Upload 11 files
Browse files- 1_Pooling/config.json +10 -0
- README.md +762 -0
- config.json +32 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:784827
|
8 |
+
- loss:ContrastiveLoss
|
9 |
+
base_model: BAAI/bge-large-en-v1.5
|
10 |
+
widget:
|
11 |
+
- source_sentence: 'Represent this sentence for searching relevant passages: Existing
|
12 |
+
methods for anomaly detection on dynamic graphs struggle with capturing complex
|
13 |
+
time information in graph structures and generating effective negative samples
|
14 |
+
for unsupervised learning. These challenges highlight the need for improved methodologies
|
15 |
+
that can address the limitations of current approaches in this field.We suggest
|
16 |
+
combining ''a message-passing framework'' and '
|
17 |
+
sentences:
|
18 |
+
- a single global model
|
19 |
+
- videos
|
20 |
+
- sequential polygon generation
|
21 |
+
- source_sentence: 'Represent this sentence for searching relevant passages: The study
|
22 |
+
addresses the need for effective tools that allow both novice and expert users
|
23 |
+
to analyze the diversity of news coverage about events. It highlights the importance
|
24 |
+
of tailoring the interface to accommodate non-expert users while also considering
|
25 |
+
the insights of journalism-savvy users, indicating a gap in existing systems that
|
26 |
+
cater to varying levels of expertise in news analysis.We suggest combining ''a
|
27 |
+
coordinated visualization interface tailored for visualization non-expert users''
|
28 |
+
and '
|
29 |
+
sentences:
|
30 |
+
- worst-case resource analysis
|
31 |
+
- Graph Convolution Networks
|
32 |
+
- a text encoder
|
33 |
+
- source_sentence: 'Represent this sentence for searching relevant passages: The accuracy
|
34 |
+
of pixel flows is crucial for achieving high-quality video enhancement, yet most
|
35 |
+
prior works focus on estimating dense flows that are generally less robust and
|
36 |
+
computationally expensive. This highlights a gap in existing methodologies that
|
37 |
+
fail to prioritize accuracy over density, necessitating a more efficient approach
|
38 |
+
to flow estimation for video enhancement tasks.We suggest combining ''sparse point
|
39 |
+
cloud data'' and '
|
40 |
+
sentences:
|
41 |
+
- a Temporal Eigenvalue Loss
|
42 |
+
- diffusion models
|
43 |
+
- explicit 3D representations, such as polygonal meshes
|
44 |
+
- source_sentence: 'Represent this sentence for searching relevant passages: The traditional
|
45 |
+
frame of discernment lacks a crucial factor, the sequence of propositions, which
|
46 |
+
limits the effectiveness of existing methods to measure uncertainty. This gap
|
47 |
+
highlights the need for a more comprehensive approach that can better represent
|
48 |
+
the relationships between the elements of the frame of discernment.We suggest
|
49 |
+
''combine the order of propositions and the mass of them'' inspired by '
|
50 |
+
sentences:
|
51 |
+
- the traditional matching-optimization methods where matching is introduced to
|
52 |
+
handle large displacements before energy-based optimizations
|
53 |
+
- encoder-decoder models
|
54 |
+
- In another vein, researchers propose new attention augmentation methods to make
|
55 |
+
transformers more accurate, efficient and interpretable
|
56 |
+
- source_sentence: 'Represent this sentence for searching relevant passages: The study
|
57 |
+
addresses the need for effective time series forecasting methods to estimate the
|
58 |
+
spread of epidemics, particularly in light of the resurgence of COVID-19 cases.
|
59 |
+
It highlights the importance of accurately modeling both linear and non-linear
|
60 |
+
features of epidemic data to provide state authorities and health officials with
|
61 |
+
reliable short-term forecasts and strategies.We suggest combining ''ARIMA'' and '
|
62 |
+
sentences:
|
63 |
+
- Transformers
|
64 |
+
- a traditional feature-mixed branch
|
65 |
+
- the human brain is able to efficiently learn effective control strategies using
|
66 |
+
limited resources
|
67 |
+
pipeline_tag: sentence-similarity
|
68 |
+
library_name: sentence-transformers
|
69 |
+
---
|
70 |
+
|
71 |
+
# SentenceTransformer based on BAAI/bge-large-en-v1.5
|
72 |
+
|
73 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
74 |
+
|
75 |
+
## Model Details
|
76 |
+
|
77 |
+
### Model Description
|
78 |
+
- **Model Type:** Sentence Transformer
|
79 |
+
- **Base model:** [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) <!-- at revision d4aa6901d3a41ba39fb536a557fa166f842b0e09 -->
|
80 |
+
- **Maximum Sequence Length:** 512 tokens
|
81 |
+
- **Output Dimensionality:** 1024 dimensions
|
82 |
+
- **Similarity Function:** Cosine Similarity
|
83 |
+
<!-- - **Training Dataset:** Unknown -->
|
84 |
+
<!-- - **Language:** Unknown -->
|
85 |
+
<!-- - **License:** Unknown -->
|
86 |
+
|
87 |
+
### Model Sources
|
88 |
+
|
89 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
90 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
91 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
92 |
+
|
93 |
+
### Full Model Architecture
|
94 |
+
|
95 |
+
```
|
96 |
+
SentenceTransformer(
|
97 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
98 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
99 |
+
(2): Normalize()
|
100 |
+
)
|
101 |
+
```
|
102 |
+
|
103 |
+
## Usage
|
104 |
+
|
105 |
+
### Direct Usage (Sentence Transformers)
|
106 |
+
|
107 |
+
First install the Sentence Transformers library:
|
108 |
+
|
109 |
+
```bash
|
110 |
+
pip install -U sentence-transformers
|
111 |
+
```
|
112 |
+
|
113 |
+
Then you can load this model and run inference.
