Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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-1564/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1564/unigram.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3128/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

@@ -0,0 +1,17 @@
+
+---
+tags:
+- autotrain
+- sentence-transformers
+widget:
+- text: "I love AutoTrain"
+datasets:
+- ucsahin/TR-Extractive-QA-5K
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Sentence Transformers
+
+## Validation Metrics
+No validation metrics available

checkpoint-1564/1_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-1564/README.md

@@ -0,0 +1,542 @@
+---
+language:
+- multilingual
+- zh
+- ja
+- ar
+- ko
+- de
+- fr
+- es
+- pt
+- hi
+- id
+- it
+- tr
+- ru
+- bn
+- ur
+- mr
+- ta
+- vi
+- fa
+- pl
+- uk
+- nl
+- sv
+- he
+- sw
+- ps
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:10K<n<100K
+- loss:CoSENTLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Is that wrong?
+  sentences:
+  - Is that such a terrible thing?
+  - Kennedy korkunç bir savcıydı.
+  - Tom bir davada tanıklık ediyordu.
+- source_sentence: Orada mıydılar?
+  sentences:
+  - Were they in there?
+  - İlki ikincisini anlamlı kılar.
+  - Alerji tedavisi gelişiyor.
+- source_sentence: He is not alone
+  sentences:
+  - It is not confusing
+  - The Hawks were humanitarians.
+  - Tom bir davada tanıklık ediyordu.
+- source_sentence: Yaptığın şey bu.
+  sentences:
+  - Onurlu işler yapıyorsunuz.
+  - Weisberg azınlık adına konuştu.
+  - Robert Ferrigno Kaliforniya'da doğdu.
+- source_sentence: Ben vatansızım.
+  sentences:
+  - I am stateless.
+  - Kendi tekniğini tercih ediyor.
+  - Mermiler camdan fırladı.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: tr ling
+      type: tr_ling
+    metrics:
+    - type: pearson_cosine
+      value: 0.037604255015168134
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.04804112988506346
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.034740275152181296
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.03769766156967754
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.03698411306484619
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.03903062430281842
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.0673696846368413
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.06818119362900125
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.0673696846368413
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.06818119362900125
+      name: Spearman Max
+---
+
+# 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) on the [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) dataset. 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 bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7)
+- **Languages:** multilingual, zh, ja, ar, ko, de, fr, es, pt, hi, id, it, tr, ru, bn, ur, mr, ta, vi, fa, pl, uk, nl, sv, he, sw, ps
+<!-- - **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 = [
+    'Ben vatansızım.',
+    'I am stateless.',
+    'Kendi tekniğini tercih ediyor.',
+]
+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: `tr_ling`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.0376     |
+| spearman_cosine    | 0.048      |
+| pearson_manhattan  | 0.0347     |
+| spearman_manhattan | 0.0377     |
+| pearson_euclidean  | 0.037      |
+| spearman_euclidean | 0.039      |
+| pearson_dot        | 0.0674     |
+| spearman_dot       | 0.0682     |
+| pearson_max        | 0.0674     |
+| **spearman_max**   | **0.0682** |
+
+<!--
+## 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
+
+#### MoritzLaurer/multilingual-nli-26lang-2mil7
+
+* Dataset: [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) at [510a233](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7/tree/510a233972a0d7ff0f767d82f46e046832c10538)
+* Size: 25,000 training samples
+* Columns: <code>premise_original</code>, <code>hypothesis_original</code>, <code>score</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise_original                                                                  | hypothesis_original                                                               | score                                                              | sentence1                                                                          | sentence2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                                                | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 29.3 tokens</li><li>max: 107 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.62 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>0: ~34.50%</li><li>1: ~33.30%</li><li>2: ~32.20%</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 28.28 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.39 tokens</li><li>max: 38 tokens</li></ul> |
+* Samples:
+  | premise_original                                                                                                                                                                                                                                                 | hypothesis_original                                                                                                                                                  | score          | sentence1                                                                                                                                                                                                                                                                   | sentence2                                                                                                                                          |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>N, the total number of LC50 values used in calculating the CV(%) varied with organism and toxicant because some data were rejected due to water hardness, lack of concentration measurements, and/or because some of the LC50s were not calculable.</code> | <code>Most discarded data was rejected due to water hardness.</code>                                                                                                 | <code>1</code> | <code>N, CV'nin hesaplanmasında kullanılan LC50 değerlerinin toplam sayısı (%) organizma ve toksik madde ile çeşitlidir, çünkü bazı veriler su sertliği, konsantrasyon ölçümlerinin eksikliği ve / veya LC50'lerin bazıları hesaplanamaz olduğu için reddedilmiştir.</code> | <code>Atılan verilerin çoğu su sertliği nedeniyle reddedildi.</code>                                                                               |
+  | <code>As the home of the Venus de Milo and Mona Lisa, the Louvre drew almost unmanageable crowds until President Mitterrand ordered its re-organization in the 1980s.</code>                                                                                     | <code>The Louvre is home of the Venus de Milo and Mona Lisa.</code>                                                                                                  | <code>0</code> | <code>Venus de Milo ve Mona Lisa'nın evi olarak Louvre, Başkan Mitterrand'ın 1980'lerde yeniden düzenlenmesini emredene kadar neredeyse yönetilemez kalabalıklar çekti.</code>                                                                                              | <code>Louvre, Venus de Milo ve Mona Lisa'nın evidir.</code>                                                                                        |
+  | <code>A year ago, the wife of the Oxford don noticed that the pattern on Kleenex quilted tissue uncannily resembled the Penrose Arrowed Rhombi tilings pattern, which Sir Roger had invented--and copyrighted--in 1974.</code>                                   | <code>It has been recently found out a similarity between the pattern on the recent Kleenex quilted tissue and the one of the Penrose Arrowed Rhombi tilings.</code> | <code>0</code> | <code>Bir yıl önce Oxford'un karısı, Kleenex kapitone dokudaki desenin 1974'te Sir Roger'ın icat ettiği -ve telif hakkı olan - Penrose Arrowed Rhombi tilings desenine benzediğini fark etti.</code>                                                                        | <code>Yakın zamanda, son Kleenex kapitone dokudaki desen ile Penrose Arrowed Rhombi döşemelerinden biri arasında bir benzerlik bulunmuştur.</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### MoritzLaurer/multilingual-nli-26lang-2mil7
+
+* Dataset: [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) at [510a233](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7/tree/510a233972a0d7ff0f767d82f46e046832c10538)
+* Size: 5,000 evaluation samples
+* Columns: <code>premise_original</code>, <code>hypothesis_original</code>, <code>score</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise_original                                                                 | hypothesis_original                                                               | score                                                              | sentence1                                                                          | sentence2                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | int                                                                | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 30.3 tokens</li><li>max: 99 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~34.50%</li><li>1: ~29.90%</li><li>2: ~35.60%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 29.94 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.29 tokens</li><li>max: 52 tokens</li></ul> |
+* Samples:
+  | premise_original                                                                                                | hypothesis_original                                                            | score          | sentence1                                                                     | sentence2                                                        |
+  |:----------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:---------------|:------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | <code>But the racism charge isn't quirky or wacky--it's demagogy.</code>                                        | <code>The accusation of prejudice based on a pedestrian kind of hatred.</code> | <code>0</code> | <code>Ama ırkçılık suçlaması tuhaf ya da tuhaf değil, bu bir demagoji.</code> | <code>Yaya nefretine dayanan önyargı suçlaması.</code>           |
+  | <code>Why would Gates allow the publication of such a book with his byline and photo on the dust jacket?</code> | <code>Gates' byline and photo are on the dust jacket</code>                    | <code>0</code> | <code>Gates neden böyle bir kitabın basılmasına izin versin ki?</code>        | <code>Gates'in çizgisi ve fotoğrafı toz ceketin üzerinde.</code> |
+  | <code>I am a nonsmoker and allergic to cigarette smoke.</code>                                                  | <code>I do not smoke.</code>                                                   | <code>0</code> | <code>Sigara içmeyen biriyim ve sigara dumanına alerjim var.</code>           | <code>Sigara içmiyorum.</code>                                   |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `ddp_find_unused_parameters`: False
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_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`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: False
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | tr_ling_spearman_max |
+|:------:|:----:|:-------------:|:------:|:--------------------:|
+| 0.0320 | 25   | 17.17         | -      | -                    |
+| 0.0639 | 50   | 16.4932       | -      | -                    |
+| 0.0959 | 75   | 16.5976       | -      | -                    |
+| 0.1279 | 100  | 15.6991       | -      | -                    |
+| 0.1598 | 125  | 14.876        | -      | -                    |
+| 0.1918 | 150  | 14.4828       | -      | -                    |
+| 0.2238 | 175  | 12.7061       | -      | -                    |
+| 0.2558 | 200  | 10.8687       | -      | -                    |
+| 0.2877 | 225  | 8.3797        | -      | -                    |
+| 0.3197 | 250  | 6.2029        | -      | -                    |
+| 0.3517 | 275  | 5.8228        | -      | -                    |
+| 0.3836 | 300  | 5.811         | -      | -                    |
+| 0.4156 | 325  | 5.8079        | -      | -                    |
+| 0.4476 | 350  | 5.8077        | -      | -                    |
+| 0.4795 | 375  | 5.8035        | -      | -                    |
+| 0.5115 | 400  | 5.8072        | -      | -                    |
+| 0.5435 | 425  | 5.8033        | -      | -                    |
+| 0.5754 | 450  | 5.8086        | -      | -                    |
+| 0.6074 | 475  | 5.81          | -      | -                    |
+| 0.6394 | 500  | 5.7949        | -      | -                    |
+| 0.6714 | 525  | 5.8079        | -      | -                    |
+| 0.7033 | 550  | 5.8057        | -      | -                    |
+| 0.7353 | 575  | 5.8097        | -      | -                    |
+| 0.7673 | 600  | 5.7986        | -      | -                    |
+| 0.7992 | 625  | 5.8051        | -      | -                    |
+| 0.8312 | 650  | 5.8041        | -      | -                    |
+| 0.8632 | 675  | 5.7907        | -      | -                    |
+| 0.8951 | 700  | 5.7991        | -      | -                    |
+| 0.9271 | 725  | 5.8035        | -      | -                    |
+| 0.9591 | 750  | 5.7945        | -      | -                    |
+| 0.9910 | 775  | 5.8077        | -      | -                    |
+| 1.0    | 782  | -             | 5.8024 | 0.0330               |
+| 1.0230 | 800  | 5.6703        | -      | -                    |
+| 1.0550 | 825  | 5.8052        | -      | -                    |
+| 1.0870 | 850  | 5.7936        | -      | -                    |
+| 1.1189 | 875  | 5.7924        | -      | -                    |
+| 1.1509 | 900  | 5.7806        | -      | -                    |
+| 1.1829 | 925  | 5.7835        | -      | -                    |
+| 1.2148 | 950  | 5.7619        | -      | -                    |
+| 1.2468 | 975  | 5.8038        | -      | -                    |
+| 1.2788 | 1000 | 5.779         | -      | -                    |
+| 1.3107 | 1025 | 5.7904        | -      | -                    |
+| 1.3427 | 1050 | 5.7696        | -      | -                    |
+| 1.3747 | 1075 | 5.7919        | -      | -                    |
+| 1.4066 | 1100 | 5.7785        | -      | -                    |
+| 1.4386 | 1125 | 5.7862        | -      | -                    |
+| 1.4706 | 1150 | 5.7703        | -      | -                    |
+| 1.5026 | 1175 | 5.773         | -      | -                    |
+| 1.5345 | 1200 | 5.7627        | -      | -                    |
+| 1.5665 | 1225 | 5.7596        | -      | -                    |
+| 1.5985 | 1250 | 5.7882        | -      | -                    |
+| 1.6304 | 1275 | 5.7828        | -      | -                    |
+| 1.6624 | 1300 | 5.771         | -      | -                    |
+| 1.6944 | 1325 | 5.788         | -      | -                    |
+| 1.7263 | 1350 | 5.7719        | -      | -                    |
+| 1.7583 | 1375 | 5.7846        | -      | -                    |
+| 1.7903 | 1400 | 5.7838        | -      | -                    |
+| 1.8223 | 1425 | 5.7912        | -      | -                    |
+| 1.8542 | 1450 | 5.7686        | -      | -                    |
+| 1.8862 | 1475 | 5.7938        | -      | -                    |
+| 1.9182 | 1500 | 5.7847        | -      | -                    |
+| 1.9501 | 1525 | 5.7952        | -      | -                    |
+| 1.9821 | 1550 | 5.7528        | -      | -                    |
+| 2.0    | 1564 | -             | 5.7933 | 0.0682               |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-1564/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "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": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-1564/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-1564/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3b103c4a050ec7c20c41f4f0bdcfee82642ecfe0cd58c6268c2bfddce5abbd
+size 470637416

