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-test
+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:5079
+- loss:CosineSimilarityLoss
+widget:
+- source_sentence: どこを探す？
+  sentences:
+  - わかんない
+  - 調子はどう？
+  - キミはどっちを選ぶ？
+- source_sentence: 祭壇の些細な違和感ってなに？
+  sentences:
+  - 他のは選べる？
+  - ぬいぐるみ
+  - ここはどこ？
+- source_sentence: あなたは魔法使い？
+  sentences:
+  - この場所は一体？
+  - 村長
+  - あなたは魔法使いですか？
+- source_sentence: 祭壇の些細な違和感ってどこ？
+  sentences:
+  - ぶさいく
+  - お気に入りの食べ物は？
+  - なんでしなきゃいけないの？
+- source_sentence: 好きじゃないの？
+  sentences:
+  - なにすればいい？
+  - どうして好きじゃないの？
+  - リリアンはどんな魔法を使うの？
+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: 0.9661417322834646
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.5446641445159912
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.8877284595300261
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.5446641445159912
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.8900523560209425
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8854166666666666
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8933564183054545
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9653543307086614
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 308.8988342285156
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.8829787234042554
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 308.8988342285156
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.9021739130434783
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8645833333333334
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9054951388455442
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.9661417322834646
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 468.23089599609375
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.8894601542416452
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 492.5838623046875
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8781725888324873
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9010416666666666
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.8992197829196469
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9669291338582677
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 21.951858520507812
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.8917525773195877
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 21.951858520507812
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.8826530612244898
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9010416666666666
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.8987390610302669
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9669291338582677
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 468.23089599609375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.8917525773195877
+      name: Max F1
+    - type: max_f1_threshold
+      value: 492.5838623046875
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.9021739130434783
+      name: Max Precision
+    - type: max_recall
+      value: 0.9010416666666666
+      name: Max Recall
+    - type: max_ap
+      value: 0.9054951388455442
+      name: Max Ap
 ---
 
-# Model Card for LeoChiuu/sbert-base-ja-arc-test
-
-<!-- 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 = [
+    '好きじゃないの？',
+    'どうして好きじゃないの？',
+    'なにすればいい？',
+]
+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              | 0.9661     |
+| cosine_accuracy_threshold    | 0.5447     |
+| cosine_f1                    | 0.8877     |
+| cosine_f1_threshold          | 0.5447     |
+| cosine_precision             | 0.8901     |
+| cosine_recall                | 0.8854     |
+| cosine_ap                    | 0.8934     |
+| dot_accuracy                 | 0.9654     |
+| dot_accuracy_threshold       | 308.8988   |
+| dot_f1                       | 0.883      |
+| dot_f1_threshold             | 308.8988   |
+| dot_precision                | 0.9022     |
+| dot_recall                   | 0.8646     |
+| dot_ap                       | 0.9055     |
+| manhattan_accuracy           | 0.9661     |
+| manhattan_accuracy_threshold | 468.2309   |
+| manhattan_f1                 | 0.8895     |
+| manhattan_f1_threshold       | 492.5839   |
+| manhattan_precision          | 0.8782     |
+| manhattan_recall             | 0.901      |
+| manhattan_ap                 | 0.8992     |
+| euclidean_accuracy           | 0.9669     |
+| euclidean_accuracy_threshold | 21.9519    |
+| euclidean_f1                 | 0.8918     |
+| euclidean_f1_threshold       | 21.9519    |
+| euclidean_precision          | 0.8827     |
+| euclidean_recall             | 0.901      |
+| euclidean_ap                 | 0.8987     |
+| max_accuracy                 | 0.9669     |
+| max_accuracy_threshold       | 468.2309   |
+| max_f1                       | 0.8918     |
+| max_f1_threshold             | 492.5839   |
+| max_precision                | 0.9022     |
+| max_recall                   | 0.901      |
+| **max_ap**                   | **0.9055** |
+
+<!--
+## 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: 5,079 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: 8.01 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.52 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~85.10%</li><li>1: ~14.90%</li></ul> |
+* Samples:
+  | text1                      | text2                   | label          |
+  |:---------------------------|:------------------------|:---------------|
+  | <code>ハロー</code>           | <code>調子はどう？</code>     | <code>0</code> |
+  | <code>村人はどんな呪文を使うの？</code> | <code>自分は今どこにいる？</code> | <code>0</code> |
+  | <code>町？</code>            | <code>べつのはないの？</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"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 1,270 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: 8.2 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.36 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~85.90%</li><li>1: ~14.10%</li></ul> |
+* Samples:
+  | text1                               | text2                     | label          |
+  |:------------------------------------|:--------------------------|:---------------|
+  | <code>賢者の木はどこにあるの？</code>           | <code>村人たちの魔法を教えて？</code> | <code>0</code> |
+  | <code>他の選択肢をちょうだい</code>            | <code>最近どう？</code>        | <code>0</code> |
+  | <code>物の姿を変える魔法が使える村人を知っている？</code> | <code>ジャックについて教えて</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   | 635  | 0.0754        | 0.0340 | 0.9055                              |
+
+
+### 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-635/README.md

