adejumobi's picture
Update README.md
04724ff verified
---
language:
- yo
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:5019
- loss:TripletLoss
base_model: Davlan/bert-base-multilingual-cased-finetuned-yoruba
datasets:
- embedding-data/QQP_triplets
metrics:
- cosine_accuracy
- dot_accuracy
- manhattan_accuracy
- euclidean_accuracy
- max_accuracy
widget:
- source_sentence: Bawo ni eniyan lasan ṣe le ṣe agbaye ni aye ti o dara julọ?
sentences:
- Ewo ni fiimu ti o dara julọ ti agbaye?
- >-
Bawo ni a ṣe le ṣe agbaye ni aye ti o dara julọ fun gbogbo ati fun iran
iwaju lati wa?
- Njẹ aiye yii dara julọ tabi buru?
- source_sentence: Ni Pokemon ati tẹmpili ti okun, kilode ti o yanilenu Manicy?
sentences:
- Kini idi ti Manafy ọmọ-ọwọ ni Pokémon ger ati tẹmpili ti okun?
- Bawo ni awọn ibeere mi ṣe wa nigbagbogbo nigbagbogbo lori Quora?
- Ṣe "Pokémon ti o wuyi ati tẹmpili ti Okun" ka akọku?
- source_sentence: Kini itumo igbesi aye yii?
sentences:
- Kini "Gbe igbesi aye rẹ" tumọ si?
- Kini o ro pe o jẹ itumọ ti igbesi aye?
- >-
Nitorinaa bawo ni MO ṣe le gba meth lati fulu jade ninu ara ni awọn wakati 2
ṣaaju idanwo togbo kan?
- source_sentence: >-
Nibo ni MO le gba ọpọlọpọ awọn aso deede, awọn aṣọ alekun & awọn aṣọ irọlẹ
ni goolu ni eti okun?
sentences:
- >-
Nibo ni MO le gba ọpọlọpọ awọn awọ ati titobi fun awọn aṣọ awọn alagbaje ni
Gold Coast?
- >-
Kini yoo ṣẹlẹ ti o ba jẹ ki o dina nkan bi Facebook tabi Google ni isansa ti
iṣan neta?
- Nibo ni MO le gba ikojọpọ ti o lẹwa fun awọn aṣọ igbeyawo ni Sydney?
- source_sentence: Kini o yẹ ki Ilu India ṣe lori ikọlu UI?
sentences:
- Bawo ni MO ṣe sọ Gẹẹsi leta ni ifọrọwanilẹnuwo kan?
- >-
Lẹhin gbogbo họọsi ti media media ti ṣẹda awọn ikọlu URI Wip, kii yoo jẹ
ohun itiju fun India ti ko ba kọlu Pakistan?
- Bawo ni India le dahun si ikọlu ẹru UI?
pipeline_tag: sentence-similarity
model-index:
- name: >-
SentenceTransformer based on
Davlan/bert-base-multilingual-cased-finetuned-yoruba
results:
- task:
type: triplet
name: Triplet
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy
value: 0.865
name: Cosine Accuracy
- type: dot_accuracy
value: 0.135
name: Dot Accuracy
- type: manhattan_accuracy
value: 0.868
name: Manhattan Accuracy
- type: euclidean_accuracy
value: 0.868
name: Euclidean Accuracy
- type: max_accuracy
value: 0.868
name: Max Accuracy
---
# SentenceTransformer based on Davlan/bert-base-multilingual-cased-finetuned-yoruba
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Davlan/bert-base-multilingual-cased-finetuned-yoruba](https://huggingface.co/Davlan/bert-base-multilingual-cased-finetuned-yoruba). 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:** [Davlan/bert-base-multilingual-cased-finetuned-yoruba](https://huggingface.co/Davlan/bert-base-multilingual-cased-finetuned-yoruba) <!-- at revision 000f80b4509f73bca9a33f9db0573d6f67396a12 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **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': 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("adejumobi/bert-base-multilingual-cased-finetuned-yoruba-IR")
# Run inference
sentences = [
'Kini o yẹ ki Ilu India ṣe lori ikọlu UI?',
'Bawo ni India le dahun si ikọlu ẹru UI?',
'Lẹhin gbogbo họọsi ti media media ti ṣẹda awọn ikọlu URI Wip, kii yoo jẹ ohun itiju fun India ti ko ba kọlu Pakistan?',
]
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
#### Triplet
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
| Metric | Value |
|:--------------------|:----------|
| **cosine_accuracy** | **0.865** |
| dot_accuracy | 0.135 |
| manhattan_accuracy | 0.868 |
| euclidean_accuracy | 0.868 |
| max_accuracy | 0.868 |
<!--
## 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
#### Unnamed Dataset
* Size: 5,019 training samples
* Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
* Approximate statistics based on the first 1000 samples:
| | query | pos | neg |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 5 tokens</li><li>mean: 24.62 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 24.14 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.71 tokens</li><li>max: 98 tokens</li></ul> |
* Samples:
| query | pos | neg |
