rjurney commited on Jun 3

Commit

2187172

unverified ·

1 Parent(s): ccc1d6b

Removing old model values

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

1_Pooling/config.json +0 -10
checkpoint-1000/1_Pooling/config.json +0 -10
checkpoint-1000/README.md +0 -466
checkpoint-1000/config.json +0 -25
checkpoint-1000/config_sentence_transformers.json +0 -10
checkpoint-1000/model.safetensors +0 -3
checkpoint-1000/modules.json +0 -14
checkpoint-1000/optimizer.pt +0 -3
checkpoint-1000/rng_state.pth +0 -3
checkpoint-1000/scheduler.pt +0 -3
checkpoint-1000/sentence_bert_config.json +0 -4
checkpoint-1000/special_tokens_map.json +0 -51
checkpoint-1000/tokenizer.json +0 -3
checkpoint-1000/tokenizer_config.json +0 -65
checkpoint-1000/trainer_state.json +0 -217
checkpoint-1000/training_args.bin +0 -3
checkpoint-1000/unigram.json +0 -3
checkpoint-1100/1_Pooling/config.json +0 -10
checkpoint-1100/README.md +0 -467
checkpoint-1100/config.json +0 -25
checkpoint-1100/config_sentence_transformers.json +0 -10
checkpoint-1100/model.safetensors +0 -3
checkpoint-1100/modules.json +0 -14
checkpoint-1100/optimizer.pt +0 -3
checkpoint-1100/rng_state.pth +0 -3
checkpoint-1100/scheduler.pt +0 -3
checkpoint-1100/sentence_bert_config.json +0 -4
checkpoint-1100/special_tokens_map.json +0 -51
checkpoint-1100/tokenizer.json +0 -3
checkpoint-1100/tokenizer_config.json +0 -65
checkpoint-1100/trainer_state.json +0 -233
checkpoint-1100/training_args.bin +0 -3
checkpoint-1100/unigram.json +0 -3
checkpoint-1200/1_Pooling/config.json +0 -10
checkpoint-1200/README.md +0 -468
checkpoint-1200/config.json +0 -25
checkpoint-1200/config_sentence_transformers.json +0 -10
checkpoint-1200/model.safetensors +0 -3
checkpoint-1200/modules.json +0 -14
checkpoint-1200/optimizer.pt +0 -3
checkpoint-1200/rng_state.pth +0 -3
checkpoint-1200/scheduler.pt +0 -3
checkpoint-1200/sentence_bert_config.json +0 -4
checkpoint-1200/special_tokens_map.json +0 -51
checkpoint-1200/tokenizer.json +0 -3
checkpoint-1200/tokenizer_config.json +0 -65
checkpoint-1200/trainer_state.json +0 -249
checkpoint-1200/training_args.bin +0 -3
checkpoint-1200/unigram.json +0 -3
checkpoint-1300/1_Pooling/config.json +0 -10

