| | --- |
| | tags: |
| | - sentence-transformers |
| | - sentence-similarity |
| | - feature-extraction |
| | - generated_from_trainer |
| | - dataset_size:784827 |
| | - loss:ContrastiveLoss |
| | base_model: intfloat/e5-large-v2 |
| | widget: |
| | - source_sentence: >- |
| | query: The study addresses the need for effective tools that allow both |
| | novice and expert users to analyze the diversity of news coverage about |
| | events. It highlights the importance of tailoring the interface to |
| | accommodate non-expert users while also considering the insights of |
| | journalism-savvy users, indicating a gap in existing systems that cater to |
| | varying levels of expertise in news analysis.We suggest combining 'a |
| | coordinated visualization interface tailored for visualization non-expert |
| | users' and |
| | sentences: |
| | - graph convolution |
| | - Monte-Carlo sampling |
| | - geometric features derived from perception sensor data |
| | - source_sentence: >- |
| | query: The accuracy of pixel flows is crucial for achieving high-quality |
| | video enhancement, yet most prior works focus on estimating dense flows that |
| | are generally less robust and computationally expensive. This highlights a |
| | gap in existing methodologies that fail to prioritize accuracy over density, |
| | necessitating a more efficient approach to flow estimation for video |
| | enhancement tasks.We suggest combining 'sparse point cloud data' and |
| | sentences: |
| | - a human cognition mechanism, object unity |
| | - Bayesian Optimization |
| | - offline supervised learning |
| | - source_sentence: >- |
| | query: The traditional frame of discernment lacks a crucial factor, the |
| | sequence of propositions, which limits the effectiveness of existing methods |
| | to measure uncertainty. This gap highlights the need for a more |
| | comprehensive approach that can better represent the relationships between |
| | the elements of the frame of discernment.We suggest 'combine the order of |
| | propositions and the mass of them' inspired by |
| | sentences: |
| | - a MIA-Module |
| | - an Explore-m problem--a well-studied problem related to multi-armed bandits |
| | - based on the novel method UGPIG |
| | - source_sentence: >- |
| | query: Existing methods for anomaly detection on dynamic graphs struggle |
| | with capturing complex time information in graph structures and generating |
| | effective negative samples for unsupervised learning. These challenges |
| | highlight the need for improved methodologies that can address the |
| | limitations of current approaches in this field.We suggest combining 'a |
| | message-passing framework' and |
| | sentences: |
| | - an LSTM encoder-decoder |
| | - an energy-based model |
| | - >- |
