Add new SentenceTransformer model.

README.md

@@ -1,201 +1,578 @@
 ---
 base_model: colorfulscoop/sbert-base-ja
-language: ja
-license: cc-by-sa-4.0
-model_name: LeoChiuu/sbert-base-ja-arc
+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:533
+- loss:CoSENTLoss
+widget:
+- source_sentence: 日中 は 、 さまざまな 人々 の 集まり が カメラ から 離れて 灰色 の 建物 の 周り を 歩いて い ます 。
+  sentences:
+  - 女性 が 崖 の 上 に 立って い ます 。
+  - 楽譜 を 編集 する 人 。
+  - 人々 は 仕事 の シフト を 去って い ます 。
+- source_sentence: 白い シャツ と 黒い 野球 帽 を かぶった 男 が レンガ の 壁 の 看板 に 手 を 伸ばし ます 。
+  sentences:
+  - 少年 は 代わり に 彼 が 歌う 楽器 を 演奏 し ませ ん
+  - 背 の 高い 人間
+  - 男の子 が 宿題 を して い ます 。
+- source_sentence: 遊歩道 に 沿って 並ぶ 自転車 。
+  sentences:
+  - 男 が 地面 に 座って い ます 。
+  - ハロウィーン パーティー で 踊る 女の子 。
+  - 自転車 は 遊歩道 近く の ラック に あり ます 。
+- source_sentence: ２ 人 の 登山 者 が 山 に 座って い ます 。
+  sentences:
+  - 二 人 の クライマー が 座って い ます
+  - 少年 は 海 の 水 の 中 を 歩いて い ます 。
+  - 丘 は 音楽 の 音 と ともに 生きて い ます 。
+- source_sentence: オクラホマ の フットボール 選手 が 試合 中 に ウィスコンシン の 選手 を 追い かけて い ます 。
+  sentences:
+  - この 写真 に は ３ 人 の 人物 が いて 、 全員 が 働いて い ます 。
+  - バスケットボール を して いる 男の子 が い ます 。
+  - 猫 は 泳ぐ こと を 学び ます 。
+model-index:
+- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: custom arc semantics data jp
+      type: custom-arc-semantics-data-jp
+    metrics:
+    - type: cosine_accuracy
+      value: 0.719626168224299
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9530074000358582
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7647058823529411
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.9352529048919678
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.7027027027027027
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8387096774193549
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7269827062837623
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.7289719626168224
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 586.882568359375
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.7794117647058824
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 580.3487548828125
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.7162162162162162
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8548387096774194
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.7165051508080719
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.7102803738317757
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 168.15194702148438
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.7647058823529411
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 197.73638916015625
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.7027027027027027
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8387096774193549
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.7257938675452797
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.7102803738317757
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 7.578760147094727
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.7647058823529411
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 8.979024887084961
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.7027027027027027
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.8387096774193549
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.7259114754786087
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.7289719626168224
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 586.882568359375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.7794117647058824
+      name: Max F1
+    - type: max_f1_threshold
+      value: 580.3487548828125
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.7162162162162162
+      name: Max Precision
+    - type: max_recall
+      value: 0.8548387096774194
+      name: Max Recall
+    - type: max_ap
+      value: 0.7269827062837623
+      name: Max Ap
 ---
 
-# Model Card for LeoChiuu/sbert-base-ja-arc
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# SentenceTransformer based on colorfulscoop/sbert-base-ja
 
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. It maps sentences & paragraphs to a 768-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:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
 
-<!-- Provide a longer summary of what this model is. -->
-
-Generates similarity embeddings
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** ja
-- **License:** cc-by-sa-4.0
-- **Finetuned from model [optional]:** colorfulscoop/sbert-base-ja
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Model Sources
 
-### Direct Use
+- **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)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Full Model Architecture
 
-[More Information Needed]
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+)
+```
 
-### Downstream Use [optional]
+## Usage
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Direct Usage (Sentence Transformers)
 
-[More Information Needed]
+First install the Sentence Transformers library:
 
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+```bash
+pip install -U sentence-transformers
+```
 
-## Bias, Risks, and Limitations
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'オクラホマ の フットボール 選手 が 試合 中 に ウィスコンシン の 選手 を 追い かけて い ます 。',
+    'バスケットボール を して いる 男の子 が い ます 。',
+    '猫 は 泳ぐ こと を 学び ます 。',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
 
-[More Information Needed]
-
-### Recommendations
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+<!--
+### Direct Usage (Transformers)
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+<details><summary>Click to see the direct usage in Transformers</summary>
 
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
+</details>
+-->
 
-### Training Data
+<!--
+### Downstream Usage (Sentence Transformers)
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+You can finetune this model on your own dataset.
 