checkpoint-1564/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-1564/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fd1f2073e2af85a9380b42823863bdcd018438654cbfa5b3aa98b918223855
+size 940212218

checkpoint-1564/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c6bc4d1d198c376a51fede7dca1cc0874e21a3307b8ae3875e98db55be87e6
+size 14244

checkpoint-1564/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc21c2650bb4344f4670f8f3de62ba81c0b68e93028800e195846665d9176d9
+size 1064

checkpoint-1564/sentence_bert_config.json

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

checkpoint-1564/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-1564/tokenizer.json

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

checkpoint-1564/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "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-1564/trainer_state.json

@@ -0,0 +1,512 @@
+{
+  "best_metric": 5.793323516845703,
+  "best_model_checkpoint": "turkish-embedding-model/checkpoint-1564",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1564,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0319693094629156,
+      "grad_norm": 70.72708129882812,
+      "learning_rate": 1.1253196930946293e-06,
+      "loss": 17.17,
+      "step": 25
+    },
+    {
+      "epoch": 0.0639386189258312,
+      "grad_norm": 81.68770599365234,
+      "learning_rate": 2.4040920716112534e-06,
+      "loss": 16.4932,
+      "step": 50
+    },
+    {
+      "epoch": 0.0959079283887468,
+      "grad_norm": 109.91338348388672,
+      "learning_rate": 3.6828644501278778e-06,
+      "loss": 16.5976,
+      "step": 75
+    },
+    {
+      "epoch": 0.1278772378516624,
+      "grad_norm": 73.892578125,
+      "learning_rate": 4.961636828644502e-06,
+      "loss": 15.6991,
+      "step": 100
+    },
+    {
+      "epoch": 0.159846547314578,
+      "grad_norm": 79.35150909423828,
+      "learning_rate": 6.240409207161126e-06,
+      "loss": 14.876,
+      "step": 125
+    },
+    {
+      "epoch": 0.1918158567774936,
+      "grad_norm": 83.0904541015625,
+      "learning_rate": 7.5191815856777495e-06,
+      "loss": 14.4828,
+      "step": 150
+    },
+    {
+      "epoch": 0.2237851662404092,
+      "grad_norm": 76.82855987548828,
+      "learning_rate": 8.797953964194374e-06,
+      "loss": 12.7061,
+      "step": 175
+    },
+    {
+      "epoch": 0.2557544757033248,
+      "grad_norm": 51.30181121826172,
+      "learning_rate": 1.0076726342710998e-05,
+      "loss": 10.8687,
+      "step": 200
+    },
+    {
+      "epoch": 0.2877237851662404,
+      "grad_norm": 18.70808219909668,
+      "learning_rate": 1.1355498721227622e-05,
+      "loss": 8.3797,
+      "step": 225
+    },
+    {
+      "epoch": 0.319693094629156,
+      "grad_norm": 1.3039417266845703,
+      "learning_rate": 1.2634271099744246e-05,
+      "loss": 6.2029,
+      "step": 250
+    },
+    {
+      "epoch": 0.3516624040920716,
+      "grad_norm": 0.2324853092432022,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 5.8228,
+      "step": 275
+    },
+    {
+      "epoch": 0.3836317135549872,
+      "grad_norm": 0.1757364720106125,
+      "learning_rate": 1.5191815856777494e-05,
+      "loss": 5.811,
+      "step": 300
+    },
+    {
+      "epoch": 0.4156010230179028,
+      "grad_norm": 0.1788654774427414,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 5.8079,
+      "step": 325
+    },
+    {
+      "epoch": 0.4475703324808184,
+      "grad_norm": 0.12862567603588104,
+      "learning_rate": 1.7749360613810744e-05,
+      "loss": 5.8077,
+      "step": 350
+    },
+    {
+      "epoch": 0.479539641943734,
+      "grad_norm": 0.14497514069080353,
+      "learning_rate": 1.9028132992327367e-05,
+      "loss": 5.8035,
+      "step": 375
+    },
+    {
+      "epoch": 0.5115089514066496,
+      "grad_norm": 0.1350390762090683,
+      "learning_rate": 1.996589940323956e-05,
+      "loss": 5.8072,
+      "step": 400
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.1435602754354477,
+      "learning_rate": 1.9823813583404378e-05,
+      "loss": 5.8033,
+      "step": 425
+    },
+    {
+      "epoch": 0.5754475703324808,
+      "grad_norm": 0.11389254033565521,
+      "learning_rate": 1.96817277635692e-05,
+      "loss": 5.8086,
+      "step": 450
+    },
+    {
+      "epoch": 0.6074168797953964,
+      "grad_norm": 0.15821650624275208,
+      "learning_rate": 1.9539641943734017e-05,
+      "loss": 5.81,
+      "step": 475
+    },
+    {
+      "epoch": 0.639386189258312,
+      "grad_norm": 0.1179889366030693,
+      "learning_rate": 1.9397556123898838e-05,
+      "loss": 5.7949,
+      "step": 500
+    },
+    {
+      "epoch": 0.6713554987212276,
+      "grad_norm": 0.10912967473268509,
+      "learning_rate": 1.9255470304063656e-05,
+      "loss": 5.8079,
+      "step": 525
+    },
+    {
+      "epoch": 0.7033248081841432,
+      "grad_norm": 0.11702870577573776,
+      "learning_rate": 1.9113384484228477e-05,
+      "loss": 5.8057,
+      "step": 550
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.13132448494434357,
+      "learning_rate": 1.8971298664393295e-05,
+      "loss": 5.8097,
+      "step": 575
+    },
+    {
+      "epoch": 0.7672634271099744,
+      "grad_norm": 0.15833145380020142,
+      "learning_rate": 1.8829212844558116e-05,
+      "loss": 5.7986,
+      "step": 600
+    },
+    {
+      "epoch": 0.7992327365728901,
+      "grad_norm": 0.11651863902807236,
+      "learning_rate": 1.8687127024722937e-05,
+      "loss": 5.8051,
+      "step": 625
+    },
+    {
+      "epoch": 0.8312020460358056,
+      "grad_norm": 0.5393890142440796,
+      "learning_rate": 1.854504120488775e-05,
+      "loss": 5.8041,
+      "step": 650
+    },
+    {
+      "epoch": 0.8631713554987213,
+      "grad_norm": 0.6457561254501343,
+      "learning_rate": 1.8402955385052572e-05,
+      "loss": 5.7907,
+      "step": 675
+    },
+    {
+      "epoch": 0.8951406649616368,
+      "grad_norm": 0.5643135905265808,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 5.7991,
+      "step": 700
+    },
+    {
+      "epoch": 0.9271099744245525,
+      "grad_norm": 3.214787721633911,
+      "learning_rate": 1.811878374538221e-05,
+      "loss": 5.8035,
+      "step": 725
+    },
+    {
+      "epoch": 0.959079283887468,
+      "grad_norm": 2.781162977218628,
+      "learning_rate": 1.7976697925547032e-05,
+      "loss": 5.7945,
+      "step": 750
+    },
+    {
+      "epoch": 0.9910485933503836,
+      "grad_norm": 0.38559335470199585,
+      "learning_rate": 1.783461210571185e-05,
+      "loss": 5.8077,
+      "step": 775
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.8023600578308105,
+      "eval_runtime": 18.0632,
+      "eval_samples_per_second": 276.805,
+      "eval_steps_per_second": 4.374,
+      "eval_tr_ling_pearson_cosine": 0.017751548525136808,
+      "eval_tr_ling_pearson_dot": 0.025703597820631346,
+      "eval_tr_ling_pearson_euclidean": 0.02195284877201089,
+      "eval_tr_ling_pearson_manhattan": 0.02083376479528459,
+      "eval_tr_ling_pearson_max": 0.025703597820631346,
+      "eval_tr_ling_spearman_cosine": 0.027108099994157316,
+      "eval_tr_ling_spearman_dot": 0.03304394653738539,
+      "eval_tr_ling_spearman_euclidean": 0.025485959636772793,
+      "eval_tr_ling_spearman_manhattan": 0.024466610177699702,
+      "eval_tr_ling_spearman_max": 0.03304394653738539,
+      "step": 782
+    },
+    {
+      "epoch": 1.0230179028132993,
+      "grad_norm": 0.3645063638687134,
+      "learning_rate": 1.769252628587667e-05,
+      "loss": 5.6703,
+      "step": 800
+    },
+    {
+      "epoch": 1.054987212276215,
+      "grad_norm": 0.9638137817382812,
+      "learning_rate": 1.7550440466041488e-05,
+      "loss": 5.8052,
+      "step": 825
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.114203691482544,
+      "learning_rate": 1.740835464620631e-05,
+      "loss": 5.7936,
+      "step": 850
+    },
+    {
+      "epoch": 1.118925831202046,
+      "grad_norm": 1.8992066383361816,
+      "learning_rate": 1.7266268826371127e-05,
+      "loss": 5.7924,
+      "step": 875
+    },
+    {
+      "epoch": 1.1508951406649617,
+      "grad_norm": 2.8299577236175537,
+      "learning_rate": 1.7124183006535948e-05,
+      "loss": 5.7806,
+      "step": 900
+    },
+    {
+      "epoch": 1.1828644501278773,
+      "grad_norm": 1.956953525543213,
+      "learning_rate": 1.698209718670077e-05,
+      "loss": 5.7835,
+      "step": 925
+    },
+    {
+      "epoch": 1.2148337595907928,
+      "grad_norm": 2.658413887023926,
+      "learning_rate": 1.6840011366865587e-05,
+      "loss": 5.7619,
+      "step": 950
+    },
+    {
+      "epoch": 1.2468030690537084,
+      "grad_norm": 1.2760388851165771,
+      "learning_rate": 1.6697925547030408e-05,
+      "loss": 5.8038,
+      "step": 975
+    },
+    {
+      "epoch": 1.278772378516624,
+      "grad_norm": 1.7434897422790527,
+      "learning_rate": 1.6555839727195226e-05,
+      "loss": 5.779,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3107416879795397,
+      "grad_norm": 1.3532071113586426,
+      "learning_rate": 1.6413753907360047e-05,
+      "loss": 5.7904,
+      "step": 1025
+    },
+    {
+      "epoch": 1.3427109974424551,
+      "grad_norm": 3.7385997772216797,
+      "learning_rate": 1.6271668087524864e-05,
+      "loss": 5.7696,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3746803069053708,
+      "grad_norm": 0.9061102867126465,
+      "learning_rate": 1.6129582267689685e-05,
+      "loss": 5.7919,
+      "step": 1075
+    },
+    {
+      "epoch": 1.4066496163682864,
+      "grad_norm": 2.7104809284210205,
+      "learning_rate": 1.5987496447854503e-05,
+      "loss": 5.7785,
+      "step": 1100
+    },
+    {
+      "epoch": 1.438618925831202,
+      "grad_norm": 1.7147830724716187,
+      "learning_rate": 1.5845410628019324e-05,
+      "loss": 5.7862,
+      "step": 1125
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 2.525214672088623,
+      "learning_rate": 1.5703324808184145e-05,
+      "loss": 5.7703,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5025575447570332,
+      "grad_norm": 1.7794997692108154,
+      "learning_rate": 1.5561238988348963e-05,
+      "loss": 5.773,
+      "step": 1175
+    },
+    {
+      "epoch": 1.5345268542199488,
+      "grad_norm": 4.901644229888916,
+      "learning_rate": 1.5419153168513784e-05,
+      "loss": 5.7627,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5664961636828645,
+      "grad_norm": 3.360812187194824,
+      "learning_rate": 1.52770673486786e-05,
+      "loss": 5.7596,
+      "step": 1225
+    },
+    {
+      "epoch": 1.59846547314578,
+      "grad_norm": 1.2768888473510742,
+      "learning_rate": 1.5134981528843423e-05,
+      "loss": 5.7882,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 2.206226348876953,
+      "learning_rate": 1.4992895709008242e-05,
+      "loss": 5.7828,
+      "step": 1275
+    },
+    {
+      "epoch": 1.6624040920716112,
+      "grad_norm": 1.4602406024932861,
+      "learning_rate": 1.4850809889173061e-05,
+      "loss": 5.771,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6943734015345269,
+      "grad_norm": 1.1597537994384766,
+      "learning_rate": 1.4708724069337881e-05,
+      "loss": 5.788,
+      "step": 1325
+    },
+    {
+      "epoch": 1.7263427109974425,
+      "grad_norm": 3.7494003772735596,
+      "learning_rate": 1.45666382495027e-05,
+      "loss": 5.7719,
+      "step": 1350
+    },
+    {
+      "epoch": 1.758312020460358,
+      "grad_norm": 1.6271498203277588,
+      "learning_rate": 1.442455242966752e-05,
+      "loss": 5.7846,
+      "step": 1375
+    },
+    {
+      "epoch": 1.7902813299232738,
+      "grad_norm": 2.0469117164611816,
+      "learning_rate": 1.4282466609832339e-05,
+      "loss": 5.7838,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8222506393861893,
+      "grad_norm": 2.533921003341675,
+      "learning_rate": 1.4140380789997158e-05,
+      "loss": 5.7912,
+      "step": 1425
+    },
+    {
+      "epoch": 1.854219948849105,
+      "grad_norm": 3.291757583618164,
+      "learning_rate": 1.3998294970161978e-05,
+      "loss": 5.7686,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8861892583120206,
+      "grad_norm": 3.0181350708007812,
+      "learning_rate": 1.3856209150326799e-05,
+      "loss": 5.7938,
+      "step": 1475
+    },
+    {
+      "epoch": 1.918158567774936,
+      "grad_norm": 2.553502321243286,
+      "learning_rate": 1.3714123330491618e-05,
+      "loss": 5.7847,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9501278772378516,
+      "grad_norm": 1.8034719228744507,
+      "learning_rate": 1.3572037510656438e-05,
+      "loss": 5.7952,
+      "step": 1525
+    },
+    {
+      "epoch": 1.9820971867007673,
+      "grad_norm": 3.7138864994049072,
+      "learning_rate": 1.3429951690821257e-05,
+      "loss": 5.7528,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.793323516845703,
+      "eval_runtime": 18.2796,
+      "eval_samples_per_second": 273.528,
+      "eval_steps_per_second": 4.322,
+      "eval_tr_ling_pearson_cosine": 0.037604255015168134,
+      "eval_tr_ling_pearson_dot": 0.0673696846368413,
+      "eval_tr_ling_pearson_euclidean": 0.03698411306484619,
+      "eval_tr_ling_pearson_manhattan": 0.034740275152181296,
+      "eval_tr_ling_pearson_max": 0.0673696846368413,
+      "eval_tr_ling_spearman_cosine": 0.04804112988506346,
+      "eval_tr_ling_spearman_dot": 0.06818119362900125,
+      "eval_tr_ling_spearman_euclidean": 0.03903062430281842,
+      "eval_tr_ling_spearman_manhattan": 0.03769766156967754,
+      "eval_tr_ling_spearman_max": 0.06818119362900125,
+      "step": 1564
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1564/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44b0bec8869c08bdad0d597184d7a293a0e13eb770d6f4384456cbbe4fe5aa4
+size 5368

checkpoint-1564/unigram.json

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

checkpoint-3128/1_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-3128/README.md