|
114 |
+
```python
|
115 |
+
from sentence_transformers import SentenceTransformer
|
116 |
+
|
117 |
+
# Download from the 🤗 Hub
|
118 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
119 |
+
# Run inference
|
120 |
+
sentences = [
|
121 |
+
"Represent this sentence for searching relevant passages: The study addresses the need for effective time series forecasting methods to estimate the spread of epidemics, particularly in light of the resurgence of COVID-19 cases. It highlights the importance of accurately modeling both linear and non-linear features of epidemic data to provide state authorities and health officials with reliable short-term forecasts and strategies.We suggest combining 'ARIMA' and ",
|
122 |
+
'Transformers',
|
123 |
+
'the human brain is able to efficiently learn effective control strategies using limited resources',
|
124 |
+
]
|
125 |
+
embeddings = model.encode(sentences)
|
126 |
+
print(embeddings.shape)
|
127 |
+
# [3, 1024]
|
128 |
+
|
129 |
+
# Get the similarity scores for the embeddings
|
130 |
+
similarities = model.similarity(embeddings, embeddings)
|
131 |
+
print(similarities.shape)
|
132 |
+
# [3, 3]
|
133 |
+
```
|
134 |
+
|
135 |
+
<!--
|
136 |
+
### Direct Usage (Transformers)
|
137 |
+
|
138 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
139 |
+
|
140 |
+
</details>
|
141 |
+
-->
|
142 |
+
|
143 |
+
<!--
|
144 |
+
### Downstream Usage (Sentence Transformers)
|
145 |
+
|
146 |
+
You can finetune this model on your own dataset.
|
147 |
+
|
148 |
+
<details><summary>Click to expand</summary>
|
149 |
+
|
150 |
+
</details>
|
151 |
+
-->
|
152 |
+
|
153 |
+
<!--
|
154 |
+
### Out-of-Scope Use
|
155 |
+
|
156 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
157 |
+
-->
|
158 |
+
|
159 |
+
<!--
|
160 |
+
## Bias, Risks and Limitations
|
161 |
+
|
162 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
163 |
+
-->
|
164 |
+
|
165 |
+
<!--
|
166 |
+
### Recommendations
|
167 |
+
|
168 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
169 |
+
-->
|
170 |
+
|
171 |
+
## Training Details
|
172 |
+
|
173 |
+
### Training Dataset
|
174 |
+
|
175 |
+
#### Unnamed Dataset
|
176 |
+
|
177 |
+
|
178 |
+
* Size: 784,827 training samples
|
179 |
+
* Columns: <code>query</code>, <code>answer</code>, and <code>label</code>
|
180 |
+
* Approximate statistics based on the first 1000 samples:
|
181 |
+
| | query | answer | label |
|
182 |
+
|:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------|
|
183 |
+
| type | string | string | int |
|
184 |
+
| details | <ul><li>min: 66 tokens</li><li>mean: 83.86 tokens</li><li>max: 99 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.63 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>0: ~96.70%</li><li>1: ~3.30%</li></ul> |
|
185 |
+
* Samples:
|
186 |
+
| query | answer | label |
|
187 |
+
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------|:---------------|
|
188 |
+
| <code>Represent this sentence for searching relevant passages: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>a multilayer perceptron</code> | <code>1</code> |
|
189 |
+
| <code>Represent this sentence for searching relevant passages: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>global expression information</code> | <code>0</code> |
|
190 |
+
| <code>Represent this sentence for searching relevant passages: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>some relevant physical parameters</code> | <code>0</code> |
|
191 |
+
* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
|
192 |
+
```json
|
193 |
+
{
|
194 |
+