1_Pooling/config.json DELETED Viewed

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

checkpoint-1000/1_Pooling/config.json DELETED Viewed

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

checkpoint-1000/README.md DELETED Viewed

@@ -1,466 +0,0 @@
----
-language:
-- en
-license: apache-2.0
-tags:
-- sentence-transformers
-- sentence-similarity
-- feature-extraction
-- generated_from_trainer
-- dataset_size:2130621
-- loss:ContrastiveLoss
-base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-widget:
-- source_sentence: Kim Chol-sam
-  sentences:
-  - Stankevich Sergey Nikolayevich
-  - Kim Chin-So’k
-  - Julen Lopetegui Agote
-- source_sentence: دينا بنت عبد الحميد
-  sentences:
-  - Alexia van Amsberg
-  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
-  - Dina bint Abdul-Hamíd
-- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
-  sentences:
-  - Karpov Anatoly Evgenyevich
-  - GNPower Mariveles Coal Plant [former]
-  - Muhammed bin Nayef bin Abdul Aziz Al Saud
-- source_sentence: Edward Gnehm
-  sentences:
-  - Шауэрте, Хартмут
-  - Ханзада Филипп, Эдинбург герцогі
-  - AFX
-- source_sentence: Schori i Lidingö
-  sentences:
-  - Yordan Canev
-  - ကားပေါ့ အန်နာတိုလီ
-  - BYSTROV, Mikhail Ivanovich
-pipeline_tag: sentence-similarity
-library_name: sentence-transformers
-metrics:
-- cosine_accuracy
-- cosine_accuracy_threshold
-- cosine_f1
-- cosine_f1_threshold
-- cosine_precision
-- cosine_recall
-- cosine_ap
-- cosine_mcc
-model-index:
-- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-  results:
-  - task:
-      type: binary-classification
-      name: Binary Classification
-    dataset:
-      name: sentence transformers paraphrase multilingual MiniLM L12 v2
-      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
-    metrics:
-    - type: cosine_accuracy
-      value: 0.9817931272716349
-      name: Cosine Accuracy
-    - type: cosine_accuracy_threshold
-      value: 0.7197962999343872
-      name: Cosine Accuracy Threshold
-    - type: cosine_f1
-      value: 0.9722373310278887
-      name: Cosine F1
-    - type: cosine_f1_threshold
-      value: 0.7091608047485352
-      name: Cosine F1 Threshold
-    - type: cosine_precision
-      value: 0.9675121928984912
-      name: Cosine Precision
-    - type: cosine_recall
-      value: 0.9770088489465266
-      name: Cosine Recall
-    - type: cosine_ap
-      value: 0.9944127523785896
-      name: Cosine Ap
-    - type: cosine_mcc
-      value: 0.9587183163648803
-      name: Cosine Mcc
----
-# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
-## Model Details
-### Model Description
-- **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
-- **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-- **Language:** en
-- **License:** apache-2.0
-### 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 = [
-    'Schori i Lidingö',
-    'Yordan Canev',
-    'ကားပေါ့ အန်နာတိုလီ',
-]
-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
-#### Binary Classification
-* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
-* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
-| Metric                    | Value      |
-|:--------------------------|:-----------|
-| cosine_accuracy           | 0.9818     |
-| cosine_accuracy_threshold | 0.7198     |
-| cosine_f1                 | 0.9722     |
-| cosine_f1_threshold       | 0.7092     |
-| cosine_precision          | 0.9675     |
-| cosine_recall             | 0.977      |
-| **cosine_ap**             | **0.9944** |
-| cosine_mcc                | 0.9587     |
-<!--
-## Bias, Risks and Limitations
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-<!--
-### Recommendations
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-## Training Details
-### Training Dataset
-#### Unnamed Dataset
-* Size: 2,130,621 training samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                         | sentence2                           | label            |
-  |:----------------------------------|:------------------------------------|:-----------------|
-  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
-  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
-  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Evaluation Dataset
-#### Unnamed Dataset
-* Size: 2,663,276 evaluation samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                             | sentence2                              | label            |
-  |:--------------------------------------|:---------------------------------------|:-----------------|
-  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
-  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
-  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Training Hyperparameters
-#### Non-Default Hyperparameters
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `gradient_accumulation_steps`: 4
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `num_train_epochs`: 8
-- `warmup_ratio`: 0.1
-- `fp16_opt_level`: O0
-- `load_best_model_at_end`: True
-- `optim`: adafactor
-#### All Hyperparameters
-<details><summary>Click to expand</summary>
-- `overwrite_output_dir`: False
-- `do_predict`: False
-- `eval_strategy`: steps
-- `prediction_loss_only`: True
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `per_gpu_train_batch_size`: None
-- `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 4
-- `eval_accumulation_steps`: None
-- `torch_empty_cache_steps`: None
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `adam_beta1`: 0.9
-- `adam_beta2`: 0.999
-- `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1.0
-- `num_train_epochs`: 8
-- `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`: False
-- `fp16_opt_level`: O0
-- `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}
-- `tp_size`: 0
-- `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`: adafactor
-- `optim_args`: None
-- `adafactor`: False
-- `group_by_length`: False
-- `length_column_name`: length
-- `ddp_find_unused_parameters`: None
-- `ddp_bucket_cap_mb`: None
-- `ddp_broadcast_buffers`: False
-- `dataloader_pin_memory`: True
-- `dataloader_persistent_workers`: False
-- `skip_memory_metrics`: True
-- `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
-- `resume_from_checkpoint`: None
-- `hub_model_id`: None
-- `hub_strategy`: every_save
-- `hub_private_repo`: None
-- `hub_always_push`: False
-- `gradient_checkpointing`: False
-- `gradient_checkpointing_kwargs`: None
-- `include_inputs_for_metrics`: False
-- `include_for_metrics`: []
-- `eval_do_concat_batches`: True
-- `fp16_backend`: auto
-- `push_to_hub_model_id`: None
-- `push_to_hub_organization`: None
-- `mp_parameters`:
-- `auto_find_batch_size`: False
-- `full_determinism`: False
-- `torchdynamo`: None
-- `ray_scope`: last
-- `ddp_timeout`: 1800
-- `torch_compile`: False
-- `torch_compile_backend`: None
-- `torch_compile_mode`: None
-- `include_tokens_per_second`: False
-- `include_num_input_tokens_seen`: False
-- `neftune_noise_alpha`: None
-- `optim_target_modules`: None
-- `batch_eval_metrics`: False
-- `eval_on_start`: False
-- `use_liger_kernel`: False
-- `eval_use_gather_object`: False
-- `average_tokens_across_devices`: False
-- `prompts`: None
-- `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
-</details>
-### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
-|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
-| -1     | -1   | -             | -               | 0.7140                                                                |
-| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
-| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
-| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
-| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
-| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
-| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
-| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
-| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
-| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
-| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
-### Framework Versions
-- Python: 3.12.9
-- Sentence Transformers: 3.4.1
-- Transformers: 4.51.3
-- PyTorch: 2.7.0+cu126
-- Accelerate: 1.6.0
-- Datasets: 3.6.0
-- Tokenizers: 0.21.1
-## Citation
-### BibTeX
-#### Sentence Transformers
-```bibtex
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "https://arxiv.org/abs/1908.10084",
-}
-```
-#### ContrastiveLoss
-```bibtex
-@inproceedings{hadsell2006dimensionality,
-    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
-    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
-    title={Dimensionality Reduction by Learning an Invariant Mapping},
-    year={2006},
-    volume={2},
-    number={},
-    pages={1735-1742},
-    doi={10.1109/CVPR.2006.100}
-}
-```
-<!--
-## Glossary
-*Clearly define terms in order to be accessible across audiences.*
--->
-<!--
-## Model Card Authors
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
-<!--
-## Model Card Contact
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->

checkpoint-1000/config.json DELETED Viewed

@@ -1,25 +0,0 @@
-{
-  "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": "4.51.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 250037
-}

