| | --- |
| | base_model: sentence-transformers/all-MiniLM-L6-v2 |
| | 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:4505 |
| | - loss:OnlineContrastiveLoss |
| | widget: |
| | - source_sentence: Greektown on the Danforth |
| | sentences: |
| | - Gregarious |
| | - Gregarious |
| | - Gregarious |
| | - source_sentence: Temple of the Emerald Buddha (Wat Phra Kaew) |
| | sentences: |
| | - Respectful |
| | - Uninterested |
| | - Respectful |
| | - source_sentence: Natureland Liat Towers |
| | sentences: |
| | - Careless |
| | - Disinterested |
| | - Aggressive |
| | - source_sentence: Old Town |
| | sentences: |
| | - Reserved |
| | - Laid-back |
| | - Callous |
| | - source_sentence: Khaosan Road |
| | sentences: |
| | - Adventurous |
| | - Adventurous |
| | - Reserved |
| | model-index: |
| | - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 |
| | results: |
| | - task: |
| | type: binary-classification |
| | name: Binary Classification |
| | dataset: |
| | name: Unknown |
| | type: unknown |
| | metrics: |
| | - type: cosine_accuracy |
| | value: 0.9573712255772646 |
| | name: Cosine Accuracy |
| | - type: cosine_accuracy_threshold |
| | value: 0.8162947297096252 |
| | name: Cosine Accuracy Threshold |
| | - type: cosine_f1 |
| | value: 0.958041958041958 |
| | name: Cosine F1 |
| | - type: cosine_f1_threshold |
| | value: 0.8131216764450073 |
| | name: Cosine F1 Threshold |
| | - type: cosine_precision |
| | value: 0.9681978798586572 |
| | name: Cosine Precision |
| | - type: cosine_recall |
| | value: 0.9480968858131488 |
| | name: Cosine Recall |
| | - type: cosine_ap |
| | value: 0.9909492524224418 |
| | name: Cosine Ap |
| | - type: dot_accuracy |
| | value: 0.9573712255772646 |
| | name: Dot Accuracy |
| | - type: dot_accuracy_threshold |
| | value: 0.8162947297096252 |
| | name: Dot Accuracy Threshold |
| | - type: dot_f1 |
| | value: 0.958041958041958 |
| | name: Dot F1 |
| | - type: dot_f1_threshold |
| | value: 0.8131217360496521 |
| | name: Dot F1 Threshold |
| | - type: dot_precision |
| | value: 0.9681978798586572 |
| | name: Dot Precision |
| | - type: dot_recall |
| | value: 0.9480968858131488 |
| | name: Dot Recall |
| | - type: dot_ap |
| | value: 0.9909492524224418 |
| | name: Dot Ap |
| | - type: manhattan_accuracy |
| | value: 0.9609236234458259 |
| | name: Manhattan Accuracy |
| | - type: manhattan_accuracy_threshold |
| | value: 9.564813613891602 |
| | name: Manhattan Accuracy Threshold |
| | - type: manhattan_f1 |
| | value: 0.9619377162629758 |
| | name: Manhattan F1 |
| | - type: manhattan_f1_threshold |
| | value: 9.564813613891602 |
| | name: Manhattan F1 Threshold |
| | - type: manhattan_precision |
| | value: 0.9619377162629758 |
| | name: Manhattan Precision |
| | - type: manhattan_recall |
| | value: 0.9619377162629758 |
| | name: Manhattan Recall |
| | - type: manhattan_ap |
| | value: 0.9908734681022205 |
| | name: Manhattan Ap |
| | - type: euclidean_accuracy |
| | value: 0.9573712255772646 |
| | name: Euclidean Accuracy |
| | - type: euclidean_accuracy_threshold |
| | value: 0.6061439514160156 |
| | name: Euclidean Accuracy Threshold |
| | - type: euclidean_f1 |
| | value: 0.958041958041958 |
| | name: Euclidean F1 |
| | - type: euclidean_f1_threshold |
| | value: 0.6113559007644653 |
| | name: Euclidean F1 Threshold |
| | - type: euclidean_precision |
| | value: 0.9681978798586572 |
| | name: Euclidean Precision |
| | - type: euclidean_recall |
| | value: 0.9480968858131488 |
| | name: Euclidean Recall |
| | - type: euclidean_ap |
| | value: 0.9909492524224418 |
| | name: Euclidean Ap |
| | - type: max_accuracy |
| | value: 0.9609236234458259 |
| | name: Max Accuracy |
| | - type: max_accuracy_threshold |
| | value: 9.564813613891602 |
| | name: Max Accuracy Threshold |
| | - type: max_f1 |
| | value: 0.9619377162629758 |
| | name: Max F1 |
| | - type: max_f1_threshold |
| | value: 9.564813613891602 |
| | name: Max F1 Threshold |
| | - type: max_precision |
| | value: 0.9681978798586572 |
| | name: Max Precision |
| | - type: max_recall |
| | value: 0.9619377162629758 |
| | name: Max Recall |
| | - type: max_ap |
| | value: 0.9909492524224418 |
| | name: Max Ap |
| | - task: |
| | type: binary-classification |