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
|
195 |
+
"margin": 0.5,
|
196 |
+
"size_average": true
|
197 |
+
}
|
198 |
+
```
|
199 |
+
|
200 |
+
### Training Hyperparameters
|
201 |
+
#### Non-Default Hyperparameters
|
202 |
+
|
203 |
+
- `per_device_train_batch_size`: 64
|
204 |
+
- `learning_rate`: 2.3351317368662443e-06
|
205 |
+
- `warmup_ratio`: 0.11883406097525227
|
206 |
+
- `bf16`: True
|
207 |
+
- `prompts`: {'query': 'Represent this sentence for searching relevant passages: '}
|
208 |
+
- `batch_sampler`: no_duplicates
|
209 |
+
|
210 |
+
#### All Hyperparameters
|
211 |
+
<details><summary>Click to expand</summary>
|
212 |
+
|
213 |
+
- `overwrite_output_dir`: False
|
214 |
+
- `do_predict`: False
|
215 |
+
- `eval_strategy`: no
|
216 |
+
- `prediction_loss_only`: True
|
217 |
+
- `per_device_train_batch_size`: 64
|
218 |
+
- `per_device_eval_batch_size`: 8
|
219 |
+
- `per_gpu_train_batch_size`: None
|
220 |
+
- `per_gpu_eval_batch_size`: None
|
221 |
+
- `gradient_accumulation_steps`: 1
|
222 |
+
- `eval_accumulation_steps`: None
|
223 |
+
- `torch_empty_cache_steps`: None
|
224 |
+
- `learning_rate`: 2.3351317368662443e-06
|
225 |
+
- `weight_decay`: 0.0
|
226 |
+
- `adam_beta1`: 0.9
|
227 |
+
- `adam_beta2`: 0.999
|
228 |
+
- `adam_epsilon`: 1e-08
|
229 |
+
- `max_grad_norm`: 1.0
|
230 |
+
- `num_train_epochs`: 3
|
231 |
+
- `max_steps`: -1
|
232 |
+
- `lr_scheduler_type`: linear
|
233 |
+
- `lr_scheduler_kwargs`: {}
|
234 |
+
- `warmup_ratio`: 0.11883406097525227
|
235 |
+
- `warmup_steps`: 0
|
236 |
+
- `log_level`: passive
|
237 |
+
- `log_level_replica`: warning
|
238 |
+
- `log_on_each_node`: True
|
239 |
+
- `logging_nan_inf_filter`: True
|
240 |
+
- `save_safetensors`: True
|
241 |
+
- `save_on_each_node`: False
|
242 |
+
- `save_only_model`: False
|
243 |
+
- `restore_callback_states_from_checkpoint`: False
|
244 |
+
- `no_cuda`: False
|
245 |
+
- `use_cpu`: False
|
246 |
+
- `use_mps_device`: False
|
247 |
+
- `seed`: 42
|
248 |
+
- `data_seed`: None
|
249 |
+
- `jit_mode_eval`: False
|
250 |
+
- `use_ipex`: False
|
251 |
+
- `bf16`: True
|
252 |
+
- `fp16`: False
|
253 |
+
- `fp16_opt_level`: O1
|
254 |
+
- `half_precision_backend`: auto
|
255 |
+
- `bf16_full_eval`: False
|
256 |
+
- `fp16_full_eval`: False
|
257 |
+
- `tf32`: None
|
258 |
+
- `local_rank`: 0
|
259 |
+
- `ddp_backend`: None
|
260 |
+
- `tpu_num_cores`: None
|
261 |
+
- `tpu_metrics_debug`: False
|
262 |
+
- `debug`: []
|
263 |
+
- `dataloader_drop_last`: False
|
264 |
+
- `dataloader_num_workers`: 0
|
265 |
+
- `dataloader_prefetch_factor`: None
|
266 |
+
- `past_index`: -1
|
267 |
+
- `disable_tqdm`: False
|
268 |
+
- `remove_unused_columns`: True
|
269 |
+
- `label_names`: None
|
270 |
+
- `load_best_model_at_end`: False
|
271 |
+
- `ignore_data_skip`: False
|
272 |
+
- `fsdp`: []
|
273 |
+
- `fsdp_min_num_params`: 0
|
274 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
275 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
276 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
277 |
+
- `deepspeed`: None
|
278 |
+
- `label_smoothing_factor`: 0.0
|
279 |
+
- `optim`: adamw_torch
|
280 |
+
- `optim_args`: None
|
281 |
+
- `adafactor`: False
|
282 |
+
- `group_by_length`: False
|
283 |
+
- `length_column_name`: length
|
284 |
+
- `ddp_find_unused_parameters`: None
|
285 |
+
- `ddp_bucket_cap_mb`: None
|
286 |
+
- `ddp_broadcast_buffers`: False
|
287 |
+
- `dataloader_pin_memory`: True
|
288 |
+
- `dataloader_persistent_workers`: False
|
289 |
+
- `skip_memory_metrics`: True
|
290 |
+
- `use_legacy_prediction_loop`: False
