5b97160cde30d9fc26874e11f7c9dfce607fd3e2a02c91a09b17e697
|
3 |
+
size 239815040
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
git_hash.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
67f724577dd70727a08a96a38e7ddb05e3946050
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": true,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.48145466,
|
8 |
+
0.4578275,
|
9 |
+
0.40821073
|
10 |
+
],
|
11 |
+
"image_processor_type": "Qwen2_5_VLImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.26862954,
|
14 |
+
0.26130258,
|
15 |
+
0.27577711
|
16 |
+
],
|
17 |
+
"max_pixels": 12845056,
|
18 |
+
"merge_size": 2,
|
19 |
+
"min_pixels": 3136,
|
20 |
+
"patch_size": 14,
|
21 |
+
"processor_class": "ColQwen2_5_Processor",
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"max_pixels": 12845056,
|
26 |
+
"min_pixels": 3136
|
27 |
+
},
|
28 |
+
"temporal_patch_size": 2
|
29 |
+
}
|
results.json
ADDED
@@ -0,0 +1,588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"timestamp": "2025-01-30T14:08:26.760026",
|
4 |
+
"vidore_benchmark_version": "4.0.3.dev20+g2d72668"
|
5 |
+
},
|
6 |
+
"metrics": {
|
7 |
+
"arxivqa_test_subsampled": {
|
8 |
+
"ndcg_at_1": 0.83,
|
9 |
+
"ndcg_at_3": 0.87855,
|
10 |
+
"ndcg_at_5": 0.88517,
|
11 |
+
"ndcg_at_10": 0.8947,
|
12 |
+
"ndcg_at_20": 0.89981,
|
13 |
+
"ndcg_at_50": 0.90189,
|
14 |
+
"ndcg_at_100": 0.90285,
|
15 |
+
"map_at_1": 0.83,
|
16 |
+
"map_at_3": 0.86633,
|
17 |
+
"map_at_5": 0.87003,
|
18 |
+
"map_at_10": 0.87386,
|
19 |
+
"map_at_20": 0.87529,
|
20 |
+
"map_at_50": 0.87566,
|
21 |
+
"map_at_100": 0.87574,
|
22 |
+
"recall_at_1": 0.83,
|
23 |
+
"recall_at_3": 0.914,
|
24 |
+
"recall_at_5": 0.93,
|
25 |
+
"recall_at_10": 0.96,
|
26 |
+
"recall_at_20": 0.98,
|
27 |
+
"recall_at_50": 0.99,
|
28 |
+
"recall_at_100": 0.996,
|
29 |
+
"precision_at_1": 0.83,
|
30 |
+
"precision_at_3": 0.30467,
|
31 |
+
"precision_at_5": 0.186,
|
32 |
+
"precision_at_10": 0.096,
|
33 |
+
"precision_at_20": 0.049,
|
34 |
+
"precision_at_50": 0.0198,
|
35 |
+
"precision_at_100": 0.00996,
|
36 |
+
"mrr_at_1": 0.834,
|
37 |
+
"mrr_at_3": 0.8696666666666666,
|
38 |
+
"mrr_at_5": 0.8724666666666667,
|
39 |
+
"mrr_at_10": 0.8768738095238096,
|
40 |
+
"mrr_at_20": 0.8780439976689977,
|
41 |
+
"mrr_at_50": 0.8784954053717398,
|
42 |
+
"mrr_at_100": 0.8785747821152928,
|
43 |
+
"naucs_at_1_max": 0.7814883612933191,
|
44 |
+
"naucs_at_1_std": -0.014564346665118771,
|
45 |
+
"naucs_at_1_diff1": 0.9431415800777861,
|
46 |
+
"naucs_at_3_max": 0.7651293075369701,
|
47 |
+
"naucs_at_3_std": 0.13162008989642363,
|
48 |
+
"naucs_at_3_diff1": 0.876392417432091,
|
49 |
+
"naucs_at_5_max": 0.7719887955182062,
|
50 |
+
"naucs_at_5_std": 0.12731759370415013,
|
51 |
+
"naucs_at_5_diff1": 0.8762838468720809,
|
52 |
+
"naucs_at_10_max": 0.8234126984126983,
|
53 |
+
"naucs_at_10_std": 0.03160597572361713,
|
54 |
+
"naucs_at_10_diff1": 0.8921568627450972,
|
55 |
+
"naucs_at_20_max": 0.8225957049486448,
|
56 |
+
"naucs_at_20_std": -0.02110177404295123,
|
57 |
+
"naucs_at_20_diff1": 0.9084967320261399,
|
58 |
+
"naucs_at_50_max": 0.9738562091503188,
|
59 |
+
"naucs_at_50_std": 0.3997198879551785,
|
60 |
+
"naucs_at_50_diff1": 0.947712418300658,
|
61 |
+
"naucs_at_100_max": 1.0,
|
62 |
+
"naucs_at_100_std": 1.0,
|
63 |
+