| | name: Binary Classification |
| | dataset: |
| | name: test |
| | type: test |
| | metrics: |
| | - type: cosine_accuracy |
| | value: 0.9592198581560284 |
| | name: Cosine Accuracy |
| | - type: cosine_accuracy_threshold |
| | value: 0.7969272136688232 |
| | name: Cosine Accuracy Threshold |
| | - type: cosine_f1 |
| | value: 0.9591474245115454 |
| | name: Cosine F1 |
| | - type: cosine_f1_threshold |
| | value: 0.7969272136688232 |
| | name: Cosine F1 Threshold |
| | - type: cosine_precision |
| | value: 0.9574468085106383 |
| | name: Cosine Precision |
| | - type: cosine_recall |
| | value: 0.9608540925266904 |
| | name: Cosine Recall |
| | - type: cosine_ap |
| | value: 0.9877694290490489 |
| | name: Cosine Ap |
| | - type: dot_accuracy |
| | value: 0.9592198581560284 |
| | name: Dot Accuracy |
| | - type: dot_accuracy_threshold |
| | value: 0.7969271540641785 |
| | name: Dot Accuracy Threshold |
| | - type: dot_f1 |
| | value: 0.9591474245115454 |
| | name: Dot F1 |
| | - type: dot_f1_threshold |
| | value: 0.7969271540641785 |
| | name: Dot F1 Threshold |
| | - type: dot_precision |
| | value: 0.9574468085106383 |
| | name: Dot Precision |
| | - type: dot_recall |
| | value: 0.9608540925266904 |
| | name: Dot Recall |
| | - type: dot_ap |
| | value: 0.9877694290490489 |
| | name: Dot Ap |
| | - type: manhattan_accuracy |
| | value: 0.9556737588652482 |
| | name: Manhattan Accuracy |
| | - type: manhattan_accuracy_threshold |
| | value: 9.808526992797852 |
| | name: Manhattan Accuracy Threshold |
| | - type: manhattan_f1 |
| | value: 0.9557522123893805 |
| | name: Manhattan F1 |
| | - type: manhattan_f1_threshold |
| | value: 9.917011260986328 |
| | name: Manhattan F1 Threshold |
| | - type: manhattan_precision |
| | value: 0.9507042253521126 |
| | name: Manhattan Precision |
| | - type: manhattan_recall |
| | value: 0.9608540925266904 |
| | name: Manhattan Recall |
| | - type: manhattan_ap |
| | value: 0.9866404317968996 |
| | name: Manhattan Ap |
| | - type: euclidean_accuracy |
| | value: 0.9592198581560284 |
| | name: Euclidean Accuracy |
| | - type: euclidean_accuracy_threshold |
| | value: 0.6372953653335571 |
| | name: Euclidean Accuracy Threshold |
| | - type: euclidean_f1 |
| | value: 0.9591474245115454 |
| | name: Euclidean F1 |
| | - type: euclidean_f1_threshold |
| | value: 0.6372953653335571 |
| | name: Euclidean F1 Threshold |
| | - type: euclidean_precision |
| | value: 0.9574468085106383 |
| | name: Euclidean Precision |
| | - type: euclidean_recall |
| | value: 0.9608540925266904 |
| | name: Euclidean Recall |
| | - type: euclidean_ap |
| | value: 0.9877694290490489 |
| | name: Euclidean Ap |
| | - type: max_accuracy |
| | value: 0.9592198581560284 |
| | name: Max Accuracy |
| | - type: max_accuracy_threshold |
| | value: 9.808526992797852 |
| | name: Max Accuracy Threshold |
| | - type: max_f1 |
| | value: 0.9591474245115454 |
| | name: Max F1 |
| | - type: max_f1_threshold |
| | value: 9.917011260986328 |
| | name: Max F1 Threshold |
| | - type: max_precision |
| | value: 0.9574468085106383 |
| | name: Max Precision |
| | - type: max_recall |
| | value: 0.9608540925266904 |
| | name: Max Recall |
| | - type: max_ap |
| | value: 0.9877694290490489 |
| | name: Max Ap |
| | --- |
| | |
| | # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 |
| |
|
| | This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-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-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 --> |
| | - **Maximum Sequence Length:** 256 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': 256, '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("overfitting-co/A2P-constrastive-all") |
| | # Run inference |
| | sentences = [ |
| | 'Khaosan Road', |
| | 'Reserved', |
| | 'Adventurous', |
| | ] |
| | 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 |
| |
|
| | * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
| |
|
| | | Metric | Value | |
| | |:-----------------------------|:-----------| |
| | | cosine_accuracy | 0.9574 | |
| | | cosine_accuracy_threshold | 0.8163 | |
| | | cosine_f1 | 0.958 | |
| | | cosine_f1_threshold | 0.8131 | |
| | | cosine_precision | 0.9682 | |
| | | cosine_recall | 0.9481 | |