|
291 |
+
- `push_to_hub`: False
|
292 |
+
- `resume_from_checkpoint`: None
|
293 |
+
- `hub_model_id`: None
|
294 |
+
- `hub_strategy`: every_save
|
295 |
+
- `hub_private_repo`: None
|
296 |
+
- `hub_always_push`: False
|
297 |
+
- `gradient_checkpointing`: False
|
298 |
+
- `gradient_checkpointing_kwargs`: None
|
299 |
+
- `include_inputs_for_metrics`: False
|
300 |
+
- `include_for_metrics`: []
|
301 |
+
- `eval_do_concat_batches`: True
|
302 |
+
- `fp16_backend`: auto
|
303 |
+
- `push_to_hub_model_id`: None
|
304 |
+
- `push_to_hub_organization`: None
|
305 |
+
- `mp_parameters`:
|
306 |
+
- `auto_find_batch_size`: False
|
307 |
+
- `full_determinism`: False
|
308 |
+
- `torchdynamo`: None
|
309 |
+
- `ray_scope`: last
|
310 |
+
- `ddp_timeout`: 1800
|
311 |
+
- `torch_compile`: False
|
312 |
+
- `torch_compile_backend`: None
|
313 |
+
- `torch_compile_mode`: None
|
314 |
+
- `dispatch_batches`: None
|
315 |
+
- `split_batches`: None
|
316 |
+
- `include_tokens_per_second`: False
|
317 |
+
- `include_num_input_tokens_seen`: False
|
318 |
+
- `neftune_noise_alpha`: None
|
319 |
+
- `optim_target_modules`: None
|
320 |
+
- `batch_eval_metrics`: False
|
321 |
+
- `eval_on_start`: False
|
322 |
+
- `use_liger_kernel`: False
|
323 |
+
- `eval_use_gather_object`: False
|
324 |
+
- `average_tokens_across_devices`: False
|
325 |
+
- `prompts`: {'query': 'Represent this sentence for searching relevant passages: '}
|
326 |
+
- `batch_sampler`: no_duplicates
|
327 |
+
- `multi_dataset_batch_sampler`: proportional
|
328 |
+
|
329 |
+
</details>
|
330 |
+
|
331 |
+
### Training Logs
|
332 |
+
<details><summary>Click to expand</summary>
|
333 |
+
|
334 |
+
| Epoch | Step | Training Loss |
|
335 |
+
|:------:|:-----:|:-------------:|
|
336 |
+
| 0.0082 | 100 | 0.0051 |
|
337 |
+
| 0.0163 | 200 | 0.0038 |
|
338 |
+
| 0.0245 | 300 | 0.0037 |
|
339 |
+
| 0.0326 | 400 | 0.0036 |
|
340 |
+
| 0.0408 | 500 | 0.0046 |
|
341 |
+
| 0.0489 | 600 | 0.0035 |
|
342 |
+
| 0.0571 | 700 | 0.0035 |
|
343 |
+
| 0.0652 | 800 | 0.0034 |
|
344 |
+
| 0.0734 | 900 | 0.0044 |
|
345 |
+
| 0.0815 | 1000 | 0.0034 |
|
346 |
+
| 0.0897 | 1100 | 0.0035 |
|
347 |
+
| 0.0979 | 1200 | 0.0034 |
|
348 |
+
| 0.1060 | 1300 | 0.0034 |
|
349 |
+
| 0.1142 | 1400 | 0.0045 |
|
350 |
+
| 0.1223 | 1500 | 0.0034 |
|
351 |
+
| 0.1305 | 1600 | 0.0034 |
|
352 |
+
| 0.1386 | 1700 | 0.0033 |
|
353 |
+
| 0.1468 | 1800 | 0.0043 |
|
354 |
+
| 0.1549 | 1900 | 0.0034 |
|
355 |
+
| 0.1631 | 2000 | 0.0033 |
|
356 |
+
| 0.1712 | 2100 | 0.0032 |
|
357 |
+
| 0.1794 | 2200 | 0.0033 |
|
358 |
+
| 0.1876 | 2300 | 0.0044 |
|
359 |
+
| 0.1957 | 2400 | 0.0033 |
|
360 |
+
| 0.2039 | 2500 | 0.0034 |
|
361 |
+
| 0.2120 | 2600 | 0.0033 |
|
362 |
+
| 0.2202 | 2700 | 0.0042 |
|
363 |
+
| 0.2283 | 2800 | 0.0034 |
|
364 |
+
| 0.2365 | 2900 | 0.0033 |
|
365 |
+
| 0.2446 | 3000 | 0.0033 |
|
366 |
+
| 0.2528 | 3100 | 0.0036 |
|
367 |
+
| 0.2609 | 3200 | 0.0039 |
|
368 |
+
| 0.2691 | 3300 | 0.0033 |
|
369 |
+
| 0.2773 | 3400 | 0.0032 |
|
370 |
+
| 0.2854 | 3500 | 0.0034 |
|
371 |
+
| 0.2936 | 3600 | 0.0041 |
|
372 |
+
| 0.3017 | 3700 | 0.0031 |
|
373 |
+
| 0.3099 | 3800 | 0.0032 |
|
374 |
+
| 0.3180 | 3900 | 0.0031 |
|
375 |
+
| 0.3262 | 4000 | 0.004 |
|
376 |
+
| 0.3343 | 4100 | 0.0034 |
|
377 |
+
| 0.3425 | 4200 | 0.003 |
|
378 |
+
| 0.3506 | 4300 | 0.0032 |
|
379 |
+
| 0.3588 | 4400 | 0.0032 |
|
380 |
+
| 0.3670 | 4500 | 0.004 |
|
381 |
+
| 0.3751 | 4600 | 0.0031 |
|
382 |
+
| 0.3833 | 4700 | 0.0033 |
|
383 |
+
| 0.3914 | 4800 | 0.0031 |
|
384 |
+
| 0.3996 | 4900 | 0.004 |
|
385 |