checkpoint-1000/config_sentence_transformers.json DELETED Viewed

@@ -1,10 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "3.4.1",
-    "transformers": "4.51.3",
-    "pytorch": "2.7.0+cu126"
-  },
-  "prompts": {},
-  "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
-}

checkpoint-1000/model.safetensors DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:53cdf706594f9c2e35f539f5023cae863f9d5c0e8588348281d86e7ac79b4662
-size 470637416

checkpoint-1000/modules.json DELETED Viewed

@@ -1,14 +0,0 @@
-[
-  {
-    "idx": 0,
-    "name": "0",
-    "path": "",
-    "type": "sentence_transformers.models.Transformer"
-  },
-  {
-    "idx": 1,
-    "name": "1",
-    "path": "1_Pooling",
-    "type": "sentence_transformers.models.Pooling"
-  }
-]

checkpoint-1000/optimizer.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c108fa814d36d19a8e9c702a9800909a0bdbcc7bbc32071418d14ec158efbaf5
-size 1715019

checkpoint-1000/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:31530f34a96cd557f736a4c9e2dbdab66da89f3ee40e3c858c87c688d4a1b9a1
-size 14645

checkpoint-1000/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8985e0cd69062d78f38bea6c82894c697cf2eff7e9a24bf93fa0da194c1b5e7
-size 1465

checkpoint-1000/sentence_bert_config.json DELETED Viewed

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

checkpoint-1000/special_tokens_map.json DELETED Viewed

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

checkpoint-1000/tokenizer.json DELETED Viewed

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

checkpoint-1000/tokenizer_config.json DELETED Viewed

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

checkpoint-1000/trainer_state.json DELETED Viewed

@@ -1,217 +0,0 @@
-{
-  "best_global_step": 1000,
-  "best_metric": 0.002240537665784359,
-  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1000",
-  "epoch": 1.8784608165180665,
-  "eval_steps": 100,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.18770530267480057,
-      "eval_loss": 0.012530049309134483,
-      "eval_runtime": 812.6802,
-      "eval_samples_per_second": 3277.151,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
-      "eval_steps_per_second": 3.278,
-      "step": 100
-    },
-    {
-      "epoch": 0.37541060534960113,
-      "eval_loss": 0.009013425558805466,
-      "eval_runtime": 792.9843,
-      "eval_samples_per_second": 3358.548,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
-      "eval_steps_per_second": 3.359,
-      "step": 200
-    },
-    {
-      "epoch": 0.5631159080244017,
-      "eval_loss": 0.006819029338657856,
-      "eval_runtime": 809.9704,
-      "eval_samples_per_second": 3288.115,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
-      "eval_steps_per_second": 3.289,
-      "step": 300
-    },
-    {
-      "epoch": 0.7508212106992023,
-      "eval_loss": 0.005150709766894579,
-      "eval_runtime": 797.9199,
-      "eval_samples_per_second": 3337.773,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
-      "eval_steps_per_second": 3.339,
-      "step": 400
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "grad_norm": 0.17396493256092072,
-      "learning_rate": 2.9428198433420364e-05,
-      "loss": 0.0409,
-      "step": 500
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "eval_loss": 0.003973629325628281,
-      "eval_runtime": 809.4532,
-      "eval_samples_per_second": 3290.216,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
-      "eval_steps_per_second": 3.291,
-      "step": 500
-    },
-    {
-      "epoch": 1.1276396058188645,
-      "eval_loss": 0.0032712339889258146,
-      "eval_runtime": 793.7573,
-      "eval_samples_per_second": 3355.277,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
-      "eval_steps_per_second": 3.356,
-      "step": 600
-    },
-    {
-      "epoch": 1.3153449084936648,
-      "eval_loss": 0.0028166945558041334,
-      "eval_runtime": 815.1943,
-      "eval_samples_per_second": 3267.044,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
-      "eval_steps_per_second": 3.268,
-      "step": 700
-    },
-    {
-      "epoch": 1.5030502111684654,
-      "eval_loss": 0.0026242006570100784,
-      "eval_runtime": 805.7115,
-      "eval_samples_per_second": 3305.496,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
-      "eval_steps_per_second": 3.306,
-      "step": 800
-    },
-    {
-      "epoch": 1.690755513843266,
-      "eval_loss": 0.002248650649562478,
-      "eval_runtime": 818.5338,
-      "eval_samples_per_second": 3253.715,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
-      "eval_steps_per_second": 3.255,
-      "step": 900
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "grad_norm": 0.07541557401418686,
-      "learning_rate": 2.5511749347258486e-05,
-      "loss": 0.0131,
-      "step": 1000
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "eval_loss": 0.002240537665784359,
-      "eval_runtime": 803.6286,
-      "eval_samples_per_second": 3314.063,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
-      "eval_steps_per_second": 3.315,
-      "step": 1000
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 4256,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 1,
-        "early_stopping_threshold": 0.0
-      },
-      "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": 1000,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1000/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
-size 6033

checkpoint-1000/unigram.json DELETED Viewed

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

checkpoint-1100/1_Pooling/config.json DELETED Viewed

@@ -1,10 +0,0 @@
-{
-  "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-1100/README.md DELETED Viewed