@@ -46,31 +46,31 @@ tags:
 - dataset_size:5079
 - loss:CosineSimilarityLoss
 widget:
-- source_sentence: イリュージョンを使うの？
+- source_sentence: どこを探す？
   sentences:
-  - なんて言った？
-  - あなた
-  - 他にはある？
-- source_sentence: あなたは呪文が使えますか？
+  - わかんない
+  - 調子はどう？
+  - キミはどっちを選ぶ？
+- source_sentence: 祭壇の些細な違和感ってなに？
   sentences:
-  - どっちを選ぶ？
-  - 屋根裏部屋の猫のぬいぐるみ
-  - 誰？
-- source_sentence: リリアンってものの形を変えられる？
+  - 他のは選べる？
+  - ぬいぐるみ
+  - ここはどこ？
+- source_sentence: あなたは魔法使い？
   sentences:
-  - どっちがいいと思う？
-  - 中に何か大事な物がある。
-  - 自分は今どこにいる？
-- source_sentence: どんな魔法なの？
+  - この場所は一体？
+  - 村長
+  - あなたは魔法使いですか？
+- source_sentence: 祭壇の些細な違和感ってどこ？
   sentences:
-  - だめじゃん
-  - こんばんは
-  - 井戸へ行った？
-- source_sentence: 屋根裏部屋に猫のぬいぐるいみがあった
+  - ぶさいく
+  - お気に入りの食べ物は？
+  - なんでしなきゃいけないの？
+- source_sentence: 好きじゃないの？
   sentences:
-  - なにが欲しい？
-  - もしもし
-  - センパーイ
+  - なにすればいい？
+  - どうして好きじゃないの？
+  - リリアンはどんな魔法を使うの？
 model-index:
 - name: SentenceTransformer based on colorfulscoop/sbert-base-ja
   results:
@@ -82,109 +82,109 @@ model-index:
       type: custom-arc-semantics-data-jp
     metrics:
     - type: cosine_accuracy
-      value: 0.9598425196850394
+      value: 0.9661417322834646
       name: Cosine Accuracy
     - type: cosine_accuracy_threshold
-      value: 0.5491387844085693
+      value: 0.5446641445159912
       name: Cosine Accuracy Threshold
     - type: cosine_f1
-      value: 0.8675324675324675
+      value: 0.8877284595300261
       name: Cosine F1
     - type: cosine_f1_threshold
-      value: 0.5491387844085693
+      value: 0.5446641445159912
       name: Cosine F1 Threshold
     - type: cosine_precision
-      value: 0.8477157360406091
+      value: 0.8900523560209425
       name: Cosine Precision
     - type: cosine_recall
-      value: 0.8882978723404256
+      value: 0.8854166666666666
       name: Cosine Recall
     - type: cosine_ap
-      value: 0.8892976796593005
+      value: 0.8933564183054545
       name: Cosine Ap
     - type: dot_accuracy
-      value: 0.9582677165354331
+      value: 0.9653543307086614
       name: Dot Accuracy
     - type: dot_accuracy_threshold
-      value: 288.5785217285156
+      value: 308.8988342285156
       name: Dot Accuracy Threshold
     - type: dot_f1
-      value: 0.8608923884514437
+      value: 0.8829787234042554
       name: Dot F1
     - type: dot_f1_threshold
-      value: 277.5242919921875
+      value: 308.8988342285156
       name: Dot F1 Threshold
     - type: dot_precision
-      value: 0.8497409326424871
+      value: 0.9021739130434783
       name: Dot Precision
     - type: dot_recall
-      value: 0.8723404255319149
+      value: 0.8645833333333334
       name: Dot Recall
     - type: dot_ap
-      value: 0.9083604180944419
+      value: 0.9054951388455442
       name: Dot Ap
     - type: manhattan_accuracy
-      value: 0.9598425196850394
+      value: 0.9661417322834646
       name: Manhattan Accuracy
     - type: manhattan_accuracy_threshold
-      value: 440.51263427734375
+      value: 468.23089599609375
       name: Manhattan Accuracy Threshold
     - type: manhattan_f1
-      value: 0.8675324675324675
+      value: 0.8894601542416452
       name: Manhattan F1
     - type: manhattan_f1_threshold
-      value: 466.3338623046875
+      value: 492.5838623046875
       name: Manhattan F1 Threshold
     - type: manhattan_precision
-      value: 0.8477157360406091
+      value: 0.8781725888324873
       name: Manhattan Precision
     - type: manhattan_recall
-      value: 0.8882978723404256
+      value: 0.9010416666666666
       name: Manhattan Recall
     - type: manhattan_ap
-      value: 0.8891655873309381
+      value: 0.8992197829196469
       name: Manhattan Ap
     - type: euclidean_accuracy
-      value: 0.9598425196850394
+      value: 0.9669291338582677
       name: Euclidean Accuracy
     - type: euclidean_accuracy_threshold
-      value: 20.36484146118164
+      value: 21.951858520507812
       name: Euclidean Accuracy Threshold
     - type: euclidean_f1
-      value: 0.8675324675324675
+      value: 0.8917525773195877
       name: Euclidean F1
     - type: euclidean_f1_threshold
-      value: 20.96413230895996
+      value: 21.951858520507812
       name: Euclidean F1 Threshold
     - type: euclidean_precision
-      value: 0.8477157360406091
+      value: 0.8826530612244898
       name: Euclidean Precision
     - type: euclidean_recall
-      value: 0.8882978723404256
+      value: 0.9010416666666666
       name: Euclidean Recall
     - type: euclidean_ap
-      value: 0.8891557631414319
+      value: 0.8987390610302669
       name: Euclidean Ap
     - type: max_accuracy
-      value: 0.9598425196850394
+      value: 0.9669291338582677
       name: Max Accuracy
     - type: max_accuracy_threshold
-      value: 440.51263427734375
+      value: 468.23089599609375
       name: Max Accuracy Threshold
     - type: max_f1
-      value: 0.8675324675324675
+      value: 0.8917525773195877
       name: Max F1
     - type: max_f1_threshold
-      value: 466.3338623046875
+      value: 492.5838623046875
       name: Max F1 Threshold
     - type: max_precision
-      value: 0.8497409326424871
+      value: 0.9021739130434783
       name: Max Precision
     - type: max_recall
-      value: 0.8882978723404256
+      value: 0.9010416666666666
       name: Max Recall
     - type: max_ap
-      value: 0.9083604180944419
+      value: 0.9054951388455442
       name: Max Ap
 ---
 