@@ -0,0 +1,610 @@
+---
+language:
+- multilingual
+- zh
+- ja
+- ar
+- ko
+- de
+- fr
+- es
+- pt
+- hi
+- id
+- it
+- tr
+- ru
+- bn
+- ur
+- mr
+- ta
+- vi
+- fa
+- pl
+- uk
+- nl
+- sv
+- he
+- sw
+- ps
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:10K<n<100K
+- loss:CoSENTLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Bottomless Mug
+  sentences:
+  - You are always safe.
+  - That trend isn't very known yet
+  - Eleanor Clift göreve koşuyor.
+- source_sentence: Tripp has a job.
+  sentences:
+  - They are having money problems.
+  - Malignite aniden ortaya çıkar.
+  - Mezarlar derin ormanlarda saklandı.
+- source_sentence: There are rules
+  sentences:
+  - There are more villians than heros.
+  - The directions should be read.
+  - Mezarlar derin ormanlarda saklandı.
+- source_sentence: K is a musician.
+  sentences:
+  - Klimt draws hotdogs.
+  - Ed Wood hiç mahkemeye çıkmadı.
+  - Çeçen Rusya yönetimi ele geçirdi.
+- source_sentence: We moved closer.
+  sentences:
+  - Clinton is unaware of the process.
+  - Nesil deneyimleri anlamsızdır.
+  - Hormonların etkileri vardır.
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: tr ling
+      type: tr_ling
+    metrics:
+    - type: pearson_cosine
+      value: 0.058743115070889876
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.059526247945378225
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.04582145815494953
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.04331287037397966
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.04709170917685587
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.04407504959649961
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.08477622619519222
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.08243745050110735
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.08477622619519222
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.08243745050110735
+      name: Spearman Max
+---
+
+# 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) on the [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) dataset. 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 bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7)
+- **Languages:** multilingual, zh, ja, ar, ko, de, fr, es, pt, hi, id, it, tr, ru, bn, ur, mr, ta, vi, fa, pl, uk, nl, sv, he, sw, ps
+<!-- - **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 = [
+    'We moved closer.',
+    'Clinton is unaware of the process.',
+    'Nesil deneyimleri anlamsızdır.',
+]
+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: `tr_ling`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.0587     |
+| spearman_cosine    | 0.0595     |
+| pearson_manhattan  | 0.0458     |
+| spearman_manhattan | 0.0433     |
+| pearson_euclidean  | 0.0471     |
+| spearman_euclidean | 0.0441     |
+| pearson_dot        | 0.0848     |
+| spearman_dot       | 0.0824     |
+| pearson_max        | 0.0848     |
+| **spearman_max**   | **0.0824** |
+
+<!--
+## 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
+
+#### MoritzLaurer/multilingual-nli-26lang-2mil7
+
+* Dataset: [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) at [510a233](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7/tree/510a233972a0d7ff0f767d82f46e046832c10538)
+* Size: 25,000 training samples
+* Columns: <code>premise_original</code>, <code>hypothesis_original</code>, <code>score</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise_original                                                                  | hypothesis_original                                                               | score                                                              | sentence1                                                                          | sentence2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                                                | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 29.3 tokens</li><li>max: 107 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.62 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>0: ~34.50%</li><li>1: ~33.30%</li><li>2: ~32.20%</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 28.28 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.39 tokens</li><li>max: 38 tokens</li></ul> |
+* Samples:
+  | premise_original                                                                                                                                                                                                                                                 | hypothesis_original                                                                                                                                                  | score          | sentence1                                                                                                                                                                                                                                                                   | sentence2                                                                                                                                          |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>N, the total number of LC50 values used in calculating the CV(%) varied with organism and toxicant because some data were rejected due to water hardness, lack of concentration measurements, and/or because some of the LC50s were not calculable.</code> | <code>Most discarded data was rejected due to water hardness.</code>                                                                                                 | <code>1</code> | <code>N, CV'nin hesaplanmasında kullanılan LC50 değerlerinin toplam sayısı (%) organizma ve toksik madde ile çeşitlidir, çünkü bazı veriler su sertliği, konsantrasyon ölçümlerinin eksikliği ve / veya LC50'lerin bazıları hesaplanamaz olduğu için reddedilmiştir.</code> | <code>Atılan verilerin çoğu su sertliği nedeniyle reddedildi.</code>                                                                               |
+  | <code>As the home of the Venus de Milo and Mona Lisa, the Louvre drew almost unmanageable crowds until President Mitterrand ordered its re-organization in the 1980s.</code>                                                                                     | <code>The Louvre is home of the Venus de Milo and Mona Lisa.</code>                                                                                                  | <code>0</code> | <code>Venus de Milo ve Mona Lisa'nın evi olarak Louvre, Başkan Mitterrand'ın 1980'lerde yeniden düzenlenmesini emredene kadar neredeyse yönetilemez kalabalıklar çekti.</code>                                                                                              | <code>Louvre, Venus de Milo ve Mona Lisa'nın evidir.</code>                                                                                        |
+  | <code>A year ago, the wife of the Oxford don noticed that the pattern on Kleenex quilted tissue uncannily resembled the Penrose Arrowed Rhombi tilings pattern, which Sir Roger had invented--and copyrighted--in 1974.</code>                                   | <code>It has been recently found out a similarity between the pattern on the recent Kleenex quilted tissue and the one of the Penrose Arrowed Rhombi tilings.</code> | <code>0</code> | <code>Bir yıl önce Oxford'un karısı, Kleenex kapitone dokudaki desenin 1974'te Sir Roger'ın icat ettiği -ve telif hakkı olan - Penrose Arrowed Rhombi tilings desenine benzediğini fark etti.</code>                                                                        | <code>Yakın zamanda, son Kleenex kapitone dokudaki desen ile Penrose Arrowed Rhombi döşemelerinden biri arasında bir benzerlik bulunmuştur.</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### MoritzLaurer/multilingual-nli-26lang-2mil7
+
+* Dataset: [MoritzLaurer/multilingual-nli-26lang-2mil7](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7) at [510a233](https://huggingface.co/datasets/MoritzLaurer/multilingual-nli-26lang-2mil7/tree/510a233972a0d7ff0f767d82f46e046832c10538)
+* Size: 5,000 evaluation samples
+* Columns: <code>premise_original</code>, <code>hypothesis_original</code>, <code>score</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise_original                                                                 | hypothesis_original                                                               | score                                                              | sentence1                                                                          | sentence2                                                                         |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | int                                                                | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 30.3 tokens</li><li>max: 99 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~34.50%</li><li>1: ~29.90%</li><li>2: ~35.60%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 29.94 tokens</li><li>max: 106 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.29 tokens</li><li>max: 52 tokens</li></ul> |
+* Samples:
+  | premise_original                                                                                                | hypothesis_original                                                            | score          | sentence1                                                                     | sentence2                                                        |
+  |:----------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------|:---------------|:------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | <code>But the racism charge isn't quirky or wacky--it's demagogy.</code>                                        | <code>The accusation of prejudice based on a pedestrian kind of hatred.</code> | <code>0</code> | <code>Ama ırkçılık suçlaması tuhaf ya da tuhaf değil, bu bir demagoji.</code> | <code>Yaya nefretine dayanan önyargı suçlaması.</code>           |
