|
---
|
|
tags:
|
|
- sentence-transformers
|
|
- sentence-similarity
|
|
- feature-extraction
|
|
- generated_from_trainer
|
|
- dataset_size:33
|
|
- loss:MatryoshkaLoss
|
|
- loss:MultipleNegativesRankingLoss
|
|
base_model: keepitreal/vietnamese-sbert
|
|
widget:
|
|
- source_sentence: Áo Polo Lacoste với chất liệu Petit Piqué và thiết kế cổ gập kinh
|
|
điển
|
|
sentences:
|
|
- Giày cao gót đẳng cấp
|
|
- Xe điều khiển từ xa
|
|
- Áo polo sang trọng
|
|
- source_sentence: Sony Alpha A7 IV với cảm biến CMOS Exmor R 33MP và khả năng quay
|
|
4K 60fps
|
|
sentences:
|
|
- Giày cao gót sang trọng
|
|
- Sách văn học tuổi thơ
|
|
- Máy ảnh chuyên nghiệp
|
|
- source_sentence: Laneige Water Bank Cream với công nghệ Hydro Ionized Mineral Water
|
|
và kết cấu gel mỏng nhẹ
|
|
sentences:
|
|
- Điện thoại flagship cao cấp
|
|
- Kem dưỡng ẩm nổi bật
|
|
- Giày tây nam lịch lãm
|
|
- source_sentence: Adidas Ultraboost với công nghệ Boost™ và đế ngoài Continental™
|
|
Rubber
|
|
sentences:
|
|
- Tai nghe chống ồn hàng đầu
|
|
- Quần short kaki trẻ trung
|
|
- Giày chạy bộ hiện đại
|
|
- source_sentence: Áo thun từ cotton mềm mại, kiểu dáng đa dạng phù hợp cho nhiều
|
|
phong cách
|
|
sentences:
|
|
- Máy ảnh vlog chuyên nghiệp
|
|
- Áo thun thoải mái
|
|
- Laptop hiệu năng mạnh mẽ
|
|
pipeline_tag: sentence-similarity
|
|
library_name: sentence-transformers
|
|
metrics:
|
|
- cosine_accuracy@1
|
|
- cosine_accuracy@3
|
|
- cosine_accuracy@5
|
|
- cosine_accuracy@10
|
|
- cosine_precision@1
|
|
- cosine_precision@3
|
|
- cosine_precision@5
|
|
- cosine_precision@10
|
|
- cosine_recall@1
|
|
- cosine_recall@3
|
|
- cosine_recall@5
|
|
- cosine_recall@10
|
|
- cosine_ndcg@10
|
|
- cosine_mrr@10
|
|
- cosine_map@100
|
|
model-index:
|
|
- name: SentenceTransformer based on keepitreal/vietnamese-sbert
|
|
results:
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: dim 768
|
|
type: dim_768
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.25
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.75
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.75
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 1.0
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.25
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.25
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.15000000000000002
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.1
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.25
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.75
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.75
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 1.0
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.6377310833652008
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.525
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.525
|
|
name: Cosine Map@100
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: dim 512
|
|
type: dim_512
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.25
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.75
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.75
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 1.0
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.25
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.25
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.15000000000000002
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.1
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.25
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.75
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.75
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 1.0
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.6079899373088598
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.4861111111111111
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.4861111111111111
|
|
name: Cosine Map@100
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: dim 256
|
|
type: dim_256
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.25
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.75
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.75
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 0.75
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.25
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.25
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.15000000000000002
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.07500000000000001
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.25
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.75
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.75
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 0.75