|:-------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
| <code>Kini idi ti Ilu India ṣe a ko ni ọkan lori ijiroro oloselu kan bi ni AMẸRIKA?</code> | <code>Kini idi ti a ko le ni ijiroro gbangba laarin awọn oloselu ni India bi ọkan ninu wa?</code> | <code>Njẹ eniyan le da quo duro de India Pakistan ariyanjiyan?A ni aisan ati ti o ri eyi lojoojumọ ni olopo?</code> |
| <code>Kini OnePlus Ọkan?</code> | <code>Bawo ni OnePlus kan?</code> | <code>Kini idi ti OnePlus Ọkan dara?</code> |
| <code>Ṣe ọkan wa ṣe iṣakoso awọn ẹdun wa?</code> | <code>Bawo ni ọlọgbọn ati awọn eniyan aṣeyọri ṣe ṣakoso awọn ẹdun wọn?</code> | <code>Bawo ni MO ṣe le ṣakoso awọn ẹdun mi rere fun awọn eniyan ti Mo nifẹ ṣugbọn wọn ko bikita nipa mi?</code> |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Evaluation Dataset
#### Unnamed Dataset
* Size: 1,000 evaluation samples
* Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
* Approximate statistics based on the first 1000 samples:
| | query | pos | neg |
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string | string |
| details | <ul><li>min: 6 tokens</li><li>mean: 24.32 tokens</li><li>max: 94 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 24.06 tokens</li><li>max: 115 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 25.58 tokens</li><li>max: 121 tokens</li></ul> |
* Samples:
| query | pos | neg |
|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
| <code>Bawo ni o jẹ ọjọ ebi?</code> | <code>Bawo ni o jẹ ọsan</code> | <code>Njẹ NEBM lueMo ṣẹlẹ lati wa awọn ifiweranṣẹ ti o sọ pe o jẹ iro ati pe ko ni itter</code> |
| <code>Kini awọn ohun elo akọkọ ti kọnputa kan?</code> | <code>Kini diẹ ninu awọn ẹya akọkọ ti kọnputa kan?Awọn iṣẹ wo ni wọn nṣe iranṣẹ?</code> | <code>Kini awọn eto kọmputa?Kini awọn iṣẹ ti awọn eto kọnputa?</code> |
| <code>Ṣe o le faffiti Artists fun sokiri Graffiti ni Rockdale County, GA?</code> | <code>Ṣe o le fun awọn ojukokoro fun fun sokiri Graffiti ni Cockdale County, Georgia?</code> | <code>Kini idi ti Graffiti jẹ arufin?</code> |
* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
```json
{
"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
"triplet_margin": 5
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 12
- `per_device_eval_batch_size`: 3
- `learning_rate`: 1e-05
- `num_train_epochs`: 5
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 12
- `per_device_eval_batch_size`: 3
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 1e-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`: 5
- `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`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
</details>
### Training Logs
| Epoch | Step | Training Loss | loss | cosine_accuracy |
|:------:|:----:|:-------------:|:------:|:---------------:|
| 0 | 0 | - | - | 0.827 |
| 0.2387 | 100 | 4.247 | 3.6056 | 0.815 |
| 0.4773 | 200 | 3.3576 | 2.7548 | 0.809 |
| 0.7160 | 300 | 2.931 | 2.3805 | 0.843 |
| 0.9547 | 400 | 2.4476 | 2.1895 | 0.858 |
| 1.1933 | 500 | 2.5839 | 2.1148 | 0.854 |
| 1.4320 | 600 | 2.0645 | 2.0497 | 0.855 |
| 1.6706 | 700 | 1.8386 | 2.0328 | 0.847 |
| 1.9093 | 800 | 1.5527 | 1.9380 | 0.857 |
| 2.1480 | 900 | 1.7298 | 1.8999 | 0.861 |
| 2.3866 | 1000 | 1.4375 | 1.8744 | 0.855 |
| 2.6253 | 1100 | 1.1605 | 1.8761 | 0.861 |
| 2.8640 | 1200 | 1.0601 | 1.8658 | 0.862 |
| 3.1026 | 1300 | 1.1019 | 1.8181 | 0.861 |
| 3.3413 | 1400 | 1.052 | 1.8088 | 0.854 |
| 3.5800 | 1500 | 0.8807 | 1.7937 | 0.862 |
| 3.8186 | 1600 | 0.7877 | 1.7963 | 0.862 |
| 4.0573 | 1700 | 0.7613 | 1.7869 | 0.868 |
| 4.2959 | 1800 | 0.8018 | 1.7696 | 0.867 |
| 4.5346 | 1900 | 0.6717 | 1.7815 | 0.865 |
| 4.7733 | 2000 | 0.6603 | 1.7776 | 0.865 |
### Framework Versions
- Python: 3.10.13
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.1.2
- Accelerate: 0.31.0
- Datasets: 2.19.2
- 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",
}
```
#### TripletLoss
```bibtex
@misc{hermans2017defense,
title={In Defense of the Triplet Loss for Person Re-Identification},
author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
year={2017},
eprint={1703.07737},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
<!--
## 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.*
-->