Add new SentenceTransformer model.

bd78e4f verified 3 months ago

19.2 kB

	---
	base_model: intfloat/multilingual-e5-small
	datasets: []
	language: []
	library_name: sentence-transformers
	metrics:
	- cosine_accuracy
	- dot_accuracy
	- manhattan_accuracy
	- euclidean_accuracy
	- max_accuracy
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:546
	- loss:TripletLoss
	widget:
	- source_sentence: How to cook a turkey?
	sentences:
	- How to make a turkey sandwich?
	- World's biggest desert by area
	- Steps to roast a turkey
	- source_sentence: What is the best way to learn a new language?
	sentences:
	- Author of the play 'Hamlet'
	- What is the fastest way to travel?
	- How can I effectively learn a new language?
	- source_sentence: Who wrote 'To Kill a Mockingbird'?
	sentences:
	- Who wrote 'The Great Gatsby'?
	- How can I effectively save money?
	- Author of 'To Kill a Mockingbird'
	- source_sentence: Who was the first person to climb Mount Everest?
	sentences:
	- Steps to visit the Great Wall of China
	- Who was the first person to climb K2?
	- First climber to reach the summit of Everest
	- source_sentence: What is the capital city of Canada?
	sentences:
	- First circumnavigator of the globe
	- What is the capital of Canada?
	- What is the capital city of Australia?
	model-index:
	- name: SentenceTransformer based on intfloat/multilingual-e5-small
	results:
	- task:
	type: triplet
	name: Triplet
	dataset:
	name: triplet validation
	type: triplet-validation
	metrics:
	- type: cosine_accuracy
	value: 0.9836065573770492
	name: Cosine Accuracy
	- type: dot_accuracy
	value: 0.01639344262295082
	name: Dot Accuracy
	- type: manhattan_accuracy
	value: 0.9836065573770492
	name: Manhattan Accuracy
	- type: euclidean_accuracy
	value: 0.9836065573770492
	name: Euclidean Accuracy
	- type: max_accuracy
	value: 0.9836065573770492
	name: Max Accuracy
	---

	# SentenceTransformer based on intfloat/multilingual-e5-small

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). 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.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 384 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': 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})
	(2): Normalize()
	)
	```

	## 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("srikarvar/multilingual-e5-small-triplet-final-2")
	# Run inference
	sentences = [
	'What is the capital city of Canada?',
	'What is the capital of Canada?',
	'What is the capital city of Australia?',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 384]

	# 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
	* Dataset: `triplet-validation`
	* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)

	\| Metric \| Value \|
	\|:-------------------\|:-----------\|
	\| cosine_accuracy \| 0.9836 \|
	\| dot_accuracy \| 0.0164 \|
	\| manhattan_accuracy \| 0.9836 \|
	\| euclidean_accuracy \| 0.9836 \|
	\| max_accuracy \| 0.9836 \|

	<!--
	## 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: 546 training samples
	* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| anchor \| positive \| negative \|
	\|:--------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \| string \|
	\| details \| <ul><li>min: 6 tokens</li><li>mean: 10.78 tokens</li><li>max: 22 tokens</li></ul> \| <ul><li>min: 4 tokens</li><li>mean: 9.52 tokens</li><li>max: 19 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 10.75 tokens</li><li>max: 22 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \| negative \|
	\|:-----------------------------------------------------\|:----------------------------------------------\|:-------------------------------------------------------\|
	\| <code>What is the capital of Brazil?</code> \| <code>Capital city of Brazil</code> \| <code>What is the capital of Argentina?</code> \|
	\| <code>How do I install Python on my computer?</code> \| <code>How do I set up Python on my PC?</code> \| <code>How do I uninstall Python on my computer?</code> \|
	\| <code>How do I apply for a credit card?</code> \| <code>How do I get a credit card?</code> \| <code>How do I cancel a credit card?</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": 0.7
	}
	```