| | learning the frame-wise associations between detections in consecutive |
| | frames |
| | - source_sentence: >- |
| | query: The study addresses the need for effective time series forecasting |
| | methods to estimate the spread of epidemics, particularly in light of the |
| | resurgence of COVID-19 cases. It highlights the importance of accurately |
| | modeling both linear and non-linear features of epidemic data to provide |
| | state authorities and health officials with reliable short-term forecasts |
| | and strategies.We suggest combining 'ARIMA' and |
| | sentences: |
| | - visualization methodologies |
| | - geometry |
| | - the utilization of a gradient signed distance field (gradient-SDF) |
| | pipeline_tag: sentence-similarity |
| | library_name: sentence-transformers |
| | license: cc |
| | datasets: |
| | - noystl/Recombination-Pred |
| | language: |
| | - en |
| | --- |
| | |
| | # SentenceTransformer based on intfloat/e5-large-v2 |
| |
|
| | This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/e5-large-v2](https://huggingface.co/intfloat/e5-large-v2). It maps sentences & paragraphs to a 1024-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/e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) <!-- at revision f169b11e22de13617baa190a028a32f3493550b6 --> |
| | - **Maximum Sequence Length:** 512 tokens |
| | - **Output Dimensionality:** 1024 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': 512, 'do_lower_case': False}) with Transformer model: BertModel |
| | (1): Pooling({'word_embedding_dimension': 1024, '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("sentence_transformers_model_id") |
| | # Run inference |
| | sentences = [ |
| | "query: The study addresses the need for effective time series forecasting methods to estimate the spread of epidemics, particularly in light of the resurgence of COVID-19 cases. It highlights the importance of accurately modeling both linear and non-linear features of epidemic data to provide state authorities and health officials with reliable short-term forecasts and strategies.We suggest combining 'ARIMA' and ", |
| | 'visualization methodologies', |
| | 'the utilization of a gradient signed distance field (gradient-SDF)', |
| | ] |
| | embeddings = model.encode(sentences) |
| | print(embeddings.shape) |
| | # [3, 1024] |
| | |
| | # 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.* |
| | --> |
| |
|
| | <!-- |
| | ## 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: 784,827 training samples |
| | * Columns: <code>query</code>, <code>answer</code>, and <code>label</code> |
| | * Approximate statistics based on the first 1000 samples: |
| | | | query | answer | label | |
| | |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------| |