@@ -237,9 +237,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    '屋根裏部屋に猫のぬいぐるいみがあった',
-    'もしもし',
-    'なにが欲しい？',
+    '好きじゃないの？',
+    'どうして好きじゃないの？',
+    'なにすればいい？',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -285,41 +285,41 @@ You can finetune this model on your own dataset.
 
 | Metric                       | Value      |
 |:-----------------------------|:-----------|
-| cosine_accuracy              | 0.9598     |
-| cosine_accuracy_threshold    | 0.5491     |
-| cosine_f1                    | 0.8675     |
-| cosine_f1_threshold          | 0.5491     |
-| cosine_precision             | 0.8477     |
-| cosine_recall                | 0.8883     |
-| cosine_ap                    | 0.8893     |
-| dot_accuracy                 | 0.9583     |
-| dot_accuracy_threshold       | 288.5785   |
-| dot_f1                       | 0.8609     |
-| dot_f1_threshold             | 277.5243   |
-| dot_precision                | 0.8497     |
-| dot_recall                   | 0.8723     |
-| dot_ap                       | 0.9084     |
-| manhattan_accuracy           | 0.9598     |
-| manhattan_accuracy_threshold | 440.5126   |
-| manhattan_f1                 | 0.8675     |
-| manhattan_f1_threshold       | 466.3339   |
-| manhattan_precision          | 0.8477     |
-| manhattan_recall             | 0.8883     |
-| manhattan_ap                 | 0.8892     |
-| euclidean_accuracy           | 0.9598     |
-| euclidean_accuracy_threshold | 20.3648    |
-| euclidean_f1                 | 0.8675     |
-| euclidean_f1_threshold       | 20.9641    |
-| euclidean_precision          | 0.8477     |
-| euclidean_recall             | 0.8883     |
-| euclidean_ap                 | 0.8892     |
-| max_accuracy                 | 0.9598     |
-| max_accuracy_threshold       | 440.5126   |
-| max_f1                       | 0.8675     |
-| max_f1_threshold             | 466.3339   |
-| max_precision                | 0.8497     |
-| max_recall                   | 0.8883     |
-| **max_ap**                   | **0.9084** |
+| cosine_accuracy              | 0.9661     |
+| cosine_accuracy_threshold    | 0.5447     |
+| cosine_f1                    | 0.8877     |
+| cosine_f1_threshold          | 0.5447     |
+| cosine_precision             | 0.8901     |
+| cosine_recall                | 0.8854     |
+| cosine_ap                    | 0.8934     |
+| dot_accuracy                 | 0.9654     |
+| dot_accuracy_threshold       | 308.8988   |
+| dot_f1                       | 0.883      |
+| dot_f1_threshold             | 308.8988   |
+| dot_precision                | 0.9022     |
+| dot_recall                   | 0.8646     |
+| dot_ap                       | 0.9055     |
+| manhattan_accuracy           | 0.9661     |
+| manhattan_accuracy_threshold | 468.2309   |
+| manhattan_f1                 | 0.8895     |
+| manhattan_f1_threshold       | 492.5839   |
+| manhattan_precision          | 0.8782     |
+| manhattan_recall             | 0.901      |
+| manhattan_ap                 | 0.8992     |
+| euclidean_accuracy           | 0.9669     |
+| euclidean_accuracy_threshold | 21.9519    |
+| euclidean_f1                 | 0.8918     |
+| euclidean_f1_threshold       | 21.9519    |
+| euclidean_precision          | 0.8827     |
+| euclidean_recall             | 0.901      |
+| euclidean_ap                 | 0.8987     |
+| max_accuracy                 | 0.9669     |
+| max_accuracy_threshold       | 468.2309   |
+| max_f1                       | 0.8918     |
+| max_f1_threshold             | 492.5839   |
+| max_precision                | 0.9022     |
+| max_recall                   | 0.901      |
+| **max_ap**                   | **0.9055** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -346,13 +346,13 @@ You can finetune this model on your own dataset.
