Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 320,
+  "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
+}

README.md

@@ -0,0 +1,475 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:753444
+- loss:CoSENTLoss
+base_model: HassanCS/TCRa_HLA_peptide_ESM
+widget:
+- source_sentence: A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E S D Y
+    Y L F W Y K Q P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A
+    A K S F S L K I S D S Q L G D A A M Y F C C A Y R S M S N Y Q L I W W G A G T
+    K L I I K P D
+  sentences:
+  - A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E N N Y Y L F W Y K Q
+    P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K
+    I S D S Q L G D T A M Y F C C A F V A N A G G T S Y G K L T F F G Q G T I L T
+    V H P N
+  - A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E S D Y Y L F W Y K Q
+    P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K
+    I S D S Q L G D A A M Y F C C A Y R S P N Y G G S Q G N L I F F G K G T K L S
+    V K P N
+  - A Q S V A Q P E D Q V N V A E G N P L T V K C T Y S V S G N P Y L F W Y V Q Y
+    P N R G L Q F L L K Y I T G D N L V K G S Y G F E A E F N K S Q T S F H L K K
+    P S A L V S D S A L Y F C A L D Q A G T A L I F G K G T T L S V S S N
+- source_sentence: L A K T T Q P I S M D S Y E G Q E V N I T C S H N N I A T N D Y
+    I T W Y Q Q F P S Q G P R F I I Q G Y K T K V T N E V A S L F I P A D R K S S
+    T L S L P R V S L S D T A V Y Y C C L P S G M N Y G G S Q G N L I F F G K G T
+    K L S V K P N
+  sentences:
+  - I L N V E Q S P Q S L H V Q E G D S T N F T C S F P S S N F Y A L H W Y R W E
+    T A K S P E A L F V M T L N G D E K K K G R I S A T L N T K E G Y S Y L Y I K
+    G S Q P E D S A T Y L C A F I T G N Q F Y F G T G T S L T V I P N
+  - A Q K I T Q T Q P G M F V Q E K E A V T L D C T Y D T S D P S Y G L F W Y K Q
+    P S S G E M I F L I Y Q G S Y D Q Q N A T E G R Y S L N F Q K A R K S A N L V
+    I S A S Q L G D S A M Y F C C A M R G D A G G T S Y G K L T F F G Q G T I L T
+    V H P N
+  - Q K E V E Q D P G P L S V P E G A I V S L N C T Y S N S A F Q Y F M W Y R Q Y
+    S R K G P E L L M Y T Y S S G N K E D G R F T A Q V D K S S K Y I S L F I R D
+    S Q P S D S A T Y L C C A M R V I G S D D K I I F F G K G T R L H I L P N
+- source_sentence: T Q L L E Q S P Q F L S I Q E G E N L T V Y C N S S S V F S S L
+    Q W Y R Q E P G E G P V L L V T V V T G G E V K K L K R L T F Q F G D A R K D
+    S S L H I T A A Q P G D T G L Y L C C A G V P Y N N N D M R F F G A G T R L T
+    V K P N
+  sentences:
+  - T Q L L E Q S P Q F L S I Q E G E N L T V Y C N S S S V F S S L Q W Y R Q E P
+    G E G P V L L V T V V T G G E V K K L K R L T F Q F G D A R K D S S L H I T A
+    A Q P G D T G L Y L C C A G A A H P L N Y G G S Q G N L I F F G K G T K L S V
+    K P N
+  - G N S V T Q M E G P V T L S E E A F L T I N C T Y T A T G Y P S L F W Y V Q Y
+    P G E G L Q L L L K A T K A D D K G S N K G F E A T Y R K E T T S F H L E K G
+    S V Q V S D S A V Y F C C A F N D Y K L S F F G A G T T V T V R A N
+  - D A K T T Q P P S M D C A E G R A A N L P C N H S T I S G N E Y V Y W Y R Q I
+    H S Q G P Q Y I I H G L K N N E T N E M A S L I I T E D R K S S T L I L P H A
+    T L R D T A V Y Y C C I V R A G G G G W S G G G A D G L T F F G K G T H L I I
+    Q P Y
+- source_sentence: L A K T T Q P I S M D S Y E G Q E V N I T C S H N N I A T N D Y
+    I T W Y Q Q F P S Q G P R F I I Q G Y K T K V T N E V A S L F I P A D R K S S
+    T L S L P R V S L S D T A V Y Y C C L V G E G P S G G Y Q K V T F F G I G T K
+    L Q V I P N
+  sentences:
+  - A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q
+    P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T
+    I T A S Q V V D S A V Y F C C A L S D A Y N F N K F Y F F G S G T K L N V K P
+    N
+  - A Q R V T Q P E K L L S V F K G A P V E L K C N Y S Y S G S P E L F W Y V Q Y
+    S R Q R L Q L L L R H I S R E S I K G F T A D L N K G E T S F H L K K P F A Q
+    E E D S A M Y Y C A L R A R G S T L G R L Y F G R G T Q L T V W P D
+  - Q K E V E Q D P G P L S V P E G A I V S L N C T Y S N S A F Q Y F M W Y R Q Y
+    S R K G P E L L M Y T Y S S G N K E D G R F T A Q V D K S S K Y I S L F I R D
+    S Q P S D S A T Y L C C A M R G Y Q K V T F F G I G T K L Q V I P N
+- source_sentence: A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y
+    Y L F W Y K Q P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S
+    T S S F N F T I T A S Q V V D S A V Y F C C A L L Y N N N D M R F F G A G T R
+    L T V K P N
+  sentences:
+  - A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q
+    P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T
+    I T A S Q V V D S A V Y F C C A L S E T P R G G G T S Y G K L T F F G Q G T I
+    L T V H P N
+  - Q K E V E Q N S G P L S V P E G A I A S L N C T Y S D R G S Q S F F W Y R Q Y