+  | <code>Why would Gates allow the publication of such a book with his byline and photo on the dust jacket?</code> | <code>Gates' byline and photo are on the dust jacket</code>                    | <code>0</code> | <code>Gates neden böyle bir kitabın basılmasına izin versin ki?</code>        | <code>Gates'in çizgisi ve fotoğrafı toz ceketin üzerinde.</code> |
+  | <code>I am a nonsmoker and allergic to cigarette smoke.</code>                                                  | <code>I do not smoke.</code>                                                   | <code>0</code> | <code>Sigara içmeyen biriyim ve sigara dumanına alerjim var.</code>           | <code>Sigara içmiyorum.</code>                                   |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `ddp_find_unused_parameters`: False
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_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`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: False
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step | Training Loss | loss   | tr_ling_spearman_max |
+|:------:|:----:|:-------------:|:------:|:--------------------:|
+| 0.0320 | 25   | 17.17         | -      | -                    |
+| 0.0639 | 50   | 16.4932       | -      | -                    |
+| 0.0959 | 75   | 16.5976       | -      | -                    |
+| 0.1279 | 100  | 15.6991       | -      | -                    |
+| 0.1598 | 125  | 14.876        | -      | -                    |
+| 0.1918 | 150  | 14.4828       | -      | -                    |
+| 0.2238 | 175  | 12.7061       | -      | -                    |
+| 0.2558 | 200  | 10.8687       | -      | -                    |
+| 0.2877 | 225  | 8.3797        | -      | -                    |
+| 0.3197 | 250  | 6.2029        | -      | -                    |
+| 0.3517 | 275  | 5.8228        | -      | -                    |
+| 0.3836 | 300  | 5.811         | -      | -                    |
+| 0.4156 | 325  | 5.8079        | -      | -                    |
+| 0.4476 | 350  | 5.8077        | -      | -                    |
+| 0.4795 | 375  | 5.8035        | -      | -                    |
+| 0.5115 | 400  | 5.8072        | -      | -                    |
+| 0.5435 | 425  | 5.8033        | -      | -                    |
+| 0.5754 | 450  | 5.8086        | -      | -                    |
+| 0.6074 | 475  | 5.81          | -      | -                    |
+| 0.6394 | 500  | 5.7949        | -      | -                    |
+| 0.6714 | 525  | 5.8079        | -      | -                    |
+| 0.7033 | 550  | 5.8057        | -      | -                    |
+| 0.7353 | 575  | 5.8097        | -      | -                    |
+| 0.7673 | 600  | 5.7986        | -      | -                    |
+| 0.7992 | 625  | 5.8051        | -      | -                    |
+| 0.8312 | 650  | 5.8041        | -      | -                    |
+| 0.8632 | 675  | 5.7907        | -      | -                    |
+| 0.8951 | 700  | 5.7991        | -      | -                    |
+| 0.9271 | 725  | 5.8035        | -      | -                    |
+| 0.9591 | 750  | 5.7945        | -      | -                    |
+| 0.9910 | 775  | 5.8077        | -      | -                    |
+| 1.0    | 782  | -             | 5.8024 | 0.0330               |
+| 1.0230 | 800  | 5.6703        | -      | -                    |
+| 1.0550 | 825  | 5.8052        | -      | -                    |
+| 1.0870 | 850  | 5.7936        | -      | -                    |
+| 1.1189 | 875  | 5.7924        | -      | -                    |
+| 1.1509 | 900  | 5.7806        | -      | -                    |
+| 1.1829 | 925  | 5.7835        | -      | -                    |
+| 1.2148 | 950  | 5.7619        | -      | -                    |
+| 1.2468 | 975  | 5.8038        | -      | -                    |
+| 1.2788 | 1000 | 5.779         | -      | -                    |
+| 1.3107 | 1025 | 5.7904        | -      | -                    |
+| 1.3427 | 1050 | 5.7696        | -      | -                    |
+| 1.3747 | 1075 | 5.7919        | -      | -                    |
+| 1.4066 | 1100 | 5.7785        | -      | -                    |
+| 1.4386 | 1125 | 5.7862        | -      | -                    |
+| 1.4706 | 1150 | 5.7703        | -      | -                    |
+| 1.5026 | 1175 | 5.773         | -      | -                    |
+| 1.5345 | 1200 | 5.7627        | -      | -                    |
+| 1.5665 | 1225 | 5.7596        | -      | -                    |
+| 1.5985 | 1250 | 5.7882        | -      | -                    |
+| 1.6304 | 1275 | 5.7828        | -      | -                    |
+| 1.6624 | 1300 | 5.771         | -      | -                    |
+| 1.6944 | 1325 | 5.788         | -      | -                    |
+| 1.7263 | 1350 | 5.7719        | -      | -                    |
+| 1.7583 | 1375 | 5.7846        | -      | -                    |
+| 1.7903 | 1400 | 5.7838        | -      | -                    |
+| 1.8223 | 1425 | 5.7912        | -      | -                    |
+| 1.8542 | 1450 | 5.7686        | -      | -                    |
+| 1.8862 | 1475 | 5.7938        | -      | -                    |
+| 1.9182 | 1500 | 5.7847        | -      | -                    |
+| 1.9501 | 1525 | 5.7952        | -      | -                    |
+| 1.9821 | 1550 | 5.7528        | -      | -                    |
+| 2.0    | 1564 | -             | 5.7933 | 0.0682               |
+| 2.0141 | 1575 | 5.65          | -      | -                    |
+| 2.0460 | 1600 | 5.7537        | -      | -                    |
+| 2.0780 | 1625 | 5.7098        | -      | -                    |
+| 2.1100 | 1650 | 5.7149        | -      | -                    |
+| 2.1419 | 1675 | 5.7585        | -      | -                    |
+| 2.1739 | 1700 | 5.7277        | -      | -                    |
+| 2.2059 | 1725 | 5.7482        | -      | -                    |
+| 2.2379 | 1750 | 5.7115        | -      | -                    |
+| 2.2698 | 1775 | 5.6895        | -      | -                    |
+| 2.3018 | 1800 | 5.7389        | -      | -                    |
+| 2.3338 | 1825 | 5.7161        | -      | -                    |
+| 2.3657 | 1850 | 5.7123        | -      | -                    |
+| 2.3977 | 1875 | 5.7322        | -      | -                    |
+| 2.4297 | 1900 | 5.7421        | -      | -                    |
+| 2.4616 | 1925 | 5.7615        | -      | -                    |
+| 2.4936 | 1950 | 5.7493        | -      | -                    |
+| 2.5256 | 1975 | 5.7298        | -      | -                    |
+| 2.5575 | 2000 | 5.7529        | -      | -                    |
+| 2.5895 | 2025 | 5.7318        | -      | -                    |
+| 2.6215 | 2050 | 5.7036        | -      | -                    |
+| 2.6535 | 2075 | 5.7158        | -      | -                    |
+| 2.6854 | 2100 | 5.7209        | -      | -                    |
+| 2.7174 | 2125 | 5.738         | -      | -                    |
+| 2.7494 | 2150 | 5.7337        | -      | -                    |
+| 2.7813 | 2175 | 5.713         | -      | -                    |
+| 2.8133 | 2200 | 5.7257        | -      | -                    |
+| 2.8453 | 2225 | 5.6958        | -      | -                    |
+| 2.8772 | 2250 | 5.7053        | -      | -                    |
+| 2.9092 | 2275 | 5.7246        | -      | -                    |
+| 2.9412 | 2300 | 5.7291        | -      | -                    |
+| 2.9731 | 2325 | 5.7139        | -      | -                    |
+| 3.0    | 2346 | -             | 5.8510 | 0.0837               |
+| 3.0051 | 2350 | 5.5715        | -      | -                    |
+| 3.0371 | 2375 | 5.6558        | -      | -                    |
+| 3.0691 | 2400 | 5.6441        | -      | -                    |
+| 3.1010 | 2425 | 5.6569        | -      | -                    |
+| 3.1330 | 2450 | 5.669         | -      | -                    |
+| 3.1650 | 2475 | 5.6361        | -      | -                    |
+| 3.1969 | 2500 | 5.6524        | -      | -                    |
+| 3.2289 | 2525 | 5.6773        | -      | -                    |
+| 3.2609 | 2550 | 5.6552        | -      | -                    |
+| 3.2928 | 2575 | 5.6807        | -      | -                    |
+| 3.3248 | 2600 | 5.6638        | -      | -                    |
+| 3.3568 | 2625 | 5.6582        | -      | -                    |
+| 3.3887 | 2650 | 5.658         | -      | -                    |
+| 3.4207 | 2675 | 5.6626        | -      | -                    |
+| 3.4527 | 2700 | 5.6802        | -      | -                    |
+| 3.4847 | 2725 | 5.6377        | -      | -                    |
+| 3.5166 | 2750 | 5.6752        | -      | -                    |
+| 3.5486 | 2775 | 5.6573        | -      | -                    |
+| 3.5806 | 2800 | 5.6963        | -      | -                    |
+| 3.6125 | 2825 | 5.7007        | -      | -                    |
+| 3.6445 | 2850 | 5.6746        | -      | -                    |
+| 3.6765 | 2875 | 5.6312        | -      | -                    |
+| 3.7084 | 2900 | 5.5596        | -      | -                    |
+| 3.7404 | 2925 | 5.7003        | -      | -                    |
+| 3.7724 | 2950 | 5.6739        | -      | -                    |
+| 3.8043 | 2975 | 5.655         | -      | -                    |
+| 3.8363 | 3000 | 5.6787        | -      | -                    |
+| 3.8683 | 3025 | 5.643         | -      | -                    |
+| 3.9003 | 3050 | 5.6412        | -      | -                    |
+| 3.9322 | 3075 | 5.758         | -      | -                    |
+| 3.9642 | 3100 | 5.6769        | -      | -                    |
+| 3.9962 | 3125 | 5.7206        | -      | -                    |
+| 4.0    | 3128 | -             | 5.9125 | 0.0824               |
+
+</details>
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-3128/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "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": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-3128/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