| | | type | string | string | int | |
| | | details | <ul><li>min: 60 tokens</li><li>mean: 77.86 tokens</li><li>max: 93 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>0: ~96.70%</li><li>1: ~3.30%</li></ul> | |
| | * Samples: |
| | | query | answer | label | |
| | |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------|:---------------| |
| | | <code>query: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>a multilayer perceptron</code> | <code>1</code> | |
| | | <code>query: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>an optimal transport problem</code> | <code>0</code> | |
| | | <code>query: The study addresses the challenge of action segmentation under weak supervision, where the available ground truth only indicates the presence of actions without providing their temporal ordering or occurrence timing in training videos. This limitation necessitates the development of a method to generate pseudo-ground truth for effective training and improve performance in action segmentation and alignment tasks.We suggest combining 'a Hidden Markov Model' and </code> | <code>a context enhancement module</code> | <code>0</code> | |
| | * Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: |
| | ```json |
| | { |
| | "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", |
| | "margin": 0.5, |
| | "size_average": true |
| | } |
| | ``` |
| |
|
| | ### Training Hyperparameters |
| | #### Non-Default Hyperparameters |
| |
|
| | - `per_device_train_batch_size`: 64 |
| | - `learning_rate`: 4.0560820385265185e-06 |
| | - `warmup_ratio`: 0.21933051020273267 |
| | - `bf16`: True |
| | - `prompts`: {'query': 'query: '} |
| | - `batch_sampler`: no_duplicates |
| | |
| | #### 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`: 64 |
| | - `per_device_eval_batch_size`: 8 |
| | - `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`: 4.0560820385265185e-06 |
| | - `weight_decay`: 0.0 |
| | - `adam_beta1`: 0.9 |
| | - `adam_beta2`: 0.999 |
| | - `adam_epsilon`: 1e-08 |
| | - `max_grad_norm`: 1.0 |
| | - `num_train_epochs`: 3 |
| | - `max_steps`: -1 |
| | - `lr_scheduler_type`: linear |
| | - `lr_scheduler_kwargs`: {} |
| | - `warmup_ratio`: 0.21933051020273267 |
| | - `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`: True |
| | - `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`: 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 |
| | - `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 |
| | - `use_liger_kernel`: False |
| | - `eval_use_gather_object`: False |
| | - `average_tokens_across_devices`: False |
| | - `prompts`: {'query': 'query: '} |
| | - `batch_sampler`: no_duplicates |
| | - `multi_dataset_batch_sampler`: proportional |
| |
|
| | </details> |
| |
|
| | ### Training Logs |
| | <details><summary>Click to expand</summary> |
