Snack_Embed / README.md

Update README.md

d6575bf verified 6 months ago

16.9 kB

	---
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dense
	- generated_from_trainer
	- dataset_size:1275
	- loss:MultipleNegativesRankingLoss
	base_model: sentence-transformers/all-mpnet-base-v2
	widget:
	- source_sentence: snickers almond
	sentences:
	- Cheetos Flamin' Hot
	- Snickers Almond
	- Tostitos Hint of Lime
	- source_sentence: hershey's special dark
	sentences:
	- Hershey's Special Dark Chocolate Bar
	- 5-Hour Energy Shot
	- Hershey's Milk Chocolate Bar
	- source_sentence: goldfish classic
	sentences:
	- 3 Musketeers Bar
	- Goldfish Crackers
	- Hot Pockets
	- source_sentence: skittles
	sentences:
	- Black Tea
	- Skittles
	- Chips Ahoy! Chewy Cookies
	- source_sentence: cheddar cheese
	sentences:
	- Cucumber
	- Cheddar Cheese Block
	- Coffee-mate Creamer
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	---

	# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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. The purpose is to create closer semantic relations with certain snack/food names (ie chips -> potato chips).

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 -->
	- Maximum Sequence Length: 384 tokens
	- Output Dimensionality: 768 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/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': 384, 'do_lower_case': False, 'architecture': 'MPNetModel'})
	(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})
	(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("Weike1000/Snack_Embed")
	# Run inference
	sentences = [
	'cheddar cheese',
	'Cheddar Cheese Block',
	'Cucumber',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[1.0000, 0.9452, 0.1340],
	# [0.9452, 1.0000, 0.1356],
	# [0.1340, 0.1356, 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.
	-->