+    S G K S P E L I M F I Y S N G D K E D G R F T A Q L N K A S Q Y V S L L I R D
+    S Q P S D S A T Y L C C A V A D D K I I F F G K G T R L H I L P N
+  - G Q S L E Q P S E V T A V E G A I V Q I N C T Y Q T S G F Y G L S W Y Q Q H D
+    G G A P T F L S Y N A L D G L E E T G R F S S F L S R S D S Y G Y L L L Q E L
+    Q M K D S A S Y F C A V S P Y G Q N F V F G P G T R L S V L P Y
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on HassanCS/TCRa_HLA_peptide_ESM
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: all dev
+      type: all-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.9059012055309352
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.955510095717775
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on HassanCS/TCRa_HLA_peptide_ESM
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [HassanCS/TCRa_HLA_peptide_ESM](https://huggingface.co/HassanCS/TCRa_HLA_peptide_ESM). It maps sentences & paragraphs to a 320-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:** [HassanCS/TCRa_HLA_peptide_ESM](https://huggingface.co/HassanCS/TCRa_HLA_peptide_ESM) <!-- at revision 7a2a4b950f3848ab396071988d3f477b45822ec9 -->
+- **Maximum Sequence Length:** 1026 tokens
+- **Output Dimensionality:** 320 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': 1026, 'do_lower_case': False}) with Transformer model: EsmModel 
+  (1): Pooling({'word_embedding_dimension': 320, '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})
+)
+```
+
+## 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("HassanCS/TCRa_HLA_peptide_ESM_4_epochs")
+# Run inference
+sentences = [
+    'A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T I T A S Q V V D S A V Y F C C A L L Y N N N D M R F F G A G T R L T V K P N',
+    'A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T I T A S Q V V D S A V Y F C C A L S E T P R G G G T S Y G K L T F F G Q G T I L T V H P N',
+    'Q K E V E Q N S G P L S V P E G A I A S L N C T Y S D R G S Q S F F W Y R Q Y S G K S P E L I M F I Y S N G D K E D G R F T A Q L N K A S Q Y V S L L I R D S Q P S D S A T Y L C C A V A D D K I I F F G K G T R L H I L P N',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 320]
+
+# 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: `all-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9059     |
+| **spearman_cosine** | **0.9555** |
+
+<!--
+## 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: 753,444 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                            | sentence2                                                                             | score                                                           |
+  |:--------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                                | float                                                           |
+  | details | <ul><li>min: 108 tokens</li><li>mean: 116.0 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 107 tokens</li><li>mean: 116.16 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.38</li><li>max: 0.97</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                                  | sentence2                                                                                                                                                                                                                                                  | score                           |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>T Q L L E Q S P Q F L S I Q E G E N L T V Y C N S S S V F S S L Q W Y R Q E P G E G P V L L V T V V T G G E V K K L K R L T F Q F G D A R K D S S L H I T A A Q P G D T G L Y L C C A G A G G G S Q G N L I F F G K G T K L S V K P N</code>         | <code>T Q L L E Q S P Q F L S I Q E G E N L T V Y C N S S S V F S S L Q W Y R Q E P G E G P V L L V T V V T G G E V K K L K R L T F Q F G D A R K D S S L H I T A A Q P G D T G L Y L C C A G G N G G S Q G N L I F F G K G T K L S V K P N</code>         | <code>0.8347107438016529</code> |
+  | <code>A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E N N Y Y L F W Y K Q P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K I S D S Q L G D T A M Y F C A F A E Y G N K L V F G A G T I L R V K S Y</code>           | <code>A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E S D Y Y L F W Y K Q P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K I S D S Q L G D A A M Y F C A L F S G S R L T F G E G T Q L T V N P D</code>             | <code>0.0</code>                |
+  | <code>A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T I T A S Q V V D S A V Y F C C A L L I F S G G Y N K L I F F G A G T R L A V H P Y</code> | <code>A Q K V T Q A Q T E I S V V E K E D V T L D C V Y E T R D T T Y Y L F W Y K Q P P S G E L V F L I R R N S F D E Q N E I S G R Y S W N F Q K S T S S F N F T I T A S Q V V D S A V Y F C C A L S E A G S G Y S T L T F F G K G T M L L V S P D</code> | <code>0.4008264462809917</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 83,716 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                             | sentence2                                                                             | score                                                           |