	### Evaluation Dataset

	#### Unnamed Dataset


	* Size: 61 evaluation samples
	* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| anchor \| positive \| negative \|
	\|:--------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \| string \|
	\| details \| <ul><li>min: 7 tokens</li><li>mean: 10.66 tokens</li><li>max: 16 tokens</li></ul> \| <ul><li>min: 5 tokens</li><li>mean: 9.43 tokens</li><li>max: 14 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 10.54 tokens</li><li>max: 17 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \| negative \|
	\|:---------------------------------------------------\|:---------------------------------------------------------\|:-----------------------------------------------------\|
	\| <code>How to create a podcast?</code> \| <code>Steps to start a podcast</code> \| <code>How to create a vlog?</code> \|
	\| <code>How many states are there in the USA?</code> \| <code>Total number of states in the United States</code> \| <code>How many provinces are there in Canada?</code> \|
	\| <code>What is the population of India?</code> \| <code>How many people live in India?</code> \| <code>What is the population of China?</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": 0.7
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: epoch
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 32
	- `gradient_accumulation_steps`: 2
	- `learning_rate`: 3e-06
	- `weight_decay`: 0.01
	- `num_train_epochs`: 22
	- `lr_scheduler_type`: cosine
	- `warmup_steps`: 50
	- `load_best_model_at_end`: True
	- `optim`: adamw_torch_fused

	#### 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`: 32
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 2
	- `eval_accumulation_steps`: None
	- `learning_rate`: 3e-06
	- `weight_decay`: 0.01
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 22
	- `max_steps`: -1
	- `lr_scheduler_type`: cosine
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.0
	- `warmup_steps`: 50
	- `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`: 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_fused
	- `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 \| triplet-validation_max_accuracy \|
	\|:--------:\|:-------:\|:-------------:\|:----------:\|:-------------------------------:\|
	\| 1.0 \| 9 \| - \| 0.6381 \| - \|
	\| 1.1111 \| 10 \| 0.6743 \| - \| - \|
	\| 2.0 \| 18 \| - \| 0.6262 \| - \|
	\| 2.2222 \| 20 \| 0.6608 \| - \| - \|
	\| 3.0 \| 27 \| - \| 0.6066 \| - \|
	\| 3.3333 \| 30 \| 0.6517 \| - \| - \|
	\| 4.0 \| 36 \| - \| 0.5795 \| - \|
	\| 4.4444 \| 40 \| 0.6288 \| - \| - \|
	\| 5.0 \| 45 \| - \| 0.5453 \| - \|
	\| 5.5556 \| 50 \| 0.5934 \| - \| - \|
	\| 6.0 \| 54 \| - \| 0.5052 \| - \|
	\| 6.6667 \| 60 \| 0.5708 \| - \| - \|
	\| 7.0 \| 63 \| - \| 0.4652 \| - \|
	\| 7.7778 \| 70 \| 0.5234 \| - \| - \|
	\| 8.0 \| 72 \| - \| 0.4270 \| - \|
	\| 8.8889 \| 80 \| 0.5041 \| - \| - \|
	\| 9.0 \| 81 \| - \| 0.3918 \| - \|
	\| 10.0 \| 90 \| 0.4666 \| 0.3589 \| - \|
	\| 11.0 \| 99 \| - \| 0.3292 \| - \|
	\| 11.1111 \| 100 \| 0.4554 \| - \| - \|
	\| 12.0 \| 108 \| - \| 0.3029 \| - \|
	\| 12.2222 \| 110 \| 0.4208 \| - \| - \|
	\| 13.0 \| 117 \| - \| 0.2797 \| - \|
	\| 13.3333 \| 120 \| 0.4076 \| - \| - \|
	\| 14.0 \| 126 \| - \| 0.2607 \| - \|
	\| 14.4444 \| 130 \| 0.3958 \| - \| - \|
	\| 15.0 \| 135 \| - \| 0.2471 \| - \|
	\| 15.5556 \| 140 \| 0.3881 \| - \| - \|
	\| 16.0 \| 144 \| - \| 0.2365 \| - \|
	\| 16.6667 \| 150 \| 0.3595 \| - \| - \|
	\| 17.0 \| 153 \| - \| 0.2286 \| - \|
	\| 17.7778 \| 160 \| 0.354 \| - \| - \|
	\| 18.0 \| 162 \| - \| 0.2232 \| - \|
	\| 18.8889 \| 170 \| 0.3506 \| - \| - \|
	\| 19.0 \| 171 \| - \| 0.2199 \| - \|
	\| 20.0 \| 180 \| 0.3555 \| 0.2182 \| - \|
	\| 21.0 \| 189 \| - \| 0.2175 \| - \|
	\| 21.1111 \| 190 \| 0.3526 \| - \| - \|
	\| 22.0 \| 198 \| - \| 0.2174 \| 0.9836 \|

	* The bold row denotes the saved checkpoint.

	### Framework Versions
	- Python: 3.10.12
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.1.2+cu121
	- Accelerate: 0.32.1
	- 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",
	}
	```

	#### 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.
	-->