Upload 77 files

.gitattributes

@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/unigram.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/unigram.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1521/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1521/unigram.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/unigram.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,386 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8100
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Apakah santri boleh keluar pondok saat dikunjungi?
+  sentences:
+  - Cukup menghubungi bagian keuangan atau humas PPS. Imam Syafi'i.
+  - Keluar pondok hanya boleh dengan izin resmi dan keadaan darurat.
+  - Ya, seperti menjadi ketua kelompok, mengatur antrian, dan memimpin doa.
+- source_sentence: Apakah santri boleh membawa HP?
+  sentences:
+  - HP tidak diperbolehkan dibawa ke lingkungan pesantren.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+  - Santri akan mendapatkan pendampingan psikologis dan konseling.
+- source_sentence: Apakah ada kegiatan kebersihan harian di TK?
+  sentences:
+  - Santri mendapat pembinaan khusus dan apresiasi.
+  - Ya, setiap pagi santri melakukan piket kebersihan lingkungan sesuai jadwal.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+- source_sentence: Apakah ada buku panduan bagi wali santri baru?
+  sentences:
+  - Wali harus mengajukan surat izin resmi dan mendapat persetujuan pengasuh.
+  - Ekskul dapat diganti satu kali di tengah semester dengan izin wali kelas.
+  - Ya, setiap wali mendapat buku panduan saat pendaftaran.
+- source_sentence: Apakah ekskul dibuka untuk santri baru?
+  sentences:
+  - Ya, santri harus menjaga ketenangan dan mengembalikan buku tepat waktu.
+  - Ya, santri baru dapat langsung mendaftar ekskul di awal semester.
+  - Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'Apakah ekskul dibuka untuk santri baru?',
+    'Ya, santri baru dapat langsung mendaftar ekskul di awal semester.',
+    'Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+
+<!--
+## 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: 8,100 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 11.19 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.87 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                  | sentence_1                                                                                    |
+  |:------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>Apakah kurikulum mencakup pendidikan karakter?</code> | <code>Ya, pembinaan karakter menjadi bagian utama kurikulum pesantren.</code>                 |
+  | <code>Apakah lingkungan pondok ramah anak?</code>           | <code>Ya, desain dan pengawasan mendukung kenyamanan dan keamanan santri.</code>              |
+  | <code>Apakah nilai adab berpengaruh pada kelulusan?</code>  | <code>Sangat berpengaruh, nilai adab menjadi pertimbangan utama dalam penilaian akhir.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | eval_spearman_cosine |
+|:------:|:----:|:--------------------:|
+| 0.1972 | 100  | nan                  |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.7.0
+- Datasets: 2.14.4
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-1000/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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-1000/README.md

@@ -0,0 +1,396 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8100
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Apakah santri boleh keluar pondok saat dikunjungi?
+  sentences:
+  - Cukup menghubungi bagian keuangan atau humas PPS. Imam Syafi'i.
+  - Keluar pondok hanya boleh dengan izin resmi dan keadaan darurat.
+  - Ya, seperti menjadi ketua kelompok, mengatur antrian, dan memimpin doa.
+- source_sentence: Apakah santri boleh membawa HP?
+  sentences:
+  - HP tidak diperbolehkan dibawa ke lingkungan pesantren.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+  - Santri akan mendapatkan pendampingan psikologis dan konseling.
+- source_sentence: Apakah ada kegiatan kebersihan harian di TK?
+  sentences:
+  - Santri mendapat pembinaan khusus dan apresiasi.
+  - Ya, setiap pagi santri melakukan piket kebersihan lingkungan sesuai jadwal.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+- source_sentence: Apakah ada buku panduan bagi wali santri baru?
+  sentences:
+  - Wali harus mengajukan surat izin resmi dan mendapat persetujuan pengasuh.
+  - Ekskul dapat diganti satu kali di tengah semester dengan izin wali kelas.
+  - Ya, setiap wali mendapat buku panduan saat pendaftaran.
+- source_sentence: Apakah ekskul dibuka untuk santri baru?
+  sentences:
+  - Ya, santri harus menjaga ketenangan dan mengembalikan buku tepat waktu.
+  - Ya, santri baru dapat langsung mendaftar ekskul di awal semester.
+  - Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'Apakah ekskul dibuka untuk santri baru?',
+    'Ya, santri baru dapat langsung mendaftar ekskul di awal semester.',
+    'Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+
+<!--
+## 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: 8,100 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 11.19 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.87 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                  | sentence_1                                                                                    |
+  |:------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>Apakah kurikulum mencakup pendidikan karakter?</code> | <code>Ya, pembinaan karakter menjadi bagian utama kurikulum pesantren.</code>                 |
+  | <code>Apakah lingkungan pondok ramah anak?</code>           | <code>Ya, desain dan pengawasan mendukung kenyamanan dan keamanan santri.</code>              |
+  | <code>Apakah nilai adab berpengaruh pada kelulusan?</code>  | <code>Sangat berpengaruh, nilai adab menjadi pertimbangan utama dalam penilaian akhir.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | eval_spearman_cosine |
+|:------:|:----:|:-------------:|:--------------------:|
+| 0.1972 | 100  | -             | nan                  |
+| 0.3945 | 200  | -             | nan                  |
+| 0.5917 | 300  | -             | nan                  |
+| 0.7890 | 400  | -             | nan                  |
+| 0.9862 | 500  | 0.28          | nan                  |
+| 1.0    | 507  | -             | nan                  |
+| 1.1834 | 600  | -             | nan                  |
+| 1.3807 | 700  | -             | nan                  |
+| 1.5779 | 800  | -             | nan                  |
+| 1.7751 | 900  | -             | nan                  |
+| 1.9724 | 1000 | 0.0393        | nan                  |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.7.0
+- Datasets: 2.14.4
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-1000/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-1000/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8aed365b353fe1a54943d41c6a59bcfaee3f3501107ca9531e092c11ab366a1
+size 470637416