"naucs_at_100_diff1": 0.9346405228758466
|
64 |
+
},
|
65 |
+
"docvqa_test_subsampled": {
|
66 |
+
"ndcg_at_1": 0.5255,
|
67 |
+
"ndcg_at_3": 0.59582,
|
68 |
+
"ndcg_at_5": 0.61852,
|
69 |
+
"ndcg_at_10": 0.6347,
|
70 |
+
"ndcg_at_20": 0.6492,
|
71 |
+
"ndcg_at_50": 0.65706,
|
72 |
+
"ndcg_at_100": 0.66361,
|
73 |
+
"map_at_1": 0.5255,
|
74 |
+
"map_at_3": 0.57871,
|
75 |
+
"map_at_5": 0.59124,
|
76 |
+
"map_at_10": 0.59815,
|
77 |
+
"map_at_20": 0.6021,
|
78 |
+
"map_at_50": 0.60333,
|
79 |
+
"map_at_100": 0.60394,
|
80 |
+
"recall_at_1": 0.5255,
|
81 |
+
"recall_at_3": 0.64523,
|
82 |
+
"recall_at_5": 0.70067,
|
83 |
+
"recall_at_10": 0.74945,
|
84 |
+
"recall_at_20": 0.8071,
|
85 |
+
"recall_at_50": 0.84701,
|
86 |
+
"recall_at_100": 0.88692,
|
87 |
+
"precision_at_1": 0.5255,
|
88 |
+
"precision_at_3": 0.21508,
|
89 |
+
"precision_at_5": 0.14013,
|
90 |
+
"precision_at_10": 0.07494,
|
91 |
+
"precision_at_20": 0.04035,
|
92 |
+
"precision_at_50": 0.01694,
|
93 |
+
"precision_at_100": 0.00887,
|
94 |
+
"mrr_at_1": 0.5254988913525499,
|
95 |
+
"mrr_at_3": 0.5798226164079823,
|
96 |
+
"mrr_at_5": 0.5909090909090909,
|
97 |
+
"mrr_at_10": 0.5981936085594622,
|
98 |
+
"mrr_at_20": 0.6018577072277826,
|
99 |
+
"mrr_at_50": 0.603184631365057,
|
100 |
+
"mrr_at_100": 0.6036950361798563,
|
101 |
+
"naucs_at_1_max": 0.3862474572443775,
|
102 |
+
"naucs_at_1_std": 0.6866980709008784,
|
103 |
+
"naucs_at_1_diff1": 0.908866111398327,
|
104 |
+
"naucs_at_3_max": 0.3232612877463118,
|
105 |
+
"naucs_at_3_std": 0.7754733885431401,
|
106 |
+
"naucs_at_3_diff1": 0.8488934990862631,
|
107 |
+
"naucs_at_5_max": 0.26561580627789727,
|
108 |
+
"naucs_at_5_std": 0.8294969802329596,
|
109 |
+
"naucs_at_5_diff1": 0.843549438877749,
|
110 |
+
"naucs_at_10_max": 0.21226897631460165,
|
111 |
+
"naucs_at_10_std": 0.9004830786766392,
|
112 |
+
"naucs_at_10_diff1": 0.8313389289681655,
|
113 |
+
"naucs_at_20_max": 0.1442628756616487,
|
114 |
+
"naucs_at_20_std": 0.9192991363569017,
|
115 |
+
"naucs_at_20_diff1": 0.8284091873092273,
|
116 |
+
"naucs_at_50_max": 0.04661475790032267,
|
117 |
+
"naucs_at_50_std": 0.9356118889205624,
|
118 |
+
"naucs_at_50_diff1": 0.8459735188892017,
|
119 |
+
"naucs_at_100_max": -0.014764226166713695,
|
120 |
+
"naucs_at_100_std": 0.9484296739649325,
|
121 |
+
"naucs_at_100_diff1": 0.853153345512516
|
122 |
+
},
|
123 |
+
"syntheticDocQA_energy_test": {
|
124 |
+
"ndcg_at_1": 0.95,
|
125 |
+
"ndcg_at_3": 0.96131,
|
126 |
+
"ndcg_at_5": 0.96131,
|
127 |
+
"ndcg_at_10": 0.96487,
|
128 |
+
"ndcg_at_20": 0.96757,
|
129 |
+
"ndcg_at_50": 0.96952,
|
130 |
+
"ndcg_at_100": 0.96952,
|
131 |
+
"map_at_1": 0.95,
|
132 |
+
"map_at_3": 0.95833,
|
133 |
+
"map_at_5": 0.95833,
|
134 |
+
"map_at_10": 0.96,
|
135 |
+
"map_at_20": 0.96083,
|
136 |
+
"map_at_50": 0.96113,
|
137 |
+
"map_at_100": 0.96113,
|
138 |
+
"recall_at_1": 0.95,
|
139 |
+
"recall_at_3": 0.97,
|
140 |
+
"recall_at_5": 0.97,
|
141 |
+
"recall_at_10": 0.98,
|
142 |
+
"recall_at_20": 0.99,
|
143 |
+
"recall_at_50": 1.0,
|
144 |
+
"recall_at_100": 1.0,
|
145 |
+
"precision_at_1": 0.95,
|
146 |
+
"precision_at_3": 0.32333,
|
147 |
+
"precision_at_5": 0.194,
|
148 |
+
"precision_at_10": 0.098,
|
149 |
+
"precision_at_20": 0.0495,
|
150 |
+
"precision_at_50": 0.02,
|
151 |
+