@@ -1,467 +0,0 @@
----
-language:
-- en
-license: apache-2.0
-tags:
-- sentence-transformers
-- sentence-similarity
-- feature-extraction
-- generated_from_trainer
-- dataset_size:2130621
-- loss:ContrastiveLoss
-base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-widget:
-- source_sentence: Kim Chol-sam
-  sentences:
-  - Stankevich Sergey Nikolayevich
-  - Kim Chin-So’k
-  - Julen Lopetegui Agote
-- source_sentence: دينا بنت عبد الحميد
-  sentences:
-  - Alexia van Amsberg
-  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
-  - Dina bint Abdul-Hamíd
-- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
-  sentences:
-  - Karpov Anatoly Evgenyevich
-  - GNPower Mariveles Coal Plant [former]
-  - Muhammed bin Nayef bin Abdul Aziz Al Saud
-- source_sentence: Edward Gnehm
-  sentences:
-  - Шауэрте, Хартмут
-  - Ханзада Филипп, Эдинбург герцогі
-  - AFX
-- source_sentence: Schori i Lidingö
-  sentences:
-  - Yordan Canev
-  - ကားပေါ့ အန်နာတိုလီ
-  - BYSTROV, Mikhail Ivanovich
-pipeline_tag: sentence-similarity
-library_name: sentence-transformers
-metrics:
-- cosine_accuracy
-- cosine_accuracy_threshold
-- cosine_f1
-- cosine_f1_threshold
-- cosine_precision
-- cosine_recall
-- cosine_ap
-- cosine_mcc
-model-index:
-- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-  results:
-  - task:
-      type: binary-classification
-      name: Binary Classification
-    dataset:
-      name: sentence transformers paraphrase multilingual MiniLM L12 v2
-      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
-    metrics:
-    - type: cosine_accuracy
-      value: 0.9828594815415578
-      name: Cosine Accuracy
-    - type: cosine_accuracy_threshold
-      value: 0.7552986741065979
-      name: Cosine Accuracy Threshold
-    - type: cosine_f1
-      value: 0.973889221813201
-      name: Cosine F1
-    - type: cosine_f1_threshold
-      value: 0.7401974201202393
-      name: Cosine F1 Threshold
-    - type: cosine_precision
-      value: 0.9661201195760486
-      name: Cosine Precision
-    - type: cosine_recall
-      value: 0.9817842882294052
-      name: Cosine Recall
-    - type: cosine_ap
-      value: 0.9950493119597241
-      name: Cosine Ap
-    - type: cosine_mcc
-      value: 0.9611601510291333
-      name: Cosine Mcc
----
-# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
-## Model Details
-### Model Description
-- **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
-- **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-- **Language:** en
-- **License:** apache-2.0
-### 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 = [
-    'Schori i Lidingö',
-    'Yordan Canev',
-    'ကားပေါ့ အန်နာတိုလီ',
-]
-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
-#### Binary Classification
-* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
-* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
-| Metric                    | Value     |
-|:--------------------------|:----------|
-| cosine_accuracy           | 0.9829    |
-| cosine_accuracy_threshold | 0.7553    |
-| cosine_f1                 | 0.9739    |
-| cosine_f1_threshold       | 0.7402    |
-| cosine_precision          | 0.9661    |
-| cosine_recall             | 0.9818    |
-| **cosine_ap**             | **0.995** |
-| cosine_mcc                | 0.9612    |
-<!--
-## Bias, Risks and Limitations
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-<!--
-### Recommendations
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-## Training Details
-### Training Dataset
-#### Unnamed Dataset
-* Size: 2,130,621 training samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                         | sentence2                           | label            |
-  |:----------------------------------|:------------------------------------|:-----------------|
-  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
-  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
-  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Evaluation Dataset
-#### Unnamed Dataset
-* Size: 2,663,276 evaluation samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                             | sentence2                              | label            |
-  |:--------------------------------------|:---------------------------------------|:-----------------|
-  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
-  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
-  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Training Hyperparameters
-#### Non-Default Hyperparameters
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `gradient_accumulation_steps`: 4
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `num_train_epochs`: 8
-- `warmup_ratio`: 0.1
-- `fp16_opt_level`: O0
-- `load_best_model_at_end`: True
-- `optim`: adafactor
-#### All Hyperparameters
-<details><summary>Click to expand</summary>
-- `overwrite_output_dir`: False
-- `do_predict`: False
-- `eval_strategy`: steps
-- `prediction_loss_only`: True
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `per_gpu_train_batch_size`: None
-- `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 4
-- `eval_accumulation_steps`: None
-- `torch_empty_cache_steps`: None
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `adam_beta1`: 0.9
-- `adam_beta2`: 0.999
-- `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1.0
-- `num_train_epochs`: 8
-- `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`: False
-- `fp16_opt_level`: O0
-- `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}
-- `tp_size`: 0
-- `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`: adafactor
-- `optim_args`: None
-- `adafactor`: False
-- `group_by_length`: False
-- `length_column_name`: length
-- `ddp_find_unused_parameters`: None
-- `ddp_bucket_cap_mb`: None
-- `ddp_broadcast_buffers`: False
-- `dataloader_pin_memory`: True
-- `dataloader_persistent_workers`: False
-- `skip_memory_metrics`: True
-- `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
-- `resume_from_checkpoint`: None
-- `hub_model_id`: None
-- `hub_strategy`: every_save
-- `hub_private_repo`: None
-- `hub_always_push`: False
-- `gradient_checkpointing`: False
-- `gradient_checkpointing_kwargs`: None
-- `include_inputs_for_metrics`: False
-- `include_for_metrics`: []
-- `eval_do_concat_batches`: True
-- `fp16_backend`: auto
-- `push_to_hub_model_id`: None
-- `push_to_hub_organization`: None
-- `mp_parameters`:
-- `auto_find_batch_size`: False
-- `full_determinism`: False
-- `torchdynamo`: None
-- `ray_scope`: last
-- `ddp_timeout`: 1800
-- `torch_compile`: False
-- `torch_compile_backend`: None
-- `torch_compile_mode`: None
-- `include_tokens_per_second`: False
-- `include_num_input_tokens_seen`: False
-- `neftune_noise_alpha`: None
-- `optim_target_modules`: None
-- `batch_eval_metrics`: False
-- `eval_on_start`: False
-- `use_liger_kernel`: False
-- `eval_use_gather_object`: False
-- `average_tokens_across_devices`: False
-- `prompts`: None
-- `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
-</details>
-### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
-|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
-| -1     | -1   | -             | -               | 0.7140                                                                |
-| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
-| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
-| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
-| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
-| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
-| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
-| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
-| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
-| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
-| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
-| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
-### Framework Versions
-- Python: 3.12.9
-- Sentence Transformers: 3.4.1
-- Transformers: 4.51.3
-- PyTorch: 2.7.0+cu126
-- Accelerate: 1.6.0
-- Datasets: 3.6.0
-- Tokenizers: 0.21.1
-## Citation
-### BibTeX
-#### Sentence Transformers
-```bibtex
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "https://arxiv.org/abs/1908.10084",
-}
-```
-#### ContrastiveLoss
-```bibtex
-@inproceedings{hadsell2006dimensionality,
-    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
-    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
-    title={Dimensionality Reduction by Learning an Invariant Mapping},
-    year={2006},
-    volume={2},
-    number={},
-    pages={1735-1742},
-    doi={10.1109/CVPR.2006.100}
-}
-```
-<!--
-## 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-1100/config.json DELETED Viewed

