|
--- |
|
base_model: sentence-transformers/all-MiniLM-L12-v2 |
|
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:100000 |
|
- loss:CosineSimilarityLoss |
|
widget: |
|
- source_sentence: Face off with a ref mid-hockey game in an arena. |
|
sentences: |
|
- Nobody is playing |
|
- A mustached man in a patterned shirt watches a boat painted blue and orange. |
|
- Two adults makes calls on there cell phones during there lunch breaks. |
|
- source_sentence: A group of people, one holding a yellow and blue umbrella, are |
|
standing at the top of some stairs. |
|
sentences: |
|
- One person wields an umbrella. |
|
- A girl is on the beach. |
|
- A man is on his couch. |
|
- source_sentence: A man waiting for the results of the machine after doing an experiment |
|
in his laboratory. |
|
sentences: |
|
- There is a man playing an instrument while running |
|
- A man in a lab waits to get more information about his experiment. |
|
- The graffiti artists admire their work. |
|
- source_sentence: People in a tent shelter near the bottom of stairs. |
|
sentences: |
|
- A boy has fallen asleep during dinner. |
|
- Three men address a crowd. |
|
- People are in a makeshift shelter at the foot of a staircase. |
|
- source_sentence: A female researcher looking through a microscope. |
|
sentences: |
|
- A man misses the rope and falls |
|
- A small girl is playing video games |
|
- A woman is researching with a microscope. |
|
model-index: |
|
- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2 |
|
results: |
|
- task: |
|
type: semantic-similarity |
|
name: Semantic Similarity |
|
dataset: |
|
name: snli dev |
|
type: snli-dev |
|
metrics: |
|
- type: pearson_cosine |
|
value: 0.48994508338253345 |
|
name: Pearson Cosine |
|
- type: spearman_cosine |
|
value: 0.4778683474663533 |
|
name: Spearman Cosine |
|
- type: pearson_manhattan |
|
value: 0.46917600703738915 |
|
name: Pearson Manhattan |
|
- type: spearman_manhattan |
|
value: 0.47754796729416876 |
|
name: Spearman Manhattan |
|
- type: pearson_euclidean |
|
value: 0.46924620767742137 |
|
name: Pearson Euclidean |
|
- type: spearman_euclidean |
|
value: 0.4778683474663533 |
|
name: Spearman Euclidean |
|
- type: pearson_dot |
|
value: 0.48994508631435785 |
|
name: Pearson Dot |
|
- type: spearman_dot |
|
value: 0.4778683472855999 |
|
name: Spearman Dot |
|
- type: pearson_max |
|
value: 0.48994508631435785 |
|
name: Pearson Max |
|
- type: spearman_max |
|
value: 0.4778683474663533 |
|
name: Spearman Max |
|
--- |
|
|
|
# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2 |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). 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:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision 30ce63ae64e71b9199b3d2eae9de99f64a26eedc --> |
|
- **Maximum Sequence Length:** 128 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': 128, '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("Nessrine9/finetuned2-snli-MiniLM-L12-v2") |
|
# Run inference |
|
sentences = [ |
|
'A female researcher looking through a microscope.', |
|
'A woman is researching with a microscope.', |
|
'A small girl is playing video games', |
|
] |
|
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 |
|
|
|
#### Semantic Similarity |
|
* Dataset: `snli-dev` |
|
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) |
|
|
|
| Metric | Value | |
|
|:-------------------|:-----------| |
|
| pearson_cosine | 0.4899 | |
|
| spearman_cosine | 0.4779 | |
|
| pearson_manhattan | 0.4692 | |
|
| spearman_manhattan | 0.4775 | |
|
| pearson_euclidean | 0.4692 | |
|
| spearman_euclidean | 0.4779 | |
|
| pearson_dot | 0.4899 | |
|
| spearman_dot | 0.4779 | |
|
| pearson_max | 0.4899 | |
|
| **spearman_max** | **0.4779** | |
|
|
|
<!-- |
|
## 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: 100,000 training samples |
|
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | sentence_0 | sentence_1 | label | |
|
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------| |
|
| type | string | string | float | |