| |
|
| | | Epoch | Step | Training Loss | |
| | |:------:|:-----:|:-------------:| |
| | | 0.0082 | 100 | 0.0321 | |
| | | 0.0163 | 200 | 0.0312 | |
| | | 0.0245 | 300 | 0.0268 | |
| | | 0.0326 | 400 | 0.0139 | |
| | | 0.0408 | 500 | 0.0052 | |
| | | 0.0489 | 600 | 0.0037 | |
| | | 0.0571 | 700 | 0.0037 | |
| | | 0.0652 | 800 | 0.0037 | |
| | | 0.0734 | 900 | 0.0047 | |
| | | 0.0815 | 1000 | 0.0038 | |
| | | 0.0897 | 1100 | 0.0037 | |
| | | 0.0979 | 1200 | 0.0037 | |
| | | 0.1060 | 1300 | 0.0037 | |
| | | 0.1142 | 1400 | 0.0049 | |
| | | 0.1223 | 1500 | 0.0037 | |
| | | 0.1305 | 1600 | 0.0036 | |
| | | 0.1386 | 1700 | 0.0037 | |
| | | 0.1468 | 1800 | 0.0048 | |
| | | 0.1549 | 1900 | 0.0037 | |
| | | 0.1631 | 2000 | 0.0036 | |
| | | 0.1712 | 2100 | 0.0037 | |
| | | 0.1794 | 2200 | 0.0037 | |
| | | 0.1876 | 2300 | 0.0048 | |
| | | 0.1957 | 2400 | 0.0036 | |
| | | 0.2039 | 2500 | 0.0037 | |
| | | 0.2120 | 2600 | 0.0036 | |
| | | 0.2202 | 2700 | 0.0046 | |
| | | 0.2283 | 2800 | 0.0036 | |
| | | 0.2365 | 2900 | 0.0035 | |
| | | 0.2446 | 3000 | 0.0035 | |
| | | 0.2528 | 3100 | 0.0038 | |
| | | 0.2609 | 3200 | 0.0042 | |
| | | 0.2691 | 3300 | 0.0036 | |
| | | 0.2773 | 3400 | 0.0035 | |
| | | 0.2854 | 3500 | 0.0035 | |
| | | 0.2936 | 3600 | 0.0045 | |
| | | 0.3017 | 3700 | 0.0034 | |
| | | 0.3099 | 3800 | 0.0035 | |
| | | 0.3180 | 3900 | 0.0034 | |
| | | 0.3262 | 4000 | 0.0043 | |
| | | 0.3343 | 4100 | 0.0036 | |
| | | 0.3425 | 4200 | 0.0033 | |
| | | 0.3506 | 4300 | 0.0034 | |
| | | 0.3588 | 4400 | 0.0035 | |
| | | 0.3670 | 4500 | 0.0042 | |
| | | 0.3751 | 4600 | 0.0033 | |
| | | 0.3833 | 4700 | 0.0035 | |
| | | 0.3914 | 4800 | 0.0034 | |
| | | 0.3996 | 4900 | 0.0043 | |
| | | 0.4077 | 5000 | 0.0034 | |
| | | 0.4159 | 5100 | 0.0033 | |
| | | 0.4240 | 5200 | 0.0033 | |
| | | 0.4322 | 5300 | 0.0033 | |
| | | 0.4403 | 5400 | 0.0043 | |
| | | 0.4485 | 5500 | 0.0033 | |
| | | 0.4567 | 5600 | 0.0033 | |
| | | 0.4648 | 5700 | 0.0034 | |
| | | 0.4730 | 5800 | 0.0042 | |
| | | 0.4811 | 5900 | 0.0033 | |
| | | 0.4893 | 6000 | 0.0033 | |
| | | 0.4974 | 6100 | 0.0032 | |
| | | 0.5056 | 6200 | 0.0035 | |
| | | 0.5137 | 6300 | 0.0037 | |
| | | 0.5219 | 6400 | 0.0034 | |
| | | 0.5300 | 6500 | 0.0034 | |
| | | 0.5382 | 6600 | 0.0033 | |
| | | 0.5464 | 6700 | 0.0041 | |
| | | 0.5545 | 6800 | 0.0033 | |
| | | 0.5627 | 6900 | 0.0033 | |
| | | 0.5708 | 7000 | 0.0031 | |
| | | 0.5790 | 7100 | 0.004 | |
| | | 0.5871 | 7200 | 0.0035 | |
| | | 0.5953 | 7300 | 0.0033 | |
| | | 0.6034 | 7400 | 0.0032 | |
| | | 0.6116 | 7500 | 0.0032 | |
| | | 0.6198 | 7600 | 0.0041 | |
| | | 0.6279 | 7700 | 0.0033 | |
| | | 0.6361 | 7800 | 0.0033 | |
| | | 0.6442 | 7900 | 0.0032 | |
| | | 0.6524 | 8000 | 0.0041 | |
| | | 0.6605 | 8100 | 0.0032 | |
| | | 0.6687 | 8200 | 0.0033 | |