   |         | text1                                                                            | text2                                                                            | label                                           |
   |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
   | type    | string                                                                           | string                                                                           | int                                             |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 8.18 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.41 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~87.80%</li><li>1: ~12.20%</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.01 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.52 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~85.10%</li><li>1: ~14.90%</li></ul> |
 * Samples:
-  | text1                     | text2                    | label          |
-  |:--------------------------|:-------------------------|:---------------|
-  | <code>井戸へ訪れたことがある？</code> | <code>どんな食べ物が好き？</code>  | <code>0</code> |
-  | <code>猫が好きな人</code>       | <code>君は何でここにいるの？</code> | <code>0</code> |
-  | <code>町って？</code>         | <code>ぬいぐるみ</code>       | <code>0</code> |
+  | text1                      | text2                   | label          |
+  |:---------------------------|:------------------------|:---------------|
+  | <code>ハロー</code>           | <code>調子はどう？</code>     | <code>0</code> |
+  | <code>村人はどんな呪文を使うの？</code> | <code>自分は今どこにいる？</code> | <code>0</code> |
+  | <code>町？</code>            | <code>べつのはないの？</code>   | <code>0</code> |
 * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
   ```json
   {
@@ -368,16 +368,16 @@ You can finetune this model on your own dataset.
 * Size: 1,270 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: 8.14 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.53 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~85.30%</li><li>1: ~14.70%</li></ul> |
+  |         | text1                                                                           | text2                                                                            | label                                           |
+  |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                          | string                                                                           | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.2 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 7.36 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>0: ~85.90%</li><li>1: ~14.10%</li></ul> |
 * Samples:
-  | text1                          | text2               | label          |
-  |:-------------------------------|:--------------------|:---------------|
-  | <code>他には選べないの？</code>         | <code>だめじゃん</code>  | <code>0</code> |
-  | <code>村長は誰？</code>             | <code>屋根裏って？</code> | <code>0</code> |
-  | <code>誰かが呪文で花をぬいぐるみに変えた</code> | <code>両方はだめ？</code> | <code>0</code> |
+  | text1                               | text2                     | label          |
+  |:------------------------------------|:--------------------------|:---------------|
+  | <code>賢者の木はどこにあるの？</code>           | <code>村人たちの魔法を教えて？</code> | <code>0</code> |
+  | <code>他の選択肢をち��うだい</code>            | <code>最近どう？</code>        | <code>0</code> |
+  | <code>物の姿を変える魔法が使える村人を知っている？</code> | <code>ジャックについて教えて</code>  | <code>0</code> |
 * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
   ```json
   {
@@ -515,7 +515,7 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | Training Loss | loss   | custom-arc-semantics-data-jp_max_ap |
 |:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
-| 1.0   | 635  | 0.0749        | 0.0361 | 0.9084                              |
+| 1.0   | 635  | 0.0754        | 0.0340 | 0.9055                              |
 
