| --- |
| base_model: intfloat/multilingual-e5-small |
| datasets: [] |
| language: [] |
| library_name: sentence-transformers |
| metrics: |
| - cosine_accuracy |
| - cosine_accuracy_threshold |
| - cosine_f1 |
| - cosine_f1_threshold |
| - cosine_precision |
| - cosine_recall |
| - cosine_ap |
| - dot_accuracy |
| - dot_accuracy_threshold |
| - dot_f1 |
| - dot_f1_threshold |
| - dot_precision |
| - dot_recall |
| - dot_ap |
| - manhattan_accuracy |
| - manhattan_accuracy_threshold |
| - manhattan_f1 |
| - manhattan_f1_threshold |
| - manhattan_precision |
| - manhattan_recall |
| - manhattan_ap |
| - euclidean_accuracy |
| - euclidean_accuracy_threshold |
| - euclidean_f1 |
| - euclidean_f1_threshold |
| - euclidean_precision |
| - euclidean_recall |
| - euclidean_ap |
| - max_accuracy |
| - max_accuracy_threshold |
| - max_f1 |
| - max_f1_threshold |
| - max_precision |
| - max_recall |
| - max_ap |
| pipeline_tag: sentence-similarity |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - generated_from_trainer |
| - dataset_size:971 |
| - loss:OnlineContrastiveLoss |
| widget: |
| - source_sentence: How to bake a pie? |
| sentences: |
| - Steps to bake a pie |
| - What are the ingredients of pizza? |
| - Steps to draft a business plan |
| - source_sentence: What are the benefits of meditation? |
| sentences: |
| - What color do yellow and blue make? |
| - Can you help me understand this recipe? |
| - What are the benefits of yoga? |
| - source_sentence: What is the capital of Canada? |
| sentences: |
| - What time does the concert start? |
| - Current President of the USA |
| - Capital city of Canada |
| - source_sentence: Share info about Shopify |
| sentences: |
| - Who discovered insulin? |
| - Tell me about Shopify |
| - Inventor of the telephone |
| - source_sentence: What is the boiling point of water at sea level? |
| sentences: |
| - What is the melting point of ice at sea level? |
| - Can you recommend a good hotel nearby? |
| - Can you tell me a joke? |
| model-index: |
| - name: SentenceTransformer based on intfloat/multilingual-e5-small |
| results: |
| - task: |
| type: binary-classification |
| name: Binary Classification |
| dataset: |
| name: pair class dev |
| type: pair-class-dev |
| metrics: |
| - type: cosine_accuracy |
| value: 0.934156378600823 |
| name: Cosine Accuracy |
| - type: cosine_accuracy_threshold |
| value: 0.7816850543022156 |
| name: Cosine Accuracy Threshold |
| - type: cosine_f1 |
| value: 0.927927927927928 |
| name: Cosine F1 |
| - type: cosine_f1_threshold |
| value: 0.7816850543022156 |
| name: Cosine F1 Threshold |
| - type: cosine_precision |
| value: 0.9035087719298246 |
| name: Cosine Precision |
| - type: cosine_recall |
| value: 0.9537037037037037 |
| name: Cosine Recall |
| - type: cosine_ap |
| value: 0.9587113018178404 |
| name: Cosine Ap |
| - type: dot_accuracy |
| value: 0.934156378600823 |
| name: Dot Accuracy |
| - type: dot_accuracy_threshold |
| value: 0.7816851139068604 |
| name: Dot Accuracy Threshold |
| - type: dot_f1 |
| value: 0.927927927927928 |
| name: Dot F1 |
| - type: dot_f1_threshold |
| value: 0.7816851139068604 |
| name: Dot F1 Threshold |
| - type: dot_precision |
| value: 0.9035087719298246 |
| name: Dot Precision |
| - type: dot_recall |
| value: 0.9537037037037037 |
| name: Dot Recall |
| - type: dot_ap |
| value: 0.9587113018178404 |
| name: Dot Ap |
| - type: manhattan_accuracy |
| value: 0.9218106995884774 |
| name: Manhattan Accuracy |
| - type: manhattan_accuracy_threshold |
| value: 10.031501770019531 |
| name: Manhattan Accuracy Threshold |
| - type: manhattan_f1 |
| value: 0.9155555555555556 |
| name: Manhattan F1 |
| - type: manhattan_f1_threshold |
| value: 10.459373474121094 |
| name: Manhattan F1 Threshold |