| | | 0.6768 | 8300 | 0.003 | |
| | | 0.6850 | 8400 | 0.003 | |
| | | 0.6931 | 8500 | 0.0038 | |
| | | 0.7013 | 8600 | 0.0033 | |
| | | 0.7095 | 8700 | 0.0031 | |
| | | 0.7176 | 8800 | 0.0029 | |
| | | 0.7258 | 8900 | 0.0037 | |
| | | 0.7339 | 9000 | 0.0034 | |
| | | 0.7421 | 9100 | 0.0031 | |
| | | 0.7502 | 9200 | 0.003 | |
| | | 0.7584 | 9300 | 0.0031 | |
| | | 0.7665 | 9400 | 0.0037 | |
| | | 0.7747 | 9500 | 0.0032 | |
| | | 0.7828 | 9600 | 0.0029 | |
| | | 0.7910 | 9700 | 0.0028 | |
| | | 0.7992 | 9800 | 0.0036 | |
| | | 0.8073 | 9900 | 0.0033 | |
| | | 0.8155 | 10000 | 0.0031 | |
| | | 0.8236 | 10100 | 0.0029 | |
| | | 0.8318 | 10200 | 0.0034 | |
| | | 0.8399 | 10300 | 0.0033 | |
| | | 0.8481 | 10400 | 0.0032 | |
| | | 0.8562 | 10500 | 0.003 | |
| | | 0.8644 | 10600 | 0.003 | |
| | | 0.8725 | 10700 | 0.0034 | |
| | | 0.8807 | 10800 | 0.0033 | |
| | | 0.8889 | 10900 | 0.003 | |
| | | 0.8970 | 11000 | 0.0029 | |
| | | 0.9052 | 11100 | 0.0036 | |
| | | 0.9133 | 11200 | 0.0031 | |
| | | 0.9215 | 11300 | 0.0031 | |
| | | 0.9296 | 11400 | 0.003 | |
| | | 0.9378 | 11500 | 0.003 | |
| | | 0.9459 | 11600 | 0.0035 | |
| | | 0.9541 | 11700 | 0.0032 | |
| | | 0.9622 | 11800 | 0.0029 | |
| | | 0.9704 | 11900 | 0.0031 | |
| | | 0.9786 | 12000 | 0.0036 | |
| | | 0.9867 | 12100 | 0.0033 | |
| | | 0.9949 | 12200 | 0.0031 | |
| | | 1.0030 | 12300 | 0.0034 | |
| | | 1.0112 | 12400 | 0.0031 | |
| | | 1.0193 | 12500 | 0.0032 | |
| | | 1.0275 | 12600 | 0.0029 | |
| | | 1.0356 | 12700 | 0.0037 | |
| | | 1.0438 | 12800 | 0.0031 | |
| | | 1.0519 | 12900 | 0.0028 | |
| | | 1.0601 | 13000 | 0.0029 | |
| | | 1.0683 | 13100 | 0.0029 | |
| | | 1.0764 | 13200 | 0.0038 | |
| | | 1.0846 | 13300 | 0.0029 | |
| | | 1.0927 | 13400 | 0.0029 | |
| | | 1.1009 | 13500 | 0.0029 | |
| | | 1.1090 | 13600 | 0.0037 | |
| | | 1.1172 | 13700 | 0.003 | |
| | | 1.1253 | 13800 | 0.003 | |
| | | 1.1335 | 13900 | 0.0029 | |
| | | 1.1416 | 14000 | 0.0034 | |
| | | 1.1498 | 14100 | 0.0031 | |
| | | 1.1580 | 14200 | 0.0029 | |
| | | 1.1661 | 14300 | 0.0029 | |
| | | 1.1743 | 14400 | 0.0028 | |
| | | 1.1824 | 14500 | 0.0037 | |
| | | 1.1906 | 14600 | 0.0029 | |
| | | 1.1987 | 14700 | 0.0028 | |
| | | 1.2069 | 14800 | 0.0029 | |
| | | 1.2150 | 14900 | 0.0035 | |
| | | 1.2232 | 15000 | 0.0029 | |
| | | 1.2313 | 15100 | 0.0029 | |
| | | 1.2395 | 15200 | 0.0027 | |
| | | 1.2477 | 15300 | 0.003 | |
| | | 1.2558 | 15400 | 0.0035 | |
| | | 1.2640 | 15500 | 0.0027 | |
| | | 1.2721 | 15600 | 0.0028 | |
| | | 1.2803 | 15700 | 0.0028 | |
| | | 1.2884 | 15800 | 0.0037 | |
| | | 1.2966 | 15900 | 0.0028 | |
| | | 1.3047 | 16000 | 0.0028 | |
| | | 1.3129 | 16100 | 0.0028 | |
| | | 1.3210 | 16200 | 0.0029 | |
| | | 1.3292 | 16300 | 0.0034 | |
| | | 1.3374 | 16400 | 0.0028 | |