+
| 0.4077 | 5000 | 0.0032 |
|
386 |
+
| 0.4159 | 5100 | 0.0031 |
|
387 |
+
| 0.4240 | 5200 | 0.0031 |
|
388 |
+
| 0.4322 | 5300 | 0.0031 |
|
389 |
+
| 0.4403 | 5400 | 0.0039 |
|
390 |
+
| 0.4485 | 5500 | 0.003 |
|
391 |
+
| 0.4567 | 5600 | 0.003 |
|
392 |
+
| 0.4648 | 5700 | 0.0031 |
|
393 |
+
| 0.4730 | 5800 | 0.0038 |
|
394 |
+
| 0.4811 | 5900 | 0.0031 |
|
395 |
+
| 0.4893 | 6000 | 0.0032 |
|
396 |
+
| 0.4974 | 6100 | 0.0031 |
|
397 |
+
| 0.5056 | 6200 | 0.0033 |
|
398 |
+
| 0.5137 | 6300 | 0.0035 |
|
399 |
+
| 0.5219 | 6400 | 0.0031 |
|
400 |
+
| 0.5300 | 6500 | 0.0031 |
|
401 |
+
| 0.5382 | 6600 | 0.0031 |
|
402 |
+
| 0.5464 | 6700 | 0.0038 |
|
403 |
+
| 0.5545 | 6800 | 0.0031 |
|
404 |
+
| 0.5627 | 6900 | 0.003 |
|
405 |
+
| 0.5708 | 7000 | 0.0029 |
|
406 |
+
| 0.5790 | 7100 | 0.0037 |
|
407 |
+
| 0.5871 | 7200 | 0.0033 |
|
408 |
+
| 0.5953 | 7300 | 0.0031 |
|
409 |
+
| 0.6034 | 7400 | 0.003 |
|
410 |
+
| 0.6116 | 7500 | 0.003 |
|
411 |
+
| 0.6198 | 7600 | 0.004 |
|
412 |
+
| 0.6279 | 7700 | 0.0031 |
|
413 |
+
| 0.6361 | 7800 | 0.0031 |
|
414 |
+
| 0.6442 | 7900 | 0.0031 |
|
415 |
+
| 0.6524 | 8000 | 0.0039 |
|
416 |
+
| 0.6605 | 8100 | 0.0029 |
|
417 |
+
| 0.6687 | 8200 | 0.003 |
|
418 |
+
| 0.6768 | 8300 | 0.0029 |
|
419 |
+
| 0.6850 | 8400 | 0.0028 |
|
420 |
+
| 0.6931 | 8500 | 0.0036 |
|
421 |
+
| 0.7013 | 8600 | 0.0031 |
|
422 |
+
| 0.7095 | 8700 | 0.0029 |
|
423 |
+
| 0.7176 | 8800 | 0.0028 |
|
424 |
+
| 0.7258 | 8900 | 0.0035 |
|
425 |
+
| 0.7339 | 9000 | 0.0033 |
|
426 |
+
| 0.7421 | 9100 | 0.003 |
|
427 |
+
| 0.7502 | 9200 | 0.0028 |
|
428 |
+
| 0.7584 | 9300 | 0.0029 |
|
429 |
+
| 0.7665 | 9400 | 0.0035 |
|
430 |
+
| 0.7747 | 9500 | 0.003 |
|
431 |
+
| 0.7828 | 9600 | 0.0028 |
|
432 |
+
| 0.7910 | 9700 | 0.0027 |
|
433 |
+
| 0.7992 | 9800 | 0.0034 |
|
434 |
+
| 0.8073 | 9900 | 0.0032 |
|
435 |
+
| 0.8155 | 10000 | 0.003 |
|
436 |
+
| 0.8236 | 10100 | 0.0029 |
|
437 |
+
| 0.8318 | 10200 | 0.0032 |
|
438 |
+
| 0.8399 | 10300 | 0.0032 |
|
439 |
+
| 0.8481 | 10400 | 0.003 |
|
440 |
+
| 0.8562 | 10500 | 0.0029 |
|
441 |
+
| 0.8644 | 10600 | 0.0029 |
|
442 |
+
| 0.8725 | 10700 | 0.0033 |
|
443 |
+
| 0.8807 | 10800 | 0.003 |
|
444 |
+
| 0.8889 | 10900 | 0.0029 |
|
445 |
+
| 0.8970 | 11000 | 0.0028 |
|
446 |
+
| 0.9052 | 11100 | 0.0035 |
|
447 |
+
| 0.9133 | 11200 | 0.003 |
|
448 |
+
| 0.9215 | 11300 | 0.0029 |
|
449 |
+
| 0.9296 | 11400 | 0.0029 |
|
450 |
+
| 0.9378 | 11500 | 0.0029 |
|
451 |
+
| 0.9459 | 11600 | 0.0034 |
|
452 |
+
| 0.9541 | 11700 | 0.0031 |
|
453 |
+
| 0.9622 | 11800 | 0.0028 |
|
454 |
+
| 0.9704 | 11900 | 0.003 |
|
455 |
+
| 0.9786 | 12000 | 0.0035 |
|
456 |
+
| 0.9867 | 12100 | 0.0032 |
|
457 |
+
| 0.9949 | 12200 | 0.003 |
|
458 |
+
| 1.0030 | 12300 | 0.0033 |
|
459 |
+
| 1.0112 | 12400 | 0.0029 |
|
460 |
+
| 1.0193 | 12500 | 0.003 |
|
461 |
+
| 1.0275 | 12600 | 0.0029 |
|
462 |
+
| 1.0356 | 12700 | 0.0036 |
|
463 |
+
| 1.0438 | 12800 | 0.003 |
|
464 |
+
| 1.0519 | 12900 | 0.0027 |
|
465 |
+
| 1.0601 | 13000 | 0.0028 |
|
466 |
+
| 1.0683 | 13100 | 0.0028 |
|
467 |
+
| 1.0764 | 13200 | 0.0036 |
|
468 |
+
| 1.0846 | 13300 | 0.0027 |
|
469 |
+
| 1.0927 | 13400 | 0.0028 |
|
470 |
+
| 1.1009 | 13500 | 0.0029 |
|
471 |
+
| 1.1090 | 13600 | 0.0037 |
|
472 |
+
| 1.1172 | 13700 | 0.0029 |
|
473 |
+
| 1.1253 | 13800 | 0.0029 |
|
474 |
+
| 1.1335 | 13900 | 0.0027 |
|
475 |
+
| 1.1416 | 14000 | 0.0033 |
|
476 |
+
| 1.1498 | 14100 | 0.003 |
|
477 |
+
| 1.1580 | 14200 | 0.0027 |
|
478 |
+
| 1.1661 | 14300 | 0.0028 |
|
479 |
+
| 1.1743 | 14400 | 0.0026 |
|
480 |
+
| 1.1824 | 14500 | 0.0036 |
|
481 |
