Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- 1_Pooling/config.json +10 -0
- README.md +62 -0
- checkpoint-69/1_Pooling/config.json +10 -0
- checkpoint-69/README.md +380 -0
- checkpoint-69/config.json +26 -0
- checkpoint-69/config_sentence_transformers.json +10 -0
- checkpoint-69/model.safetensors +3 -0
- checkpoint-69/modules.json +14 -0
- checkpoint-69/optimizer.pt +3 -0
- checkpoint-69/rng_state.pth +3 -0
- checkpoint-69/scheduler.pt +3 -0
- checkpoint-69/sentence_bert_config.json +4 -0
- checkpoint-69/special_tokens_map.json +51 -0
- checkpoint-69/tokenizer.json +3 -0
- checkpoint-69/tokenizer_config.json +65 -0
- checkpoint-69/trainer_state.json +185 -0
- checkpoint-69/training_args.bin +3 -0
- checkpoint-69/unigram.json +3 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- runs/May22_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909403.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.0 +2 -2
- runs/May22_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909665.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.1 +3 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- training_params.json +33 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ 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 |
+
checkpoint-69/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
checkpoint-69/unigram.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
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 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
library_name: sentence-transformers
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
- feature-extraction
|
8 |
+
- autotrain
|
9 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
10 |
+
widget:
|
11 |
+
- source_sentence: 'search_query: i love autotrain'
|
12 |
+
sentences:
|
13 |
+
- 'search_query: huggingface auto train'
|
14 |
+
- 'search_query: hugging face auto train'
|
15 |
+
- 'search_query: i love autotrain'
|
16 |
+
pipeline_tag: sentence-similarity
|
17 |
+
---
|
18 |
+
|
19 |
+
# Model Trained Using AutoTrain
|
20 |
+
|
21 |
+
- Problem type: Sentence Transformers
|
22 |
+
|
23 |
+
## Validation Metrics
|
24 |
+
loss: 0.4411565661430359
|
25 |
+
|
26 |
+
runtime: 2.0186
|
27 |
+
|
28 |
+
samples_per_second: 90.16
|
29 |
+
|
30 |
+
steps_per_second: 5.945
|
31 |
+
|
32 |
+
: 3.0
|
33 |
+
|
34 |
+
## Usage
|
35 |
+
|
36 |
+
### Direct Usage (Sentence Transformers)
|
37 |
+
|
38 |
+
First install the Sentence Transformers library:
|
39 |
+
|
40 |
+
```bash
|
41 |
+
pip install -U sentence-transformers
|
42 |
+
```
|
43 |
+
|
44 |
+
Then you can load this model and run inference.
|
45 |
+
```python
|
46 |
+
from sentence_transformers import SentenceTransformer
|
47 |
+
|
48 |
+
# Download from the Hugging Face Hub
|
49 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
50 |
+
# Run inference
|
51 |
+
sentences = [
|
52 |
+
'search_query: autotrain',
|
53 |
+
'search_query: auto train',
|
54 |
+
'search_query: i love autotrain',
|
55 |
+
]
|
56 |
+
embeddings = model.encode(sentences)
|
57 |
+
print(embeddings.shape)
|
58 |
+
|
59 |
+
# Get the similarity scores for the embeddings
|
60 |
+
similarities = model.similarity(embeddings, embeddings)
|
61 |
+
print(similarities.shape)
|
62 |
+
```
|
checkpoint-69/1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
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 |
+
}
|
checkpoint-69/README.md
ADDED
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:182
|
8 |
+
- loss:SoftmaxLoss
|
9 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
10 |
+
widget:
|
11 |
+
- source_sentence: 太陽
|
12 |
+
sentences:
|
13 |
+
- bright
|
14 |
+
- natural
|
15 |
+
- bright
|
16 |
+
- source_sentence: 明るくない
|
17 |
+
sentences:
|
18 |
+
- cozy
|
19 |
+
- cozy
|
20 |
+
- bright
|
21 |
+
- source_sentence: natural
|
22 |
+
sentences:
|
23 |
+
- natural
|
24 |
+
- cozy
|
25 |
+
- natural
|
26 |
+
- source_sentence: sunlight
|
27 |
+
sentences:
|
28 |
+
- bright
|
29 |
+
- natural
|
30 |
+
- cozy
|
31 |
+
- source_sentence: 日光
|
32 |
+
sentences:
|
33 |
+
- bright
|
34 |
+
- cozy
|
35 |
+
- natural
|
36 |
+
pipeline_tag: sentence-similarity
|
37 |
+
library_name: sentence-transformers
|
38 |
+
---
|
39 |
+
|
40 |
+
# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
41 |
+
|
42 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
43 |
+
|
44 |
+
## Model Details
|
45 |
+
|
46 |
+
### Model Description
|
47 |
+
- **Model Type:** Sentence Transformer
|
48 |
+
- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
|
49 |
+
- **Maximum Sequence Length:** 128 tokens
|
50 |
+
- **Output Dimensionality:** 384 dimensions
|
51 |
+
- **Similarity Function:** Cosine Similarity
|
52 |
+
<!-- - **Training Dataset:** Unknown -->
|
53 |
+
<!-- - **Language:** Unknown -->
|
54 |
+
<!-- - **License:** Unknown -->
|
55 |
+
|
56 |
+
### Model Sources
|
57 |
+
|
58 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
59 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
60 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
61 |
+
|
62 |
+
### Full Model Architecture
|
63 |
+
|
64 |
+
```
|
65 |
+
SentenceTransformer(
|
66 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
67 |
+
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
68 |
+
)
|
69 |
+
```
|
70 |
+
|
71 |
+
## Usage
|
72 |
+
|
73 |
+
### Direct Usage (Sentence Transformers)
|
74 |
+
|
75 |
+
First install the Sentence Transformers library:
|
76 |
+
|
77 |
+
```bash
|
78 |
+
pip install -U sentence-transformers
|
79 |
+
```
|
80 |
+
|
81 |
+
Then you can load this model and run inference.
|
82 |
+
```python
|
83 |
+
from sentence_transformers import SentenceTransformer
|
84 |
+
|
85 |
+
# Download from the 🤗 Hub
|
86 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
87 |
+
# Run inference
|
88 |
+
sentences = [
|
89 |
+
'日光',
|
90 |
+
'natural',
|
91 |
+
'bright',
|
92 |
+
]
|
93 |
+
embeddings = model.encode(sentences)
|
94 |
+
print(embeddings.shape)
|
95 |
+
# [3, 384]
|
96 |
+
|
97 |
+
# Get the similarity scores for the embeddings
|
98 |
+
similarities = model.similarity(embeddings, embeddings)
|
99 |
+
print(similarities.shape)
|
100 |
+
# [3, 3]
|
101 |
+
```
|
102 |
+
|
103 |
+
<!--
|
104 |
+
### Direct Usage (Transformers)
|
105 |
+
|
106 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
107 |
+
|
108 |
+
</details>
|
109 |
+
-->
|
110 |
+
|
111 |
+
<!--
|
112 |
+
### Downstream Usage (Sentence Transformers)
|
113 |
+
|
114 |
+
You can finetune this model on your own dataset.
|
115 |
+
|
116 |
+
<details><summary>Click to expand</summary>
|
117 |
+
|
118 |
+
</details>
|
119 |
+
-->
|
120 |
+
|
121 |
+
<!--
|
122 |
+
### Out-of-Scope Use
|
123 |
+
|
124 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
125 |
+
-->
|
126 |
+
|
127 |
+
<!--
|
128 |
+
## Bias, Risks and Limitations
|
129 |
+
|
130 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
131 |
+
-->
|
132 |
+
|
133 |
+
<!--
|
134 |
+
### Recommendations
|
135 |
+
|
136 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
137 |
+
-->
|
138 |
+
|
139 |
+
## Training Details
|
140 |
+
|
141 |
+
### Training Dataset
|
142 |
+
|
143 |
+
#### Unnamed Dataset
|
144 |
+
|
145 |
+
|
146 |
+
* Size: 182 training samples
|
147 |
+
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
|
148 |
+
* Approximate statistics based on the first 182 samples:
|
149 |
+
| | premise | hypothesis | label |
|
150 |
+
|:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
|