checkpoint-3128/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f15c426e0a8e3ede12b4f3bb95161ed5a4c5a51bcb20ab519919596e330412
+size 470637416

checkpoint-3128/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-3128/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a405964bc0e82a7e1469514b996b71e65018ff76733fce47d9f2788f24fc5ab
+size 940212218

checkpoint-3128/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c53b1054e154626ecf95cb41fffe8108cccf21bc4843652c954100009a36a3
+size 14180

checkpoint-3128/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72a55fbec173081120a6cdf969c078f1cc9ef4f2e0dc0f64b604e716642a81e
+size 1064

checkpoint-3128/sentence_bert_config.json

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

checkpoint-3128/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-3128/tokenizer.json

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

checkpoint-3128/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "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-3128/trainer_state.json

@@ -0,0 +1,989 @@
+{
+  "best_metric": 5.793323516845703,
+  "best_model_checkpoint": "turkish-embedding-model/checkpoint-1564",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 3128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0319693094629156,
+      "grad_norm": 70.72708129882812,
+      "learning_rate": 1.1253196930946293e-06,
+      "loss": 17.17,
+      "step": 25
+    },
+    {
+      "epoch": 0.0639386189258312,
+      "grad_norm": 81.68770599365234,
+      "learning_rate": 2.4040920716112534e-06,
+      "loss": 16.4932,
+      "step": 50
+    },
+    {
+      "epoch": 0.0959079283887468,
+      "grad_norm": 109.91338348388672,
+      "learning_rate": 3.6828644501278778e-06,
+      "loss": 16.5976,
+      "step": 75
+    },
+    {
+      "epoch": 0.1278772378516624,
+      "grad_norm": 73.892578125,
+      "learning_rate": 4.961636828644502e-06,
+      "loss": 15.6991,
+      "step": 100
+    },
+    {
+      "epoch": 0.159846547314578,
+      "grad_norm": 79.35150909423828,
+      "learning_rate": 6.240409207161126e-06,
+      "loss": 14.876,
+      "step": 125
+    },
+    {
+      "epoch": 0.1918158567774936,
+      "grad_norm": 83.0904541015625,
+      "learning_rate": 7.5191815856777495e-06,
+      "loss": 14.4828,
+      "step": 150
+    },
+    {
+      "epoch": 0.2237851662404092,
+      "grad_norm": 76.82855987548828,
+      "learning_rate": 8.797953964194374e-06,
+      "loss": 12.7061,
+      "step": 175
+    },
+    {
+      "epoch": 0.2557544757033248,
+      "grad_norm": 51.30181121826172,
+      "learning_rate": 1.0076726342710998e-05,
+      "loss": 10.8687,
+      "step": 200
+    },
+    {
+      "epoch": 0.2877237851662404,
+      "grad_norm": 18.70808219909668,
+      "learning_rate": 1.1355498721227622e-05,
+      "loss": 8.3797,
+      "step": 225
+    },
+    {
+      "epoch": 0.319693094629156,
+      "grad_norm": 1.3039417266845703,
+      "learning_rate": 1.2634271099744246e-05,
+      "loss": 6.2029,
+      "step": 250
+    },
+    {
+      "epoch": 0.3516624040920716,
+      "grad_norm": 0.2324853092432022,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 5.8228,
+      "step": 275
+    },
+    {
+      "epoch": 0.3836317135549872,
+      "grad_norm": 0.1757364720106125,
+      "learning_rate": 1.5191815856777494e-05,
+      "loss": 5.811,
+      "step": 300
+    },
+    {
+      "epoch": 0.4156010230179028,
+      "grad_norm": 0.1788654774427414,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 5.8079,
+      "step": 325
+    },
+    {
+      "epoch": 0.4475703324808184,
+      "grad_norm": 0.12862567603588104,
+      "learning_rate": 1.7749360613810744e-05,
+      "loss": 5.8077,
+      "step": 350
+    },
+    {
+      "epoch": 0.479539641943734,
+      "grad_norm": 0.14497514069080353,
+      "learning_rate": 1.9028132992327367e-05,
+      "loss": 5.8035,
+      "step": 375
+    },
+    {
+      "epoch": 0.5115089514066496,
+      "grad_norm": 0.1350390762090683,
+      "learning_rate": 1.996589940323956e-05,
+      "loss": 5.8072,
+      "step": 400
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.1435602754354477,
+      "learning_rate": 1.9823813583404378e-05,
+      "loss": 5.8033,
+      "step": 425
+    },
+    {
+      "epoch": 0.5754475703324808,
+      "grad_norm": 0.11389254033565521,
+      "learning_rate": 1.96817277635692e-05,
+      "loss": 5.8086,
+      "step": 450
+    },
+    {
+      "epoch": 0.6074168797953964,
+      "grad_norm": 0.15821650624275208,
+      "learning_rate": 1.9539641943734017e-05,
+      "loss": 5.81,
+      "step": 475
+    },
+    {
+      "epoch": 0.639386189258312,
+      "grad_norm": 0.1179889366030693,
+      "learning_rate": 1.9397556123898838e-05,
+      "loss": 5.7949,
+      "step": 500
+    },
+    {
+      "epoch": 0.6713554987212276,
+      "grad_norm": 0.10912967473268509,
+      "learning_rate": 1.9255470304063656e-05,
+      "loss": 5.8079,
+      "step": 525
+    },
+    {
+      "epoch": 0.7033248081841432,
+      "grad_norm": 0.11702870577573776,
+      "learning_rate": 1.9113384484228477e-05,
+      "loss": 5.8057,
+      "step": 550
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.13132448494434357,
+      "learning_rate": 1.8971298664393295e-05,
+      "loss": 5.8097,
+      "step": 575
+    },
+    {
+      "epoch": 0.7672634271099744,
+      "grad_norm": 0.15833145380020142,
+      "learning_rate": 1.8829212844558116e-05,
+      "loss": 5.7986,
+      "step": 600
+    },
+    {
+      "epoch": 0.7992327365728901,
+      "grad_norm": 0.11651863902807236,
+      "learning_rate": 1.8687127024722937e-05,
+      "loss": 5.8051,
+      "step": 625
+    },
+    {
+      "epoch": 0.8312020460358056,
+      "grad_norm": 0.5393890142440796,
+      "learning_rate": 1.854504120488775e-05,
+      "loss": 5.8041,
+      "step": 650
+    },
+    {
+      "epoch": 0.8631713554987213,
+      "grad_norm": 0.6457561254501343,
+      "learning_rate": 1.8402955385052572e-05,
+      "loss": 5.7907,
+      "step": 675
+    },
+    {
+      "epoch": 0.8951406649616368,
+      "grad_norm": 0.5643135905265808,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 5.7991,
+      "step": 700
+    },
+    {
+      "epoch": 0.9271099744245525,
+      "grad_norm": 3.214787721633911,
+      "learning_rate": 1.811878374538221e-05,
+      "loss": 5.8035,
+      "step": 725
+    },
+    {
+      "epoch": 0.959079283887468,
+      "grad_norm": 2.781162977218628,
+      "learning_rate": 1.7976697925547032e-05,
+      "loss": 5.7945,
+      "step": 750
+    },
+    {
+      "epoch": 0.9910485933503836,
+      "grad_norm": 0.38559335470199585,
+      "learning_rate": 1.783461210571185e-05,
+      "loss": 5.8077,
+      "step": 775
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.8023600578308105,
+      "eval_runtime": 18.0632,
+      "eval_samples_per_second": 276.805,
+      "eval_steps_per_second": 4.374,
+      "eval_tr_ling_pearson_cosine": 0.017751548525136808,
+      "eval_tr_ling_pearson_dot": 0.025703597820631346,
+      "eval_tr_ling_pearson_euclidean": 0.02195284877201089,
+      "eval_tr_ling_pearson_manhattan": 0.02083376479528459,
+      "eval_tr_ling_pearson_max": 0.025703597820631346,
+      "eval_tr_ling_spearman_cosine": 0.027108099994157316,
+      "eval_tr_ling_spearman_dot": 0.03304394653738539,
+      "eval_tr_ling_spearman_euclidean": 0.025485959636772793,
+      "eval_tr_ling_spearman_manhattan": 0.024466610177699702,
+      "eval_tr_ling_spearman_max": 0.03304394653738539,
+      "step": 782
+    },
+    {
+      "epoch": 1.0230179028132993,
+      "grad_norm": 0.3645063638687134,
+      "learning_rate": 1.769252628587667e-05,
+      "loss": 5.6703,
+      "step": 800
+    },
+    {
+      "epoch": 1.054987212276215,
+      "grad_norm": 0.9638137817382812,
+      "learning_rate": 1.7550440466041488e-05,
+      "loss": 5.8052,
+      "step": 825
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 2.114203691482544,
+      "learning_rate": 1.740835464620631e-05,
+      "loss": 5.7936,
+      "step": 850
+    },
+    {
+      "epoch": 1.118925831202046,
+      "grad_norm": 1.8992066383361816,
+      "learning_rate": 1.7266268826371127e-05,
+      "loss": 5.7924,
+      "step": 875
+    },
+    {
+      "epoch": 1.1508951406649617,
+      "grad_norm": 2.8299577236175537,
+      "learning_rate": 1.7124183006535948e-05,
+      "loss": 5.7806,
+      "step": 900
+    },
+    {
+      "epoch": 1.1828644501278773,
+      "grad_norm": 1.956953525543213,
+      "learning_rate": 1.698209718670077e-05,
+      "loss": 5.7835,
+      "step": 925
+    },
+    {
+      "epoch": 1.2148337595907928,
+      "grad_norm": 2.658413887023926,
+      "learning_rate": 1.6840011366865587e-05,
+      "loss": 5.7619,
+      "step": 950
+    },
+    {
+      "epoch": 1.2468030690537084,
+      "grad_norm": 1.2760388851165771,
+      "learning_rate": 1.6697925547030408e-05,
+      "loss": 5.8038,