| - type: manhattan_precision |
| value: 0.8803418803418803 |
| name: Manhattan Precision |
| - type: manhattan_recall |
| value: 0.9537037037037037 |
| name: Manhattan Recall |
| - type: manhattan_ap |
| value: 0.9569878972892534 |
| name: Manhattan Ap |
| - type: euclidean_accuracy |
| value: 0.934156378600823 |
| name: Euclidean Accuracy |
| - type: euclidean_accuracy_threshold |
| value: 0.6607794761657715 |
| name: Euclidean Accuracy Threshold |
| - type: euclidean_f1 |
| value: 0.927927927927928 |
| name: Euclidean F1 |
| - type: euclidean_f1_threshold |
| value: 0.6607794761657715 |
| name: Euclidean F1 Threshold |
| - type: euclidean_precision |
| value: 0.9035087719298246 |
| name: Euclidean Precision |
| - type: euclidean_recall |
| value: 0.9537037037037037 |
| name: Euclidean Recall |
| - type: euclidean_ap |
| value: 0.9587113018178404 |
| name: Euclidean Ap |
| - type: max_accuracy |
| value: 0.934156378600823 |
| name: Max Accuracy |
| - type: max_accuracy_threshold |
| value: 10.031501770019531 |
| name: Max Accuracy Threshold |
| - type: max_f1 |
| value: 0.927927927927928 |
| name: Max F1 |
| - type: max_f1_threshold |
| value: 10.459373474121094 |
| name: Max F1 Threshold |
| - type: max_precision |
| value: 0.9035087719298246 |
| name: Max Precision |
| - type: max_recall |
| value: 0.9537037037037037 |
| name: Max Recall |
| - type: max_ap |
| value: 0.9587113018178404 |
| name: Max Ap |
| - task: |
| type: binary-classification |
| name: Binary Classification |
| dataset: |
| name: pair class test |
| type: pair-class-test |
| metrics: |
| - type: cosine_accuracy |
| value: 0.934156378600823 |
| name: Cosine Accuracy |
| - type: cosine_accuracy_threshold |
| value: 0.7816850543022156 |
| name: Cosine Accuracy Threshold |
| - type: cosine_f1 |
| value: 0.927927927927928 |
| name: Cosine F1 |
| - type: cosine_f1_threshold |
| value: 0.7816850543022156 |
| name: Cosine F1 Threshold |
| - type: cosine_precision |
| value: 0.9035087719298246 |
| name: Cosine Precision |
| - type: cosine_recall |
| value: 0.9537037037037037 |
| name: Cosine Recall |
| - type: cosine_ap |
| value: 0.9587113018178404 |
| name: Cosine Ap |
| - type: dot_accuracy |
| value: 0.934156378600823 |
| name: Dot Accuracy |
| - type: dot_accuracy_threshold |
| value: 0.7816851139068604 |
| name: Dot Accuracy Threshold |
| - type: dot_f1 |
| value: 0.927927927927928 |
| name: Dot F1 |
| - type: dot_f1_threshold |
| value: 0.7816851139068604 |
| name: Dot F1 Threshold |
| - type: dot_precision |
| value: 0.9035087719298246 |
| name: Dot Precision |
| - type: dot_recall |
| value: 0.9537037037037037 |
| name: Dot Recall |
| - type: dot_ap |
| value: 0.9587113018178404 |
| name: Dot Ap |
| - type: manhattan_accuracy |
| value: 0.9218106995884774 |
| name: Manhattan Accuracy |
| - type: manhattan_accuracy_threshold |
| value: 10.031501770019531 |
| name: Manhattan Accuracy Threshold |
| - type: manhattan_f1 |
| value: 0.9155555555555556 |
| name: Manhattan F1 |
| - type: manhattan_f1_threshold |
| value: 10.459373474121094 |
| name: Manhattan F1 Threshold |
| - type: manhattan_precision |
| value: 0.8803418803418803 |
| name: Manhattan Precision |
| - type: manhattan_recall |
| value: 0.9537037037037037 |
| name: Manhattan Recall |
| - type: manhattan_ap |
| value: 0.9569878972892534 |
| name: Manhattan Ap |
| - type: euclidean_accuracy |
| value: 0.934156378600823 |
| name: Euclidean Accuracy |
| - type: euclidean_accuracy_threshold |
| value: 0.6607794761657715 |
| name: Euclidean Accuracy Threshold |
| - type: euclidean_f1 |
| value: 0.927927927927928 |
| name: Euclidean F1 |
| - type: euclidean_f1_threshold |
| value: 0.6607794761657715 |
| name: Euclidean F1 Threshold |
| - type: euclidean_precision |