checkpoint-1000/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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6cff9449516512dcb2d88111e071dd61e9b7a1213709ef6775fbfe5fb29747
+size 940212218

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e60ec7c6daffa2345890216a615b934b4e3c644297c631caadc8f76c5bdf44
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e973e9591cee2efb2deae3b216d2c5736cc6ba56a19a94afca78b909c125c023
+size 1064

checkpoint-1000/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.972386587771203,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19723865877712032,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2181,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.39447731755424065,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.5897,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.591715976331361,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.847,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7889546351084813,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.166,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 8.998483657836914,
+      "learning_rate": 1.4372355430183358e-05,
+      "loss": 0.28,
+      "step": 500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2219,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.183431952662722,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 3.4138,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3806706114398422,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.3764,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5779092702169626,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2387,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2026,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.972386587771203,
+      "grad_norm": 0.12859900295734406,
+      "learning_rate": 7.320169252468266e-06,
+      "loss": 0.0393,
+      "step": 1000
+    },
+    {
+      "epoch": 1.972386587771203,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 4.1539,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1521,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b0c772261a311993bb357660901823f0e8111b9d4198a0bb2d995ed7daee06
+size 5496

checkpoint-1000/unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260

checkpoint-1500/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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-1500/README.md

@@ -0,0 +1,402 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8100
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Apakah santri boleh keluar pondok saat dikunjungi?
+  sentences:
+  - Cukup menghubungi bagian keuangan atau humas PPS. Imam Syafi'i.
+  - Keluar pondok hanya boleh dengan izin resmi dan keadaan darurat.
+  - Ya, seperti menjadi ketua kelompok, mengatur antrian, dan memimpin doa.
+- source_sentence: Apakah santri boleh membawa HP?
+  sentences:
+  - HP tidak diperbolehkan dibawa ke lingkungan pesantren.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+  - Santri akan mendapatkan pendampingan psikologis dan konseling.
+- source_sentence: Apakah ada kegiatan kebersihan harian di TK?
+  sentences:
+  - Santri mendapat pembinaan khusus dan apresiasi.
+  - Ya, setiap pagi santri melakukan piket kebersihan lingkungan sesuai jadwal.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+- source_sentence: Apakah ada buku panduan bagi wali santri baru?
+  sentences:
+  - Wali harus mengajukan surat izin resmi dan mendapat persetujuan pengasuh.
+  - Ekskul dapat diganti satu kali di tengah semester dengan izin wali kelas.
+  - Ya, setiap wali mendapat buku panduan saat pendaftaran.
+- source_sentence: Apakah ekskul dibuka untuk santri baru?
+  sentences:
+  - Ya, santri harus menjaga ketenangan dan mengembalikan buku tepat waktu.
+  - Ya, santri baru dapat langsung mendaftar ekskul di awal semester.
+  - Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'Apakah ekskul dibuka untuk santri baru?',
+    'Ya, santri baru dapat langsung mendaftar ekskul di awal semester.',
+    'Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+
+<!--
+## 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: 8,100 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 11.19 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.87 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                  | sentence_1                                                                                    |
+  |:------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>Apakah kurikulum mencakup pendidikan karakter?</code> | <code>Ya, pembinaan karakter menjadi bagian utama kurikulum pesantren.</code>                 |
+  | <code>Apakah lingkungan pondok ramah anak?</code>           | <code>Ya, desain dan pengawasan mendukung kenyamanan dan keamanan santri.</code>              |
+  | <code>Apakah nilai adab berpengaruh pada kelulusan?</code>  | <code>Sangat berpengaruh, nilai adab menjadi pertimbangan utama dalam penilaian akhir.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | eval_spearman_cosine |
+|:------:|:----:|:-------------:|:--------------------:|
+| 0.1972 | 100  | -             | nan                  |
+| 0.3945 | 200  | -             | nan                  |
+| 0.5917 | 300  | -             | nan                  |
+| 0.7890 | 400  | -             | nan                  |
+| 0.9862 | 500  | 0.28          | nan                  |
+| 1.0    | 507  | -             | nan                  |
+| 1.1834 | 600  | -             | nan                  |
+| 1.3807 | 700  | -             | nan                  |
+| 1.5779 | 800  | -             | nan                  |
+| 1.7751 | 900  | -             | nan                  |
+| 1.9724 | 1000 | 0.0393        | nan                  |
+| 2.0    | 1014 | -             | nan                  |
+| 2.1696 | 1100 | -             | nan                  |
+| 2.3669 | 1200 | -             | nan                  |
+| 2.5641 | 1300 | -             | nan                  |
+| 2.7613 | 1400 | -             | nan                  |
+| 2.9586 | 1500 | 0.0274        | nan                  |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.7.0
+- Datasets: 2.14.4
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-1500/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-1500/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912d6a3b8bf777d9a898b03f0c4dbfab1b45d564b490b270afd867103372f2c5
+size 470637416