"precision_at_100": 0.01,
|
152 |
+
"mrr_at_1": 0.95,
|
153 |
+
"mrr_at_3": 0.9583333333333333,
|
154 |
+
"mrr_at_5": 0.9603333333333333,
|
155 |
+
"mrr_at_10": 0.9603333333333333,
|
156 |
+
"mrr_at_20": 0.9612424242424242,
|
157 |
+
"mrr_at_50": 0.9615549242424243,
|
158 |
+
"mrr_at_100": 0.9615549242424243,
|
159 |
+
"naucs_at_1_max": 0.5612511671335213,
|
160 |
+
"naucs_at_1_std": -0.8497665732959815,
|
161 |
+
"naucs_at_1_diff1": 0.9477124183006508,
|
162 |
+
"naucs_at_3_max": 0.807812013694371,
|
163 |
+
"naucs_at_3_std": -0.6484593837535022,
|
164 |
+
"naucs_at_3_diff1": 0.9564270152505466,
|
165 |
+
"naucs_at_5_max": 0.807812013694364,
|
166 |
+
"naucs_at_5_std": -0.6484593837535011,
|
167 |
+
"naucs_at_5_diff1": 0.9564270152505424,
|
168 |
+
"naucs_at_10_max": 0.9346405228758136,
|
169 |
+
"naucs_at_10_std": -0.10270774976657283,
|
170 |
+
"naucs_at_10_diff1": 0.9346405228758136,
|
171 |
+
"naucs_at_20_max": 0.8692810457516413,
|
172 |
+
"naucs_at_20_std": -0.5634920634920767,
|
173 |
+
"naucs_at_20_diff1": 1.0,
|
174 |
+
"naucs_at_50_max": null,
|
175 |
+
"naucs_at_50_std": null,
|
176 |
+
"naucs_at_50_diff1": null,
|
177 |
+
"naucs_at_100_max": null,
|
178 |
+
"naucs_at_100_std": null,
|
179 |
+
"naucs_at_100_diff1": null
|
180 |
+
},
|
181 |
+
"tatdqa_test": {
|
182 |
+
"ndcg_at_1": 0.69502,
|
183 |
+
"ndcg_at_3": 0.78919,
|
184 |
+
"ndcg_at_5": 0.80833,
|
185 |
+
"ndcg_at_10": 0.82129,
|
186 |
+
"ndcg_at_20": 0.82519,
|
187 |
+
"ndcg_at_50": 0.82963,
|
188 |
+
"ndcg_at_100": 0.83159,
|
189 |
+
"map_at_1": 0.69502,
|
190 |
+
"map_at_3": 0.76701,
|
191 |
+
"map_at_5": 0.77755,
|
192 |
+
"map_at_10": 0.78302,
|
193 |
+
"map_at_20": 0.7842,
|
194 |
+
"map_at_50": 0.78491,
|
195 |
+
"map_at_100": 0.78508,
|
196 |
+
"recall_at_1": 0.69502,
|
197 |
+
"recall_at_3": 0.85298,
|
198 |
+
"recall_at_5": 0.89976,
|
199 |
+
"recall_at_10": 0.93925,
|
200 |
+
"recall_at_20": 0.95383,
|
201 |
+
"recall_at_50": 0.97631,
|
202 |
+
"recall_at_100": 0.98846,
|
203 |
+
"precision_at_1": 0.69502,
|
204 |
+
"precision_at_3": 0.28433,
|
205 |
+
"precision_at_5": 0.17995,
|
206 |
+
"precision_at_10": 0.09392,
|
207 |
+
"precision_at_20": 0.04769,
|
208 |
+
"precision_at_50": 0.01953,
|
209 |
+
"precision_at_100": 0.00988,
|
210 |
+
"mrr_at_1": 0.6950182260024301,
|
211 |
+
"mrr_at_3": 0.7656946132037261,
|
212 |
+
"mrr_at_5": 0.7770554880518429,
|
213 |
+
"mrr_at_10": 0.7827320681208895,
|
214 |
+
"mrr_at_20": 0.783837406855329,
|
215 |
+
"mrr_at_50": 0.784510459247072,
|
216 |
+
"mrr_at_100": 0.7846961562032659,
|
217 |
+
"naucs_at_1_max": 0.2747145592665206,
|
218 |
+
"naucs_at_1_std": -0.09557716491043182,
|
219 |
+
"naucs_at_1_diff1": 0.8084384046681937,
|
220 |
+
"naucs_at_3_max": 0.3330280541363154,
|
221 |
+
"naucs_at_3_std": -0.0389562599865292,
|
222 |
+
"naucs_at_3_diff1": 0.7240601862039753,
|
223 |
+
"naucs_at_5_max": 0.352919194006459,
|
224 |
+
"naucs_at_5_std": 0.0514244344972758,
|
225 |
+
"naucs_at_5_diff1": 0.6583624352004738,
|
226 |
+
"naucs_at_10_max": 0.43229730811413347,
|
227 |
+
"naucs_at_10_std": 0.2815741957749473,
|
228 |
+
"naucs_at_10_diff1": 0.6007108794001051,
|
229 |
+
"naucs_at_20_max": 0.4241317350379727,
|
230 |
+
"naucs_at_20_std": 0.2971486230084223,
|
231 |
+
"naucs_at_20_diff1": 0.5874614197126973,
|
232 |