@@ -1,25 +0,0 @@
-{
-  "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": "4.51.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 250037
-}

checkpoint-1100/config_sentence_transformers.json DELETED Viewed

@@ -1,10 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "3.4.1",
-    "transformers": "4.51.3",
-    "pytorch": "2.7.0+cu126"
-  },
-  "prompts": {},
-  "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
-}

checkpoint-1100/model.safetensors DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:763540a5075ed486170f85323b5ee9b40182439ea8f51d889e8674424cce13c2
-size 470637416

checkpoint-1100/modules.json DELETED Viewed

@@ -1,14 +0,0 @@
-[
-  {
-    "idx": 0,
-    "name": "0",
-    "path": "",
-    "type": "sentence_transformers.models.Transformer"
-  },
-  {
-    "idx": 1,
-    "name": "1",
-    "path": "1_Pooling",
-    "type": "sentence_transformers.models.Pooling"
-  }
-]

checkpoint-1100/optimizer.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e0711e7f2b2b4728583424781a68346e4cb105f82c5b3e33e835ff6603b1b546
-size 1715019

checkpoint-1100/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d533d8579fdbb2634c2232f32ae13c2e79a071512c8f417a9f5453a5c0587c27
-size 14645

checkpoint-1100/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a3efc25b9c32ace074d8642ed698ba4f27854c75c4022587a44f288f2399a9b
-size 1465

checkpoint-1100/sentence_bert_config.json DELETED Viewed

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

checkpoint-1100/special_tokens_map.json DELETED Viewed

@@ -1,51 +0,0 @@
-{
-  "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-1100/tokenizer.json DELETED Viewed

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

checkpoint-1100/tokenizer_config.json DELETED Viewed

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

checkpoint-1100/trainer_state.json DELETED Viewed

@@ -1,233 +0,0 @@
-{
-  "best_global_step": 1100,
-  "best_metric": 0.0018734760815277696,
-  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1100",
-  "epoch": 2.0675739089629284,
-  "eval_steps": 100,
-  "global_step": 1100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.18770530267480057,
-      "eval_loss": 0.012530049309134483,
-      "eval_runtime": 812.6802,
-      "eval_samples_per_second": 3277.151,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
-      "eval_steps_per_second": 3.278,
-      "step": 100
-    },
-    {
-      "epoch": 0.37541060534960113,
-      "eval_loss": 0.009013425558805466,
-      "eval_runtime": 792.9843,
-      "eval_samples_per_second": 3358.548,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
-      "eval_steps_per_second": 3.359,
-      "step": 200
-    },
-    {
-      "epoch": 0.5631159080244017,
-      "eval_loss": 0.006819029338657856,
-      "eval_runtime": 809.9704,
-      "eval_samples_per_second": 3288.115,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
-      "eval_steps_per_second": 3.289,
-      "step": 300
-    },
-    {
-      "epoch": 0.7508212106992023,
-      "eval_loss": 0.005150709766894579,
-      "eval_runtime": 797.9199,
-      "eval_samples_per_second": 3337.773,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
-      "eval_steps_per_second": 3.339,
-      "step": 400
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "grad_norm": 0.17396493256092072,
-      "learning_rate": 2.9428198433420364e-05,
-      "loss": 0.0409,
-      "step": 500
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "eval_loss": 0.003973629325628281,
-      "eval_runtime": 809.4532,
-      "eval_samples_per_second": 3290.216,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
-      "eval_steps_per_second": 3.291,
-      "step": 500
-    },
-    {
-      "epoch": 1.1276396058188645,
-      "eval_loss": 0.0032712339889258146,
-      "eval_runtime": 793.7573,
-      "eval_samples_per_second": 3355.277,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
-      "eval_steps_per_second": 3.356,
-      "step": 600
-    },
-    {
-      "epoch": 1.3153449084936648,
-      "eval_loss": 0.0028166945558041334,
-      "eval_runtime": 815.1943,
-      "eval_samples_per_second": 3267.044,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
-      "eval_steps_per_second": 3.268,
-      "step": 700
-    },
-    {
-      "epoch": 1.5030502111684654,
-      "eval_loss": 0.0026242006570100784,
-      "eval_runtime": 805.7115,
-      "eval_samples_per_second": 3305.496,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
-      "eval_steps_per_second": 3.306,
-      "step": 800
-    },
-    {
-      "epoch": 1.690755513843266,
-      "eval_loss": 0.002248650649562478,
-      "eval_runtime": 818.5338,
-      "eval_samples_per_second": 3253.715,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
-      "eval_steps_per_second": 3.255,
-      "step": 900
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "grad_norm": 0.07541557401418686,
-      "learning_rate": 2.5511749347258486e-05,
-      "loss": 0.0131,
-      "step": 1000
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "eval_loss": 0.002240537665784359,
-      "eval_runtime": 803.6286,
-      "eval_samples_per_second": 3314.063,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
-      "eval_steps_per_second": 3.315,
-      "step": 1000
-    },
-    {
-      "epoch": 2.0675739089629284,
-      "eval_loss": 0.0018734760815277696,
-      "eval_runtime": 807.0812,
-      "eval_samples_per_second": 3299.886,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9828594815415578,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7552986741065979,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9950493119597241,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.973889221813201,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7401974201202393,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9611601510291333,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9661201195760486,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9817842882294052,
-      "eval_steps_per_second": 3.301,
-      "step": 1100
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 4256,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 1,
-        "early_stopping_threshold": 0.0
-      },
-      "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": 1000,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1100/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
-size 6033