+      "step": 975
+    },
+    {
+      "epoch": 1.278772378516624,
+      "grad_norm": 1.7434897422790527,
+      "learning_rate": 1.6555839727195226e-05,
+      "loss": 5.779,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3107416879795397,
+      "grad_norm": 1.3532071113586426,
+      "learning_rate": 1.6413753907360047e-05,
+      "loss": 5.7904,
+      "step": 1025
+    },
+    {
+      "epoch": 1.3427109974424551,
+      "grad_norm": 3.7385997772216797,
+      "learning_rate": 1.6271668087524864e-05,
+      "loss": 5.7696,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3746803069053708,
+      "grad_norm": 0.9061102867126465,
+      "learning_rate": 1.6129582267689685e-05,
+      "loss": 5.7919,
+      "step": 1075
+    },
+    {
+      "epoch": 1.4066496163682864,
+      "grad_norm": 2.7104809284210205,
+      "learning_rate": 1.5987496447854503e-05,
+      "loss": 5.7785,
+      "step": 1100
+    },
+    {
+      "epoch": 1.438618925831202,
+      "grad_norm": 1.7147830724716187,
+      "learning_rate": 1.5845410628019324e-05,
+      "loss": 5.7862,
+      "step": 1125
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 2.525214672088623,
+      "learning_rate": 1.5703324808184145e-05,
+      "loss": 5.7703,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5025575447570332,
+      "grad_norm": 1.7794997692108154,
+      "learning_rate": 1.5561238988348963e-05,
+      "loss": 5.773,
+      "step": 1175
+    },
+    {
+      "epoch": 1.5345268542199488,
+      "grad_norm": 4.901644229888916,
+      "learning_rate": 1.5419153168513784e-05,
+      "loss": 5.7627,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5664961636828645,
+      "grad_norm": 3.360812187194824,
+      "learning_rate": 1.52770673486786e-05,
+      "loss": 5.7596,
+      "step": 1225
+    },
+    {
+      "epoch": 1.59846547314578,
+      "grad_norm": 1.2768888473510742,
+      "learning_rate": 1.5134981528843423e-05,
+      "loss": 5.7882,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 2.206226348876953,
+      "learning_rate": 1.4992895709008242e-05,
+      "loss": 5.7828,
+      "step": 1275
+    },
+    {
+      "epoch": 1.6624040920716112,
+      "grad_norm": 1.4602406024932861,
+      "learning_rate": 1.4850809889173061e-05,
+      "loss": 5.771,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6943734015345269,
+      "grad_norm": 1.1597537994384766,
+      "learning_rate": 1.4708724069337881e-05,
+      "loss": 5.788,
+      "step": 1325
+    },
+    {
+      "epoch": 1.7263427109974425,
+      "grad_norm": 3.7494003772735596,
+      "learning_rate": 1.45666382495027e-05,
+      "loss": 5.7719,
+      "step": 1350
+    },
+    {
+      "epoch": 1.758312020460358,
+      "grad_norm": 1.6271498203277588,
+      "learning_rate": 1.442455242966752e-05,
+      "loss": 5.7846,
+      "step": 1375
+    },
+    {
+      "epoch": 1.7902813299232738,
+      "grad_norm": 2.0469117164611816,
+      "learning_rate": 1.4282466609832339e-05,
+      "loss": 5.7838,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8222506393861893,
+      "grad_norm": 2.533921003341675,
+      "learning_rate": 1.4140380789997158e-05,
+      "loss": 5.7912,
+      "step": 1425
+    },
+    {
+      "epoch": 1.854219948849105,
+      "grad_norm": 3.291757583618164,
+      "learning_rate": 1.3998294970161978e-05,
+      "loss": 5.7686,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8861892583120206,
+      "grad_norm": 3.0181350708007812,
+      "learning_rate": 1.3856209150326799e-05,
+      "loss": 5.7938,
+      "step": 1475
+    },
+    {
+      "epoch": 1.918158567774936,
+      "grad_norm": 2.553502321243286,
+      "learning_rate": 1.3714123330491618e-05,
+      "loss": 5.7847,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9501278772378516,
+      "grad_norm": 1.8034719228744507,
+      "learning_rate": 1.3572037510656438e-05,
+      "loss": 5.7952,
+      "step": 1525
+    },
+    {
+      "epoch": 1.9820971867007673,
+      "grad_norm": 3.7138864994049072,
+      "learning_rate": 1.3429951690821257e-05,
+      "loss": 5.7528,
+      "step": 1550
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.793323516845703,
+      "eval_runtime": 18.2796,
+      "eval_samples_per_second": 273.528,
+      "eval_steps_per_second": 4.322,
+      "eval_tr_ling_pearson_cosine": 0.037604255015168134,
+      "eval_tr_ling_pearson_dot": 0.0673696846368413,
+      "eval_tr_ling_pearson_euclidean": 0.03698411306484619,
+      "eval_tr_ling_pearson_manhattan": 0.034740275152181296,
+      "eval_tr_ling_pearson_max": 0.0673696846368413,
+      "eval_tr_ling_spearman_cosine": 0.04804112988506346,
+      "eval_tr_ling_spearman_dot": 0.06818119362900125,
+      "eval_tr_ling_spearman_euclidean": 0.03903062430281842,
+      "eval_tr_ling_spearman_manhattan": 0.03769766156967754,
+      "eval_tr_ling_spearman_max": 0.06818119362900125,
+      "step": 1564
+    },
+    {
+      "epoch": 2.0140664961636827,
+      "grad_norm": 2.8085248470306396,
+      "learning_rate": 1.3287865870986076e-05,
+      "loss": 5.65,
+      "step": 1575
+    },
+    {
+      "epoch": 2.0460358056265986,
+      "grad_norm": 3.3792033195495605,
+      "learning_rate": 1.3145780051150896e-05,
+      "loss": 5.7537,
+      "step": 1600
+    },
+    {
+      "epoch": 2.078005115089514,
+      "grad_norm": 3.44346022605896,
+      "learning_rate": 1.3003694231315715e-05,
+      "loss": 5.7098,
+      "step": 1625
+    },
+    {
+      "epoch": 2.10997442455243,
+      "grad_norm": 5.481964588165283,
+      "learning_rate": 1.2861608411480534e-05,
+      "loss": 5.7149,
+      "step": 1650
+    },
+    {
+      "epoch": 2.1419437340153453,
+      "grad_norm": 2.9816033840179443,
+      "learning_rate": 1.2719522591645354e-05,
+      "loss": 5.7585,
+      "step": 1675
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 3.2157652378082275,
+      "learning_rate": 1.2577436771810175e-05,
+      "loss": 5.7277,
+      "step": 1700
+    },
+    {
+      "epoch": 2.2058823529411766,
+      "grad_norm": 2.92006516456604,
+      "learning_rate": 1.2435350951974994e-05,
+      "loss": 5.7482,
+      "step": 1725
+    },
+    {
+      "epoch": 2.237851662404092,
+      "grad_norm": 3.7664051055908203,
+      "learning_rate": 1.2293265132139814e-05,
+      "loss": 5.7115,
+      "step": 1750
+    },
+    {
+      "epoch": 2.2698209718670075,
+      "grad_norm": 5.3445353507995605,
+      "learning_rate": 1.2151179312304633e-05,
+      "loss": 5.6895,
+      "step": 1775
+    },
+    {
+      "epoch": 2.3017902813299234,
+      "grad_norm": 4.100110054016113,
+      "learning_rate": 1.2009093492469452e-05,
+      "loss": 5.7389,
+      "step": 1800
+    },
+    {
+      "epoch": 2.333759590792839,
+      "grad_norm": 5.986413478851318,
+      "learning_rate": 1.1867007672634272e-05,
+      "loss": 5.7161,
+      "step": 1825
+    },
+    {
+      "epoch": 2.3657289002557547,
+      "grad_norm": 4.717130661010742,
+      "learning_rate": 1.1724921852799091e-05,
+      "loss": 5.7123,
+      "step": 1850
+    },
+    {
+      "epoch": 2.39769820971867,
+      "grad_norm": 2.833897352218628,
+      "learning_rate": 1.158283603296391e-05,
+      "loss": 5.7322,
+      "step": 1875
+    },
+    {
+      "epoch": 2.4296675191815855,
+      "grad_norm": 3.9461288452148438,
+      "learning_rate": 1.144075021312873e-05,
+      "loss": 5.7421,
+      "step": 1900
+    },
+    {
+      "epoch": 2.4616368286445014,
+      "grad_norm": 5.360823154449463,
+      "learning_rate": 1.1298664393293551e-05,
+      "loss": 5.7615,
+      "step": 1925
+    },
+    {
+      "epoch": 2.493606138107417,
+      "grad_norm": 3.290187120437622,
+      "learning_rate": 1.115657857345837e-05,
+      "loss": 5.7493,
+      "step": 1950
+    },
+    {
+      "epoch": 2.5255754475703327,
+      "grad_norm": 2.8723881244659424,
+      "learning_rate": 1.101449275362319e-05,
+      "loss": 5.7298,
+      "step": 1975
+    },
+    {
+      "epoch": 2.557544757033248,
+      "grad_norm": 12.763352394104004,
+      "learning_rate": 1.0872406933788009e-05,
+      "loss": 5.7529,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5895140664961636,
+      "grad_norm": 3.423097610473633,
+      "learning_rate": 1.0730321113952828e-05,
+      "loss": 5.7318,
+      "step": 2025
+    },
+    {
+      "epoch": 2.6214833759590794,
+      "grad_norm": 3.546499252319336,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 5.7036,
+      "step": 2050
+    },
+    {
+      "epoch": 2.653452685421995,
+      "grad_norm": 4.731326103210449,
+      "learning_rate": 1.0446149474282467e-05,
+      "loss": 5.7158,
+      "step": 2075
+    },
+    {
+      "epoch": 2.6854219948849103,
+      "grad_norm": 5.279483318328857,
+      "learning_rate": 1.0304063654447287e-05,
+      "loss": 5.7209,
+      "step": 2100
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 5.814947605133057,
+      "learning_rate": 1.0161977834612106e-05,