| | | 1.3455 | 16500 | 0.0026 | |
| | | 1.3537 | 16600 | 0.0029 | |
| | | 1.3618 | 16700 | 0.0034 | |
| | | 1.3700 | 16800 | 0.0028 | |
| | | 1.3781 | 16900 | 0.0027 | |
| | | 1.3863 | 17000 | 0.003 | |
| | | 1.3944 | 17100 | 0.0034 | |
| | | 1.4026 | 17200 | 0.0028 | |
| | | 1.4107 | 17300 | 0.0028 | |
| | | 1.4189 | 17400 | 0.0027 | |
| | | 1.4271 | 17500 | 0.0028 | |
| | | 1.4352 | 17600 | 0.0036 | |
| | | 1.4434 | 17700 | 0.0028 | |
| | | 1.4515 | 17800 | 0.0027 | |
| | | 1.4597 | 17900 | 0.0028 | |
| | | 1.4678 | 18000 | 0.0032 | |
| | | 1.4760 | 18100 | 0.0029 | |
| | | 1.4841 | 18200 | 0.0028 | |
| | | 1.4923 | 18300 | 0.0028 | |
| | | 1.5004 | 18400 | 0.0028 | |
| | | 1.5086 | 18500 | 0.0033 | |
| | | 1.5168 | 18600 | 0.0026 | |
| | | 1.5249 | 18700 | 0.0027 | |
| | | 1.5331 | 18800 | 0.0028 | |
| | | 1.5412 | 18900 | 0.0035 | |
| | | 1.5494 | 19000 | 0.0026 | |
| | | 1.5575 | 19100 | 0.0027 | |
| | | 1.5657 | 19200 | 0.0027 | |
| | | 1.5738 | 19300 | 0.0028 | |
| | | 1.5820 | 19400 | 0.0033 | |
| | | 1.5901 | 19500 | 0.0026 | |
| | | 1.5983 | 19600 | 0.0028 | |
| | | 1.6065 | 19700 | 0.0026 | |
| | | 1.6146 | 19800 | 0.0033 | |
| | | 1.6228 | 19900 | 0.0026 | |
| | | 1.6309 | 20000 | 0.0027 | |
| | | 1.6391 | 20100 | 0.0029 | |
| | | 1.6472 | 20200 | 0.0032 | |
| | | 1.6554 | 20300 | 0.0028 | |
| | | 1.6635 | 20400 | 0.0025 | |
| | | 1.6717 | 20500 | 0.0025 | |
| | | 1.6798 | 20600 | 0.0025 | |
| | | 1.6880 | 20700 | 0.003 | |
| | | 1.6962 | 20800 | 0.0028 | |
| | | 1.7043 | 20900 | 0.0026 | |
| | | 1.7125 | 21000 | 0.0024 | |
| | | 1.7206 | 21100 | 0.0028 | |
| | | 1.7288 | 21200 | 0.0028 | |
| | | 1.7369 | 21300 | 0.0026 | |
| | | 1.7451 | 21400 | 0.0026 | |
| | | 1.7532 | 21500 | 0.0025 | |
| | | 1.7614 | 21600 | 0.003 | |
| | | 1.7696 | 21700 | 0.0027 | |
| | | 1.7777 | 21800 | 0.0023 | |
| | | 1.7859 | 21900 | 0.0025 | |
| | | 1.7940 | 22000 | 0.0028 | |
| | | 1.8022 | 22100 | 0.0025 | |
| | | 1.8103 | 22200 | 0.0026 | |
| | | 1.8185 | 22300 | 0.0024 | |
| | | 1.8266 | 22400 | 0.0025 | |
| | | 1.8348 | 22500 | 0.0029 | |
| | | 1.8429 | 22600 | 0.0028 | |
| | | 1.8511 | 22700 | 0.0024 | |
| | | 1.8593 | 22800 | 0.0026 | |
| | | 1.8674 | 22900 | 0.003 | |
| | | 1.8756 | 23000 | 0.0026 | |
| | | 1.8837 | 23100 | 0.0025 | |
| | | 1.8919 | 23200 | 0.0025 | |
| | | 1.9000 | 23300 | 0.0027 | |
| | | 1.9082 | 23400 | 0.0025 | |
| | | 1.9163 | 23500 | 0.0026 | |
| | | 1.9245 | 23600 | 0.0026 | |
| | | 1.9326 | 23700 | 0.0026 | |
| | | 1.9408 | 23800 | 0.003 | |
| | | 1.9490 | 23900 | 0.0026 | |
| | | 1.9571 | 24000 | 0.0026 | |
| | | 1.9653 | 24100 | 0.0025 | |
| | | 1.9734 | 24200 | 0.003 | |
| | | 1.9816 | 24300 | 0.0028 | |
| | | 1.9897 | 24400 | 0.0025 | |
| | | 1.9979 | 24500 | 0.0028 | |
| | | 2.0060 | 24600 | 0.0029 | |