+
"naucs_at_50_max": 0.5140385840003181,
|
233 |
+
"naucs_at_50_std": 0.518664544400799,
|
234 |
+
"naucs_at_50_diff1": 0.5976629425860989,
|
235 |
+
"naucs_at_100_max": 0.4955447990957944,
|
236 |
+
"naucs_at_100_std": 0.5556756488737464,
|
237 |
+
"naucs_at_100_diff1": 0.6696787538618733
|
238 |
+
},
|
239 |
+
"infovqa_test_subsampled": {
|
240 |
+
"ndcg_at_1": 0.88664,
|
241 |
+
"ndcg_at_3": 0.91826,
|
242 |
+
"ndcg_at_5": 0.92479,
|
243 |
+
"ndcg_at_10": 0.93028,
|
244 |
+
"ndcg_at_20": 0.93185,
|
245 |
+
"ndcg_at_50": 0.93365,
|
246 |
+
"ndcg_at_100": 0.93435,
|
247 |
+
"map_at_1": 0.88664,
|
248 |
+
"map_at_3": 0.91093,
|
249 |
+
"map_at_5": 0.91447,
|
250 |
+
"map_at_10": 0.91689,
|
251 |
+
"map_at_20": 0.91735,
|
252 |
+
"map_at_50": 0.91756,
|
253 |
+
"map_at_100": 0.91763,
|
254 |
+
"recall_at_1": 0.88664,
|
255 |
+
"recall_at_3": 0.93927,
|
256 |
+
"recall_at_5": 0.95547,
|
257 |
+
"recall_at_10": 0.97166,
|
258 |
+
"recall_at_20": 0.97773,
|
259 |
+
"recall_at_50": 0.98785,
|
260 |
+
"recall_at_100": 0.9919,
|
261 |
+
"precision_at_1": 0.88664,
|
262 |
+
"precision_at_3": 0.31309,
|
263 |
+
"precision_at_5": 0.19109,
|
264 |
+
"precision_at_10": 0.09717,
|
265 |
+
"precision_at_20": 0.04889,
|
266 |
+
"precision_at_50": 0.01976,
|
267 |
+
"precision_at_100": 0.00992,
|
268 |
+
"mrr_at_1": 0.8846153846153846,
|
269 |
+
"mrr_at_3": 0.9092442645074225,
|
270 |
+
"mrr_at_5": 0.9127867746288799,
|
271 |
+
"mrr_at_10": 0.9150801683696421,
|
272 |
+
"mrr_at_20": 0.9155341004025214,
|
273 |
+
"mrr_at_50": 0.9157652608527469,
|
274 |
+
"mrr_at_100": 0.9158356239262059,
|
275 |
+
"naucs_at_1_max": 0.6077965938527005,
|
276 |
+
"naucs_at_1_std": -0.034859963613718514,
|
277 |
+
"naucs_at_1_diff1": 0.9382491207886892,
|
278 |
+
"naucs_at_3_max": 0.7083430308645834,
|
279 |
+
"naucs_at_3_std": 0.09173878193665044,
|
280 |
+
"naucs_at_3_diff1": 0.941058293792039,
|
281 |
+
"naucs_at_5_max": 0.828261285914772,
|
282 |
+
"naucs_at_5_std": 0.25360809635439513,
|
283 |
+
"naucs_at_5_diff1": 0.9374342352707031,
|
284 |
+
"naucs_at_10_max": 0.8969865162710334,
|
285 |
+
"naucs_at_10_std": 0.5367916133086486,
|
286 |
+
"naucs_at_10_diff1": 0.9521757785748344,
|
287 |
+
"naucs_at_20_max": 0.927259949634811,
|
288 |
+
"naucs_at_20_std": 0.6312197158498455,
|
289 |
+
"naucs_at_20_diff1": 0.9643814216187027,
|
290 |
+
"naucs_at_50_max": 0.9129323639568211,
|
291 |
+
"naucs_at_50_std": 0.5625809313845725,
|
292 |
+
"naucs_at_50_diff1": 0.9564661819783937,
|
293 |
+
"naucs_at_100_max": 0.9346992729676393,
|
294 |
+
"naucs_at_100_std": 0.7480140525249407,
|
295 |
+
"naucs_at_100_diff1": 0.9673496364838197
|
296 |
+
},
|
297 |
+
"syntheticDocQA_healthcare_industry_test": {
|
298 |
+
"ndcg_at_1": 0.97,
|
299 |
+
"ndcg_at_3": 0.98762,
|
300 |
+
"ndcg_at_5": 0.98762,
|
301 |
+
"ndcg_at_10": 0.98762,
|
302 |
+
"ndcg_at_20": 0.98762,
|
303 |
+
"ndcg_at_50": 0.98762,
|
304 |
+
"ndcg_at_100": 0.98762,
|
305 |
+
"map_at_1": 0.97,
|
306 |
+
"map_at_3": 0.98333,
|
307 |
+
"map_at_5": 0.98333,
|
308 |
+
"map_at_10": 0.98333,
|
309 |
+
"map_at_20": 0.98333,
|
310 |
+
"map_at_50": 0.98333,
|
311 |
+
"map_at_100": 0.98333,
|
312 |
+
"recall_at_1": 0.97,
|
313 |
+
"recall_at_3": 1.0,
|
314 |
+
"recall_at_5": 1.0,
|
315 |
+
"recall_at_10": 1.0,
|
316 |
+
