Add new SentenceTransformer model.

README.md

@@ -1,201 +1,563 @@
 ---
 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:7464
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: なにか思い出せることは？
+  sentences:
+  - なんて言った？
+  - なにが欲しい？
+  - いつ失くしたの？
+- source_sentence: 木にスカーフがひっかかってる?
+  sentences:
+  - 物の姿を変えられる魔法
+  - 木にスカーフがひっかかってる?
+  - あの木の上のやつ、スカーフ？
+- source_sentence: どんなスカーフ？
+  sentences:
+  - お気に入りの食べ物は？
+  - くさい
+  - もしもし
+- source_sentence: どうやったら猫が話せる？
+  sentences:
+  - どっちがいいと思う？
+  - ワゴンにスカーフはあった？
+  - 井戸へ行ったことある？
+- source_sentence: なにか思い出せることは？
+  sentences:
+  - 村人はどんな呪文が使えるの？
+  - 町って？
+  - キミならどっちがいい？
+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: 0.9705409748259239
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.5118279457092285
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9102773246329527
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.45031607151031494
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8857142857142857
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9362416107382551
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9236294738598163
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9694697375468666
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 251.2455596923828
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9060955518945634
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 246.36648559570312
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.889967637540453
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9228187919463087
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9196731890884118
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.9716122121049813
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 514.571533203125
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9132569558101473
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 514.571533203125
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8913738019169329
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9362416107382551
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9255015709844487
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9721478307445099
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 23.195274353027344
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9147540983606558
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 23.195274353027344
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.8942307692307693
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9362416107382551
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9259440018381992
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9721478307445099
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 514.571533203125
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9147540983606558
+      name: Max F1
+    - type: max_f1_threshold
+      value: 514.571533203125
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.8942307692307693
+      name: Max Precision
+    - type: max_recall
+      value: 0.9362416107382551
+      name: Max Recall
+    - type: max_ap
+      value: 0.9259440018381992
+      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). 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:** Unknown -->
+<!-- - **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 = [
+    'なにか思い出せることは？',
+    '村人はどんな呪文が使えるの？',
+    'キミならどっちがいい？',
+]
+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              | 0.9705     |
+| cosine_accuracy_threshold    | 0.5118     |
+| cosine_f1                    | 0.9103     |
+| cosine_f1_threshold          | 0.4503     |
+| cosine_precision             | 0.8857     |
+| cosine_recall                | 0.9362     |
+| cosine_ap                    | 0.9236     |
+| dot_accuracy                 | 0.9695     |
+| dot_accuracy_threshold       | 251.2456   |
+| dot_f1                       | 0.9061     |
+| dot_f1_threshold             | 246.3665   |
+| dot_precision                | 0.89       |
+| dot_recall                   | 0.9228     |
+| dot_ap                       | 0.9197     |
+| manhattan_accuracy           | 0.9716     |
+| manhattan_accuracy_threshold | 514.5715   |
+| manhattan_f1                 | 0.9133     |
+| manhattan_f1_threshold       | 514.5715   |
+| manhattan_precision          | 0.8914     |
+| manhattan_recall             | 0.9362     |
+| manhattan_ap                 | 0.9255     |
+| euclidean_accuracy           | 0.9721     |
+| euclidean_accuracy_threshold | 23.1953    |
+| euclidean_f1                 | 0.9148     |
+| euclidean_f1_threshold       | 23.1953    |
+| euclidean_precision          | 0.8942     |
+| euclidean_recall             | 0.9362     |
+| euclidean_ap                 | 0.9259     |
+| max_accuracy                 | 0.9721     |
+| max_accuracy_threshold       | 514.5715   |
+| max_f1                       | 0.9148     |
+| max_f1_threshold             | 514.5715   |
+| max_precision                | 0.8942     |
+| max_recall                   | 0.9362     |
+| **max_ap**                   | **0.9259** |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 7,464 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                            | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.32 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.93 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~86.30%</li><li>1: ~13.70%</li></ul> |
+* Samples:
+  | text1                         | text2                    | label          |
+  |:------------------------------|:-------------------------|:---------------|
+  | <code>昨日夕飯にチキンヌードル食べた？</code> | <code>何か企んでる？</code>     | <code>0</code> |
+  | <code>どっちも欲しくない</code>        | <code>お気に入りの食べ物は？</code> | <code>0</code> |
+  | <code>見た目を変える魔法</code>        | <code>物の姿を変えられる魔法</code> | <code>1</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 1,867 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                           | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.24 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.1 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~83.40%</li><li>1: ~16.60%</li></ul> |
+* Samples:
+  | text1                         | text2                    | label          |
+  |:------------------------------|:-------------------------|:---------------|
+  | <code>例えば？</code>             | <code>どうも</code>         | <code>0</code> |
+  | <code>何を作ったの？</code>          | <code>君は何でここにいるの？</code> | <code>0</code> |
+  | <code>昨日夕飯にビーフシチュー食べた？</code> | <code>屋根裏って？</code>      | <code>0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `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`: 1
+- `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   | 933  | 0.0601        | 0.0303 | 0.9259                              |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- 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",
+}
+```
+
+<!--
+## 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.*
+-->