 
 ### Framework Versions

checkpoint-635/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e261e54e4da3ac1a9f063562a898ea4572ee18c1d23ad59efc8dfe6d9bbf50d6
+oid sha256:207e694bf4253af2a260bcf591c3786f6d5c604c9a4c35f0a76247ceb2ec65cc
 size 442491744

checkpoint-635/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668754c43972d2ed352104962d48d40b4ef765128dcb79b8c306709669636e52
+oid sha256:eca94c4541555e72da1506863829c57ccf3bbcef2ec628e81d715017ad398cec
 size 880373306

checkpoint-635/trainer_state.json

@@ -10,52 +10,52 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.6132362484931946,
+      "grad_norm": 0.3670412003993988,
       "learning_rate": 0.0,
-      "loss": 0.0749,
+      "loss": 0.0754,
       "step": 635
     },
     {
       "epoch": 1.0,
-      "eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9598425196850394,
-      "eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5491387844085693,
-      "eval_custom-arc-semantics-data-jp_cosine_ap": 0.8892976796593005,
-      "eval_custom-arc-semantics-data-jp_cosine_f1": 0.8675324675324675,
-      "eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5491387844085693,
-      "eval_custom-arc-semantics-data-jp_cosine_precision": 0.8477157360406091,
-      "eval_custom-arc-semantics-data-jp_cosine_recall": 0.8882978723404256,
-      "eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9582677165354331,
-      "eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 288.5785217285156,
-      "eval_custom-arc-semantics-data-jp_dot_ap": 0.9083604180944419,
-      "eval_custom-arc-semantics-data-jp_dot_f1": 0.8608923884514437,
-      "eval_custom-arc-semantics-data-jp_dot_f1_threshold": 277.5242919921875,
-      "eval_custom-arc-semantics-data-jp_dot_precision": 0.8497409326424871,
-      "eval_custom-arc-semantics-data-jp_dot_recall": 0.8723404255319149,
-      "eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9598425196850394,
-      "eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 20.36484146118164,
-      "eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8891557631414319,
-      "eval_custom-arc-semantics-data-jp_euclidean_f1": 0.8675324675324675,
-      "eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 20.96413230895996,
-      "eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8477157360406091,
-      "eval_custom-arc-semantics-data-jp_euclidean_recall": 0.8882978723404256,
-      "eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9598425196850394,
-      "eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 440.51263427734375,
-      "eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8891655873309381,
-      "eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8675324675324675,
-      "eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 466.3338623046875,
-      "eval_custom-arc-semantics-data-jp_manhattan_precision": 0.8477157360406091,
-      "eval_custom-arc-semantics-data-jp_manhattan_recall": 0.8882978723404256,
-      "eval_custom-arc-semantics-data-jp_max_accuracy": 0.9598425196850394,
-      "eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 440.51263427734375,
-      "eval_custom-arc-semantics-data-jp_max_ap": 0.9083604180944419,
-      "eval_custom-arc-semantics-data-jp_max_f1": 0.8675324675324675,
-      "eval_custom-arc-semantics-data-jp_max_f1_threshold": 466.3338623046875,
-      "eval_custom-arc-semantics-data-jp_max_precision": 0.8497409326424871,
-      "eval_custom-arc-semantics-data-jp_max_recall": 0.8882978723404256,
-      "eval_loss": 0.03608229011297226,
-      "eval_runtime": 147.9419,
-      "eval_samples_per_second": 8.584,
-      "eval_steps_per_second": 1.075,
+      "eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.9661417322834646,