"recall_at_20": 1.0,
|
317 |
+
"recall_at_50": 1.0,
|
318 |
+
"recall_at_100": 1.0,
|
319 |
+
"precision_at_1": 0.97,
|
320 |
+
"precision_at_3": 0.33333,
|
321 |
+
"precision_at_5": 0.2,
|
322 |
+
"precision_at_10": 0.1,
|
323 |
+
"precision_at_20": 0.05,
|
324 |
+
"precision_at_50": 0.02,
|
325 |
+
"precision_at_100": 0.01,
|
326 |
+
"mrr_at_1": 0.97,
|
327 |
+
"mrr_at_3": 0.9833333333333333,
|
328 |
+
"mrr_at_5": 0.9833333333333333,
|
329 |
+
"mrr_at_10": 0.9833333333333333,
|
330 |
+
"mrr_at_20": 0.9833333333333333,
|
331 |
+
"mrr_at_50": 0.9833333333333333,
|
332 |
+
"mrr_at_100": 0.9833333333333333,
|
333 |
+
"naucs_at_1_max": 0.8202614379084989,
|
334 |
+
"naucs_at_1_std": -0.2198879551820713,
|
335 |
+
"naucs_at_1_diff1": 0.9564270152505465,
|
336 |
+
"naucs_at_3_max": 1.0,
|
337 |
+
"naucs_at_3_std": 1.0,
|
338 |
+
"naucs_at_3_diff1": 1.0,
|
339 |
+
"naucs_at_5_max": 1.0,
|
340 |
+
"naucs_at_5_std": 1.0,
|
341 |
+
"naucs_at_5_diff1": 1.0,
|
342 |
+
"naucs_at_10_max": 1.0,
|
343 |
+
"naucs_at_10_std": 1.0,
|
344 |
+
"naucs_at_10_diff1": 1.0,
|
345 |
+
"naucs_at_20_max": 1.0,
|
346 |
+
"naucs_at_20_std": 1.0,
|
347 |
+
"naucs_at_20_diff1": 1.0,
|
348 |
+
"naucs_at_50_max": null,
|
349 |
+
"naucs_at_50_std": null,
|
350 |
+
"naucs_at_50_diff1": null,
|
351 |
+
"naucs_at_100_max": null,
|
352 |
+
"naucs_at_100_std": null,
|
353 |
+
"naucs_at_100_diff1": null
|
354 |
+
},
|
355 |
+
"tabfquad_test_subsampled": {
|
356 |
+
"ndcg_at_1": 0.83571,
|
357 |
+
"ndcg_at_3": 0.88699,
|
358 |
+
"ndcg_at_5": 0.89851,
|
359 |
+
"ndcg_at_10": 0.90549,
|
360 |
+
"ndcg_at_20": 0.91018,
|
361 |
+
"ndcg_at_50": 0.9125,
|
362 |
+
"ndcg_at_100": 0.9125,
|
363 |
+
"map_at_1": 0.83571,
|
364 |
+
"map_at_3": 0.875,
|
365 |
+
"map_at_5": 0.88125,
|
366 |
+
"map_at_10": 0.88416,
|
367 |
+
"map_at_20": 0.88553,
|
368 |
+
"map_at_50": 0.88598,
|
369 |
+
"map_at_100": 0.88598,
|
370 |
+
"recall_at_1": 0.83571,
|
371 |
+
"recall_at_3": 0.92143,
|
372 |
+
"recall_at_5": 0.95,
|
373 |
+
"recall_at_10": 0.97143,
|
374 |
+
"recall_at_20": 0.98929,
|
375 |
+
"recall_at_50": 1.0,
|
376 |
+
"recall_at_100": 1.0,
|
377 |
+
"precision_at_1": 0.83571,
|
378 |
+
"precision_at_3": 0.30714,
|
379 |
+
"precision_at_5": 0.19,
|
380 |
+
"precision_at_10": 0.09714,
|
381 |
+
"precision_at_20": 0.04946,
|
382 |
+
"precision_at_50": 0.02,
|
383 |
+
"precision_at_100": 0.01,
|
384 |
+
"mrr_at_1": 0.8392857142857143,
|
385 |
+
"mrr_at_3": 0.8767857142857143,
|
386 |
+
"mrr_at_5": 0.8830357142857143,
|
387 |
+
"mrr_at_10": 0.8858517573696145,
|
388 |
+
"mrr_at_20": 0.8872690305726021,
|
389 |
+
"mrr_at_50": 0.8877252707609851,
|
390 |
+
"mrr_at_100": 0.8877252707609851,
|
391 |
+
"naucs_at_1_max": 0.4880524536858767,
|
392 |
+
"naucs_at_1_std": 0.1966050571171859,
|
393 |
+
"naucs_at_1_diff1": 0.9065802421597565,
|
394 |
+
"naucs_at_3_max": 0.5683515830574649,
|
395 |
+
"naucs_at_3_std": 0.33952975129445734,
|
396 |
+
"naucs_at_3_diff1": 0.8935786435786452,
|
397 |
+
"naucs_at_5_max": 0.7507669734560504,
|
398 |
+
"naucs_at_5_std": 0.5118714152327615,
|
399 |
+
"naucs_at_5_diff1": 0.9109643857543043,
|
400 |
+
"naucs_at_10_max": 0.8150093370681609,
|
401 |
+
"naucs_at_10_std": 0.5556722689075682,
|
402 |
+
"naucs_at_10_diff1": 0.934640522875815,
|
403 |
+
"naucs_at_20_max": 0.9128540305011011,