151 |
+
| type | string | string | int |
|
152 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 5.39 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.36 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~25.27%</li><li>1: ~74.73%</li></ul> |
|
153 |
+
* Samples:
|
154 |
+
| premise | hypothesis | label |
|
155 |
+
|:----------------------|:--------------------|:---------------|
|
156 |
+
| <code>bright</code> | <code>bright</code> | <code>1</code> |
|
157 |
+
| <code>luminous</code> | <code>bright</code> | <code>1</code> |
|
158 |
+
| <code>well-lit</code> | <code>bright</code> | <code>1</code> |
|
159 |
+
* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
|
160 |
+
|
161 |
+
### Evaluation Dataset
|
162 |
+
|
163 |
+
#### Unnamed Dataset
|
164 |
+
|
165 |
+
|
166 |
+
* Size: 182 evaluation samples
|
167 |
+
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
|
168 |
+
* Approximate statistics based on the first 182 samples:
|
169 |
+
| | premise | hypothesis | label |
|
170 |
+
|:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
|
171 |
+
| type | string | string | int |
|
172 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 5.39 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.36 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~25.27%</li><li>1: ~74.73%</li></ul> |
|
173 |
+
* Samples:
|
174 |
+
| premise | hypothesis | label |
|
175 |
+
|:----------------------|:--------------------|:---------------|
|
176 |
+
| <code>bright</code> | <code>bright</code> | <code>1</code> |
|
177 |
+
| <code>luminous</code> | <code>bright</code> | <code>1</code> |
|
178 |
+
| <code>well-lit</code> | <code>bright</code> | <code>1</code> |
|
179 |
+
* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
|
180 |
+
|
181 |
+
### Training Hyperparameters
|
182 |
+
#### Non-Default Hyperparameters
|
183 |
+
|
184 |
+
- `eval_strategy`: epoch
|
185 |
+
- `per_device_eval_batch_size`: 16
|
186 |
+
- `learning_rate`: 3e-05
|
187 |
+
- `warmup_ratio`: 0.1
|
188 |
+
- `fp16`: True
|
189 |
+
- `load_best_model_at_end`: True
|
190 |
+
- `ddp_find_unused_parameters`: False
|
191 |
+
|
192 |
+
#### All Hyperparameters
|
193 |
+
<details><summary>Click to expand</summary>
|
194 |
+
|
195 |
+
- `overwrite_output_dir`: False
|
196 |
+
- `do_predict`: False
|
197 |
+
- `eval_strategy`: epoch
|
198 |
+
- `prediction_loss_only`: True
|
199 |
+
- `per_device_train_batch_size`: 8
|
200 |
+
- `per_device_eval_batch_size`: 16
|
201 |
+
- `per_gpu_train_batch_size`: None
|
202 |
+
- `per_gpu_eval_batch_size`: None
|
203 |
+
- `gradient_accumulation_steps`: 1
|
204 |
+
- `eval_accumulation_steps`: None
|
205 |
+
- `torch_empty_cache_steps`: None
|
206 |
+
- `learning_rate`: 3e-05
|
207 |
+
- `weight_decay`: 0.0
|
208 |
+
- `adam_beta1`: 0.9
|
209 |
+
- `adam_beta2`: 0.999
|
210 |
+
- `adam_epsilon`: 1e-08
|
211 |
+
- `max_grad_norm`: 1.0
|
212 |
+
- `num_train_epochs`: 3
|
213 |
+
- `max_steps`: -1
|
214 |
+
- `lr_scheduler_type`: linear
|
215 |
+
- `lr_scheduler_kwargs`: {}
|
216 |
+
- `warmup_ratio`: 0.1
|
217 |
+
- `warmup_steps`: 0
|
218 |
+
- `log_level`: passive
|
219 |
+
- `log_level_replica`: warning
|
220 |
+
- `log_on_each_node`: True
|
221 |
+
- `logging_nan_inf_filter`: True
|
222 |
+
- `save_safetensors`: True
|
223 |
+
- `save_on_each_node`: False
|
224 |
+
- `save_only_model`: False
|
225 |
+
- `restore_callback_states_from_checkpoint`: False
|
226 |
+
- `no_cuda`: False
|
227 |
+
- `use_cpu`: False
|
228 |
+
- `use_mps_device`: False
|
229 |
+
- `seed`: 42
|
230 |
+
- `data_seed`: None
|
231 |
+
- `jit_mode_eval`: False
|
232 |
+
- `use_ipex`: False
|
233 |
+
- `bf16`: False
|
234 |
+
- `fp16`: True
|
235 |
+
- `fp16_opt_level`: O1
|
236 |
+