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.5
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.41666666666666663
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.43749999999999994
|
|
name: Cosine Map@100
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: dim 128
|
|
type: dim_128
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.5
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.75
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.75
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 1.0
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.5
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.25
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.15000000000000002
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.1
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.5
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.75
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.75
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 1.0
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.7410657717261977
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.6607142857142857
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.6607142857142857
|
|
name: Cosine Map@100
|
|
- task:
|
|
type: information-retrieval
|
|
name: Information Retrieval
|
|
dataset:
|
|
name: dim 64
|
|
type: dim_64
|
|
metrics:
|
|
- type: cosine_accuracy@1
|
|
value: 0.0
|
|
name: Cosine Accuracy@1
|
|
- type: cosine_accuracy@3
|
|
value: 0.5
|
|
name: Cosine Accuracy@3
|
|
- type: cosine_accuracy@5
|
|
value: 0.5
|
|
name: Cosine Accuracy@5
|
|
- type: cosine_accuracy@10
|
|
value: 0.75
|
|
name: Cosine Accuracy@10
|
|
- type: cosine_precision@1
|
|
value: 0.0
|
|
name: Cosine Precision@1
|
|
- type: cosine_precision@3
|
|
value: 0.16666666666666666
|
|
name: Cosine Precision@3
|
|
- type: cosine_precision@5
|
|
value: 0.1
|
|
name: Cosine Precision@5
|
|
- type: cosine_precision@10
|
|
value: 0.07500000000000001
|
|
name: Cosine Precision@10
|
|
- type: cosine_recall@1
|
|
value: 0.0
|
|
name: Cosine Recall@1
|
|
- type: cosine_recall@3
|
|
value: 0.5
|
|
name: Cosine Recall@3
|
|
- type: cosine_recall@5
|
|
value: 0.5
|
|
name: Cosine Recall@5
|
|
- type: cosine_recall@10
|
|
value: 0.75
|
|
name: Cosine Recall@10
|
|
- type: cosine_ndcg@10
|
|
value: 0.4045166735627343
|
|
name: Cosine Ndcg@10
|
|
- type: cosine_mrr@10
|
|
value: 0.29166666666666663
|
|
name: Cosine Mrr@10
|
|
- type: cosine_map@100
|
|
value: 0.30952380952380953
|
|
name: Cosine Map@100
|
|
---
|
|
|
|
# SentenceTransformer based on keepitreal/vietnamese-sbert
|
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
|
|
|
## Model Details
|
|
|
|
### Model Description
|
|
- **Model Type:** Sentence Transformer
|
|
- **Base model:** [keepitreal/vietnamese-sbert](https://huggingface.co/keepitreal/vietnamese-sbert) <!-- at revision a9467ef2ef47caa6448edeabfd8e5e5ce0fa2a23 -->
|
|
- **Maximum Sequence Length:** 256 tokens
|
|
- **Output Dimensionality:** 768 dimensions
|
|
- **Similarity Function:** Cosine Similarity
|
|
- **Training Dataset:**
|
|
- json
|
|
<!-- - **Language:** Unknown -->
|
|
<!-- - **License:** Unknown -->
|
|
|
|
### Model Sources
|
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
|
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
|
|
|
### Full Model Architecture
|
|
|
|
```
|
|
SentenceTransformer(
|
|
(0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: RobertaModel
|
|
(1): Pooling({'word_embedding_dimension': 768, '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})
|
|
)
|
|
```
|
|
|
|
## Usage
|
|
|
|
### Direct Usage (Sentence Transformers)
|
|
|
|
First install the Sentence Transformers library:
|
|
|
|
```bash
|
|
pip install -U sentence-transformers
|
|
```
|
|
|
|
Then you can load this model and run inference.
|
|
```python
|
|
from sentence_transformers import SentenceTransformer
|
|
|
|
# Download from the 🤗 Hub
|
|
model = SentenceTransformer("NghiBuine/product-search-model")
|
|
# Run inference
|
|
sentences = [
|
|
'Áo thun từ cotton mềm mại, kiểu dáng đa dạng phù hợp cho nhiều phong cách',
|
|
'Áo thun thoải mái',
|
|
'Laptop hiệu năng mạnh mẽ',
|
|
]
|
|
embeddings = model.encode(sentences)
|
|
print(embeddings.shape)
|
|
# [3, 768]
|
|
|
|
# Get the similarity scores for the embeddings
|
|
similarities = model.similarity(embeddings, embeddings)
|
|
print(similarities.shape)
|
|
# [3, 3]
|
|
```
|
|
|
|
<!--
|
|
### Direct Usage (Transformers)
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary>
|
|
|
|
</details>
|
|
-->
|
|
|
|
<!--
|
|
### Downstream Usage (Sentence Transformers)
|
|
|
|
You can finetune this model on your own dataset.