-[More Information Needed]
+<details><summary>Click to expand</summary>
 
-### Training Procedure
+</details>
+-->
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+<!--
+### Out-of-Scope Use
 
-[More Information Needed]
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
+### Metrics
+
+#### Binary Classification
+* Dataset: `custom-arc-semantics-data-jp`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value     |
+|:-----------------------------|:----------|
+| cosine_accuracy              | 0.7196    |
+| cosine_accuracy_threshold    | 0.953     |
+| cosine_f1                    | 0.7647    |
+| cosine_f1_threshold          | 0.9353    |
+| cosine_precision             | 0.7027    |
+| cosine_recall                | 0.8387    |
+| cosine_ap                    | 0.727     |
+| dot_accuracy                 | 0.729     |
+| dot_accuracy_threshold       | 586.8826  |
+| dot_f1                       | 0.7794    |
+| dot_f1_threshold             | 580.3488  |
+| dot_precision                | 0.7162    |
+| dot_recall                   | 0.8548    |
+| dot_ap                       | 0.7165    |
+| manhattan_accuracy           | 0.7103    |
+| manhattan_accuracy_threshold | 168.1519  |
+| manhattan_f1                 | 0.7647    |
+| manhattan_f1_threshold       | 197.7364  |
+| manhattan_precision          | 0.7027    |
+| manhattan_recall             | 0.8387    |
+| manhattan_ap                 | 0.7258    |
+| euclidean_accuracy           | 0.7103    |
+| euclidean_accuracy_threshold | 7.5788    |
+| euclidean_f1                 | 0.7647    |
+| euclidean_f1_threshold       | 8.979     |
+| euclidean_precision          | 0.7027    |
+| euclidean_recall             | 0.8387    |
+| euclidean_ap                 | 0.7259    |
+| max_accuracy                 | 0.729     |
+| max_accuracy_threshold       | 586.8826  |
+| max_f1                       | 0.7794    |
+| max_f1_threshold             | 580.3488  |
+| max_precision                | 0.7162    |
+| max_recall                   | 0.8548    |
+| **max_ap**                   | **0.727** |
+
+<!--
+## 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
 
-## Model Card Authors [optional]
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
 
-[More Information Needed]
+## Training Details
 
+### Training Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 533 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 533 samples:
+  |         | text1                                                                               | text2                                                                             | label                                           |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                              | string                                                                            | int                                             |
+  | details | <ul><li>min: 12 tokens</li><li>mean: 36.54 tokens</li><li>max: 108 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 23.04 tokens</li><li>max: 62 tokens</li></ul> | <ul><li>0: ~37.09%</li><li>1: ~62.91%</li></ul> |
+* Samples:
+  | text1                                                                  | text2                                                          | label          |
+  |:-----------------------------------------------------------------------|:---------------------------------------------------------------|:---------------|
+  | <code>男性 の グループ は 古い 軍事 衣装 を 着て 、 パレード の ように 楽器 を 運んで い ます 。</code>    | <code>まるで 戦争 の 準備 の ように 、 男性 の グループ は 武器 を 運んで い ます 。</code>   | <code>1</code> |
+  | <code>赤い Ｔシャツ を 着た 男性 は 、 ジャケット を 着て い なくて も スノーボード を して い ます 。</code> | <code>スノー ボーダー が Ｔシャツ を 着て い ます 。</code>                       | <code>0</code> |
+  | <code>男 が パン ハンドラー に 寄付 し ます 。</code>                                  | <code>古い パン ハンドラー に は 、 若い 大学生 から の 寛大な 寄付 が 与え られ ます 。</code> | <code>1</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
+
+#### csv
+
+* Dataset: csv
+* Size: 533 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 533 samples:
+  |         | text1                                                                             | text2                                                                             | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 33.4 tokens</li><li>max: 84 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 21.71 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>0: ~42.06%</li><li>1: ~57.94%</li></ul> |
+* Samples:
+  | text1                                                          | text2                                           | label          |
+  |:---------------------------------------------------------------|:------------------------------------------------|:---------------|
+  | <code>黒い シャツ と ジーンズ を 着た 男性 が 配管 システム に 取り組んで いる ようです 。</code> | <code>パイプ の 隣 の 男 。</code>                      | <code>0</code> |
+  | <code>一緒に 通り を 歩いて いる 人 。</code>                               | <code>背 の 高い 人間 が 歩いて</code>                    | <code>1</code> |
+  | <code>女の子 が ロボット の Ｗａｌｌ － Ｅ に ｄｒｅｓｓ 装 して い ます 。</code>         | <code>ロボット の 衣装 を 着て いる Ｗａｌｌ － Ｅ の 女の子 。</code> | <code>1</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`: epoch
+- `learning_rate`: 2e-05
+- `warmup_ratio`: 0.4
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### 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`: 8
+- `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`: 2e-05
+- `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`: 0.4
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data-jp_max_ap |
+|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
+| 1.0   | 54   | 6.8257        | 2.9371 | 0.6004                              |
+| 2.0   | 108  | 2.5093        | 2.5029 | 0.7100                              |
+| 3.0   | 162  | 2.2611        | 2.6394 | 0.7270                              |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.0
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.20.0
+- 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",
+}
+```
+
+#### 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
 
-[More Information Needed]
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb1a02b8262293fcf8abdf762d4bf31c669f3a846a8dc2d230dcfe6159a4bfa
+oid sha256:11289ad3b76cfd7cb74302ed4af41feddd84af8ad2e28f01cac891d9b87a34d2
 size 442491744

runs/Sep17_03-51-54_default/events.out.tfevents.1726545116.default.8326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ec8bd7b79b1f187055f093fc759dce936eeeec5d8065c70001cfdd5114e893
+size 15245