- `half_precision_backend`: auto
|
237 |
+
- `bf16_full_eval`: False
|
238 |
+
- `fp16_full_eval`: False
|
239 |
+
- `tf32`: None
|
240 |
+
- `local_rank`: 0
|
241 |
+
- `ddp_backend`: None
|
242 |
+
- `tpu_num_cores`: None
|
243 |
+
- `tpu_metrics_debug`: False
|
244 |
+
- `debug`: []
|
245 |
+
- `dataloader_drop_last`: False
|
246 |
+
- `dataloader_num_workers`: 0
|
247 |
+
- `dataloader_prefetch_factor`: None
|
248 |
+
- `past_index`: -1
|
249 |
+
- `disable_tqdm`: False
|
250 |
+
- `remove_unused_columns`: True
|
251 |
+
- `label_names`: None
|
252 |
+
- `load_best_model_at_end`: True
|
253 |
+
- `ignore_data_skip`: False
|
254 |
+
- `fsdp`: []
|
255 |
+
- `fsdp_min_num_params`: 0
|
256 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
257 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
258 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
259 |
+
- `deepspeed`: None
|
260 |
+
- `label_smoothing_factor`: 0.0
|
261 |
+
- `optim`: adamw_torch
|
262 |
+
- `optim_args`: None
|
263 |
+
- `adafactor`: False
|
264 |
+
- `group_by_length`: False
|
265 |
+
- `length_column_name`: length
|
266 |
+
- `ddp_find_unused_parameters`: False
|
267 |
+
- `ddp_bucket_cap_mb`: None
|
268 |
+
- `ddp_broadcast_buffers`: False
|
269 |
+
- `dataloader_pin_memory`: True
|
270 |
+
- `dataloader_persistent_workers`: False
|
271 |
+
- `skip_memory_metrics`: True
|
272 |
+
- `use_legacy_prediction_loop`: False
|
273 |
+
- `push_to_hub`: False
|
274 |
+
- `resume_from_checkpoint`: None
|
275 |
+
- `hub_model_id`: None
|
276 |
+
- `hub_strategy`: every_save
|
277 |
+
- `hub_private_repo`: None
|
278 |
+
- `hub_always_push`: False
|
279 |
+
- `gradient_checkpointing`: False
|
280 |
+
- `gradient_checkpointing_kwargs`: None
|
281 |
+
- `include_inputs_for_metrics`: False
|
282 |
+
- `include_for_metrics`: []
|
283 |
+
- `eval_do_concat_batches`: True
|
284 |
+
- `fp16_backend`: auto
|
285 |
+
- `push_to_hub_model_id`: None
|
286 |
+
- `push_to_hub_organization`: None
|
287 |
+
- `mp_parameters`:
|
288 |
+
- `auto_find_batch_size`: False
|
289 |
+
- `full_determinism`: False
|
290 |
+
- `torchdynamo`: None
|
291 |
+
- `ray_scope`: last
|
292 |
+
- `ddp_timeout`: 1800
|
293 |
+
- `torch_compile`: False
|
294 |
+
- `torch_compile_backend`: None
|
295 |
+
- `torch_compile_mode`: None
|
296 |
+
- `dispatch_batches`: None
|
297 |
+
- `split_batches`: None
|
298 |
+
- `include_tokens_per_second`: False
|
299 |
+
- `include_num_input_tokens_seen`: False
|
300 |
+
- `neftune_noise_alpha`: None
|
301 |
+
- `optim_target_modules`: None
|
302 |
+
- `batch_eval_metrics`: False
|
303 |
+
- `eval_on_start`: False
|
304 |
+
- `use_liger_kernel`: False
|
305 |
+
- `eval_use_gather_object`: False
|
306 |
+
- `average_tokens_across_devices`: False
|
307 |
+
- `prompts`: None
|
308 |
+
- `batch_sampler`: batch_sampler
|
309 |
+
- `multi_dataset_batch_sampler`: proportional
|
310 |
+
|
311 |
+
</details>
|
312 |
+
|
313 |
+
### Training Logs
|
314 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
315 |
+
|:------:|:----:|:-------------:|:---------------:|
|
316 |
+
| 0.1739 | 4 | 0.7869 | - |
|
317 |
+
| 0.3478 | 8 | 0.7022 | - |
|
318 |
+
| 0.5217 | 12 | 0.6482 | - |
|
319 |
+
| 0.6957 | 16 | 0.5571 | - |
|
320 |
+
| 0.8696 | 20 | 0.5698 | - |
|
321 |
+
| 1.0 | 23 | - | 0.5250 |
|
322 |
+
| 1.0435 | 24 | 0.4771 | - |
|
323 |
+
| 1.2174 | 28 | 0.444 | - |
|
324 |
+
| 1.3913 | 32 | 0.6149 | - |
|
325 |
+
| 1.5652 | 36 | 0.5523 | - |
|
326 |
+
| 1.7391 | 40 | 0.4806 | - |
|
327 |
+
| 1.9130 | 44 | 0.4623 | - |
|
328 |
+
| 2.0 | 46 | - | 0.4654 |
|
329 |
+
| 2.0870 | 48 | 0.4039 | - |
|
330 |
+
| 2.2609 | 52 | 0.47 | - |
|
331 |
+
| 2.4348 | 56 | 0.3878 | - |
|
332 |
+
| 2.6087 | 60 | 0.5158 | - |
|
333 |
+