checkpoint-1500/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-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a8db289c9bb2d1a7f7e4cab91157c90af1334ee158f670ba4edbed5acfdf20
+size 940212218

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dfee4901e3a689f3d66ecbc899041b4ba253322395c73cd095c44cc6f098d4d
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c6d2d58a3b9966705e49a7c4047f9889d86d517c933ee6e63399fdc64fd784
+size 1064

checkpoint-1500/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9585798816568047,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19723865877712032,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2181,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.39447731755424065,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.5897,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.591715976331361,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.847,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7889546351084813,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.166,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 8.998483657836914,
+      "learning_rate": 1.4372355430183358e-05,
+      "loss": 0.28,
+      "step": 500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2219,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.183431952662722,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 3.4138,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3806706114398422,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.3764,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5779092702169626,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2387,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2026,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.972386587771203,
+      "grad_norm": 0.12859900295734406,
+      "learning_rate": 7.320169252468266e-06,
+      "loss": 0.0393,
+      "step": 1000
+    },
+    {
+      "epoch": 1.972386587771203,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 4.1539,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.1696252465483234,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2677,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.366863905325444,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2481,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.5014,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7613412228796843,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.6007,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 2.3075523376464844,
+      "learning_rate": 2.679830747531735e-07,
+      "loss": 0.0274,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.6228,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1521,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b0c772261a311993bb357660901823f0e8111b9d4198a0bb2d995ed7daee06
+size 5496

checkpoint-1500/unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260

checkpoint-1521/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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-1521/README.md

