Add new SentenceTransformer model

54f4e7b verified 10 days ago

22.9 kB

	---
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dense
	- generated_from_trainer
	- dataset_size:200000
	- loss:MSELoss
	base_model: nreimers/TinyBERT_L-4_H-312_v2
	widget:
	- source_sentence: At an outdoor event in an Asian-themed area, a crowd congregates
	as one person in a yellow Chinese dragon costume confronts the camera.
	sentences:
	- Boy dressed in blue holds a toy.
	- the animal is running
	- Two young asian men are squatting.
	- source_sentence: A man with a shopping cart is studying the shelves in a supermarket
	aisle.
	sentences:
	- The children are watching TV at home.
	- Three young boys one is holding a camera and another is holding a green toy all
	are wearing t-shirt and smiling.
	- A large group of people are gathered outside of a brick building lit with spotlights.
	- source_sentence: The door is open.
	sentences:
	- A girl is using an apple laptop with her headphones in her ears.
	- There are three men in this picture, two are on motorbikes, one of the men has
	a large piece of furniture on the back of his bike, the other is about to be handed
	a piece of paper by a man in a white shirt.
	- Three girls are standing together in a room, one is listening, one is writing
	on a wall and the third is talking to them.
	- source_sentence: A small group of children are standing in a classroom and one of
	them has a foot in a trashcan, which also has a rope leading out of it.
	sentences:
	- People are playing music.
	- Children are swimming at the beach.
	- Women are celebrating at a bar.
	- source_sentence: A black dog is drinking next to a brown and white dog that is looking
	at an orange ball in the lake, whilst a horse and rider passes behind.
	sentences:
	- Some men with jerseys are in a bar, watching a soccer match.
	- the guy is dead
	- There are two people running around a track in lane three and the one wearing
	a blue shirt with a green thing over the eyes is just barely ahead of the guy
	wearing an orange shirt and sunglasses.
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	metrics:
	- pearson_cosine
	- spearman_cosine
	- negative_mse
	co2_eq_emissions:
	emissions: 2.8523555208748004
	energy_consumed: 0.010658150379545777
	source: codecarbon
	training_type: fine-tuning
	on_cloud: false
	cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
	ram_total_size: 31.777088165283203
	hours_used: 0.06
	hardware_used: 1 x NVIDIA GeForce RTX 3090
	model-index:
	- name: SentenceTransformer based on nreimers/TinyBERT_L-4_H-312_v2
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev
	type: sts-dev
	metrics:
	- type: pearson_cosine
	value: 0.808118809417341
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8213188524284026
	name: Spearman Cosine
	- task:
	type: knowledge-distillation
	name: Knowledge Distillation
	dataset:
	name: Unknown
	type: unknown
	metrics:
	- type: negative_mse
	value: -78.18629741668701
	name: Negative Mse
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts test
	type: sts-test
	metrics:
	- type: pearson_cosine
	value: 0.7496317179823885
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.7520734191438844
	name: Spearman Cosine
	---