| value: 0.9035087719298246 |
| name: Euclidean Precision |
| - type: euclidean_recall |
| value: 0.9537037037037037 |
| name: Euclidean Recall |
| - type: euclidean_ap |
| value: 0.9587113018178404 |
| name: Euclidean Ap |
| - type: max_accuracy |
| value: 0.934156378600823 |
| name: Max Accuracy |
| - type: max_accuracy_threshold |
| value: 10.031501770019531 |
| name: Max Accuracy Threshold |
| - type: max_f1 |
| value: 0.927927927927928 |
| name: Max F1 |
| - type: max_f1_threshold |
| value: 10.459373474121094 |
| name: Max F1 Threshold |
| - type: max_precision |
| value: 0.9035087719298246 |
| name: Max Precision |
| - type: max_recall |
| value: 0.9537037037037037 |
| name: Max Recall |
| - type: max_ap |
| value: 0.9587113018178404 |
| name: Max Ap |
| --- |
| |
| # 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-pairclass-2") |
| # Run inference |
| sentences = [ |
| 'What is the boiling point of water at sea level?', |
| 'What is the melting point of ice at sea level?', |
| 'Can you recommend a good hotel nearby?', |
| ] |
| 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 |
|
|
| #### Binary Classification |
| * Dataset: `pair-class-dev` |
| * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
|
|
| | Metric | Value | |
| |:-----------------------------|:-----------| |
| | cosine_accuracy | 0.9342 | |
| | cosine_accuracy_threshold | 0.7817 | |
| | cosine_f1 | 0.9279 | |
| | cosine_f1_threshold | 0.7817 | |
| | cosine_precision | 0.9035 | |
| | cosine_recall | 0.9537 | |
| | cosine_ap | 0.9587 | |
| | dot_accuracy | 0.9342 | |
| | dot_accuracy_threshold | 0.7817 | |
| | dot_f1 | 0.9279 | |
| | dot_f1_threshold | 0.7817 | |
| | dot_precision | 0.9035 | |
| | dot_recall | 0.9537 | |
| | dot_ap | 0.9587 | |
| | manhattan_accuracy | 0.9218 | |
| | manhattan_accuracy_threshold | 10.0315 | |
| | manhattan_f1 | 0.9156 | |
| | manhattan_f1_threshold | 10.4594 | |
| | manhattan_precision | 0.8803 | |
| | manhattan_recall | 0.9537 | |
| | manhattan_ap | 0.957 | |
| | euclidean_accuracy | 0.9342 | |
| | euclidean_accuracy_threshold | 0.6608 | |
| | euclidean_f1 | 0.9279 | |
| | euclidean_f1_threshold | 0.6608 | |
| | euclidean_precision | 0.9035 | |
| | euclidean_recall | 0.9537 | |
| | euclidean_ap | 0.9587 | |
| | max_accuracy | 0.9342 | |
| | max_accuracy_threshold | 10.0315 | |
| | max_f1 | 0.9279 | |
| | max_f1_threshold | 10.4594 | |
| | max_precision | 0.9035 | |
| | max_recall | 0.9537 | |
| | **max_ap** | **0.9587** | |
| |
| #### Binary Classification |
| * Dataset: `pair-class-test` |
| * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
| |
| | Metric | Value | |
| |:-----------------------------|:-----------| |
| | cosine_accuracy | 0.9342 | |
| | cosine_accuracy_threshold | 0.7817 | |
| | cosine_f1 | 0.9279 | |
| | cosine_f1_threshold | 0.7817 | |
| | cosine_precision | 0.9035 | |
| | cosine_recall | 0.9537 | |
| | cosine_ap | 0.9587 | |
| | dot_accuracy | 0.9342 | |
| | dot_accuracy_threshold | 0.7817 | |
| | dot_f1 | 0.9279 | |
| | dot_f1_threshold | 0.7817 | |
| | dot_precision | 0.9035 | |
| | dot_recall | 0.9537 | |
| | dot_ap | 0.9587 | |
| | manhattan_accuracy | 0.9218 | |
| | manhattan_accuracy_threshold | 10.0315 | |
| | manhattan_f1 | 0.9156 | |
| | manhattan_f1_threshold | 10.4594 | |
| | manhattan_precision | 0.8803 | |
| | manhattan_recall | 0.9537 | |
| | manhattan_ap | 0.957 | |
| | euclidean_accuracy | 0.9342 | |
| | euclidean_accuracy_threshold | 0.6608 | |
| | euclidean_f1 | 0.9279 | |
| | euclidean_f1_threshold | 0.6608 | |
| | euclidean_precision | 0.9035 | |
| | euclidean_recall | 0.9537 | |
| | euclidean_ap | 0.9587 | |
| | max_accuracy | 0.9342 | |
| | max_accuracy_threshold | 10.0315 | |
| | max_f1 | 0.9279 | |
| | max_f1_threshold | 10.4594 | |