+      "loss": 5.738,
+      "step": 2125
+    },
+    {
+      "epoch": 2.7493606138107416,
+      "grad_norm": 4.115816116333008,
+      "learning_rate": 1.0019892014776927e-05,
+      "loss": 5.7337,
+      "step": 2150
+    },
+    {
+      "epoch": 2.781329923273657,
+      "grad_norm": 4.176394462585449,
+      "learning_rate": 9.877806194941746e-06,
+      "loss": 5.713,
+      "step": 2175
+    },
+    {
+      "epoch": 2.813299232736573,
+      "grad_norm": 3.36919903755188,
+      "learning_rate": 9.735720375106566e-06,
+      "loss": 5.7257,
+      "step": 2200
+    },
+    {
+      "epoch": 2.8452685421994883,
+      "grad_norm": 4.4527482986450195,
+      "learning_rate": 9.593634555271385e-06,
+      "loss": 5.6958,
+      "step": 2225
+    },
+    {
+      "epoch": 2.877237851662404,
+      "grad_norm": 7.66256856918335,
+      "learning_rate": 9.451548735436205e-06,
+      "loss": 5.7053,
+      "step": 2250
+    },
+    {
+      "epoch": 2.9092071611253196,
+      "grad_norm": 11.90414810180664,
+      "learning_rate": 9.309462915601024e-06,
+      "loss": 5.7246,
+      "step": 2275
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 3.27648663520813,
+      "learning_rate": 9.167377095765843e-06,
+      "loss": 5.7291,
+      "step": 2300
+    },
+    {
+      "epoch": 2.973145780051151,
+      "grad_norm": 5.769582271575928,
+      "learning_rate": 9.025291275930663e-06,
+      "loss": 5.7139,
+      "step": 2325
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.851009845733643,
+      "eval_runtime": 18.263,
+      "eval_samples_per_second": 273.777,
+      "eval_steps_per_second": 4.326,
+      "eval_tr_ling_pearson_cosine": 0.06129823646086187,
+      "eval_tr_ling_pearson_dot": 0.08667935948713909,
+      "eval_tr_ling_pearson_euclidean": 0.050963674624173616,
+      "eval_tr_ling_pearson_manhattan": 0.049471366228539336,
+      "eval_tr_ling_pearson_max": 0.08667935948713909,
+      "eval_tr_ling_spearman_cosine": 0.06262320788887717,
+      "eval_tr_ling_spearman_dot": 0.0836754651265069,
+      "eval_tr_ling_spearman_euclidean": 0.04874454654419082,
+      "eval_tr_ling_spearman_manhattan": 0.04780108900980343,
+      "eval_tr_ling_spearman_max": 0.0836754651265069,
+      "step": 2346
+    },
+    {
+      "epoch": 3.0051150895140664,
+      "grad_norm": 6.343133449554443,
+      "learning_rate": 8.883205456095482e-06,
+      "loss": 5.5715,
+      "step": 2350
+    },
+    {
+      "epoch": 3.0370843989769822,
+      "grad_norm": 7.939487457275391,
+      "learning_rate": 8.741119636260303e-06,
+      "loss": 5.6558,
+      "step": 2375
+    },
+    {
+      "epoch": 3.0690537084398977,
+      "grad_norm": 3.734879493713379,
+      "learning_rate": 8.599033816425122e-06,
+      "loss": 5.6441,
+      "step": 2400
+    },
+    {
+      "epoch": 3.101023017902813,
+      "grad_norm": 6.058401584625244,
+      "learning_rate": 8.456947996589942e-06,
+      "loss": 5.6569,
+      "step": 2425
+    },
+    {
+      "epoch": 3.132992327365729,
+      "grad_norm": 4.311662673950195,
+      "learning_rate": 8.314862176754761e-06,
+      "loss": 5.669,
+      "step": 2450
+    },
+    {
+      "epoch": 3.1649616368286444,
+      "grad_norm": 8.782428741455078,
+      "learning_rate": 8.17277635691958e-06,
+      "loss": 5.6361,
+      "step": 2475
+    },
+    {
+      "epoch": 3.1969309462915603,
+      "grad_norm": 7.427972793579102,
+      "learning_rate": 8.0306905370844e-06,
+      "loss": 5.6524,
+      "step": 2500
+    },
+    {
+      "epoch": 3.2289002557544757,
+      "grad_norm": 5.069025993347168,
+      "learning_rate": 7.88860471724922e-06,
+      "loss": 5.6773,
+      "step": 2525
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 8.149388313293457,
+      "learning_rate": 7.746518897414039e-06,
+      "loss": 5.6552,
+      "step": 2550
+    },
+    {
+      "epoch": 3.292838874680307,
+      "grad_norm": 6.453441619873047,
+      "learning_rate": 7.604433077578858e-06,
+      "loss": 5.6807,
+      "step": 2575
+    },
+    {
+      "epoch": 3.3248081841432224,
+      "grad_norm": 6.5807719230651855,
+      "learning_rate": 7.4623472577436775e-06,
+      "loss": 5.6638,
+      "step": 2600
+    },
+    {
+      "epoch": 3.3567774936061383,
+      "grad_norm": 10.392335891723633,
+      "learning_rate": 7.320261437908497e-06,
+      "loss": 5.6582,
+      "step": 2625
+    },
+    {
+      "epoch": 3.3887468030690537,
+      "grad_norm": 9.251813888549805,
+      "learning_rate": 7.178175618073316e-06,
+      "loss": 5.658,
+      "step": 2650
+    },
+    {
+      "epoch": 3.420716112531969,
+      "grad_norm": 5.527411460876465,
+      "learning_rate": 7.036089798238136e-06,
+      "loss": 5.6626,
+      "step": 2675
+    },
+    {
+      "epoch": 3.452685421994885,
+      "grad_norm": 5.650461673736572,
+      "learning_rate": 6.894003978402956e-06,
+      "loss": 5.6802,
+      "step": 2700
+    },
+    {
+      "epoch": 3.4846547314578005,
+      "grad_norm": 7.156338691711426,
+      "learning_rate": 6.751918158567775e-06,
+      "loss": 5.6377,
+      "step": 2725
+    },
+    {
+      "epoch": 3.516624040920716,
+      "grad_norm": 6.843425750732422,
+      "learning_rate": 6.6098323387325946e-06,
+      "loss": 5.6752,
+      "step": 2750
+    },
+    {
+      "epoch": 3.5485933503836318,
+      "grad_norm": 14.204697608947754,
+      "learning_rate": 6.467746518897414e-06,
+      "loss": 5.6573,
+      "step": 2775
+    },
+    {
+      "epoch": 3.580562659846547,
+      "grad_norm": 3.9053664207458496,
+      "learning_rate": 6.325660699062234e-06,
+      "loss": 5.6963,
+      "step": 2800
+    },
+    {
+      "epoch": 3.612531969309463,
+      "grad_norm": 13.336016654968262,
+      "learning_rate": 6.1835748792270535e-06,
+      "loss": 5.7007,
+      "step": 2825
+    },
+    {
+      "epoch": 3.6445012787723785,
+      "grad_norm": 5.112432956695557,
+      "learning_rate": 6.041489059391873e-06,
+      "loss": 5.6746,
+      "step": 2850
+    },
+    {
+      "epoch": 3.6764705882352944,
+      "grad_norm": 6.077632427215576,
+      "learning_rate": 5.899403239556692e-06,
+      "loss": 5.6312,
+      "step": 2875
+    },
+    {
+      "epoch": 3.70843989769821,
+      "grad_norm": 10.304828643798828,
+      "learning_rate": 5.757317419721512e-06,
+      "loss": 5.5596,
+      "step": 2900
+    },
+    {
+      "epoch": 3.7404092071611252,
+      "grad_norm": 9.45308780670166,
+      "learning_rate": 5.615231599886332e-06,
+      "loss": 5.7003,
+      "step": 2925
+    },
+    {
+      "epoch": 3.772378516624041,
+      "grad_norm": 6.124211311340332,
+      "learning_rate": 5.473145780051151e-06,
+      "loss": 5.6739,
+      "step": 2950
+    },
+    {
+      "epoch": 3.8043478260869565,
+      "grad_norm": 8.547770500183105,
+      "learning_rate": 5.331059960215971e-06,
+      "loss": 5.655,
+      "step": 2975
+    },
+    {
+      "epoch": 3.836317135549872,
+      "grad_norm": 6.203834533691406,
+      "learning_rate": 5.18897414038079e-06,
+      "loss": 5.6787,
+      "step": 3000
+    },
+    {
+      "epoch": 3.868286445012788,
+      "grad_norm": 4.0565643310546875,
+      "learning_rate": 5.04688832054561e-06,
+      "loss": 5.643,
+      "step": 3025
+    },
+    {
+      "epoch": 3.9002557544757033,
+      "grad_norm": 9.590073585510254,
+      "learning_rate": 4.90480250071043e-06,
+      "loss": 5.6412,
+      "step": 3050
+    },
+    {
+      "epoch": 3.9322250639386187,
+      "grad_norm": 9.556587219238281,
+      "learning_rate": 4.762716680875249e-06,
+      "loss": 5.758,
+      "step": 3075
+    },
+    {
+      "epoch": 3.9641943734015346,
+      "grad_norm": 5.743387222290039,
+      "learning_rate": 4.620630861040068e-06,
+      "loss": 5.6769,
+      "step": 3100
+    },
+    {
+      "epoch": 3.99616368286445,
+      "grad_norm": 7.73360013961792,
+      "learning_rate": 4.478545041204888e-06,
+      "loss": 5.7206,
+      "step": 3125
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.9124884605407715,
+      "eval_runtime": 18.3869,
+      "eval_samples_per_second": 271.933,
+      "eval_steps_per_second": 4.297,
+      "eval_tr_ling_pearson_cosine": 0.058743115070889876,
+      "eval_tr_ling_pearson_dot": 0.08477622619519222,
+      "eval_tr_ling_pearson_euclidean": 0.04709170917685587,
+      "eval_tr_ling_pearson_manhattan": 0.04582145815494953,
+      "eval_tr_ling_pearson_max": 0.08477622619519222,
+      "eval_tr_ling_spearman_cosine": 0.059526247945378225,
+      "eval_tr_ling_spearman_dot": 0.08243745050110735,
+      "eval_tr_ling_spearman_euclidean": 0.04407504959649961,
+      "eval_tr_ling_spearman_manhattan": 0.04331287037397966,
+      "eval_tr_ling_spearman_max": 0.08243745050110735,
+      "step": 3128
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3128/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44b0bec8869c08bdad0d597184d7a293a0e13eb770d6f4384456cbbe4fe5aa4
+size 5368