| 2.7826 | 64 | 0.5203 | - |
|
334 |
+
| 2.9565 | 68 | 0.4446 | - |
|
335 |
+
| 3.0 | 69 | - | 0.4412 |
|
336 |
+
|
337 |
+
|
338 |
+
### Framework Versions
|
339 |
+
- Python: 3.10.16
|
340 |
+
- Sentence Transformers: 3.3.1
|
341 |
+
- Transformers: 4.48.0
|
342 |
+
- PyTorch: 2.4.0
|
343 |
+
- Accelerate: 1.2.1
|
344 |
+
- Datasets: 3.2.0
|
345 |
+
- Tokenizers: 0.21.0
|
346 |
+
|
347 |
+
## Citation
|
348 |
+
|
349 |
+
### BibTeX
|
350 |
+
|
351 |
+
#### Sentence Transformers and SoftmaxLoss
|
352 |
+
```bibtex
|
353 |
+
@inproceedings{reimers-2019-sentence-bert,
|
354 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
355 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
356 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
357 |
+
month = "11",
|
358 |
+
year = "2019",
|
359 |
+
publisher = "Association for Computational Linguistics",
|
360 |
+
url = "https://arxiv.org/abs/1908.10084",
|
361 |
+
}
|
362 |
+
```
|
363 |
+
|
364 |
+
<!--
|
365 |
+
## Glossary
|
366 |
+
|
367 |
+
*Clearly define terms in order to be accessible across audiences.*
|
368 |
+
-->
|
369 |
+
|
370 |
+
<!--
|
371 |
+
## Model Card Authors
|
372 |
+
|
373 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
374 |
+
-->
|
375 |
+
|
376 |
+
<!--
|
377 |
+
## Model Card Contact
|
378 |
+
|
379 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
380 |
+
-->
|
checkpoint-69/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
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": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.48.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
checkpoint-69/config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.48.0",
|
5 |
+
"pytorch": "2.4.0"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
checkpoint-69/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13f531f1b6b1777ecaa3ed1f5e1dcb13b5285ded13de4667c2c369a308622017
|
3 |
+
size 470637416
|
checkpoint-69/modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
]
|
checkpoint-69/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ee8db425650850a8eb75b151178d0623b5f841998d7ec80aeb40266e9762ea0
|
3 |
+
size 940226682
|
checkpoint-69/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:928defb185d37229cef46a59a4356e668dd7bab7ed52898f983eea654ae182be
|
3 |
+
size 13990
|
checkpoint-69/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd1ba2e1ef1a7931ed9ce00b46e8e8da1deed03835dbf66fa6156db8675a6ef9
|
3 |
+
size 1064
|
checkpoint-69/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
checkpoint-69/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
checkpoint-69/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
|
3 |
+
size 17082987
|
checkpoint-69/tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"extra_special_tokens": {},
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 128,
|
52 |
+
"model_max_length": 128,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"sep_token": "</s>",
|
58 |
+
"stride": 0,
|
59 |
+
"strip_accents": null,
|
60 |
+
"tokenize_chinese_chars": true,
|
61 |
+
"tokenizer_class": "BertTokenizer",
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
+
"unk_token": "<unk>"
|
65 |
+
}
|
checkpoint-69/trainer_state.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4411565661430359,
|
3 |
+
"best_model_checkpoint": "autotrain-3c51k-w49bn/checkpoint-69",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 69,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17391304347826086,
|
13 |
+
"grad_norm": 3.44027042388916,
|
14 |
+
"learning_rate": 1.7142857142857142e-05,
|
15 |
+
"loss": 0.7869,
|
16 |
+
"step": 4
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.34782608695652173,
|
20 |
+
"grad_norm": 1.9074159860610962,
|
21 |
+