+
| 1.1906 | 14600 | 0.0028 |
|
482 |
+
| 1.1987 | 14700 | 0.0027 |
|
483 |
+
| 1.2069 | 14800 | 0.0029 |
|
484 |
+
| 1.2150 | 14900 | 0.0035 |
|
485 |
+
| 1.2232 | 15000 | 0.0027 |
|
486 |
+
| 1.2313 | 15100 | 0.0027 |
|
487 |
+
| 1.2395 | 15200 | 0.0027 |
|
488 |
+
| 1.2477 | 15300 | 0.0028 |
|
489 |
+
| 1.2558 | 15400 | 0.0035 |
|
490 |
+
| 1.2640 | 15500 | 0.0027 |
|
491 |
+
| 1.2721 | 15600 | 0.0027 |
|
492 |
+
| 1.2803 | 15700 | 0.0027 |
|
493 |
+
| 1.2884 | 15800 | 0.0037 |
|
494 |
+
| 1.2966 | 15900 | 0.0027 |
|
495 |
+
| 1.3047 | 16000 | 0.0027 |
|
496 |
+
| 1.3129 | 16100 | 0.0027 |
|
497 |
+
| 1.3210 | 16200 | 0.0028 |
|
498 |
+
| 1.3292 | 16300 | 0.0033 |
|
499 |
+
| 1.3374 | 16400 | 0.0026 |
|
500 |
+
| 1.3455 | 16500 | 0.0025 |
|
501 |
+
| 1.3537 | 16600 | 0.0028 |
|
502 |
+
| 1.3618 | 16700 | 0.0034 |
|
503 |
+
| 1.3700 | 16800 | 0.0027 |
|
504 |
+
| 1.3781 | 16900 | 0.0026 |
|
505 |
+
| 1.3863 | 17000 | 0.0027 |
|
506 |
+
| 1.3944 | 17100 | 0.0033 |
|
507 |
+
| 1.4026 | 17200 | 0.0027 |
|
508 |
+
| 1.4107 | 17300 | 0.0027 |
|
509 |
+
| 1.4189 | 17400 | 0.0026 |
|
510 |
+
| 1.4271 | 17500 | 0.0027 |
|
511 |
+
| 1.4352 | 17600 | 0.0034 |
|
512 |
+
| 1.4434 | 17700 | 0.0027 |
|
513 |
+
| 1.4515 | 17800 | 0.0025 |
|
514 |
+
| 1.4597 | 17900 | 0.0027 |
|
515 |
+
| 1.4678 | 18000 | 0.0031 |
|
516 |
+
| 1.4760 | 18100 | 0.0027 |
|
517 |
+
| 1.4841 | 18200 | 0.0027 |
|
518 |
+
| 1.4923 | 18300 | 0.0027 |
|
519 |
+
| 1.5004 | 18400 | 0.0027 |
|
520 |
+
| 1.5086 | 18500 | 0.0031 |
|
521 |
+
| 1.5168 | 18600 | 0.0025 |
|
522 |
+
| 1.5249 | 18700 | 0.0026 |
|
523 |
+
| 1.5331 | 18800 | 0.0027 |
|
524 |
+
| 1.5412 | 18900 | 0.0035 |
|
525 |
+
| 1.5494 | 19000 | 0.0025 |
|
526 |
+
| 1.5575 | 19100 | 0.0027 |
|
527 |
+
| 1.5657 | 19200 | 0.0026 |
|
528 |
+
| 1.5738 | 19300 | 0.0028 |
|
529 |
+
| 1.5820 | 19400 | 0.0032 |
|
530 |
+
| 1.5901 | 19500 | 0.0025 |
|
531 |
+
| 1.5983 | 19600 | 0.0027 |
|
532 |
+
| 1.6065 | 19700 | 0.0026 |
|
533 |
+
| 1.6146 | 19800 | 0.0034 |
|
534 |
+
| 1.6228 | 19900 | 0.0027 |
|
535 |
+
| 1.6309 | 20000 | 0.0027 |
|
536 |
+
| 1.6391 | 20100 | 0.0028 |
|
537 |
+
| 1.6472 | 20200 | 0.0031 |
|
538 |
+
| 1.6554 | 20300 | 0.0028 |
|
539 |
+
| 1.6635 | 20400 | 0.0025 |
|
540 |
+
| 1.6717 | 20500 | 0.0025 |
|
541 |
+
| 1.6798 | 20600 | 0.0026 |
|
542 |
+
| 1.6880 | 20700 | 0.003 |
|
543 |
+
| 1.6962 | 20800 | 0.0029 |
|
544 |
+
| 1.7043 | 20900 | 0.0027 |
|
545 |
+
| 1.7125 | 21000 | 0.0025 |
|
546 |
+
| 1.7206 | 21100 | 0.0029 |
|
547 |
+
| 1.7288 | 21200 | 0.0029 |
|
548 |
+
| 1.7369 | 21300 | 0.0027 |
|
549 |
+
| 1.7451 | 21400 | 0.0026 |
|
550 |
+
| 1.7532 | 21500 | 0.0025 |
|
551 |
+
| 1.7614 | 21600 | 0.003 |
|
552 |
+
| 1.7696 | 21700 | 0.0028 |
|
553 |
+
| 1.7777 | 21800 | 0.0024 |
|
554 |
+
| 1.7859 | 21900 | 0.0025 |
|
555 |
+
| 1.7940 | 22000 | 0.003 |
|
556 |
+
| 1.8022 | 22100 | 0.0026 |
|
557 |
+
| 1.8103 | 22200 | 0.0027 |
|
558 |
+
| 1.8185 | 22300 | 0.0027 |
|
559 |
+
| 1.8266 | 22400 | 0.0026 |
|
560 |
+
| 1.8348 | 22500 | 0.003 |
|
561 |
+
| 1.8429 | 22600 | 0.0029 |
|
562 |
+
| 1.8511 | 22700 | 0.0025 |
|
563 |
+
| 1.8593 | 22800 | 0.0026 |
|
564 |
+
| 1.8674 | 22900 | 0.0031 |
|
565 |
+
| 1.8756 | 23000 | 0.0027 |
|
566 |
+
| 1.8837 | 23100 | 0.0026 |
|
567 |
+
| 1.8919 | 23200 | 0.0025 |
|
568 |
+
| 1.9000 | 23300 | 0.0028 |
|
569 |
+
| 1.9082 | 23400 | 0.0027 |
|
570 |
+
| 1.9163 | 23500 | 0.0027 |
|
571 |
+
| 1.9245 | 23600 | 0.0027 |
|
572 |
+
| 1.9326 | 23700 | 0.0026 |
|
573 |
+
| 1.9408 | 23800 | 0.0031 |
|
574 |
+
| 1.9490 | 23900 | 0.0027 |
|
575 |
+