| | | cosine_ap | 0.9909 | |
| | | dot_accuracy | 0.9574 | |
| | | dot_accuracy_threshold | 0.8163 | |
| | | dot_f1 | 0.958 | |
| | | dot_f1_threshold | 0.8131 | |
| | | dot_precision | 0.9682 | |
| | | dot_recall | 0.9481 | |
| | | dot_ap | 0.9909 | |
| | | manhattan_accuracy | 0.9609 | |
| | | manhattan_accuracy_threshold | 9.5648 | |
| | | manhattan_f1 | 0.9619 | |
| | | manhattan_f1_threshold | 9.5648 | |
| | | manhattan_precision | 0.9619 | |
| | | manhattan_recall | 0.9619 | |
| | | manhattan_ap | 0.9909 | |
| | | euclidean_accuracy | 0.9574 | |
| | | euclidean_accuracy_threshold | 0.6061 | |
| | | euclidean_f1 | 0.958 | |
| | | euclidean_f1_threshold | 0.6114 | |
| | | euclidean_precision | 0.9682 | |
| | | euclidean_recall | 0.9481 | |
| | | euclidean_ap | 0.9909 | |
| | | max_accuracy | 0.9609 | |
| | | max_accuracy_threshold | 9.5648 | |
| | | max_f1 | 0.9619 | |
| | | max_f1_threshold | 9.5648 | |
| | | max_precision | 0.9682 | |
| | | max_recall | 0.9619 | |
| | | **max_ap** | **0.9909** | |
| | |
| | #### Binary Classification |
| | * Dataset: `test` |
| | * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
| | |
| | | Metric | Value | |
| | |:-----------------------------|:-----------| |
| | | cosine_accuracy | 0.9592 | |
| | | cosine_accuracy_threshold | 0.7969 | |
| | | cosine_f1 | 0.9591 | |
| | | cosine_f1_threshold | 0.7969 | |
| | | cosine_precision | 0.9574 | |
| | | cosine_recall | 0.9609 | |
| | | cosine_ap | 0.9878 | |
| | | dot_accuracy | 0.9592 | |
| | | dot_accuracy_threshold | 0.7969 | |
| | | dot_f1 | 0.9591 | |
| | | dot_f1_threshold | 0.7969 | |
| | | dot_precision | 0.9574 | |
| | | dot_recall | 0.9609 | |
| | | dot_ap | 0.9878 | |
| | | manhattan_accuracy | 0.9557 | |
| | | manhattan_accuracy_threshold | 9.8085 | |
| | | manhattan_f1 | 0.9558 | |
| | | manhattan_f1_threshold | 9.917 | |
| | | manhattan_precision | 0.9507 | |
| | | manhattan_recall | 0.9609 | |
| | | manhattan_ap | 0.9866 | |
| | | euclidean_accuracy | 0.9592 | |
| | | euclidean_accuracy_threshold | 0.6373 | |
| | | euclidean_f1 | 0.9591 | |
| | | euclidean_f1_threshold | 0.6373 | |
| | | euclidean_precision | 0.9574 | |
| | | euclidean_recall | 0.9609 | |
| | | euclidean_ap | 0.9878 | |
| | | max_accuracy | 0.9592 | |
| | | max_accuracy_threshold | 9.8085 | |
| | | max_f1 | 0.9591 | |
| | | max_f1_threshold | 9.917 | |
| | | max_precision | 0.9574 | |
| | | max_recall | 0.9609 | |
| | | **max_ap** | **0.9878** | |
| |
|
| | <!-- |
| | ## 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: 4,505 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 | int | |
| | | details | <ul><li>min: 3 tokens</li><li>mean: 6.49 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.79 tokens</li><li>max: 8 tokens</li></ul> | <ul><li>0: ~52.30%</li><li>1: ~47.70%</li></ul> | |
| | * Samples: |
| | | sentence_0 | sentence_1 | label | |
| | |:----------------------------------------|:-------------------------|:---------------| |
| | | <code>N Seoul Tower</code> | <code>Laid-back</code> | <code>0</code> | |
| | | <code>Magere Brug</code> | <code>Romantic</code> | <code>1</code> | |
| | | <code>Polynesian Cultural Center</code> | <code>Adventurous</code> | <code>1</code> | |
| | * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
| |
|
| | ### Training Hyperparameters |
| | #### Non-Default Hyperparameters |
| |
|
| | - `per_device_train_batch_size`: 32 |
| | - `per_device_eval_batch_size`: 32 |
| | - `num_train_epochs`: 5 |
| | - `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`: 32 |
| | - `per_device_eval_batch_size`: 32 |
| | - `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`: 5 |
| | - `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} |
| | - `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 | max_ap | test_max_ap | |
| | |:------:|:----:|:-------------:|:------:|:-----------:| |
| | | 1.0 | 141 | - | 0.6780 | - | |
| | | 2.0 | 282 | - | 0.7538 | - | |
| | | 3.0 | 423 | - | 0.8064 | - | |
| | | 3.5461 | 500 | 6.7404 | - | - | |
| | | 4.0 | 564 | - | 0.9751 | - | |
| | | 5.0 | 705 | - | 0.9909 | 0.9878 | |
| |
|
| |
|
| | ### 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: 3.1.0 |
| | - 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.* |
| | --> |