checkpoint-3128/unigram.json

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

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "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": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c62de6c84b1b2f1dd37271b7c328633d87e20fa33799d8acc6dd17e7276782d
+size 470637416

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"
+  }
+]

runs/May29_18-52-15_338a77628651/events.out.tfevents.1717008737.338a77628651.19835.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5774c9706e36237c87022fe6c74d36b8271a65724734def30bdcacf5b57d7733
-size 88
+oid sha256:a1632c2aa6d9fe6916a4273d267eaecda68935aa9551a1745cdf8635a0fda945
+size 11052

sentence_bert_config.json

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

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
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f2c16c1654f713df68c72180bda7d273f3cdf401edb9ec64dfe4946a012590
+size 5368

training_params.json

@@ -0,0 +1,33 @@
+{
+    "data_path": "ucsahin/TR-Extractive-QA-5K",
+    "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+    "lr": 2e-05,
+    "epochs": 5,
+    "max_seq_length": 128,
+    "batch_size": 32,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": null,
+    "logging_steps": -1,
+    "project_name": "turkish-embedding-model",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "acayir64",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01,
+    "trainer": "qa",
+    "sentence1_column": "question",
+    "sentence2_column": "answer",
+    "sentence3_column": "sentence3",
+    "target_column": "target"
+}

unigram.json

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