	<!--
	## 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: 1,275 training samples
	* Columns: <code>sentence_0</code> and <code>sentence_1</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence_0 \| sentence_1 \|
	\|:--------\|:---------------------------------------------------------------------------------\|:--------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 3 tokens</li><li>mean: 5.33 tokens</li><li>max: 11 tokens</li></ul> \| <ul><li>min: 3 tokens</li><li>mean: 6.4 tokens</li><li>max: 15 tokens</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \|
	\|:------------------------------\|:------------------------------------------------\|
	\| <code>fudge stripes</code> \| <code>Keebler Fudge Stripes Cookies</code> \|
	\| <code>gummy bears bag</code> \| <code>Gummy Bears</code> \|
	\| <code>kind bar caramel</code> \| <code>Kind Bar Caramel Almond & Sea Salt</code> \|
	* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim"
	}
	```

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

	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `num_train_epochs`: 1000
	- `multi_dataset_batch_sampler`: round_robin

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: no
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `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`: 5e-05
	- `weight_decay`: 0.0
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1
	- `num_train_epochs`: 1000
	- `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`: 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`: 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}
	- `tp_size`: 0
	- `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
	- `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
	- `eval_use_gather_object`: False
	- `average_tokens_across_devices`: False
	- `prompts`: None
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: round_robin
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}

	</details>

	### Training Logs
	<details><summary>Click to expand</summary>

	\| Epoch \| Step \| Training Loss \|
	\|:------:\|:-----:\|:-------------:\|
	\| 6.25 \| 500 \| 0.0756 \|
	\| 12.5 \| 1000 \| 0.0396 \|
	\| 18.75 \| 1500 \| 0.033 \|
	\| 25.0 \| 2000 \| 0.0283 \|
	\| 31.25 \| 2500 \| 0.0257 \|
	\| 37.5 \| 3000 \| 0.0249 \|
	\| 43.75 \| 3500 \| 0.0248 \|
	\| 50.0 \| 4000 \| 0.019 \|
	\| 56.25 \| 4500 \| 0.0242 \|
	\| 62.5 \| 5000 \| 0.0203 \|
	\| 68.75 \| 5500 \| 0.0205 \|
	\| 75.0 \| 6000 \| 0.0225 \|
	\| 81.25 \| 6500 \| 0.0183 \|
	\| 87.5 \| 7000 \| 0.0227 \|
	\| 93.75 \| 7500 \| 0.0224 \|
	\| 100.0 \| 8000 \| 0.022 \|
	\| 106.25 \| 8500 \| 0.0244 \|
	\| 112.5 \| 9000 \| 0.0231 \|
	\| 118.75 \| 9500 \| 0.021 \|
	\| 125.0 \| 10000 \| 0.0215 \|
	\| 131.25 \| 10500 \| 0.0166 \|
	\| 137.5 \| 11000 \| 0.0186 \|
	\| 143.75 \| 11500 \| 0.0211 \|
	\| 150.0 \| 12000 \| 0.0208 \|
	\| 156.25 \| 12500 \| 0.0214 \|
	\| 162.5 \| 13000 \| 0.0207 \|
	\| 168.75 \| 13500 \| 0.0216 \|
	\| 175.0 \| 14000 \| 0.0214 \|
	\| 181.25 \| 14500 \| 0.0209 \|
	\| 187.5 \| 15000 \| 0.0197 \|
	\| 193.75 \| 15500 \| 0.022 \|
	\| 200.0 \| 16000 \| 0.0183 \|
	\| 206.25 \| 16500 \| 0.0189 \|
	\| 212.5 \| 17000 \| 0.0188 \|
	\| 218.75 \| 17500 \| 0.0163 \|
	\| 225.0 \| 18000 \| 0.0209 \|
	\| 231.25 \| 18500 \| 0.0185 \|
	\| 237.5 \| 19000 \| 0.0211 \|
	\| 243.75 \| 19500 \| 0.02 \|
	\| 250.0 \| 20000 \| 0.0206 \|
	\| 256.25 \| 20500 \| 0.0222 \|
	\| 262.5 \| 21000 \| 0.0185 \|
	\| 268.75 \| 21500 \| 0.0205 \|
	\| 275.0 \| 22000 \| 0.0165 \|
	\| 281.25 \| 22500 \| 0.0185 \|
	\| 287.5 \| 23000 \| 0.0164 \|
	\| 293.75 \| 23500 \| 0.0191 \|
	\| 300.0 \| 24000 \| 0.0197 \|
	\| 306.25 \| 24500 \| 0.0195 \|
	\| 312.5 \| 25000 \| 0.0185 \|
	\| 318.75 \| 25500 \| 0.017 \|
	\| 325.0 \| 26000 \| 0.0184 \|
	\| 331.25 \| 26500 \| 0.0184 \|