|
| details | <ul><li>min: 7 tokens</li><li>mean: 16.32 tokens</li><li>max: 86 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.46 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> | |
|
* Samples: |
|
| sentence_0 | sentence_1 | label | |
|
|:---------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------|:-----------------| |
|
| <code>A man wearing jeans and a t-shirt plays guitar for a smiling woman and child as they sit on a staircase near red and orange balloons.</code> | <code>A man is in jail.</code> | <code>1.0</code> | |
|
| <code>A boy wearing blue short standing on the traffic signal pole.</code> | <code>The boy is carrying his school books.</code> | <code>0.5</code> | |
|
| <code>Several people on a busy street or perhaps at a fair.</code> | <code>They are walkng.</code> | <code>0.5</code> | |
|
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: |
|
```json |
|
{ |
|
"loss_fct": "torch.nn.modules.loss.MSELoss" |
|
} |
|
``` |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `eval_strategy`: steps |
|
- `per_device_train_batch_size`: 16 |
|
- `per_device_eval_batch_size`: 16 |
|
- `num_train_epochs`: 4 |
|
- `fp16`: True |
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
#### 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`: 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`: 4 |
|
- `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`: 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 |
|
- `eval_on_start`: False |
|
- `eval_use_gather_object`: False |
|
- `batch_sampler`: batch_sampler |
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | snli-dev_spearman_max | |
|
|:------:|:-----:|:-------------:|:---------------------:| |
|
| 0.08 | 500 | 0.1832 | 0.3114 | |
|
| 0.16 | 1000 | 0.1489 | 0.3518 | |
|
| 0.24 | 1500 | 0.1468 | 0.3697 | |
|
| 0.32 | 2000 | 0.1411 | 0.3723 | |
|
| 0.4 | 2500 | 0.14 | 0.4062 | |
|
| 0.48 | 3000 | 0.1366 | 0.3923 | |
|
| 0.56 | 3500 | 0.1379 | 0.4143 | |
|
| 0.64 | 4000 | 0.1357 | 0.3928 | |
|
| 0.72 | 4500 | 0.1331 | 0.4067 | |
|
| 0.8 | 5000 | 0.1338 | 0.4293 | |
|
| 0.88 | 5500 | 0.1294 | 0.4183 | |
|
| 0.96 | 6000 | 0.1305 | 0.4402 | |
|
| 1.0 | 6250 | - | 0.4454 | |
|
| 1.04 | 6500 | 0.1303 | 0.4408 | |
|
| 1.12 | 7000 | 0.1275 | 0.4416 | |
|
| 1.2 | 7500 | 0.1285 | 0.4287 | |
|
| 1.28 | 8000 | 0.125 | 0.4404 | |
|
| 1.3600 | 8500 | 0.1253 | 0.4408 | |
|
| 1.44 | 9000 | 0.1246 | 0.4293 | |
|
| 1.52 | 9500 | 0.126 | 0.4535 | |
|
| 1.6 | 10000 | 0.1257 | 0.4455 | |
|
| 1.6800 | 10500 | 0.1264 | 0.4520 | |
|
| 1.76 | 11000 | 0.1248 | 0.4526 | |
|
| 1.8400 | 11500 | 0.1208 | 0.4631 | |
|
| 1.92 | 12000 | 0.1236 | 0.4635 | |
|
| 2.0 | 12500 | 0.1239 | 0.4573 | |
|
| 2.08 | 13000 | 0.1209 | 0.4569 | |
|
| 2.16 | 13500 | 0.1194 | 0.4642 | |
|
| 2.24 | 14000 | 0.1206 | 0.4539 | |
|
| 2.32 | 14500 | 0.117 | 0.4633 | |
|
| 2.4 | 15000 | 0.1171 | 0.4657 | |
|
| 2.48 | 15500 | 0.1181 | 0.4633 | |
|
| 2.56 | 16000 | 0.1197 | 0.4552 | |
|
| 2.64 | 16500 | 0.1182 | 0.4670 | |
|
| 2.7200 | 17000 | 0.1155 | 0.4684 | |
|
| 2.8 | 17500 | 0.1171 | 0.4640 | |
|
| 2.88 | 18000 | 0.1139 | 0.4715 | |
|
| 2.96 | 18500 | 0.1164 | 0.4769 | |
|
| 3.0 | 18750 | - | 0.4709 | |
|
| 3.04 | 19000 | 0.1151 | 0.4704 | |
|
| 3.12 | 19500 | 0.1144 | 0.4759 | |
|
| 3.2 | 20000 | 0.1121 | 0.4795 | |
|
| 3.2800 | 20500 | 0.1104 | 0.4697 | |
|
| 3.36 | 21000 | 0.1127 | 0.4763 | |
|
| 3.44 | 21500 | 0.1115 | 0.4742 | |
|
| 3.52 | 22000 | 0.1126 | 0.4697 | |
|
| 3.6 | 22500 | 0.1123 | 0.4735 | |
|
| 3.68 | 23000 | 0.1132 | 0.4750 | |
|
| 3.76 | 23500 | 0.1127 | 0.4743 | |
|
| 3.84 | 24000 | 0.1086 | 0.4752 | |
|
| 3.92 | 24500 | 0.1107 | 0.4781 | |
|
| 4.0 | 25000 | 0.1114 | 0.4779 | |
|
|
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.2.1 |
|
- Transformers: 4.44.2 |
|
- PyTorch: 2.5.0+cu121 |
|
- Accelerate: 0.34.2 |
|
- Datasets: 3.0.2 |
|
- 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", |
|
} |
|
``` |
|
|
|
<!-- |
|
## 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.* |
|
--> |