	# SentenceTransformer based on nreimers/TinyBERT_L-4_H-312_v2

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nreimers/TinyBERT_L-4_H-312_v2](https://huggingface.co/nreimers/TinyBERT_L-4_H-312_v2). It maps sentences & paragraphs to a 312-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: [nreimers/TinyBERT_L-4_H-312_v2](https://huggingface.co/nreimers/TinyBERT_L-4_H-312_v2) <!-- at revision d782507ee95c6565fe5924fcd6090999055e8db6 -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 312 dimensions
	- 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/huggingface/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, 'architecture': 'BertModel'})
	(1): Pooling({'word_embedding_dimension': 312, '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("tomaarsen/TinyBERT_L-4_H-312_v2-distilled-from-stsb-roberta-base-v2-L2-normalized")
	# Run inference
	sentences = [
	'A black dog is drinking next to a brown and white dog that is looking at an orange ball in the lake, whilst a horse and rider passes behind.',
	'Some men with jerseys are in a bar, watching a soccer match.',
	'There are two people running around a track in lane three and the one wearing a blue shirt with a green thing over the eyes is just barely ahead of the guy wearing an orange shirt and sunglasses.',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 312]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[ 1.0000, -0.0448, 0.0490],
	# [-0.0448, 1.0000, 0.3433],
	# [ 0.0490, 0.3433, 1.0000]])
	```

	<!--
	### 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

	* Datasets: `sts-dev` and `sts-test`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| sts-dev \| sts-test \|
	\|:--------------------\|:-----------\|:-----------\|
	\| pearson_cosine \| 0.8081 \| 0.7496 \|
	\| spearman_cosine \| 0.8213 \| 0.7521 \|

	#### Knowledge Distillation

	* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)

	\| Metric \| Value \|
	\|:-----------------\|:-------------\|
	\| negative_mse \| -78.1863 \|

	<!--
	## 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: 200,000 training samples
	* Columns: <code>sentence</code> and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:-------------------------------------\|
	\| type \| string \| list \|
	\| details \| <ul><li>min: 4 tokens</li><li>mean: 12.24 tokens</li><li>max: 52 tokens</li></ul> \| <ul><li>size: 312 elements</li></ul> \|
	* Samples:
	\| sentence \| label \|
	\|:---------------------------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>A person on a horse jumps over a broken down airplane.</code> \| <code>[0.005435045808553696, 0.042343951761722565, -0.1521506905555725, 0.10078108310699463, 0.06585284322500229, ...]</code> \|
	\| <code>Children smiling and waving at camera</code> \| <code>[-0.14921779930591583, 0.17264199256896973, 0.3912944793701172, 0.2817707657814026, -0.1517026573419571, ...]</code> \|
	\| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> \| <code>[0.1835351139307022, 0.17705069482326508, 0.07568985968828201, 0.37269654870033264, -0.04005592316389084, ...]</code> \|
	* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)

	### Evaluation Dataset

	#### Unnamed Dataset

	* Size: 10,000 evaluation samples
	* Columns: <code>sentence</code> and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:-------------------------------------\|
	\| type \| string \| list \|
	\| details \| <ul><li>min: 5 tokens</li><li>mean: 13.23 tokens</li><li>max: 57 tokens</li></ul> \| <ul><li>size: 312 elements</li></ul> \|
	* Samples:
	\| sentence \| label \|
	\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>Two women are embracing while holding to go packages.</code> \| <code>[-0.3905734717845917, -0.12415792047977448, 0.13489434123039246, -0.13027705252170563, 0.09115917980670929, ...]</code> \|
	\| <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> \| <code>[-0.11542800068855286, 0.039172928780317307, 0.16285762190818787, 0.2441333532333374, -0.1625598669052124, ...]</code> \|
	\| <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code> \| <code>[0.20657853782176971, 0.18892505764961243, -0.011273683980107307, -0.15149112045764923, 0.18431058526039124, ...]</code> \|
	* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)