+  |:--------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                                | string                                                                                | float                                                           |
+  | details | <ul><li>min: 106 tokens</li><li>mean: 116.08 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 109 tokens</li><li>mean: 116.05 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.39</li><li>max: 0.97</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                                                                            | sentence2                                                                                                                                                                                                                                            | score                            |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------|
+  | <code>G E N V E Q H P S T L S V Q E G D S A V I K C T Y S D S A S N Y F P W Y K Q E L G K G P Q L I I D I R S N V G E K K D Q R I A V T L N K T A K H F S L H I T E T Q P E D S A V Y F C A A S M N N Y G Q N F V F G P G T R L S V L P Y</code>     | <code>G E D V E Q S L F L S V R E G D S S V I N C T Y T D S S S T Y L Y W Y K Q E P G A G L Q L L T Y I F S N M D M K Q D Q R L T V L L N K K D K H L S L R I A D T Q T G D S A I Y F C A E R A G A N N L F F G T G T R L T V I P Y</code>           | <code>0.09297520661157023</code> |
+  | <code>A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E N N Y Y L F W Y K Q P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K I S D S Q L G D T A M Y F C C A S H M N N A R L M F F G D G T Q L V V K P N</code> | <code>A Q T V T Q S Q P E M S V Q E A E T V T L S C T Y D T S E N N Y Y L F W Y K Q P P S R Q M I L V I R Q E A Y K Q Q N A T E N R F S V N F Q K A A K S F S L K I S D S Q L G D T A M Y F C C S S G G G A D G L T F F G K G T H L I I Q P Y</code> | <code>0.00826446280991735</code> |
+  | <code>G Q S L E Q P S E V T A V E G A I V Q I N C T Y Q T S G F Y G L S W Y Q Q H D G G A P T F L S Y N A L D G L E E T G R F S S F L S R S D S Y G Y L L L Q E L Q M K D S A S Y F C C A L A G G G N K L T F F G T G T Q L K V E L N</code>         | <code>K N Q V E Q S P Q S L I I L E G K N C T L Q C N Y T V S P F S N L R W Y K Q D T G R G P V S L T I M T F S E N T K S N G R Y T A T L D A D T K Q S S L H I T A S Q L S D S A S Y I C C V V S S Y S S A S K I I F F G S G T R L S I R P N</code> | <code>0.9690082644628099</code>  |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 0.001
+- `weight_decay`: 0.0001
+- `num_train_epochs`: 2
+- `fp16`: True
+- `load_best_model_at_end`: True
+
+#### 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`: 128
+- `per_device_eval_batch_size`: 128
+- `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`: 0.001
+- `weight_decay`: 0.0001
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 2
+- `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`: 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
+- `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`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step      | Training Loss | Validation Loss | all-dev_spearman_cosine |
+|:----------:|:---------:|:-------------:|:---------------:|:-----------------------:|
+| 0.3397     | 2000      | 8.5046        | 8.4428          | 0.8656                  |
+| 0.6795     | 4000      | 8.3672        | 8.2836          | 0.9072                  |
+| 1.0192     | 6000      | 8.2267        | 8.1731          | 0.9299                  |
+| 1.3589     | 8000      | 8.0775        | 8.0600          | 0.9447                  |
+| **1.6987** | **10000** | **7.9766**    | **7.9564**      | **0.9555**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.0
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 3.3.1
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/kaggle/working/TCRa-HLA-peptide-final",
+  "architectures": [
+    "EsmModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 320,
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "is_folding_model": false,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.0",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c245714685b8161f6873777868302861812238db3d028b593f563ba5f4c31afd
+size 31372596

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1026,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1026,
+  "pad_token": "<pad>",
+  "tokenizer_class": "EsmTokenizer",
+  "unk_token": "<unk>"
+}

vocab.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>