|
|
|
|
<details><summary>Click to expand</summary>
|
|
|
|
</details>
|
|
-->
|
|
|
|
<!--
|
|
### Out-of-Scope Use
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
|
-->
|
|
|
|
## Evaluation
|
|
|
|
### Metrics
|
|
|
|
#### Information Retrieval
|
|
|
|
* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
|
|
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
|
|
|
| Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
|
|
|:--------------------|:-----------|:----------|:--------|:-----------|:-----------|
|
|
| cosine_accuracy@1 | 0.25 | 0.25 | 0.25 | 0.5 | 0.0 |
|
|
| cosine_accuracy@3 | 0.75 | 0.75 | 0.75 | 0.75 | 0.5 |
|
|
| cosine_accuracy@5 | 0.75 | 0.75 | 0.75 | 0.75 | 0.5 |
|
|
| cosine_accuracy@10 | 1.0 | 1.0 | 0.75 | 1.0 | 0.75 |
|
|
| cosine_precision@1 | 0.25 | 0.25 | 0.25 | 0.5 | 0.0 |
|
|
| cosine_precision@3 | 0.25 | 0.25 | 0.25 | 0.25 | 0.1667 |
|
|
| cosine_precision@5 | 0.15 | 0.15 | 0.15 | 0.15 | 0.1 |
|
|
| cosine_precision@10 | 0.1 | 0.1 | 0.075 | 0.1 | 0.075 |
|
|
| cosine_recall@1 | 0.25 | 0.25 | 0.25 | 0.5 | 0.0 |
|
|
| cosine_recall@3 | 0.75 | 0.75 | 0.75 | 0.75 | 0.5 |
|
|
| cosine_recall@5 | 0.75 | 0.75 | 0.75 | 0.75 | 0.5 |
|
|
| cosine_recall@10 | 1.0 | 1.0 | 0.75 | 1.0 | 0.75 |
|
|
| **cosine_ndcg@10** | **0.6377** | **0.608** | **0.5** | **0.7411** | **0.4045** |
|
|
| cosine_mrr@10 | 0.525 | 0.4861 | 0.4167 | 0.6607 | 0.2917 |
|
|
| cosine_map@100 | 0.525 | 0.4861 | 0.4375 | 0.6607 | 0.3095 |
|
|
|
|
<!--
|
|
## Bias, Risks and Limitations
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
|
-->
|
|
|
|
<!--
|
|
### Recommendations
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
|
-->
|
|
|
|
## Training Details
|
|
|
|
### Training Dataset
|
|
|
|
#### json
|
|
|
|
* Dataset: json
|
|
* Size: 33 training samples
|
|
* Columns: <code>positive</code> and <code>anchor</code>
|
|
* Approximate statistics based on the first 33 samples:
|
|
| | positive | anchor |
|
|
|:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
|
|
| type | string | string |
|
|
| details | <ul><li>min: 18 tokens</li><li>mean: 22.82 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 6.97 tokens</li><li>max: 8 tokens</li></ul> |
|
|
* Samples:
|
|
| positive | anchor |
|
|
|:-----------------------------------------------------------------------------------------------|:-----------------------------------------|
|
|
| <code>Áo Sơ Mi Nam Trắng Classic với chất liệu cotton cao cấp, kiểu dáng lịch lãm</code> | <code>Áo sơ mi tinh tế</code> |
|
|
| <code>Đắc Nhân Tâm của Dale Carnegie với những nguyên tắc xây dựng mối quan hệ hiệu quả</code> | <code>Sách kinh điển về giao tiếp</code> |
|
|
| <code>Nike Air Force 1 với thiết kế logo Swoosh và công nghệ Air-Sole</code> | <code>Giày sneaker cổ điển</code> |
|
|
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
|
```json
|
|
{
|
|
"loss": "MultipleNegativesRankingLoss",
|
|
"matryoshka_dims": [
|
|
768,
|
|
512,
|
|
256,
|
|
128,
|
|
64
|
|
],
|
|
"matryoshka_weights": [