checkpoint-933/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

checkpoint-933/README.md

@@ -0,0 +1,563 @@
+---
+base_model: colorfulscoop/sbert-base-ja
+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:7464
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: なにか思い出せることは？
+  sentences:
+  - なんて言った？
+  - なにが欲しい？
+  - いつ失くしたの？
+- source_sentence: 木にスカーフがひっかかってる?
+  sentences:
+  - 物の姿を変えられる魔法
+  - 木にスカーフがひっかかってる?
+  - あの木の上のやつ、スカーフ？
+- source_sentence: どんなスカーフ？
+  sentences:
+  - お気に入りの食べ物は？
+  - くさい
+  - もしもし
+- source_sentence: どうやったら猫が話せる？
+  sentences:
+  - どっちがいいと思う？
+  - ワゴンにスカーフはあった？
+  - 井戸へ行ったことある？
+- source_sentence: なにか思い出せることは？
+  sentences:
+  - 村人はどんな呪文が使えるの？
+  - 町って？
+  - キミならどっちがいい？
+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: 0.9705409748259239
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.5118279457092285
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9102773246329527
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.45031607151031494
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8857142857142857
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9362416107382551
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9236294738598163
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9694697375468666
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 251.2455596923828
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9060955518945634
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 246.36648559570312
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.889967637540453
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9228187919463087
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9196731890884118
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.9716122121049813
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 514.571533203125
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9132569558101473
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 514.571533203125
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8913738019169329
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9362416107382551
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9255015709844487
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9721478307445099
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 23.195274353027344
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9147540983606558
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 23.195274353027344
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.8942307692307693
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9362416107382551
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9259440018381992
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9721478307445099
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 514.571533203125
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9147540983606558
+      name: Max F1
+    - type: max_f1_threshold
+      value: 514.571533203125
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.8942307692307693
+      name: Max Precision
+    - type: max_recall
+      value: 0.9362416107382551
+      name: Max Recall
+    - type: max_ap
+      value: 0.9259440018381992
+      name: Max Ap
+---
+
+# 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). 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:** 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': 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})
+)
+```
+
+## 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 = [
+    'なにか思い出せることは？',
+    '村人はどんな呪文が使えるの？',
+    'キミならどっちがいい？',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Binary Classification
+* Dataset: `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              | 0.9705     |
+| cosine_accuracy_threshold    | 0.5118     |
+| cosine_f1                    | 0.9103     |
+| cosine_f1_threshold          | 0.4503     |
+| cosine_precision             | 0.8857     |
+| cosine_recall                | 0.9362     |
+| cosine_ap                    | 0.9236     |
+| dot_accuracy                 | 0.9695     |
+| dot_accuracy_threshold       | 251.2456   |
+| dot_f1                       | 0.9061     |
+| dot_f1_threshold             | 246.3665   |
+| dot_precision                | 0.89       |
+| dot_recall                   | 0.9228     |
+| dot_ap                       | 0.9197     |
+| manhattan_accuracy           | 0.9716     |
+| manhattan_accuracy_threshold | 514.5715   |
+| manhattan_f1                 | 0.9133     |
+| manhattan_f1_threshold       | 514.5715   |
+| manhattan_precision          | 0.8914     |
+| manhattan_recall             | 0.9362     |
+| manhattan_ap                 | 0.9255     |
+| euclidean_accuracy           | 0.9721     |
+| euclidean_accuracy_threshold | 23.1953    |
+| euclidean_f1                 | 0.9148     |
+| euclidean_f1_threshold       | 23.1953    |
+| euclidean_precision          | 0.8942     |
+| euclidean_recall             | 0.9362     |
+| euclidean_ap                 | 0.9259     |
+| max_accuracy                 | 0.9721     |
+| max_accuracy_threshold       | 514.5715   |
+| max_f1                       | 0.9148     |
+| max_f1_threshold             | 514.5715   |
+| max_precision                | 0.8942     |
+| max_recall                   | 0.9362     |
+| **max_ap**                   | **0.9259** |
+
+<!--
+## 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: 7,464 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                            | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.32 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.93 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~86.30%</li><li>1: ~13.70%</li></ul> |
+* Samples:
+  | text1                         | text2                    | label          |
+  |:------------------------------|:-------------------------|:---------------|
+  | <code>昨日夕飯にチキンヌードル食べた？</code> | <code>何か企んでる？</code>     | <code>0</code> |
+  | <code>どっちも欲しくない</code>        | <code>お気に入りの食べ物は？</code> | <code>0</code> |
+  | <code>見た目を変える魔法</code>        | <code>物の姿を変えられる魔法</code> | <code>1</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 1,867 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                            | text2                                                                           | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.24 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.1 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~83.40%</li><li>1: ~16.60%</li></ul> |
+* Samples:
+  | text1                         | text2                    | label          |
+  |:------------------------------|:-------------------------|:---------------|
+  | <code>例えば？</code>             | <code>どうも</code>         | <code>0</code> |
+  | <code>何を作ったの？</code>          | <code>君は何でここにいるの？</code> | <code>0</code> |
+  | <code>昨日夕飯にビーフシチュー食べた？</code> | <code>屋根裏って？</code>      | <code>0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `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`: 1
+- `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   | 933  | 0.0601        | 0.0303 | 0.9259                              |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- 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",
+}
+```
+
+<!--
+## 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.*
+-->