| 1.9571 | 24000 | 0.0027 |
|
576 |
+
| 1.9653 | 24100 | 0.0026 |
|
577 |
+
| 1.9734 | 24200 | 0.0032 |
|
578 |
+
| 1.9816 | 24300 | 0.0029 |
|
579 |
+
| 1.9897 | 24400 | 0.0026 |
|
580 |
+
| 1.9979 | 24500 | 0.0028 |
|
581 |
+
| 2.0060 | 24600 | 0.0029 |
|
582 |
+
| 2.0142 | 24700 | 0.0026 |
|
583 |
+
| 2.0223 | 24800 | 0.0027 |
|
584 |
+
| 2.0305 | 24900 | 0.0033 |
|
585 |
+
| 2.0387 | 25000 | 0.0026 |
|
586 |
+
| 2.0468 | 25100 | 0.0026 |
|
587 |
+
| 2.0550 | 25200 | 0.0024 |
|
588 |
+
| 2.0631 | 25300 | 0.0026 |
|
589 |
+
| 2.0713 | 25400 | 0.0033 |
|
590 |
+
| 2.0794 | 25500 | 0.0025 |
|
591 |
+
| 2.0876 | 25600 | 0.0026 |
|
592 |
+
| 2.0957 | 25700 | 0.0026 |
|
593 |
+
| 2.1039 | 25800 | 0.0033 |
|
594 |
+
| 2.1120 | 25900 | 0.0025 |
|
595 |
+
| 2.1202 | 26000 | 0.0026 |
|
596 |
+
| 2.1284 | 26100 | 0.0026 |
|
597 |
+
| 2.1365 | 26200 | 0.0025 |
|
598 |
+
| 2.1447 | 26300 | 0.0031 |
|
599 |
+
| 2.1528 | 26400 | 0.0026 |
|
600 |
+
| 2.1610 | 26500 | 0.0025 |
|
601 |
+
| 2.1691 | 26600 | 0.0026 |
|
602 |
+
| 2.1773 | 26700 | 0.0032 |
|
603 |
+
| 2.1854 | 26800 | 0.0026 |
|
604 |
+
| 2.1936 | 26900 | 0.0026 |
|
605 |
+
| 2.2017 | 27000 | 0.0025 |
|
606 |
+
| 2.2099 | 27100 | 0.0032 |
|
607 |
+
| 2.2181 | 27200 | 0.0025 |
|
608 |
+
| 2.2262 | 27300 | 0.0025 |
|
609 |
+
| 2.2344 | 27400 | 0.0024 |
|
610 |
+
| 2.2425 | 27500 | 0.0025 |
|
611 |
+
| 2.2507 | 27600 | 0.0033 |
|
612 |
+
| 2.2588 | 27700 | 0.0024 |
|
613 |
+
| 2.2670 | 27800 | 0.0024 |
|
614 |
+
| 2.2751 | 27900 | 0.0024 |
|
615 |
+
| 2.2833 | 28000 | 0.0033 |
|
616 |
+
| 2.2914 | 28100 | 0.0025 |
|
617 |
+
| 2.2996 | 28200 | 0.0024 |
|
618 |
+
| 2.3078 | 28300 | 0.0026 |
|
619 |
+
| 2.3159 | 28400 | 0.0024 |
|
620 |
+
| 2.3241 | 28500 | 0.0032 |
|
621 |
+
| 2.3322 | 28600 | 0.0025 |
|
622 |
+
| 2.3404 | 28700 | 0.0024 |
|
623 |
+
| 2.3485 | 28800 | 0.0024 |
|
624 |
+
| 2.3567 | 28900 | 0.0032 |
|
625 |
+
| 2.3648 | 29000 | 0.0025 |
|
626 |
+
| 2.3730 | 29100 | 0.0024 |
|
627 |
+
| 2.3811 | 29200 | 0.0024 |
|
628 |
+
| 2.3893 | 29300 | 0.0028 |
|
629 |
+
| 2.3975 | 29400 | 0.003 |
|
630 |
+
| 2.4056 | 29500 | 0.0023 |
|
631 |
+
| 2.4138 | 29600 | 0.0025 |
|
632 |
+
| 2.4219 | 29700 | 0.0024 |
|
633 |
+
| 2.4301 | 29800 | 0.0032 |
|
634 |
+
| 2.4382 | 29900 | 0.0025 |
|
635 |
+
| 2.4464 | 30000 | 0.0024 |
|
636 |
+
| 2.4545 | 30100 | 0.0023 |
|
637 |
+
| 2.4627 | 30200 | 0.003 |
|
638 |
+
| 2.4708 | 30300 | 0.0024 |
|
639 |
+
| 2.4790 | 30400 | 0.0025 |
|
640 |
+
| 2.4872 | 30500 | 0.0025 |
|
641 |
+
| 2.4953 | 30600 | 0.0025 |
|
642 |
+
| 2.5035 | 30700 | 0.0031 |
|
643 |
+
| 2.5116 | 30800 | 0.0022 |
|
644 |
+
| 2.5198 | 30900 | 0.0024 |
|
645 |
+
| 2.5279 | 31000 | 0.0024 |
|
646 |
+
| 2.5361 | 31100 | 0.0032 |
|
647 |
+
| 2.5442 | 31200 | 0.0024 |
|
648 |
+
| 2.5524 | 31300 | 0.0023 |
|
649 |
+
| 2.5605 | 31400 | 0.0025 |
|
650 |
+
| 2.5687 | 31500 | 0.0024 |
|
651 |
+
| 2.5769 | 31600 | 0.0031 |
|
652 |
+
| 2.5850 | 31700 | 0.0024 |
|
653 |
+
| 2.5932 | 31800 | 0.0024 |
|
654 |
+
| 2.6013 | 31900 | 0.0024 |
|
655 |
+
| 2.6095 | 32000 | 0.0031 |
|
656 |
+
| 2.6176 | 32100 | 0.0025 |
|
657 |
+
| 2.6258 | 32200 | 0.0025 |
|
658 |
+
| 2.6339 | 32300 | 0.0025 |
|
659 |
+
| 2.6421 | 32400 | 0.0027 |
|
660 |
+
| 2.6502 | 32500 | 0.0029 |
|
661 |
+
| 2.6584 | 32600 | 0.0024 |
|
662 |
+
| 2.6666 | 32700 | 0.0023 |
|
663 |
+
| 2.6747 | 32800 | 0.0025 |
|
664 |
+
| 2.6829 | 32900 | 0.0028 |
|
665 |
+
| 2.6910 | 33000 | 0.0026 |
|
666 |
+
| 2.6992 | 33100 | 0.0025 |
|
667 |
+
| 2.7073 | 33200 | 0.0024 |
|
668 |
+
| 2.7155 | 33300 | 0.0025 |
|
669 |
+