checkpoint-1100/unigram.json DELETED Viewed

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

checkpoint-1200/1_Pooling/config.json DELETED Viewed

@@ -1,10 +0,0 @@
-{
-  "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-1200/README.md DELETED Viewed

@@ -1,468 +0,0 @@
----
-language:
-- en
-license: apache-2.0
-tags:
-- sentence-transformers
-- sentence-similarity
-- feature-extraction
-- generated_from_trainer
-- dataset_size:2130621
-- loss:ContrastiveLoss
-base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-widget:
-- source_sentence: Kim Chol-sam
-  sentences:
-  - Stankevich Sergey Nikolayevich
-  - Kim Chin-So’k
-  - Julen Lopetegui Agote
-- source_sentence: دينا بنت عبد الحميد
-  sentences:
-  - Alexia van Amsberg
-  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
-  - Dina bint Abdul-Hamíd
-- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
-  sentences:
-  - Karpov Anatoly Evgenyevich
-  - GNPower Mariveles Coal Plant [former]
-  - Muhammed bin Nayef bin Abdul Aziz Al Saud
-- source_sentence: Edward Gnehm
-  sentences:
-  - Шауэрте, Хартмут
-  - Ханзада Филипп, Эдинбург герцогі
-  - AFX
-- source_sentence: Schori i Lidingö
-  sentences:
-  - Yordan Canev
-  - ကားပေါ့ အန်နာတိုလီ
-  - BYSTROV, Mikhail Ivanovich
-pipeline_tag: sentence-similarity
-library_name: sentence-transformers
-metrics:
-- cosine_accuracy
-- cosine_accuracy_threshold
-- cosine_f1
-- cosine_f1_threshold
-- cosine_precision
-- cosine_recall
-- cosine_ap
-- cosine_mcc
-model-index:
-- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-  results:
-  - task:
-      type: binary-classification
-      name: Binary Classification
-    dataset:
-      name: sentence transformers paraphrase multilingual MiniLM L12 v2
-      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
-    metrics:
-    - type: cosine_accuracy
-      value: 0.9843050674356433
-      name: Cosine Accuracy
-    - type: cosine_accuracy_threshold
-      value: 0.742120623588562
-      name: Cosine Accuracy Threshold
-    - type: cosine_f1
-      value: 0.9760932477723254
-      name: Cosine F1
-    - type: cosine_f1_threshold
-      value: 0.742120623588562
-      name: Cosine F1 Threshold
-    - type: cosine_precision
-      value: 0.9703216856372878
-      name: Cosine Precision
-    - type: cosine_recall
-      value: 0.9819338803033267
-      name: Cosine Recall
-    - type: cosine_ap
-      value: 0.9955554741842152
-      name: Cosine Ap
-    - type: cosine_mcc
-      value: 0.964449493634366
-      name: Cosine Mcc
----
-# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
-## Model Details
-### Model Description
-- **Model Type:** Sentence Transformer
-- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
-- **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 384 dimensions
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-- **Language:** en
-- **License:** apache-2.0
-### 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 = [
-    'Schori i Lidingö',
-    'Yordan Canev',
-    'ကားပေါ့ အန်နာတိုလီ',
-]
-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
-#### Binary Classification
-* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
-* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
-| Metric                    | Value      |
-|:--------------------------|:-----------|
-| cosine_accuracy           | 0.9843     |
-| cosine_accuracy_threshold | 0.7421     |
-| cosine_f1                 | 0.9761     |
-| cosine_f1_threshold       | 0.7421     |
-| cosine_precision          | 0.9703     |
-| cosine_recall             | 0.9819     |
-| **cosine_ap**             | **0.9956** |
-| cosine_mcc                | 0.9644     |
-<!--
-## Bias, Risks and Limitations
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-<!--
-### Recommendations
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-## Training Details
-### Training Dataset
-#### Unnamed Dataset
-* Size: 2,130,621 training samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                         | sentence2                           | label            |
-  |:----------------------------------|:------------------------------------|:-----------------|
-  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
-  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
-  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Evaluation Dataset
-#### Unnamed Dataset
-* Size: 2,663,276 evaluation samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                            | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                             | sentence2                              | label            |
-  |:--------------------------------------|:---------------------------------------|:-----------------|
-  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
-  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
-  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
-  ```json
-  {
-      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
-      "margin": 0.5,
-      "size_average": true
-  }
-  ```
-### Training Hyperparameters
-#### Non-Default Hyperparameters
-- `eval_strategy`: steps
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `gradient_accumulation_steps`: 4
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `num_train_epochs`: 8
-- `warmup_ratio`: 0.1
-- `fp16_opt_level`: O0
-- `load_best_model_at_end`: True
-- `optim`: adafactor
-#### All Hyperparameters
-<details><summary>Click to expand</summary>
-- `overwrite_output_dir`: False
-- `do_predict`: False
-- `eval_strategy`: steps
-- `prediction_loss_only`: True