|
404 |
+
"naucs_at_20_std": 0.807812013694365,
|
405 |
+
"naucs_at_20_diff1": 0.9564270152505505,
|
406 |
+
"naucs_at_50_max": 1.0,
|
407 |
+
"naucs_at_50_std": 1.0,
|
408 |
+
"naucs_at_50_diff1": 1.0,
|
409 |
+
"naucs_at_100_max": 1.0,
|
410 |
+
"naucs_at_100_std": 1.0,
|
411 |
+
"naucs_at_100_diff1": 1.0
|
412 |
+
},
|
413 |
+
"syntheticDocQA_government_reports_test": {
|
414 |
+
"ndcg_at_1": 0.91,
|
415 |
+
"ndcg_at_3": 0.94393,
|
416 |
+
"ndcg_at_5": 0.95254,
|
417 |
+
"ndcg_at_10": 0.9561,
|
418 |
+
"ndcg_at_20": 0.9561,
|
419 |
+
"ndcg_at_50": 0.9561,
|
420 |
+
"ndcg_at_100": 0.9561,
|
421 |
+
"map_at_1": 0.91,
|
422 |
+
"map_at_3": 0.935,
|
423 |
+
"map_at_5": 0.94,
|
424 |
+
"map_at_10": 0.94167,
|
425 |
+
"map_at_20": 0.94167,
|
426 |
+
"map_at_50": 0.94167,
|
427 |
+
"map_at_100": 0.94167,
|
428 |
+
"recall_at_1": 0.91,
|
429 |
+
"recall_at_3": 0.97,
|
430 |
+
"recall_at_5": 0.99,
|
431 |
+
"recall_at_10": 1.0,
|
432 |
+
"recall_at_20": 1.0,
|
433 |
+
"recall_at_50": 1.0,
|
434 |
+
"recall_at_100": 1.0,
|
435 |
+
"precision_at_1": 0.91,
|
436 |
+
"precision_at_3": 0.32333,
|
437 |
+
"precision_at_5": 0.198,
|
438 |
+
"precision_at_10": 0.1,
|
439 |
+
"precision_at_20": 0.05,
|
440 |
+
"precision_at_50": 0.02,
|
441 |
+
"precision_at_100": 0.01,
|
442 |
+
"mrr_at_1": 0.91,
|
443 |
+
"mrr_at_3": 0.9383333333333332,
|
444 |
+
"mrr_at_5": 0.9428333333333333,
|
445 |
+
"mrr_at_10": 0.9428333333333333,
|
446 |
+
"mrr_at_20": 0.9428333333333333,
|
447 |
+
"mrr_at_50": 0.9428333333333333,
|
448 |
+
"mrr_at_100": 0.9428333333333333,
|
449 |
+
"naucs_at_1_max": 0.8246706089843343,
|
450 |
+
"naucs_at_1_std": 0.4518103537711367,
|
451 |
+
"naucs_at_1_diff1": 0.9564270152505436,
|
452 |
+
"naucs_at_3_max": 0.7027699968876487,
|
453 |
+
"naucs_at_3_std": 0.460939931528168,
|
454 |
+
"naucs_at_3_diff1": 0.9564270152505466,
|
455 |
+
"naucs_at_5_max": 0.5541549953314738,
|
456 |
+
"naucs_at_5_std": -0.1713352007469681,
|
457 |
+
"naucs_at_5_diff1": 1.0,
|
458 |
+
"naucs_at_10_max": 1.0,
|
459 |
+
"naucs_at_10_std": 1.0,
|
460 |
+
"naucs_at_10_diff1": 1.0,
|
461 |
+
"naucs_at_20_max": 1.0,
|
462 |
+
"naucs_at_20_std": 1.0,
|
463 |
+
"naucs_at_20_diff1": 1.0,
|
464 |
+
"naucs_at_50_max": null,
|
465 |
+
"naucs_at_50_std": null,
|
466 |
+
"naucs_at_50_diff1": null,
|
467 |
+
"naucs_at_100_max": null,
|
468 |
+
"naucs_at_100_std": null,
|
469 |
+
"naucs_at_100_diff1": null
|
470 |
+
},
|
471 |
+
"shiftproject_test": {
|
472 |
+
"ndcg_at_1": 0.73,
|
473 |
+
"ndcg_at_3": 0.85095,
|
474 |
+
"ndcg_at_5": 0.85526,
|
475 |
+
"ndcg_at_10": 0.86174,
|
476 |
+
"ndcg_at_20": 0.86703,
|
477 |
+
"ndcg_at_50": 0.87134,
|
478 |
+
"ndcg_at_100": 0.87134,
|
479 |
+
"map_at_1": 0.73,
|
480 |
+
"map_at_3": 0.82333,
|
481 |
+
"map_at_5": 0.82583,
|
482 |
+
"map_at_10": 0.82851,
|
483 |
+
"map_at_20": 0.83009,
|
484 |
+
"map_at_50": 0.83092,
|
485 |
+
"map_at_100": 0.83092,
|
486 |
+
"recall_at_1": 0.73,
|
487 |
+
"recall_at_3": 0.93,
|
488 |
+
"recall_at_5": 0.94,
|
489 |
+
"recall_at_10": 0.96,
|
490 |
+
"recall_at_20": 0.98,
|
491 |
+
"recall_at_50": 1.0,
|
492 |
+
"recall_at_100": 1.0,
|
493 |
+
"precision_at_1": 0.73,
|
494 |
+
"precision_at_3": 0.31,
|
495 |
+
"precision_at_5": 0.188,
|
496 |
+
"precision_at_10": 0.096,
|
497 |
+