"learning_rate": 2.9516129032258067e-05,
|
22 |
+
"loss": 0.7022,
|
23 |
+
"step": 8
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5217391304347826,
|
27 |
+
"grad_norm": 3.345827579498291,
|
28 |
+
"learning_rate": 2.758064516129032e-05,
|
29 |
+
"loss": 0.6482,
|
30 |
+
"step": 12
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6956521739130435,
|
34 |
+
"grad_norm": 2.091654062271118,
|
35 |
+
"learning_rate": 2.5645161290322582e-05,
|
36 |
+
"loss": 0.5571,
|
37 |
+
"step": 16
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8695652173913043,
|
41 |
+
"grad_norm": 1.436171054840088,
|
42 |
+
"learning_rate": 2.370967741935484e-05,
|
43 |
+
"loss": 0.5698,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"eval_loss": 0.5249526500701904,
|
49 |
+
"eval_runtime": 3.0089,
|
50 |
+
"eval_samples_per_second": 60.487,
|
51 |
+
"eval_steps_per_second": 3.988,
|
52 |
+
"step": 23
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 1.0434782608695652,
|
56 |
+
"grad_norm": 1.838670015335083,
|
57 |
+
"learning_rate": 2.1774193548387097e-05,
|
58 |
+
"loss": 0.4771,
|
59 |
+
"step": 24
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.2173913043478262,
|
63 |
+
"grad_norm": 1.2238214015960693,
|
64 |
+
"learning_rate": 1.9838709677419355e-05,
|
65 |
+
"loss": 0.444,
|
66 |
+
"step": 28
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.391304347826087,
|
70 |
+
"grad_norm": 2.102836847305298,
|
71 |
+
"learning_rate": 1.7903225806451616e-05,
|
72 |
+
"loss": 0.6149,
|
73 |
+
"step": 32
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.5652173913043477,
|
77 |
+
"grad_norm": 1.8485645055770874,
|
78 |
+
"learning_rate": 1.596774193548387e-05,
|
79 |
+
"loss": 0.5523,
|
80 |
+
"step": 36
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.7391304347826086,
|
84 |
+
"grad_norm": 2.7359752655029297,
|
85 |
+
"learning_rate": 1.403225806451613e-05,
|
86 |
+
"loss": 0.4806,
|
87 |
+
"step": 40
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.9130434782608696,
|
91 |
+
"grad_norm": 1.4217264652252197,
|
92 |
+
"learning_rate": 1.2096774193548387e-05,
|
93 |
+
"loss": 0.4623,
|
94 |
+
"step": 44
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 2.0,
|
98 |
+
"eval_loss": 0.46536698937416077,
|
99 |
+
"eval_runtime": 3.1677,
|
100 |
+
"eval_samples_per_second": 57.456,
|
101 |
+
"eval_steps_per_second": 3.788,
|
102 |
+
"step": 46
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 2.0869565217391304,
|
106 |
+
"grad_norm": 1.995253562927246,
|
107 |
+
"learning_rate": 1.0161290322580644e-05,
|
108 |
+
"loss": 0.4039,
|
109 |
+
"step": 48
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 2.260869565217391,
|
113 |
+
"grad_norm": 2.4988834857940674,
|
114 |
+
"learning_rate": 8.225806451612904e-06,
|
115 |
+
"loss": 0.47,
|
116 |
+
"step": 52
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.4347826086956523,
|
120 |
+
"grad_norm": 1.7685775756835938,
|
121 |
+
"learning_rate": 6.290322580645162e-06,
|
122 |
+
"loss": 0.3878,
|
123 |
+
"step": 56
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.608695652173913,
|
127 |
+
"grad_norm": 2.7405200004577637,
|
128 |
+
"learning_rate": 4.35483870967742e-06,
|
129 |
+
"loss": 0.5158,
|
130 |
+
"step": 60
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.782608695652174,
|
134 |
+
"grad_norm": 3.4083738327026367,
|
135 |
+
"learning_rate": 2.4193548387096776e-06,
|
136 |
+
"loss": 0.5203,
|
137 |
+
"step": 64
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.9565217391304346,
|
141 |
+
"grad_norm": 1.6851589679718018,
|
142 |
+
"learning_rate": 4.838709677419355e-07,
|
143 |
+
"loss": 0.4446,
|
144 |
+
"step": 68
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.0,
|
148 |