checkpoint-933/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-933/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "colorfulscoop/sbert-base-ja",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "cls_token_id": 2,
+  "eos_token_id": 3,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "mask_token_id": 4,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 3,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "unk_token_id": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-933/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-933/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6758040556e3bed519545360ca6a8f7d1c3ff78255d7efbc798100fd8d614605
+size 442491744

checkpoint-933/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"
+  }
+]

checkpoint-933/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f76ead72c4689b772f64f31fc106718bfcaf4307dcd8502d294f672594af69c
+size 880373306

checkpoint-933/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbf81be34d062a44e2dcc657dd3503e2a438f425d97b38baa29179afc6ff94a
+size 13990

checkpoint-933/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053c342b66b6e453e6ad0b9ef5f6adae981132986ee181a29d59722609f26a43
+size 1064

checkpoint-933/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

checkpoint-933/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-933/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
+size 802713

checkpoint-933/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-933/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 933,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4457938075065613,
+      "learning_rate": 0.0,
+      "loss": 0.0601,
+      "step": 933
+    },
+    {
+      "epoch": 1.0,
+      "eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9705409748259239,
+      "eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5118279457092285,
+      "eval_custom-arc-semantics-data-jp_cosine_ap": 0.9236294738598163,
+      "eval_custom-arc-semantics-data-jp_cosine_f1": 0.9102773246329527,
+      "eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.45031607151031494,
+      "eval_custom-arc-semantics-data-jp_cosine_precision": 0.8857142857142857,
+      "eval_custom-arc-semantics-data-jp_cosine_recall": 0.9362416107382551,
+      "eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9694697375468666,
+      "eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 251.2455596923828,
+      "eval_custom-arc-semantics-data-jp_dot_ap": 0.9196731890884118,
+      "eval_custom-arc-semantics-data-jp_dot_f1": 0.9060955518945634,
+      "eval_custom-arc-semantics-data-jp_dot_f1_threshold": 246.36648559570312,
+      "eval_custom-arc-semantics-data-jp_dot_precision": 0.889967637540453,
+      "eval_custom-arc-semantics-data-jp_dot_recall": 0.9228187919463087,
+      "eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9721478307445099,
+      "eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 23.195274353027344,
+      "eval_custom-arc-semantics-data-jp_euclidean_ap": 0.9259440018381992,
+      "eval_custom-arc-semantics-data-jp_euclidean_f1": 0.9147540983606558,
+      "eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 23.195274353027344,
+      "eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8942307692307693,
+      "eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9362416107382551,
+      "eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9716122121049813,
+      "eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 514.571533203125,
+      "eval_custom-arc-semantics-data-jp_manhattan_ap": 0.9255015709844487,
+      "eval_custom-arc-semantics-data-jp_manhattan_f1": 0.9132569558101473,
+      "eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 514.571533203125,
+      "eval_custom-arc-semantics-data-jp_manhattan_precision": 0.8913738019169329,
+      "eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9362416107382551,
+      "eval_custom-arc-semantics-data-jp_max_accuracy": 0.9721478307445099,
+      "eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 514.571533203125,
+      "eval_custom-arc-semantics-data-jp_max_ap": 0.9259440018381992,
+      "eval_custom-arc-semantics-data-jp_max_f1": 0.9147540983606558,
+      "eval_custom-arc-semantics-data-jp_max_f1_threshold": 514.571533203125,
+      "eval_custom-arc-semantics-data-jp_max_precision": 0.8942307692307693,
+      "eval_custom-arc-semantics-data-jp_max_recall": 0.9362416107382551,
+      "eval_loss": 0.030283836647868156,
+      "eval_runtime": 238.5188,
+      "eval_samples_per_second": 7.827,
+      "eval_steps_per_second": 0.981,
+      "step": 933
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 933,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-933/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183d9908193d1ee6d3162bb02d34344be732b5c1f0df4a2c1f5c6d3be91b5cd4
+size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae0b6ad5037f334c3bcd004f08b177103224beb1e729fccd69cd3224b3c7dab
+oid sha256:6758040556e3bed519545360ca6a8f7d1c3ff78255d7efbc798100fd8d614605
 size 442491744

runs/Sep19_22-03-26_default/events.out.tfevents.1726783408.default.3567.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5289ac2fdee49b730acbdfad03fc3a7aa20fd0d669c155971393539406aa7b9
+size 8199