@@ -0,0 +1,402 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:8100
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Apakah santri boleh keluar pondok saat dikunjungi?
+  sentences:
+  - Cukup menghubungi bagian keuangan atau humas PPS. Imam Syafi'i.
+  - Keluar pondok hanya boleh dengan izin resmi dan keadaan darurat.
+  - Ya, seperti menjadi ketua kelompok, mengatur antrian, dan memimpin doa.
+- source_sentence: Apakah santri boleh membawa HP?
+  sentences:
+  - HP tidak diperbolehkan dibawa ke lingkungan pesantren.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+  - Santri akan mendapatkan pendampingan psikologis dan konseling.
+- source_sentence: Apakah ada kegiatan kebersihan harian di TK?
+  sentences:
+  - Santri mendapat pembinaan khusus dan apresiasi.
+  - Ya, setiap pagi santri melakukan piket kebersihan lingkungan sesuai jadwal.
+  - Ya, kurikulum disesuaikan dengan tingkat perkembangan santri.
+- source_sentence: Apakah ada buku panduan bagi wali santri baru?
+  sentences:
+  - Wali harus mengajukan surat izin resmi dan mendapat persetujuan pengasuh.
+  - Ekskul dapat diganti satu kali di tengah semester dengan izin wali kelas.
+  - Ya, setiap wali mendapat buku panduan saat pendaftaran.
+- source_sentence: Apakah ekskul dibuka untuk santri baru?
+  sentences:
+  - Ya, santri harus menjaga ketenangan dan mengembalikan buku tepat waktu.
+  - Ya, santri baru dapat langsung mendaftar ekskul di awal semester.
+  - Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: pearson_cosine
+      value: .nan
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: .nan
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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 = [
+    'Apakah ekskul dibuka untuk santri baru?',
+    'Ya, santri baru dapat langsung mendaftar ekskul di awal semester.',
+    'Ya, kurikulum terus dievaluasi dan disesuaikan dengan tantangan era modern.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value   |
+|:--------------------|:--------|
+| pearson_cosine      | nan     |
+| **spearman_cosine** | **nan** |
+
+<!--
+## 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: 8,100 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | sentence_1                                                                        |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 11.19 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.87 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                  | sentence_1                                                                                    |
+  |:------------------------------------------------------------|:----------------------------------------------------------------------------------------------|
+  | <code>Apakah kurikulum mencakup pendidikan karakter?</code> | <code>Ya, pembinaan karakter menjadi bagian utama kurikulum pesantren.</code>                 |
+  | <code>Apakah lingkungan pondok ramah anak?</code>           | <code>Ya, desain dan pengawasan mendukung kenyamanan dan keamanan santri.</code>              |
+  | <code>Apakah nilai adab berpengaruh pada kelulusan?</code>  | <code>Sangat berpengaruh, nilai adab menjadi pertimbangan utama dalam penilaian akhir.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | eval_spearman_cosine |
+|:------:|:----:|:-------------:|:--------------------:|
+| 0.1972 | 100  | -             | nan                  |
+| 0.3945 | 200  | -             | nan                  |
+| 0.5917 | 300  | -             | nan                  |
+| 0.7890 | 400  | -             | nan                  |
+| 0.9862 | 500  | 0.28          | nan                  |
+| 1.0    | 507  | -             | nan                  |
+| 1.1834 | 600  | -             | nan                  |
+| 1.3807 | 700  | -             | nan                  |
+| 1.5779 | 800  | -             | nan                  |
+| 1.7751 | 900  | -             | nan                  |
+| 1.9724 | 1000 | 0.0393        | nan                  |
+| 2.0    | 1014 | -             | nan                  |
+| 2.1696 | 1100 | -             | nan                  |
+| 2.3669 | 1200 | -             | nan                  |
+| 2.5641 | 1300 | -             | nan                  |
+| 2.7613 | 1400 | -             | nan                  |
+| 2.9586 | 1500 | 0.0274        | nan                  |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.7.0
+- Datasets: 2.14.4
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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-1521/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-1521/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-1521/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3dcd6d2d9140cbd7c02ecc37a617f845a0054d900bd1eda5819e0d7663ebe2a
+size 470637416

checkpoint-1521/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-1521/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927ca651bdb6433b442b7c5e009f5e424eb2480f9ece6f60717af5c320ac0beb
+size 940212218

checkpoint-1521/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c997fe6a93ef53310c727d6001a259df7f798f43848aaa19c09caf8e7df80ab
+size 14244

checkpoint-1521/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947e75d17a87abcec3ab62aa97fe552d39f14ab8277603337044f9ca9009bd02
+size 1064

checkpoint-1521/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

checkpoint-1521/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1521/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

checkpoint-1521/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

checkpoint-1521/trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1521,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19723865877712032,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2181,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.39447731755424065,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.5897,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.591715976331361,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.847,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7889546351084813,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 2.166,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 8.998483657836914,
+      "learning_rate": 1.4372355430183358e-05,
+      "loss": 0.28,
+      "step": 500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2219,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.183431952662722,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 3.4138,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3806706114398422,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.3764,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5779092702169626,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2387,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7751479289940828,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2026,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.972386587771203,
+      "grad_norm": 0.12859900295734406,
+      "learning_rate": 7.320169252468266e-06,
+      "loss": 0.0393,
+      "step": 1000
+    },
+    {
+      "epoch": 1.972386587771203,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 4.1539,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.1696252465483234,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2677,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.366863905325444,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.2481,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.5014,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7613412228796843,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.6007,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 2.3075523376464844,
+      "learning_rate": 2.679830747531735e-07,
+      "loss": 0.0274,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_pearson_cosine": NaN,
+      "eval_runtime": 1.6228,
+      "eval_samples_per_second": 0.0,
+      "eval_spearman_cosine": NaN,
+      "eval_steps_per_second": 0.0,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1521,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1521/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b0c772261a311993bb357660901823f0e8111b9d4198a0bb2d995ed7daee06
+size 5496