| | max_precision | 0.9035 | |
| | max_recall | 0.9537 | |
| | **max_ap** | **0.9587** | |
|
|
| <!-- |
| ## 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: 971 training samples |
| * Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | label | sentence1 | sentence2 | |
| |:--------|:------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | int | string | string | |
| | details | <ul><li>0: ~48.61%</li><li>1: ~51.39%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.82 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.12 tokens</li><li>max: 22 tokens</li></ul> | |
| * Samples: |
| | label | sentence1 | sentence2 | |
| |:---------------|:--------------------------------------------------------|:----------------------------------------------------------| |
| | <code>1</code> | <code>How many bones are in the human body?</code> | <code>Total number of bones in an adult human body</code> | |
| | <code>0</code> | <code>What is the largest lake in North America?</code> | <code>What is the largest river in North America?</code> | |
| | <code>0</code> | <code>What is the capital of New Zealand?</code> | <code>What is the capital of Australia?</code> | |
| * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
| ### Evaluation Dataset |
|
|
| #### Unnamed Dataset |
|
|
|
|
| * Size: 243 evaluation samples |
| * Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | label | sentence1 | sentence2 | |
| |:--------|:------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | int | string | string | |
| | details | <ul><li>0: ~55.56%</li><li>1: ~44.44%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.55 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.09 tokens</li><li>max: 20 tokens</li></ul> | |
| * Samples: |
| | label | sentence1 | sentence2 | |
| |:---------------|:---------------------------------------------------------------|:-------------------------------------------------------------| |
| | <code>1</code> | <code>What are the different types of renewable energy?</code> | <code>What are the various forms of renewable energy?</code> | |
| | <code>1</code> | <code>Who discovered gravity?</code> | <code>Gravity discoverer</code> | |
| | <code>0</code> | <code>Can you help me understand this report?</code> | <code>Can you help me write this report?</code> | |
| * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
| ### 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`: 15 |
| - `lr_scheduler_type`: reduce_lr_on_plateau |
| - `warmup_ratio`: 0.1 |
| - `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`: 15 |
| - `max_steps`: -1 |
| - `lr_scheduler_type`: reduce_lr_on_plateau |
| - `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`: 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 | loss | pair-class-dev_max_ap | pair-class-test_max_ap | |
| |:-----------:|:-------:|:----------:|:---------------------:|:----------------------:| |
| | 0 | 0 | - | 0.6426 | - | |
| | 0.9677 | 15 | 3.1942 | 0.7846 | - | |
| | 2.0 | 31 | 2.2259 | 0.8691 | - | |
| | 2.9677 | 46 | 1.8185 | 0.9075 | - | |
| | 4.0 | 62 | 1.6203 | 0.9240 | - | |
| | 4.9677 | 77 | 1.4360 | 0.9308 | - | |
| | 6.0 | 93 | 1.3889 | 0.9351 | - | |
| | 6.9677 | 108 | 1.2959 | 0.9381 | - | |
| | 8.0 | 124 | 1.1657 | 0.9425 | - | |
| | 8.9677 | 139 | 1.1238 | 0.9439 | - | |
| | 10.0 | 155 | 1.0300 | 0.9473 | - | |
| | 10.9677 | 170 | 0.9543 | 0.9503 | - | |
| | 12.0 | 186 | 0.8371 | 0.9540 | - | |
| | 12.9677 | 201 | 0.8020 | 0.9558 | - | |
| | 14.0 | 217 | 0.7933 | 0.9579 | - | |
| | **14.5161** | **225** | **0.7888** | **0.9587** | **0.9587** | |
|
|
| * 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", |
| } |
| ``` |
|
|
| <!-- |
| ## 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.* |
| --> |