-- `per_device_train_batch_size`: 1000
-- `per_device_eval_batch_size`: 1000
-- `per_gpu_train_batch_size`: None
-- `per_gpu_eval_batch_size`: None
-- `gradient_accumulation_steps`: 4
-- `eval_accumulation_steps`: None
-- `torch_empty_cache_steps`: None
-- `learning_rate`: 3e-05
-- `weight_decay`: 0.01
-- `adam_beta1`: 0.9
-- `adam_beta2`: 0.999
-- `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1.0
-- `num_train_epochs`: 8
-- `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`: False
-- `fp16_opt_level`: O0
-- `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}
-- `tp_size`: 0
-- `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`: adafactor
-- `optim_args`: None
-- `adafactor`: False
-- `group_by_length`: False
-- `length_column_name`: length
-- `ddp_find_unused_parameters`: None
-- `ddp_bucket_cap_mb`: None
-- `ddp_broadcast_buffers`: False
-- `dataloader_pin_memory`: True
-- `dataloader_persistent_workers`: False
-- `skip_memory_metrics`: True
-- `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
-- `resume_from_checkpoint`: None
-- `hub_model_id`: None
-- `hub_strategy`: every_save
-- `hub_private_repo`: None
-- `hub_always_push`: False
-- `gradient_checkpointing`: False
-- `gradient_checkpointing_kwargs`: None
-- `include_inputs_for_metrics`: False
-- `include_for_metrics`: []
-- `eval_do_concat_batches`: True
-- `fp16_backend`: auto
-- `push_to_hub_model_id`: None
-- `push_to_hub_organization`: None
-- `mp_parameters`:
-- `auto_find_batch_size`: False
-- `full_determinism`: False
-- `torchdynamo`: None
-- `ray_scope`: last
-- `ddp_timeout`: 1800
-- `torch_compile`: False
-- `torch_compile_backend`: None
-- `torch_compile_mode`: None
-- `include_tokens_per_second`: False
-- `include_num_input_tokens_seen`: False
-- `neftune_noise_alpha`: None
-- `optim_target_modules`: None
-- `batch_eval_metrics`: False
-- `eval_on_start`: False
-- `use_liger_kernel`: False
-- `eval_use_gather_object`: False
-- `average_tokens_across_devices`: False
-- `prompts`: None
-- `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: proportional
-</details>
-### Training Logs
-| Epoch  | Step | Training Loss | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
-|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
-| -1     | -1   | -             | -               | 0.7140                                                                |
-| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
-| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
-| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
-| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
-| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
-| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
-| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
-| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
-| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
-| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
-| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
-| 2.2553 | 1200 | -             | 0.0017          | 0.9956                                                                |
-### Framework Versions
-- Python: 3.12.9
-- Sentence Transformers: 3.4.1
-- Transformers: 4.51.3
-- PyTorch: 2.7.0+cu126
-- Accelerate: 1.6.0
-- Datasets: 3.6.0
-- Tokenizers: 0.21.1
-## Citation
-### BibTeX
-#### Sentence Transformers
-```bibtex
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "https://arxiv.org/abs/1908.10084",
-}
-```
-#### ContrastiveLoss
-```bibtex
-@inproceedings{hadsell2006dimensionality,
-    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
-    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
-    title={Dimensionality Reduction by Learning an Invariant Mapping},
-    year={2006},
-    volume={2},
-    number={},
-    pages={1735-1742},
-    doi={10.1109/CVPR.2006.100}
-}
-```
-<!--
-## 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-1200/config.json DELETED Viewed

@@ -1,25 +0,0 @@
-{
-  "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": "4.51.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 250037
-}

checkpoint-1200/config_sentence_transformers.json DELETED Viewed

@@ -1,10 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "3.4.1",
-    "transformers": "4.51.3",
-    "pytorch": "2.7.0+cu126"
-  },
-  "prompts": {},
-  "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
-}

checkpoint-1200/model.safetensors DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a16798609ad3be64f1c33cafbc6d8595006225a97722265fbba67e2dfaf916a
-size 470637416

checkpoint-1200/modules.json DELETED Viewed

@@ -1,14 +0,0 @@
-[
-  {
-    "idx": 0,
-    "name": "0",
-    "path": "",
-    "type": "sentence_transformers.models.Transformer"
-  },
-  {
-    "idx": 1,
-    "name": "1",
-    "path": "1_Pooling",
-    "type": "sentence_transformers.models.Pooling"
-  }
-]

checkpoint-1200/optimizer.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e6c0d2369b6fe2e14855dd6ee01f523f4a5901a968149aedc664f3defacc964
-size 1715019

checkpoint-1200/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:51a5e12d95d9820ac91d074df8188d98ce5f4fc76cb3ec8a63d860d96a200697
-size 14645

checkpoint-1200/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:efdbea4967733a900bbe36cb7fab0e417825ab1560e9b509550180a0f55ecc51
-size 1465

checkpoint-1200/sentence_bert_config.json DELETED Viewed

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

checkpoint-1200/special_tokens_map.json DELETED Viewed

@@ -1,51 +0,0 @@
-{
-  "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-1200/tokenizer.json DELETED Viewed