| | | 2.0142 | 24700 | 0.0025 | |
| | | 2.0223 | 24800 | 0.0026 | |
| | | 2.0305 | 24900 | 0.0031 | |
| | | 2.0387 | 25000 | 0.0025 | |
| | | 2.0468 | 25100 | 0.0025 | |
| | | 2.0550 | 25200 | 0.0023 | |
| | | 2.0631 | 25300 | 0.0024 | |
| | | 2.0713 | 25400 | 0.0031 | |
| | | 2.0794 | 25500 | 0.0024 | |
| | | 2.0876 | 25600 | 0.0025 | |
| | | 2.0957 | 25700 | 0.0024 | |
| | | 2.1039 | 25800 | 0.0031 | |
| | | 2.1120 | 25900 | 0.0024 | |
| | | 2.1202 | 26000 | 0.0025 | |
| | | 2.1284 | 26100 | 0.0025 | |
| | | 2.1365 | 26200 | 0.0024 | |
| | | 2.1447 | 26300 | 0.003 | |
| | | 2.1528 | 26400 | 0.0025 | |
| | | 2.1610 | 26500 | 0.0024 | |
| | | 2.1691 | 26600 | 0.0026 | |
| | | 2.1773 | 26700 | 0.003 | |
| | | 2.1854 | 26800 | 0.0025 | |
| | | 2.1936 | 26900 | 0.0025 | |
| | | 2.2017 | 27000 | 0.0024 | |
| | | 2.2099 | 27100 | 0.003 | |
| | | 2.2181 | 27200 | 0.0024 | |
| | | 2.2262 | 27300 | 0.0026 | |
| | | 2.2344 | 27400 | 0.0023 | |
| | | 2.2425 | 27500 | 0.0023 | |
| | | 2.2507 | 27600 | 0.0031 | |
| | | 2.2588 | 27700 | 0.0023 | |
| | | 2.2670 | 27800 | 0.0022 | |
| | | 2.2751 | 27900 | 0.0024 | |
| | | 2.2833 | 28000 | 0.0032 | |
| | | 2.2914 | 28100 | 0.0024 | |
| | | 2.2996 | 28200 | 0.0023 | |
| | | 2.3078 | 28300 | 0.0026 | |
| | | 2.3159 | 28400 | 0.0023 | |
| | | 2.3241 | 28500 | 0.0031 | |
| | | 2.3322 | 28600 | 0.0024 | |
| | | 2.3404 | 28700 | 0.0023 | |
| | | 2.3485 | 28800 | 0.0023 | |
| | | 2.3567 | 28900 | 0.0031 | |
| | | 2.3648 | 29000 | 0.0024 | |
| | | 2.3730 | 29100 | 0.0023 | |
| | | 2.3811 | 29200 | 0.0025 | |
| | | 2.3893 | 29300 | 0.0027 | |
| | | 2.3975 | 29400 | 0.0029 | |
| | | 2.4056 | 29500 | 0.0022 | |
| | | 2.4138 | 29600 | 0.0024 | |
| | | 2.4219 | 29700 | 0.0023 | |
| | | 2.4301 | 29800 | 0.0031 | |
| | | 2.4382 | 29900 | 0.0024 | |
| | | 2.4464 | 30000 | 0.0023 | |
| | | 2.4545 | 30100 | 0.0022 | |
| | | 2.4627 | 30200 | 0.0029 | |
| | | 2.4708 | 30300 | 0.0024 | |
| | | 2.4790 | 30400 | 0.0025 | |
| | | 2.4872 | 30500 | 0.0024 | |
| | | 2.4953 | 30600 | 0.0024 | |
| | | 2.5035 | 30700 | 0.003 | |
| | | 2.5116 | 30800 | 0.0021 | |
| | | 2.5198 | 30900 | 0.0023 | |
| | | 2.5279 | 31000 | 0.0024 | |
| | | 2.5361 | 31100 | 0.0032 | |
| | | 2.5442 | 31200 | 0.0023 | |
| | | 2.5524 | 31300 | 0.0022 | |
| | | 2.5605 | 31400 | 0.0024 | |
| | | 2.5687 | 31500 | 0.0023 | |
| | | 2.5769 | 31600 | 0.0029 | |
| | | 2.5850 | 31700 | 0.0023 | |
| | | 2.5932 | 31800 | 0.0023 | |
| | | 2.6013 | 31900 | 0.0023 | |
| | | 2.6095 | 32000 | 0.003 | |
| | | 2.6176 | 32100 | 0.0023 | |
| | | 2.6258 | 32200 | 0.0023 | |
| | | 2.6339 | 32300 | 0.0024 | |
| | | 2.6421 | 32400 | 0.0027 | |
| | | 2.6502 | 32500 | 0.0028 | |
| | | 2.6584 | 32600 | 0.0023 | |
| | | 2.6666 | 32700 | 0.0021 | |
| | | 2.6747 | 32800 | 0.0023 | |