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1
|
|
],
|
|
"n_dims_per_step": -1
|
|
}
|
|
```
|
|
|
|
### Training Hyperparameters
|
|
#### Non-Default Hyperparameters
|
|
|
|
- `eval_strategy`: epoch
|
|
- `per_device_train_batch_size`: 32
|
|
- `gradient_accumulation_steps`: 16
|
|
- `learning_rate`: 2e-05
|
|
- `num_train_epochs`: 4
|
|
- `bf16`: True
|
|
- `load_best_model_at_end`: True
|
|
|
|
#### All Hyperparameters
|
|
<details><summary>Click to expand</summary>
|
|
|
|
- `overwrite_output_dir`: False
|
|
- `do_predict`: False
|
|
- `eval_strategy`: epoch
|
|
- `prediction_loss_only`: True
|
|
- `per_device_train_batch_size`: 32
|
|
- `per_device_eval_batch_size`: 8
|
|
- `per_gpu_train_batch_size`: None
|
|
- `per_gpu_eval_batch_size`: None
|
|
- `gradient_accumulation_steps`: 16
|
|
- `eval_accumulation_steps`: None
|
|
- `learning_rate`: 2e-05
|
|
- `weight_decay`: 0.0
|
|
- `adam_beta1`: 0.9
|
|
- `adam_beta2`: 0.999
|
|
- `adam_epsilon`: 1e-08
|
|
- `max_grad_norm`: 1.0
|
|
- `num_train_epochs`: 4
|
|
- `max_steps`: -1
|
|
- `lr_scheduler_type`: linear
|
|
- `lr_scheduler_kwargs`: {}
|
|
- `warmup_ratio`: 0.0
|
|
- `warmup_steps`: 0
|
|
- `log_level`: passive
|
|
- `log_level_replica`: warning
|
|
- `log_on_each_node`: True
|
|
- `logging_nan_inf_filter`: True
|
|
- `save_safetensors`: True
|
|
- `save_on_each_node`: False
|
|
- `save_only_model`: False
|
|
- `restore_callback_states_from_checkpoint`: False
|
|
- `no_cuda`: False
|
|
- `use_cpu`: False
|
|
- `use_mps_device`: False
|
|
- `seed`: 42
|
|
- `data_seed`: None
|
|
- `jit_mode_eval`: False
|
|
- `use_ipex`: False
|
|
- `bf16`: True
|
|
- `fp16`: False
|
|
- `fp16_opt_level`: O1
|
|
- `half_precision_backend`: auto
|
|
- `bf16_full_eval`: False
|
|
- `fp16_full_eval`: False
|
|
- `tf32`: None
|
|
- `local_rank`: 0
|
|
- `ddp_backend`: None
|
|
- `tpu_num_cores`: None
|
|
- `tpu_metrics_debug`: False
|
|
- `debug`: []
|
|
- `dataloader_drop_last`: False
|
|
- `dataloader_num_workers`: 0
|
|
- `dataloader_prefetch_factor`: None
|
|
- `past_index`: -1
|
|
- `disable_tqdm`: False
|
|
- `remove_unused_columns`: True
|
|
- `label_names`: None
|
|
- `load_best_model_at_end`: True
|
|
- `ignore_data_skip`: False
|
|
- `fsdp`: []
|
|
- `fsdp_min_num_params`: 0
|
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
|
- `fsdp_transformer_layer_cls_to_wrap`: None
|
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
|
- `deepspeed`: None
|
|
- `label_smoothing_factor`: 0.0
|
|
- `optim`: adamw_torch
|
|
- `optim_args`: None
|
|
- `adafactor`: False
|
|
- `group_by_length`: False
|
|
- `length_column_name`: length
|
|
- `ddp_find_unused_parameters`: None
|
|
- `ddp_bucket_cap_mb`: None
|
|
- `ddp_broadcast_buffers`: False
|
|
- `dataloader_pin_memory`: True
|
|
- `dataloader_persistent_workers`: False
|
|
- `skip_memory_metrics`: True
|
|
- `use_legacy_prediction_loop`: False
|
|
- `push_to_hub`: False
|
|
- `resume_from_checkpoint`: None
|
|
- `hub_model_id`: None
|
|
- `hub_strategy`: every_save
|
|