	\| 337.5 \| 27000 \| 0.0211 \|
	\| 343.75 \| 27500 \| 0.0182 \|
	\| 350.0 \| 28000 \| 0.0189 \|
	\| 356.25 \| 28500 \| 0.0172 \|
	\| 362.5 \| 29000 \| 0.0195 \|
	\| 368.75 \| 29500 \| 0.0221 \|
	\| 375.0 \| 30000 \| 0.0197 \|
	\| 381.25 \| 30500 \| 0.0228 \|
	\| 387.5 \| 31000 \| 0.0173 \|
	\| 393.75 \| 31500 \| 0.0191 \|
	\| 400.0 \| 32000 \| 0.0203 \|
	\| 406.25 \| 32500 \| 0.0202 \|
	\| 412.5 \| 33000 \| 0.0186 \|
	\| 418.75 \| 33500 \| 0.0178 \|
	\| 425.0 \| 34000 \| 0.018 \|
	\| 431.25 \| 34500 \| 0.0192 \|
	\| 437.5 \| 35000 \| 0.0186 \|
	\| 443.75 \| 35500 \| 0.0211 \|
	\| 450.0 \| 36000 \| 0.0209 \|
	\| 456.25 \| 36500 \| 0.0216 \|
	\| 462.5 \| 37000 \| 0.0201 \|
	\| 468.75 \| 37500 \| 0.0227 \|
	\| 475.0 \| 38000 \| 0.02 \|
	\| 481.25 \| 38500 \| 0.018 \|
	\| 487.5 \| 39000 \| 0.0218 \|
	\| 493.75 \| 39500 \| 0.0237 \|
	\| 500.0 \| 40000 \| 0.0208 \|
	\| 506.25 \| 40500 \| 0.0185 \|
	\| 512.5 \| 41000 \| 0.0188 \|
	\| 518.75 \| 41500 \| 0.0188 \|
	\| 525.0 \| 42000 \| 0.0168 \|
	\| 531.25 \| 42500 \| 0.017 \|
	\| 537.5 \| 43000 \| 0.0165 \|
	\| 543.75 \| 43500 \| 0.0197 \|
	\| 550.0 \| 44000 \| 0.0159 \|
	\| 556.25 \| 44500 \| 0.0224 \|
	\| 562.5 \| 45000 \| 0.0179 \|
	\| 568.75 \| 45500 \| 0.0188 \|
	\| 575.0 \| 46000 \| 0.0203 \|
	\| 581.25 \| 46500 \| 0.018 \|
	\| 587.5 \| 47000 \| 0.0195 \|
	\| 593.75 \| 47500 \| 0.0194 \|
	\| 600.0 \| 48000 \| 0.0205 \|
	\| 606.25 \| 48500 \| 0.0185 \|
	\| 612.5 \| 49000 \| 0.0208 \|
	\| 618.75 \| 49500 \| 0.0205 \|
	\| 625.0 \| 50000 \| 0.0201 \|
	\| 631.25 \| 50500 \| 0.0175 \|
	\| 637.5 \| 51000 \| 0.0171 \|
	\| 643.75 \| 51500 \| 0.0184 \|
	\| 650.0 \| 52000 \| 0.0228 \|
	\| 656.25 \| 52500 \| 0.0203 \|
	\| 662.5 \| 53000 \| 0.0222 \|
	\| 668.75 \| 53500 \| 0.0188 \|
	\| 675.0 \| 54000 \| 0.0235 \|
	\| 681.25 \| 54500 \| 0.0182 \|
	\| 687.5 \| 55000 \| 0.0215 \|
	\| 693.75 \| 55500 \| 0.018 \|
	\| 700.0 \| 56000 \| 0.0227 \|
	\| 706.25 \| 56500 \| 0.0185 \|
	\| 712.5 \| 57000 \| 0.0179 \|
	\| 718.75 \| 57500 \| 0.0176 \|
	\| 725.0 \| 58000 \| 0.0233 \|
	\| 731.25 \| 58500 \| 0.0213 \|
	\| 737.5 \| 59000 \| 0.0208 \|
	\| 743.75 \| 59500 \| 0.015 \|
	\| 750.0 \| 60000 \| 0.0199 \|
	\| 756.25 \| 60500 \| 0.0197 \|
	\| 762.5 \| 61000 \| 0.0199 \|
	\| 768.75 \| 61500 \| 0.0209 \|
	\| 775.0 \| 62000 \| 0.0185 \|
	\| 781.25 \| 62500 \| 0.0183 \|
	\| 787.5 \| 63000 \| 0.0169 \|
	\| 793.75 \| 63500 \| 0.0176 \|
	\| 800.0 \| 64000 \| 0.0206 \|
	\| 806.25 \| 64500 \| 0.0186 \|
	\| 812.5 \| 65000 \| 0.0181 \|
	\| 818.75 \| 65500 \| 0.0179 \|
	\| 825.0 \| 66000 \| 0.0184 \|
	\| 831.25 \| 66500 \| 0.0157 \|
	\| 837.5 \| 67000 \| 0.0181 \|
	\| 843.75 \| 67500 \| 0.0174 \|
	\| 850.0 \| 68000 \| 0.0185 \|
	\| 856.25 \| 68500 \| 0.0213 \|
	\| 862.5 \| 69000 \| 0.0181 \|
	\| 868.75 \| 69500 \| 0.02 \|
	\| 875.0 \| 70000 \| 0.0141 \|
	\| 881.25 \| 70500 \| 0.0168 \|
	\| 887.5 \| 71000 \| 0.0218 \|
	\| 893.75 \| 71500 \| 0.0188 \|
	\| 900.0 \| 72000 \| 0.0139 \|
	\| 906.25 \| 72500 \| 0.0188 \|
	\| 912.5 \| 73000 \| 0.022 \|
	\| 918.75 \| 73500 \| 0.0154 \|
	\| 925.0 \| 74000 \| 0.0165 \|
	\| 931.25 \| 74500 \| 0.0186 \|
	\| 937.5 \| 75000 \| 0.0191 \|
	\| 943.75 \| 75500 \| 0.0188 \|
	\| 950.0 \| 76000 \| 0.0176 \|
	\| 956.25 \| 76500 \| 0.0218 \|
	\| 962.5 \| 77000 \| 0.0185 \|
	\| 968.75 \| 77500 \| 0.0193 \|
	\| 975.0 \| 78000 \| 0.0218 \|
	\| 981.25 \| 78500 \| 0.0161 \|
	\| 987.5 \| 79000 \| 0.0216 \|
	\| 993.75 \| 79500 \| 0.0225 \|
	\| 1000.0 \| 80000 \| 0.0194 \|

	</details>

	### Framework Versions
	- Python: 3.9.6
	- Sentence Transformers: 5.0.0
	- Transformers: 4.51.3
	- PyTorch: 2.7.0
	- Accelerate: 1.7.0
	- Datasets: 4.0.0
	- Tokenizers: 0.21.1

	## 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",
	}
	```

	#### 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.
	-->