+      "eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.5446641445159912,
+      "eval_custom-arc-semantics-data-jp_cosine_ap": 0.8933564183054545,
+      "eval_custom-arc-semantics-data-jp_cosine_f1": 0.8877284595300261,
+      "eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.5446641445159912,
+      "eval_custom-arc-semantics-data-jp_cosine_precision": 0.8900523560209425,
+      "eval_custom-arc-semantics-data-jp_cosine_recall": 0.8854166666666666,
+      "eval_custom-arc-semantics-data-jp_dot_accuracy": 0.9653543307086614,
+      "eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 308.8988342285156,
+      "eval_custom-arc-semantics-data-jp_dot_ap": 0.9054951388455442,
+      "eval_custom-arc-semantics-data-jp_dot_f1": 0.8829787234042554,
+      "eval_custom-arc-semantics-data-jp_dot_f1_threshold": 308.8988342285156,
+      "eval_custom-arc-semantics-data-jp_dot_precision": 0.9021739130434783,
+      "eval_custom-arc-semantics-data-jp_dot_recall": 0.8645833333333334,
+      "eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.9669291338582677,
+      "eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 21.951858520507812,
+      "eval_custom-arc-semantics-data-jp_euclidean_ap": 0.8987390610302669,
+      "eval_custom-arc-semantics-data-jp_euclidean_f1": 0.8917525773195877,
+      "eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 21.951858520507812,
+      "eval_custom-arc-semantics-data-jp_euclidean_precision": 0.8826530612244898,
+      "eval_custom-arc-semantics-data-jp_euclidean_recall": 0.9010416666666666,
+      "eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.9661417322834646,
+      "eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 468.23089599609375,
+      "eval_custom-arc-semantics-data-jp_manhattan_ap": 0.8992197829196469,
+      "eval_custom-arc-semantics-data-jp_manhattan_f1": 0.8894601542416452,
+      "eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 492.5838623046875,
+      "eval_custom-arc-semantics-data-jp_manhattan_precision": 0.8781725888324873,
+      "eval_custom-arc-semantics-data-jp_manhattan_recall": 0.9010416666666666,
+      "eval_custom-arc-semantics-data-jp_max_accuracy": 0.9669291338582677,
+      "eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 468.23089599609375,
+      "eval_custom-arc-semantics-data-jp_max_ap": 0.9054951388455442,
+      "eval_custom-arc-semantics-data-jp_max_f1": 0.8917525773195877,
+      "eval_custom-arc-semantics-data-jp_max_f1_threshold": 492.5838623046875,
+      "eval_custom-arc-semantics-data-jp_max_precision": 0.9021739130434783,
+      "eval_custom-arc-semantics-data-jp_max_recall": 0.9010416666666666,
+      "eval_loss": 0.03398558497428894,
+      "eval_runtime": 83.9867,
+      "eval_samples_per_second": 15.121,
+      "eval_steps_per_second": 1.893,
       "step": 635
     }
   ],

checkpoint-635/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3bb81dcbb006be8123e58d559f74c79ef4ed77636d54bdac407600b7ec5e8ee
+oid sha256:498c703eb29ebb9feee1c4ab0937646f0c0aaa99e0def968f89236d227021869
 size 5432

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e261e54e4da3ac1a9f063562a898ea4572ee18c1d23ad59efc8dfe6d9bbf50d6
+oid sha256:207e694bf4253af2a260bcf591c3786f6d5c604c9a4c35f0a76247ceb2ec65cc
 size 442491744

runs/Sep20_22-03-34_default/events.out.tfevents.1726869818.default.8973.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2b2d5dd59a7681909e717d31001c6fbe04d0a6d78d98ae8e44962e83c4078f
+size 4293

runs/Sep20_22-12-39_default/events.out.tfevents.1726870361.default.9160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f303006c148002e9a345b84f77c3c69dac3b5b83864ab981a61bb6a21015ab6
+size 8214