4bs4lr2 / README.md
cassador's picture
Add new SentenceTransformer model.
13666b1 verified
---
base_model: indobenchmark/indobert-base-p2
datasets:
- afaji/indonli
language:
- id
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:6915
- loss:SoftmaxLoss
widget:
- source_sentence: Pesta Olahraga Asia Tenggara atau Southeast Asian Games, biasa
disingkat SEA Games, adalah ajang olahraga yang diadakan setiap dua tahun dan
melibatkan 11 negara Asia Tenggara.
sentences:
- Sekarang tahun 2017.
- Warna kulit tidak mempengaruhi waktu berjemur yang baik untuk mengatifkan pro-vitamin
D3.
- Pesta Olahraga Asia Tenggara diadakan setiap tahun.
- source_sentence: Menjalani aktivitas Ramadhan di tengah wabah Corona tentunya tidak
mudah.
sentences:
- Tidak ada observasi yang pernah dilansir oleh Business Insider.
- Wabah Corona membuat aktivitas Ramadhan tidak mudah dijalani.
- Piala Sudirman pertama digelar pada tahun 1989.
- source_sentence: Dalam bidang politik, partai ini memperjuangkan agar kekuasaan
sepenuhnya berada di tangan rakyat.
sentences:
- Galileo tidak berhasil mengetes hasil dari Hukum Inert.
- Kudeta 14 Februari 1946 gagal merebut kekuasaan Belanda.
- Partai ini berusaha agar kekuasaan sepenuhnya berada di tangan rakyat.
- source_sentence: Keluarga mendiang Prince menuduh layanan musik streaming Tidal
memasukkan karya milik sang penyanyi legendaris tanpa izin .
sentences:
- Rosier adalah pelayan setia Lord Voldemort.
- Bangunan ini digunakan untuk penjualan.
- Keluarga mendiang Prince sudah memberi izin kepada TImbal untuk menggunakan lagu
milik Prince.
- source_sentence: Tujuan dari acara dengar pendapat CRTC adalah untuk mengumpulkan
respons dari pada pemangku kepentingan industri ini dan dari masyarakat umum.
sentences:
- Pembuat Rooms hanya bisa membuat meeting yang terbuka.
- Masyarakat umum dilibatkan untuk memberikan respon dalam acara dengar pendapat
CRTC.
- Eminem dirasa tidak akan memulai kembali kariernya tahun ini.
model-index:
- name: SentenceTransformer based on indobenchmark/indobert-base-p2
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts dev
type: sts-dev
metrics:
- type: pearson_cosine
value: 0.6086483919467034
name: Pearson Cosine
- type: spearman_cosine
value: 0.5957239631216208
name: Spearman Cosine
- type: pearson_manhattan
value: 0.5922712402608701
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.587803408019803
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6025076942104072
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.5921960802996976
name: Spearman Euclidean
- type: pearson_dot
value: 0.6142627736326208
name: Pearson Dot
- type: spearman_dot
value: 0.6070693135603054
name: Spearman Dot
- type: pearson_max
value: 0.6142627736326208
name: Pearson Max
- type: spearman_max
value: 0.6070693135603054
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test
type: sts-test
metrics:
- type: pearson_cosine
value: 0.3358355665097759
name: Pearson Cosine
- type: spearman_cosine
value: 0.30366523911959453
name: Spearman Cosine
- type: pearson_manhattan
value: 0.2926304091437024
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.2892617235512195
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.307849173953621
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.29286510016277595
name: Spearman Euclidean
- type: pearson_dot
value: 0.3501215321086179
name: Pearson Dot
- type: spearman_dot
value: 0.33369282261837974
name: Spearman Dot
- type: pearson_max
value: 0.3501215321086179
name: Pearson Max
- type: spearman_max
value: 0.33369282261837974
name: Spearman Max
---
# SentenceTransformer based on indobenchmark/indobert-base-p2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on the [afaji/indonli](https://huggingface.co/datasets/afaji/indonli) 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:** [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) <!-- at revision 94b4e0a82081fa57f227fcc2024d1ea89b57ac1f -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [afaji/indonli](https://huggingface.co/datasets/afaji/indonli)
- **Language:** id