"precision_at_20": 0.049,
|
498 |
+
"precision_at_50": 0.02,
|
499 |
+
"precision_at_100": 0.01,
|
500 |
+
"mrr_at_1": 0.75,
|
501 |
+
"mrr_at_3": 0.8316666666666667,
|
502 |
+
"mrr_at_5": 0.8341666666666667,
|
503 |
+
"mrr_at_10": 0.8380238095238096,
|
504 |
+
"mrr_at_20": 0.8386904761904762,
|
505 |
+
"mrr_at_50": 0.8395600414078674,
|
506 |
+
"mrr_at_100": 0.8395600414078674,
|
507 |
+
"naucs_at_1_max": -0.0662092826672433,
|
508 |
+
"naucs_at_1_std": -0.3356071477717276,
|
509 |
+
"naucs_at_1_diff1": 0.7686999941024986,
|
510 |
+
"naucs_at_3_max": -0.05822328931572497,
|
511 |
+
"naucs_at_3_std": -0.2665732959850601,
|
512 |
+
"naucs_at_3_diff1": 0.7789782579698524,
|
513 |
+
"naucs_at_5_max": 0.22206660441954526,
|
514 |
+
"naucs_at_5_std": -0.33146591970121353,
|
515 |
+
"naucs_at_5_diff1": 0.8883442265795238,
|
516 |
+
"naucs_at_10_max": 0.05240429505135564,
|
517 |
+
"naucs_at_10_std": -0.4458450046685252,
|
518 |
+
"naucs_at_10_diff1": 0.8651960784313721,
|
519 |
+
"naucs_at_20_max": -0.5088702147525547,
|
520 |
+
"naucs_at_20_std": -0.5929038281979383,
|
521 |
+
"naucs_at_20_diff1": 0.9346405228758136,
|
522 |
+
"naucs_at_50_max": null,
|
523 |
+
"naucs_at_50_std": null,
|
524 |
+
"naucs_at_50_diff1": null,
|
525 |
+
"naucs_at_100_max": null,
|
526 |
+
"naucs_at_100_std": null,
|
527 |
+
"naucs_at_100_diff1": null
|
528 |
+
},
|
529 |
+
"syntheticDocQA_artificial_intelligence_test": {
|
530 |
+
"ndcg_at_1": 0.98,
|
531 |
+
"ndcg_at_3": 0.99262,
|
532 |
+
"ndcg_at_5": 0.99262,
|
533 |
+
"ndcg_at_10": 0.99262,
|
534 |
+
"ndcg_at_20": 0.99262,
|
535 |
+
"ndcg_at_50": 0.99262,
|
536 |
+
"ndcg_at_100": 0.99262,
|
537 |
+
"map_at_1": 0.98,
|
538 |
+
"map_at_3": 0.99,
|
539 |
+
"map_at_5": 0.99,
|
540 |
+
"map_at_10": 0.99,
|
541 |
+
"map_at_20": 0.99,
|
542 |
+
"map_at_50": 0.99,
|
543 |
+
"map_at_100": 0.99,
|
544 |
+
"recall_at_1": 0.98,
|
545 |
+
"recall_at_3": 1.0,
|
546 |
+
"recall_at_5": 1.0,
|
547 |
+
"recall_at_10": 1.0,
|
548 |
+
"recall_at_20": 1.0,
|
549 |
+
"recall_at_50": 1.0,
|
550 |
+
"recall_at_100": 1.0,
|
551 |
+
"precision_at_1": 0.98,
|
552 |
+
"precision_at_3": 0.33333,
|
553 |
+
"precision_at_5": 0.2,
|
554 |
+
"precision_at_10": 0.1,
|
555 |
+
"precision_at_20": 0.05,
|
556 |
+
"precision_at_50": 0.02,
|
557 |
+
"precision_at_100": 0.01,
|
558 |
+
"mrr_at_1": 0.98,
|
559 |
+
"mrr_at_3": 0.99,
|
560 |
+
"mrr_at_5": 0.99,
|
561 |
+
"mrr_at_10": 0.99,
|
562 |
+
"mrr_at_20": 0.99,
|
563 |
+
"mrr_at_50": 0.99,
|
564 |
+
"mrr_at_100": 0.99,
|
565 |
+
"naucs_at_1_max": 0.3489729225023353,
|
566 |
+
"naucs_at_1_std": -0.2987861811391249,
|
567 |
+
"naucs_at_1_diff1": 1.0,
|
568 |
+
"naucs_at_3_max": 1.0,
|
569 |
+
"naucs_at_3_std": 1.0,
|
570 |
+
"naucs_at_3_diff1": 1.0,
|
571 |
+
"naucs_at_5_max": 1.0,
|
572 |
+
"naucs_at_5_std": 1.0,
|
573 |
+
"naucs_at_5_diff1": 1.0,
|
574 |
+
"naucs_at_10_max": 1.0,
|
575 |
+
"naucs_at_10_std": 1.0,
|
576 |
+
"naucs_at_10_diff1": 1.0,
|
577 |
+
"naucs_at_20_max": 1.0,
|
578 |
+
"naucs_at_20_std": 1.0,
|
579 |
+
"naucs_at_20_diff1": 1.0,
|
580 |
+
"naucs_at_50_max": null,
|
581 |
+
"naucs_at_50_std": null,
|
582 |
+
"naucs_at_50_diff1": null,
|
583 |
+
"naucs_at_100_max": null,
|
584 |
+
"naucs_at_100_std": null,
|
585 |
+
"naucs_at_100_diff1": null
|
586 |
+
}
|
587 |
+
}