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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 64
	- `per_device_eval_batch_size`: 64
	- `learning_rate`: 0.0001
	- `num_train_epochs`: 1
	- `warmup_ratio`: 0.1
	- `fp16`: True
	- `load_best_model_at_end`: True

	#### 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`: 64
	- `per_device_eval_batch_size`: 64
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `torch_empty_cache_steps`: None
	- `learning_rate`: 0.0001
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 1
	- `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`: 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`: None
	- `hub_always_push`: False
	- `hub_revision`: None
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `include_for_metrics`: []
	- `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
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `eval_on_start`: False
	- `use_liger_kernel`: False
	- `liger_kernel_config`: None
	- `eval_use_gather_object`: False
	- `average_tokens_across_devices`: False
	- `prompts`: None
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: proportional
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| Validation Loss \| sts-dev_spearman_cosine \| negative_mse \| sts-test_spearman_cosine \|
	\|:--------:\|:--------:\|:-------------:\|:---------------:\|:-----------------------:\|:------------:\|:------------------------:\|
	\| 0.032 \| 100 \| 1.3189 \| - \| - \| - \| - \|
	\| 0.064 \| 200 \| 1.1638 \| - \| - \| - \| - \|
	\| 0.096 \| 300 \| 1.0132 \| - \| - \| - \| - \|
	\| 0.128 \| 400 \| 0.924 \| - \| - \| - \| - \|
	\| 0.16 \| 500 \| 0.8666 \| 0.9844 \| 0.7668 \| -79.6441 \| - \|
	\| 0.192 \| 600 \| 0.8265 \| - \| - \| - \| - \|
	\| 0.224 \| 700 \| 0.7954 \| - \| - \| - \| - \|
	\| 0.256 \| 800 \| 0.7749 \| - \| - \| - \| - \|
	\| 0.288 \| 900 \| 0.7542 \| - \| - \| - \| - \|
	\| 0.32 \| 1000 \| 0.7318 \| 0.8942 \| 0.7966 \| -78.8491 \| - \|
	\| 0.352 \| 1100 \| 0.7207 \| - \| - \| - \| - \|
	\| 0.384 \| 1200 \| 0.7085 \| - \| - \| - \| - \|
	\| 0.416 \| 1300 \| 0.6996 \| - \| - \| - \| - \|
	\| 0.448 \| 1400 \| 0.6889 \| - \| - \| - \| - \|
	\| 0.48 \| 1500 \| 0.6823 \| 0.8533 \| 0.8125 \| -78.5136 \| - \|
	\| 0.512 \| 1600 \| 0.6704 \| - \| - \| - \| - \|
	\| 0.544 \| 1700 \| 0.6662 \| - \| - \| - \| - \|
	\| 0.576 \| 1800 \| 0.6587 \| - \| - \| - \| - \|
	\| 0.608 \| 1900 \| 0.6515 \| - \| - \| - \| - \|
	\| 0.64 \| 2000 \| 0.6479 \| 0.8323 \| 0.8160 \| -78.3540 \| - \|
	\| 0.672 \| 2100 \| 0.6463 \| - \| - \| - \| - \|
	\| 0.704 \| 2200 \| 0.6423 \| - \| - \| - \| - \|
	\| 0.736 \| 2300 \| 0.6379 \| - \| - \| - \| - \|
	\| 0.768 \| 2400 \| 0.6343 \| - \| - \| - \| - \|
	\| 0.8 \| 2500 \| 0.6309 \| 0.8185 \| 0.8196 \| -78.2491 \| - \|
	\| 0.832 \| 2600 \| 0.6275 \| - \| - \| - \| - \|
	\| 0.864 \| 2700 \| 0.628 \| - \| - \| - \| - \|
	\| 0.896 \| 2800 \| 0.6232 \| - \| - \| - \| - \|
	\| 0.928 \| 2900 \| 0.623 \| - \| - \| - \| - \|
	\| 0.96 \| 3000 \| 0.6229 \| 0.8107 \| 0.8213 \| -78.1863 \| - \|
	\| 0.992 \| 3100 \| 0.6208 \| - \| - \| - \| - \|
	\| -1 \| -1 \| - \| - \| - \| - \| 0.7521 \|

	* The bold row denotes the saved checkpoint.

	### Environmental Impact
	Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
	- Energy Consumed: 0.011 kWh
	- Carbon Emitted: 0.003 kg of CO2
	- Hours Used: 0.06 hours

	### Training Hardware
	- On Cloud: No
	- GPU Model: 1 x NVIDIA GeForce RTX 3090
	- CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
	- RAM Size: 31.78 GB

	### Framework Versions
	- Python: 3.11.6
	- Sentence Transformers: 5.2.0.dev0
	- Transformers: 4.53.3
	- PyTorch: 2.8.0+cu128
	- Accelerate: 1.6.0
	- Datasets: 4.2.0
	- Tokenizers: 0.21.4

	## 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",
	}
	```

	#### MSELoss
	```bibtex
	@inproceedings{reimers-2020-multilingual-sentence-bert,
	title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
	author = "Reimers, Nils and Gurevych, Iryna",
	booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
	month = "11",
	year = "2020",
	publisher = "Association for Computational Linguistics",
	url = "https://arxiv.org/abs/2004.09813",
	}
	```

	<!--
	## 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.
	-->