<!-- - **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': 512, 'do_lower_case': False}) with Transformer model: BertModel
(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("cassador/4bs4lr2")
# Run inference
sentences = [
'Tujuan dari acara dengar pendapat CRTC adalah untuk mengumpulkan respons dari pada pemangku kepentingan industri ini dan dari masyarakat umum.',
'Masyarakat umum dilibatkan untuk memberikan respon dalam acara dengar pendapat CRTC.',
'Pembuat Rooms hanya bisa membuat meeting yang terbuka.',
]
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
#### Semantic Similarity
* Dataset: `sts-dev`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.6086 |
| **spearman_cosine** | **0.5957** |
| pearson_manhattan | 0.5923 |
| spearman_manhattan | 0.5878 |
| pearson_euclidean | 0.6025 |
| spearman_euclidean | 0.5922 |
| pearson_dot | 0.6143 |
| spearman_dot | 0.6071 |
| pearson_max | 0.6143 |
| spearman_max | 0.6071 |
#### Semantic Similarity
* Dataset: `sts-test`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.3358 |
| **spearman_cosine** | **0.3037** |
| pearson_manhattan | 0.2926 |
| spearman_manhattan | 0.2893 |
| pearson_euclidean | 0.3078 |
| spearman_euclidean | 0.2929 |
| pearson_dot | 0.3501 |
| spearman_dot | 0.3337 |
| pearson_max | 0.3501 |
| spearman_max | 0.3337 |
<!--
## 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
#### afaji/indonli
* Dataset: [afaji/indonli](https://huggingface.co/datasets/afaji/indonli)
* Size: 6,915 training samples
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | premise | hypothesis | label |
|:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 12 tokens</li><li>mean: 29.26 tokens</li><li>max: 135 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.13 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>0: ~51.00%</li><li>1: ~49.00%</li></ul> |
* Samples:
| premise | hypothesis | label |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------|:---------------|
| <code>Presiden Joko Widodo (Jokowi) menyampaikan prediksi bahwa wabah virus Corona (COVID-19) di Indonesia akan selesai akhir tahun ini.</code> | <code>Prediksi akhir wabah tidak disampaikan Jokowi.</code> | <code>0</code> |
| <code>Meski biasanya hanya digunakan di fasilitas kesehatan, saat ini masker dan sarung tangan sekali pakai banyak dipakai di tingkat rumah tangga.</code> | <code>Masker sekali pakai banyak dipakai di tingkat rumah tangga.</code> | <code>1</code> |
| <code>Seperti namanya, paket internet sahur Telkomsel ini ditujukan bagi pengguna yang menginginkan kuota ekstra, untuk menemani momen sahur sepanjang bulan puasa.</code> | <code>Paket internet sahur tidak ditujukan untuk saat sahur.</code> | <code>0</code> |
* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
### Evaluation Dataset
#### afaji/indonli
* Dataset: [afaji/indonli](https://huggingface.co/datasets/afaji/indonli)
* Size: 1,556 evaluation samples
* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
| | premise | hypothesis | label |
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details | <ul><li>min: 9 tokens</li><li>mean: 28.07 tokens</li><li>max: 179 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.15 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>0: ~47.90%</li><li>1: ~52.10%</li></ul> |
* Samples:
| premise | hypothesis | label |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:---------------|
| <code>Manuskrip tersebut berisi tiga catatan yang menceritakan bagaimana peristiwa jatuhnya meteorit serta laporan kematian akibat kejadian tersebut seperti dilansir dari Science Alert, Sabtu (25/4/2020).</code> | <code>Manuskrip tersebut tidak mencatat laporan kematian.</code> | <code>0</code> |
| <code>Dilansir dari Business Insider, menurut observasi dari Mauna Loa Observatory di Hawaii pada karbon dioksida (CO2) di level mencapai 410 ppm tidak langsung memberikan efek pada pernapasan, karena tubuh manusia juga masih membutuhkan CO2 dalam kadar tertentu.</code> | <code>Tidak ada observasi yang pernah dilansir oleh Business Insider.</code> | <code>0</code> |