- `hub_private_repo`: False
|
|
- `hub_always_push`: False
|
|
- `gradient_checkpointing`: False
|
|
- `gradient_checkpointing_kwargs`: None
|
|
- `include_inputs_for_metrics`: False
|
|
- `eval_do_concat_batches`: True
|
|
- `fp16_backend`: auto
|
|
- `push_to_hub_model_id`: None
|
|
- `push_to_hub_organization`: None
|
|
- `mp_parameters`:
|
|
- `auto_find_batch_size`: False
|
|
- `full_determinism`: False
|
|
- `torchdynamo`: None
|
|
- `ray_scope`: last
|
|
- `ddp_timeout`: 1800
|
|
- `torch_compile`: False
|
|
- `torch_compile_backend`: None
|
|
- `torch_compile_mode`: None
|
|
- `dispatch_batches`: None
|
|
- `split_batches`: None
|
|
- `include_tokens_per_second`: False
|
|
- `include_num_input_tokens_seen`: False
|
|
- `neftune_noise_alpha`: None
|
|
- `optim_target_modules`: None
|
|
- `batch_eval_metrics`: False
|
|
- `prompts`: None
|
|
- `batch_sampler`: batch_sampler
|
|
- `multi_dataset_batch_sampler`: proportional
|
|
|
|
</details>
|
|
|
|
### Training Logs
|
|
| Epoch | Step | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
|
|
|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
|
|
| 1.0 | 1 | 0.6050 | 0.6050 | 0.5 | 0.7083 | 0.5767 |
|
|
| **2.0** | **2** | **0.605** | **0.608** | **0.5** | **0.7411** | **0.4045** |
|
|
| 3.0 | 3 | 0.6377 | 0.6080 | 0.5 | 0.6488 | 0.4045 |
|
|
| 4.0 | 4 | 0.6377 | 0.6080 | 0.5 | 0.7411 | 0.4045 |
|
|
|
|
* The bold row denotes the saved checkpoint.
|
|
|
|
### Framework Versions
|
|
- Python: 3.11.0
|
|
- Sentence Transformers: 3.3.1
|
|
- Transformers: 4.41.2
|
|
- PyTorch: 2.5.1+cu124
|
|
- Accelerate: 1.2.1
|
|
- Datasets: 2.19.1
|
|
- Tokenizers: 0.19.1
|
|
|
|
## Citation
|
|
|
|
### BibTeX
|
|
|
|
#### Sentence Transformers
|
|
```bibtex
|
|
@inproceedings{reimers-2019-sentence-bert,
|
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
|
author = "Reimers, Nils and Gurevych, Iryna",
|
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
|
month = "11",
|
|
year = "2019",
|
|
publisher = "Association for Computational Linguistics",
|
|
url = "https://arxiv.org/abs/1908.10084",
|
|
}
|
|
```
|
|
|
|
#### MatryoshkaLoss
|
|
```bibtex
|
|
@misc{kusupati2024matryoshka,
|
|
title={Matryoshka Representation Learning},
|
|
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
|
year={2024},
|
|
eprint={2205.13147},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.LG}
|
|
}
|
|
```
|
|
|
|
#### MultipleNegativesRankingLoss
|
|
```bibtex
|
|
@misc{henderson2017efficient,
|
|
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
|
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
|
year={2017},
|
|
eprint={1705.00652},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL}
|
|
}
|
|
```
|
|
|
|
<!--
|
|
## Glossary
|
|
|
|
*Clearly define terms in order to be accessible across audiences.*
|
|
-->
|
|
|
|
<!--
|
|
## Model Card Authors
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
|
-->
|
|
|
|
<!--
|
|
## Model Card Contact
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
|
--> |