| | | 2.6829 | 32900 | 0.0026 | |
| | | 2.6910 | 33000 | 0.0024 | |
| | | 2.6992 | 33100 | 0.0023 | |
| | | 2.7073 | 33200 | 0.0023 | |
| | | 2.7155 | 33300 | 0.0024 | |
| | | 2.7236 | 33400 | 0.0024 | |
| | | 2.7318 | 33500 | 0.0024 | |
| | | 2.7399 | 33600 | 0.0023 | |
| | | 2.7481 | 33700 | 0.0022 | |
| | | 2.7563 | 33800 | 0.0027 | |
| | | 2.7644 | 33900 | 0.0023 | |
| | | 2.7726 | 34000 | 0.0023 | |
| | | 2.7807 | 34100 | 0.0021 | |
| | | 2.7889 | 34200 | 0.0025 | |
| | | 2.7970 | 34300 | 0.0022 | |
| | | 2.8052 | 34400 | 0.0022 | |
| | | 2.8133 | 34500 | 0.0021 | |
| | | 2.8215 | 34600 | 0.0022 | |
| | | 2.8297 | 34700 | 0.0026 | |
| | | 2.8378 | 34800 | 0.0024 | |
| | | 2.8460 | 34900 | 0.0023 | |
| | | 2.8541 | 35000 | 0.0022 | |
| | | 2.8623 | 35100 | 0.0026 | |
| | | 2.8704 | 35200 | 0.0023 | |
| | | 2.8786 | 35300 | 0.0022 | |
| | | 2.8867 | 35400 | 0.0023 | |
| | | 2.8949 | 35500 | 0.0022 | |
| | | 2.9030 | 35600 | 0.0025 | |
| | | 2.9112 | 35700 | 0.0023 | |
| | | 2.9194 | 35800 | 0.0022 | |
| | | 2.9275 | 35900 | 0.0022 | |
| | | 2.9357 | 36000 | 0.0028 | |
| | | 2.9438 | 36100 | 0.0022 | |
| | | 2.9520 | 36200 | 0.0023 | |
| | | 2.9601 | 36300 | 0.0022 | |
| | | 2.9683 | 36400 | 0.0026 | |
| | | 2.9764 | 36500 | 0.0024 | |
| | | 2.9846 | 36600 | 0.0024 | |
| | | 2.9927 | 36700 | 0.0023 | |
| |
|
| | </details> |
| |
|
| | ### Framework Versions |
| | - Python: 3.11.2 |
| | - Sentence Transformers: 3.3.1 |
| | - Transformers: 4.49.0 |
| | - PyTorch: 2.5.1+cu124 |
| | - Accelerate: 1.0.1 |
| | - Datasets: 3.1.0 |
| | - Tokenizers: 0.21.0 |
| |
|
| | ## Citation |
| |
|
| | ### BibTeX |
| | ```bibtex |
| | @misc{sternlicht2025chimeraknowledgebaseidea, |
| | title={CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature}, |
| | author={Noy Sternlicht and Tom Hope}, |
| | year={2025}, |
| | eprint={2505.20779}, |
| | archivePrefix={arXiv}, |
| | primaryClass={cs.CL}, |
| | url={https://arxiv.org/abs/2505.20779}, |
| | } |
| | ``` |
| |
|
| | #### 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", |
| | } |
| | ``` |
| |
|
| | #### ContrastiveLoss |
| | ```bibtex |
| | @inproceedings{hadsell2006dimensionality, |
| | author={Hadsell, R. and Chopra, S. and LeCun, Y.}, |
| | booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, |
| | title={Dimensionality Reduction by Learning an Invariant Mapping}, |
| | year={2006}, |
| | volume={2}, |
| | number={}, |
| | pages={1735-1742}, |
| | doi={10.1109/CVPR.2006.100} |
| | } |
| | ``` |
| |
|
| | **Quick Links** |
| | - 🌐 [Project](https://noy-sternlicht.github.io/CHIMERA-Web) |
| | - 📃 [Paper](https://arxiv.org/abs/2505.20779) |
| | - 🛠️ [Code](https://github.com/noy-sternlicht/CHIMERA-KB) |
| |
|
| | <!-- |
| | ## 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.* |
| | --> |