| <code>Seorang wanita asal New York mengaku sangat benci air putih.</code> | <code>Tidak ada orang dari New York yang membenci air putih.</code> | <code>0</code> |
* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 4
- `per_device_eval_batch_size`: 4
- `learning_rate`: 2e-05
- `num_train_epochs`: 4
- `warmup_ratio`: 0.1
- `fp16`: 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`: 4
- `per_device_eval_batch_size`: 4
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `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`: 0.1
- `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`: False
- `fp16`: True
- `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`: False
- `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
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
|:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
| 0 | 0 | - | - | 0.1277 | - |
| 0.0578 | 100 | 0.706 | - | - | - |
| 0.1157 | 200 | 0.6251 | - | - | - |
| 0.1735 | 300 | 0.509 | - | - | - |
| 0.2313 | 400 | 0.5822 | - | - | - |
| 0.2892 | 500 | 0.6089 | - | - | - |
| 0.3470 | 600 | 0.5497 | - | - | - |
| 0.4049 | 700 | 0.6176 | - | - | - |
| 0.4627 | 800 | 0.584 | - | - | - |
| 0.5205 | 900 | 0.5317 | - | - | - |
| 0.5784 | 1000 | 0.6706 | - | - | - |
| 0.6362 | 1100 | 0.5508 | - | - | - |
| 0.6940 | 1200 | 0.569 | - | - | - |
| 0.7519 | 1300 | 0.6095 | - | - | - |
| 0.8097 | 1400 | 0.5107 | - | - | - |
| 0.8676 | 1500 | 0.5799 | - | - | - |
| 0.9254 | 1600 | 0.5481 | - | - | - |
| 0.9832 | 1700 | 0.4749 | - | - | - |
| 1.0 | 1729 | - | 0.4679 | 0.5346 | - |
| 1.0411 | 1800 | 0.4321 | - | - | - |
| 1.0989 | 1900 | 0.4594 | - | - | - |
| 1.1567 | 2000 | 0.4428 | - | - | - |
| 1.2146 | 2100 | 0.479 | - | - | - |
| 1.2724 | 2200 | 0.3944 | - | - | - |
| 1.3302 | 2300 | 0.434 | - | - | - |
| 1.3881 | 2400 | 0.3981 | - | - | - |
| 1.4459 | 2500 | 0.5058 | - | - | - |
| 1.5038 | 2600 | 0.4254 | - | - | - |
| 1.5616 | 2700 | 0.5089 | - | - | - |
| 1.6194 | 2800 | 0.4669 | - | - | - |
| 1.6773 | 2900 | 0.5093 | - | - | - |
| 1.7351 | 3000 | 0.4673 | - | - | - |
| 1.7929 | 3100 | 0.4964 | - | - | - |
| 1.8508 | 3200 | 0.366 | - | - | - |
| 1.9086 | 3300 | 0.5168 | - | - | - |
| 1.9665 | 3400 | 0.4976 | - | - | - |
| 2.0 | 3458 | - | 0.4956 | 0.5756 | - |
| 2.0243 | 3500 | 0.4112 | - | - | - |
| 2.0821 | 3600 | 0.3139 | - | - | - |
| 2.1400 | 3700 | 0.2579 | - | - | - |
| 2.1978 | 3800 | 0.3207 | - | - | - |
| 2.2556 | 3900 | 0.2962 | - | - | - |
| 2.3135 | 4000 | 0.3924 | - | - | - |
| 2.3713 | 4100 | 0.3059 | - | - | - |
| 2.4291 | 4200 | 0.2762 | - | - | - |
| 2.4870 | 4300 | 0.3425 | - | - | - |
| 2.5448 | 4400 | 0.3165 | - | - | - |
| 2.6027 | 4500 | 0.2786 | - | - | - |
| 2.6605 | 4600 | 0.3183 | - | - | - |
| 2.7183 | 4700 | 0.4492 | - | - | - |
| 2.7762 | 4800 | 0.2414 | - | - | - |
| 2.8340 | 4900 | 0.3064 | - | - | - |
| 2.8918 | 5000 | 0.3164 | - | - | - |
| 2.9497 | 5100 | 0.2612 | - | - | - |
| 3.0 | 5187 | - | 0.8414 | 0.6116 | - |
| 3.0075 | 5200 | 0.318 | - | - | - |
| 3.0654 | 5300 | 0.201 | - | - | - |
| 3.1232 | 5400 | 0.1045 | - | - | - |
| 3.1810 | 5500 | 0.1038 | - | - | - |
| 3.2389 | 5600 | 0.1365 | - | - | - |
| 3.2967 | 5700 | 0.1279 | - | - | - |
| 3.3545 | 5800 | 0.2304 | - | - | - |
| 3.4124 | 5900 | 0.1515 | - | - | - |
| 3.4702 | 6000 | 0.1682 | - | - | - |
| 3.5281 | 6100 | 0.2008 | - | - | - |
| 3.5859 | 6200 | 0.1955 | - | - | - |
| 3.6437 | 6300 | 0.103 | - | - | - |
| 3.7016 | 6400 | 0.1482 | - | - | - |
| 3.7594 | 6500 | 0.1093 | - | - | - |
| 3.8172 | 6600 | 0.1478 | - | - | - |
| 3.8751 | 6700 | 0.1708 | - | - | - |
| 3.9329 | 6800 | 0.2399 | - | - | - |
| 3.9907 | 6900 | 0.1805 | - | - | - |
| 4.0 | 6916 | - | 1.0672 | 0.5957 | 0.3037 |
### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- Tokenizers: 0.19.1
## Citation
### BibTeX
#### Sentence Transformers and SoftmaxLoss
```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",
}
```
<!--
## 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.*
-->