| 2.7236 | 33400 | 0.0026 |
|
670 |
+
| 2.7318 | 33500 | 0.0027 |
|
671 |
+
| 2.7399 | 33600 | 0.0025 |
|
672 |
+
| 2.7481 | 33700 | 0.0024 |
|
673 |
+
| 2.7563 | 33800 | 0.0028 |
|
674 |
+
| 2.7644 | 33900 | 0.0025 |
|
675 |
+
| 2.7726 | 34000 | 0.0024 |
|
676 |
+
| 2.7807 | 34100 | 0.0023 |
|
677 |
+
| 2.7889 | 34200 | 0.0027 |
|
678 |
+
| 2.7970 | 34300 | 0.0024 |
|
679 |
+
| 2.8052 | 34400 | 0.0025 |
|
680 |
+
| 2.8133 | 34500 | 0.0024 |
|
681 |
+
| 2.8215 | 34600 | 0.0024 |
|
682 |
+
| 2.8297 | 34700 | 0.0029 |
|
683 |
+
| 2.8378 | 34800 | 0.0027 |
|
684 |
+
| 2.8460 | 34900 | 0.0025 |
|
685 |
+
| 2.8541 | 35000 | 0.0023 |
|
686 |
+
| 2.8623 | 35100 | 0.0029 |
|
687 |
+
| 2.8704 | 35200 | 0.0025 |
|
688 |
+
| 2.8786 | 35300 | 0.0024 |
|
689 |
+
| 2.8867 | 35400 | 0.0024 |
|
690 |
+
| 2.8949 | 35500 | 0.0024 |
|
691 |
+
| 2.9030 | 35600 | 0.0028 |
|
692 |
+
| 2.9112 | 35700 | 0.0026 |
|
693 |
+
| 2.9194 | 35800 | 0.0023 |
|
694 |
+
| 2.9275 | 35900 | 0.0024 |
|
695 |
+
| 2.9357 | 36000 | 0.003 |
|
696 |
+
| 2.9438 | 36100 | 0.0025 |
|
697 |
+
| 2.9520 | 36200 | 0.0025 |
|
698 |
+
| 2.9601 | 36300 | 0.0024 |
|
699 |
+
| 2.9683 | 36400 | 0.0028 |
|
700 |
+
| 2.9764 | 36500 | 0.0027 |
|
701 |
+
| 2.9846 | 36600 | 0.0027 |
|
702 |
+
| 2.9927 | 36700 | 0.0025 |
|
703 |
+
|
704 |
+
</details>
|
705 |
+
|
706 |
+
### Framework Versions
|
707 |
+
- Python: 3.11.2
|
708 |
+
- Sentence Transformers: 3.3.1
|
709 |
+
- Transformers: 4.49.0
|
710 |
+
- PyTorch: 2.5.1+cu124
|
711 |
+
- Accelerate: 1.0.1
|
712 |
+
- Datasets: 3.1.0
|
713 |
+
- Tokenizers: 0.21.0
|
714 |
+
|
715 |
+
## Citation
|
716 |
+
|
717 |
+
### BibTeX
|
718 |
+
|
719 |
+
#### Sentence Transformers
|
720 |
+
```bibtex
|
721 |
+
@inproceedings{reimers-2019-sentence-bert,
|
722 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
723 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
724 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
725 |
+
month = "11",
|
726 |
+
year = "2019",
|
727 |
+
publisher = "Association for Computational Linguistics",
|
728 |
+
url = "https://arxiv.org/abs/1908.10084",
|
729 |
+
}
|
730 |
+
```
|
731 |
+
|
732 |
+
#### ContrastiveLoss
|
733 |
+
```bibtex
|
734 |
+
@inproceedings{hadsell2006dimensionality,
|
735 |
+
author={Hadsell, R. and Chopra, S. and LeCun, Y.},
|
736 |
+
booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
|
737 |
+
title={Dimensionality Reduction by Learning an Invariant Mapping},
|
738 |
+
year={2006},
|
739 |
+
volume={2},
|
740 |
+
number={},
|
741 |
+
pages={1735-1742},
|
742 |
+
doi={10.1109/CVPR.2006.100}
|
743 |
+
}
|
744 |
+
```
|
745 |
+
|
746 |
+
<!--
|
747 |
+
## Glossary
|
748 |
+
|
749 |
+
*Clearly define terms in order to be accessible across audiences.*
|
750 |
+
-->
|
751 |
+
|
752 |
+
<!--
|
753 |
+
## Model Card Authors
|
754 |
+
|
755 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
756 |
+
-->
|
757 |
+
|
758 |
+
<!--
|
759 |
+
## Model Card Contact
|
760 |
+
|
761 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
762 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-large-en-v1.5",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 16,
|
24 |
+
"num_hidden_layers": 24,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.49.0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.49.0",
|
5 |
+
"pytorch": "2.5.1+cu124"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5fbbe1b27a976024c628b566d028d31ebf72c3e24ab1ae775880361c195076c
|
3 |
+
size 1340612432
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": true
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|