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

checkpoint-1200/tokenizer_config.json DELETED Viewed

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

checkpoint-1200/trainer_state.json DELETED Viewed

@@ -1,249 +0,0 @@
-{
-  "best_global_step": 1200,
-  "best_metric": 0.0017435119953006506,
-  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1200",
-  "epoch": 2.255279211637729,
-  "eval_steps": 100,
-  "global_step": 1200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.18770530267480057,
-      "eval_loss": 0.012530049309134483,
-      "eval_runtime": 812.6802,
-      "eval_samples_per_second": 3277.151,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
-      "eval_steps_per_second": 3.278,
-      "step": 100
-    },
-    {
-      "epoch": 0.37541060534960113,
-      "eval_loss": 0.009013425558805466,
-      "eval_runtime": 792.9843,
-      "eval_samples_per_second": 3358.548,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
-      "eval_steps_per_second": 3.359,
-      "step": 200
-    },
-    {
-      "epoch": 0.5631159080244017,
-      "eval_loss": 0.006819029338657856,
-      "eval_runtime": 809.9704,
-      "eval_samples_per_second": 3288.115,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
-      "eval_steps_per_second": 3.289,
-      "step": 300
-    },
-    {
-      "epoch": 0.7508212106992023,
-      "eval_loss": 0.005150709766894579,
-      "eval_runtime": 797.9199,
-      "eval_samples_per_second": 3337.773,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
-      "eval_steps_per_second": 3.339,
-      "step": 400
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "grad_norm": 0.17396493256092072,
-      "learning_rate": 2.9428198433420364e-05,
-      "loss": 0.0409,
-      "step": 500
-    },
-    {
-      "epoch": 0.9385265133740028,
-      "eval_loss": 0.003973629325628281,
-      "eval_runtime": 809.4532,
-      "eval_samples_per_second": 3290.216,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
-      "eval_steps_per_second": 3.291,
-      "step": 500
-    },
-    {
-      "epoch": 1.1276396058188645,
-      "eval_loss": 0.0032712339889258146,
-      "eval_runtime": 793.7573,
-      "eval_samples_per_second": 3355.277,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
-      "eval_steps_per_second": 3.356,
-      "step": 600
-    },
-    {
-      "epoch": 1.3153449084936648,
-      "eval_loss": 0.0028166945558041334,
-      "eval_runtime": 815.1943,
-      "eval_samples_per_second": 3267.044,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
-      "eval_steps_per_second": 3.268,
-      "step": 700
-    },
-    {
-      "epoch": 1.5030502111684654,
-      "eval_loss": 0.0026242006570100784,
-      "eval_runtime": 805.7115,
-      "eval_samples_per_second": 3305.496,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
-      "eval_steps_per_second": 3.306,
-      "step": 800
-    },
-    {
-      "epoch": 1.690755513843266,
-      "eval_loss": 0.002248650649562478,
-      "eval_runtime": 818.5338,
-      "eval_samples_per_second": 3253.715,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
-      "eval_steps_per_second": 3.255,
-      "step": 900
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "grad_norm": 0.07541557401418686,
-      "learning_rate": 2.5511749347258486e-05,
-      "loss": 0.0131,
-      "step": 1000
-    },
-    {
-      "epoch": 1.8784608165180665,
-      "eval_loss": 0.002240537665784359,
-      "eval_runtime": 803.6286,
-      "eval_samples_per_second": 3314.063,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
-      "eval_steps_per_second": 3.315,
-      "step": 1000
-    },
-    {
-      "epoch": 2.0675739089629284,
-      "eval_loss": 0.0018734760815277696,
-      "eval_runtime": 807.0812,
-      "eval_samples_per_second": 3299.886,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9828594815415578,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7552986741065979,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9950493119597241,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.973889221813201,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7401974201202393,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9611601510291333,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9661201195760486,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9817842882294052,
-      "eval_steps_per_second": 3.301,
-      "step": 1100
-    },
-    {
-      "epoch": 2.255279211637729,
-      "eval_loss": 0.0017435119953006506,
-      "eval_runtime": 802.6162,
-      "eval_samples_per_second": 3318.244,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9843050674356433,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.742120623588562,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955554741842152,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9760932477723254,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.742120623588562,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.964449493634366,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9703216856372878,
-      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9819338803033267,
-      "eval_steps_per_second": 3.319,
-      "step": 1200
-    }
-  ],
-  "logging_steps": 500,
-  "max_steps": 4256,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 1,
-        "early_stopping_threshold": 0.0
-      },
-      "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": 1000,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1200/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
-size 6033

checkpoint-1200/unigram.json DELETED Viewed

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

checkpoint-1300/1_Pooling/config.json DELETED Viewed

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