|
588 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 {{- 'You are a helpful assistant.' }}\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\\nYou are a helpful assistant.<|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": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 131072,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"processor_class": "ColQwen2_5_Processor",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
training_config.yml
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
config:
|
2 |
+
(): colpali_engine.trainer.colmodel_training.ColModelTrainingConfig
|
3 |
+
output_dir: !path ../../../models/colqwen2_5_train
|
4 |
+
processor:
|
5 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
6 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2_5_Processor
|
7 |
+
pretrained_model_name_or_path: "./models/ColQwen2.5-VL-3B-Instruct" # "./models/paligemma-3b-mix-448"
|
8 |
+
# num_image_tokens: 2048
|
9 |
+
# max_length: 50
|
10 |
+
|
11 |
+
model:
|
12 |
+
(): colpali_engine.utils.transformers_wrappers.AllPurposeWrapper
|
13 |
+
class_to_instanciate: !ext colpali_engine.models.ColQwen2_5
|
14 |
+
pretrained_model_name_or_path: "./models/ColQwen2.5-VL-3B-Instruct"
|
15 |
+
torch_dtype: !ext torch.bfloat16
|
16 |
+
use_cache: false
|
17 |
+
attn_implementation: "flash_attention_2"
|
18 |
+
# device_map: "auto"
|
19 |
+
# quantization_config:
|
20 |
+
# (): transformers.BitsAndBytesConfig
|
21 |
+
# load_in_4bit: true
|
22 |
+
# bnb_4bit_quant_type: "nf4"
|
23 |
+
# bnb_4bit_compute_dtype: "bfloat16"
|
24 |
+
# bnb_4bit_use_double_quant: true
|
25 |
+
|
26 |
+
dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set
|
27 |
+
eval_dataset_loader: !import ../data/test_data.yaml
|
28 |
+
|
29 |
+
# max_length: 50
|
30 |
+
run_eval: true
|
31 |
+
loss_func:
|
32 |
+
(): colpali_engine.loss.late_interaction_losses.ColbertPairwiseCELoss
|
33 |
+
tr_args:
|
34 |
+
(): transformers.training_args.TrainingArguments
|
35 |
+
output_dir: null
|
36 |
+
overwrite_output_dir: true
|
37 |
+
num_train_epochs: 3
|
38 |
+
per_device_train_batch_size: 32
|
39 |
+
gradient_checkpointing: true
|
40 |
+
gradient_checkpointing_kwargs: { "use_reentrant": false }
|
41 |
+
# gradient_checkpointing: true
|
42 |
+
# 6 x 8 gpus = 48 batch size
|
43 |
+
# gradient_accumulation_steps: 4
|
44 |
+
per_device_eval_batch_size: 16
|
45 |
+
eval_strategy: "steps"
|
46 |
+
dataloader_num_workers: 8
|
47 |
+
# bf16: true
|
48 |
+
save_steps: 500
|
49 |
+
logging_steps: 10
|
50 |
+
eval_steps: 100
|
51 |
+
warmup_steps: 500
|
52 |
+
learning_rate: 1e-4
|
53 |
+
save_total_limit: 1
|
54 |
+
# resume_from_checkpoint: true
|
55 |
+
# optim: "paged_adamw_8bit"
|
56 |
+
# wandb logging
|
57 |
+
# wandb_project: "colqwen2"
|
58 |
+
# run_name: "colqwen2-ba32-nolora"
|
59 |
+
report_to: "wandb"
|
60 |
+
|
61 |
+
|
62 |
+
peft_config:
|
63 |
+
(): peft.LoraConfig
|
64 |
+
r: 32
|
65 |
+
lora_alpha: 32
|
66 |
+
lora_dropout: 0.1
|
67 |
+
init_lora_weights: "gaussian"
|
68 |
+
bias: "none"
|
69 |
+
task_type: "FEATURE_EXTRACTION"
|
70 |
+
target_modules: '(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
71 |
+
# target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
72 |
+
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|