+
"eval_loss": 0.4411565661430359,
|
149 |
+
"eval_runtime": 1.7496,
|
150 |
+
"eval_samples_per_second": 104.022,
|
151 |
+
"eval_steps_per_second": 6.859,
|
152 |
+
"step": 69
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"logging_steps": 4,
|
156 |
+
"max_steps": 69,
|
157 |
+
"num_input_tokens_seen": 0,
|
158 |
+
"num_train_epochs": 3,
|
159 |
+
"save_steps": 500,
|
160 |
+
"stateful_callbacks": {
|
161 |
+
"EarlyStoppingCallback": {
|
162 |
+
"args": {
|
163 |
+
"early_stopping_patience": 5,
|
164 |
+
"early_stopping_threshold": 0.01
|
165 |
+
},
|
166 |
+
"attributes": {
|
167 |
+
"early_stopping_patience_counter": 0
|
168 |
+
}
|
169 |
+
},
|
170 |
+
"TrainerControl": {
|
171 |
+
"args": {
|
172 |
+
"should_epoch_stop": false,
|
173 |
+
"should_evaluate": false,
|
174 |
+
"should_log": false,
|
175 |
+
"should_save": true,
|
176 |
+
"should_training_stop": true
|
177 |
+
},
|
178 |
+
"attributes": {}
|
179 |
+
}
|
180 |
+
},
|
181 |
+
"total_flos": 0.0,
|
182 |
+
"train_batch_size": 8,
|
183 |
+
"trial_name": null,
|
184 |
+
"trial_params": null
|
185 |
+
}
|
checkpoint-69/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ea6dcc876978d9aca3f5bd72ab2275d18944971f3a2ae08b4f63b216d3d2b51
|
3 |
+
size 5624
|
checkpoint-69/unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
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": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.48.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.3.1",
|
4 |
+
"transformers": "4.48.0",
|
5 |
+
"pytorch": "2.4.0"
|
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 sha256:13f531f1b6b1777ecaa3ed1f5e1dcb13b5285ded13de4667c2c369a308622017
|
3 |
+
size 470637416
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
]
|
runs/May22_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909403.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c57b90c01e200d37c17c463d8c1db5b1990d21a65b71c017ae4021c00e5dfeb6
|
3 |
+
size 9089
|
runs/May22_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909665.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ac90fb3fe0f7d6046219246eb082070cde829ad41a9c3a72ffc17af3cc93429
|
3 |
+
size 354
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
|
3 |
+
size 17082987
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"extra_special_tokens": {},
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 128,
|
52 |
+
"model_max_length": 128,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"sep_token": "</s>",
|
58 |
+
"stride": 0,
|
59 |
+
"strip_accents": null,
|
60 |
+
"tokenize_chinese_chars": true,
|
61 |
+
"tokenizer_class": "BertTokenizer",
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
+
"unk_token": "<unk>"
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ea6dcc876978d9aca3f5bd72ab2275d18944971f3a2ae08b4f63b216d3d2b51
|
3 |
+
size 5624
|
training_params.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-3c51k-w49bn/autotrain-data",
|
3 |
+
"model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
4 |
+
"lr": 3e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"logging_steps": -1,
|
18 |
+
"project_name": "autotrain-3c51k-w49bn",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"save_total_limit": 1,
|
22 |
+
"push_to_hub": true,
|
23 |
+
"eval_strategy": "epoch",
|
24 |
+
"username": "nabil-tazi",
|
25 |
+
"log": "tensorboard",
|
26 |
+
"early_stopping_patience": 5,
|
27 |
+
"early_stopping_threshold": 0.01,
|
28 |
+
"trainer": "pair_class",
|
29 |
+
"sentence1_column": "autotrain_sentence1",
|
30 |
+
"sentence2_column": "autotrain_sentence2",
|
31 |
+
"sentence3_column": "autotrain_sentence3",
|
32 |
+
"target_column": "autotrain_target"
|
33 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|