Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,562 @@
+---
+base_model: intfloat/multilingual-e5-large
+library_name: sentence-transformers
+metrics:
+- negative_mse
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:22076
+- loss:MSELoss
+widget:
+- source_sentence: 'passage: Nagpadala ang Navy ng 16 Warships, Alinsunod sa Pagsusuri
+    ng Presidential Fleet https://bit.ly/3O0qSiV'
+  sentences:
+  - 'passage: Happy Birthday ti nakaskasdaaw unay a nanang iti lubong! #panagkasangay
+    #selebrasion'
+  - 'passage: Isang kagubatan na gumagawa ng mga puno ng oak para sa mga materyales
+    sa pagtatayo'
+  - 'passage: Ang pagkadiskaril sa tren miresulta sa daghang mga samad ug kadaot sa
+    palibot nga mga kabtangan.'
+- source_sentence: 'passage: Online and Remote Learning Proves to be Effective During
+    Lockdown'
+  sentences:
+  - 'passage: Gisuspinde sa Ecuador ang rasyon sa kuryente sa pagbalik sa ulan https://t.co/RWCqU0noSq'
+  - 'passage: i feel regretful that i didnt bring overnight gear'
+  - "passage: Creative Dad Has A Delicious Way To Teach His Daughter The ABCs \n"
+- source_sentence: 'passage: Ang pagbibigay ng maling gamot sa isang pasyente na nagreresulta
+    sa mga komplikasyon sa kalusugan'
+  sentences:
+  - 'passage: Rugian ti Iraq dagiti panagregget a mangbangon manen kalpasan ti adu
+    a tawen a gubat'
+  - 'passage: RT @dayurad_: 24 anyos nga Puntland Casino Garowe! @Bulshaawi_ https://t.co/ExWnH7fdW5'
+  - 'passage: PAG-ALAGAD SA PANGKALAHATAG SA GOBYERNO: Libre na ang Flu Shots Anaa
+    na sa Tanang Lokal nga Health Centers'
+- source_sentence: "passage: Girl Does Ice Bucket Challenge... After Having Wisdom\
+    \ Teeth Pulled \n"
+  sentences:
+  - 'passage: New study shows the impact of immigration on social conditions. #ImmigrationImpact'
+  - 'passage: Nabati nako ang akong kaugalingon nga naigo niining katingad-an nga
+    gabon nga bungbong'
+  - 'passage: Just got my child’s educational grading report and couldn’t be more
+    proud of their progress!'
+- source_sentence: "passage: Fit Bodies Aren't Perfect, Either \n"
+  sentences:
+  - 'passage: Royals attend extravagant ceremony to celebrate the opening of new museum'
+  - 'passage: Researchers publish study on the social and psychological impact of
+    online dating'
+  - "passage: Native-American Kids Doused With Beer at SD Hockey Game \n"
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-large
+  results:
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: negative_mse
+      value: -0.0055574404541403055
+      name: Negative Mse
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It maps sentences & paragraphs to a 1024-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+  (2): Normalize()
+)
+```
+
+## 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 = [
+    "passage: Fit Bodies Aren't Perfect, Either \n",
+    'passage: Royals attend extravagant ceremony to celebrate the opening of new museum',
+    'passage: Native-American Kids Doused With Beer at SD Hockey Game \n',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Knowledge Distillation
+
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value       |
+|:-----------------|:------------|
+| **negative_mse** | **-0.0056** |
+
+<!--
+## 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: 22,076 training samples
+* Columns: <code>sentence_0</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                        | label                                 |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------|
+  | type    | string                                                                            | list                                  |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 24.27 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                    | label                                                                                                                             |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------|
+  | <code>passage: Nahibal-an ni Jon Stewart kung kinsa ang modaog sa usa ka gubat tali sa Texas ug Florida <br></code>                           | <code>[0.028687365353107452, -0.017304804176092148, -0.04063289240002632, -0.06607247143983841, 0.012475084513425827, ...]</code> |
+  | <code>passage: Kinabahan si Sarah tungkol sa mga pagsubok at eksaminasyong pang-edukasyon ngunit nagtagumpay silang lahat!</code>             | <code>[0.02698751911520958, -0.04083320125937462, -0.020052699372172356, -0.037999920547008514, 0.025929132476449013, ...]</code> |
+  | <code>passage: (Update)166645: Malinaw na ang obstruction sa N2 Northbound pagkatapos ng Ramp mula sa Umdloti. Mag-ingat sa Pagmaneho.</code> | <code>[0.04197411611676216, -0.017068173736333847, 0.005260208155959845, -0.02268386073410511, 0.016873840242624283, ...]</code>  |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 20
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 20
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch   | Step  | Training Loss | negative_mse |
+|:-------:|:-----:|:-------------:|:------------:|
+| 0.1449  | 200   | -             | -0.0077      |
+| 0.2899  | 400   | -             | -0.0072      |
+| 0.3623  | 500   | 0.0001        | -            |
+| 0.4348  | 600   | -             | -0.0070      |
+| 0.5797  | 800   | -             | -0.0068      |
+| 0.7246  | 1000  | 0.0001        | -0.0067      |
+| 0.8696  | 1200  | -             | -0.0066      |
+| 1.0     | 1380  | -             | -0.0065      |
+| 1.0145  | 1400  | -             | -0.0065      |
+| 1.0870  | 1500  | 0.0           | -            |
+| 1.1594  | 1600  | -             | -0.0064      |
+| 1.3043  | 1800  | -             | -0.0064      |
+| 1.4493  | 2000  | 0.0           | -0.0064      |
+| 1.5942  | 2200  | -             | -0.0063      |
+| 1.7391  | 2400  | -             | -0.0063      |
+| 1.8116  | 2500  | 0.0           | -            |
+| 1.8841  | 2600  | -             | -0.0063      |
+| 2.0     | 2760  | -             | -0.0063      |
+| 2.0290  | 2800  | -             | -0.0063      |
+| 2.1739  | 3000  | 0.0           | -0.0062      |
+| 2.3188  | 3200  | -             | -0.0062      |
+| 2.4638  | 3400  | -             | -0.0061      |
+| 2.5362  | 3500  | 0.0           | -            |
+| 2.6087  | 3600  | -             | -0.0062      |
+| 2.7536  | 3800  | -             | -0.0061      |
+| 2.8986  | 4000  | 0.0           | -0.0061      |
+| 3.0     | 4140  | -             | -0.0061      |
+| 3.0435  | 4200  | -             | -0.0061      |
+| 3.1884  | 4400  | -             | -0.0061      |
+| 3.2609  | 4500  | 0.0           | -            |
+| 3.3333  | 4600  | -             | -0.0061      |
+| 3.4783  | 4800  | -             | -0.0061      |
+| 3.6232  | 5000  | 0.0           | -0.0060      |
+| 3.7681  | 5200  | -             | -0.0060      |
+| 3.9130  | 5400  | -             | -0.0060      |
+| 3.9855  | 5500  | 0.0           | -            |
+| 4.0     | 5520  | -             | -0.0060      |
+| 4.0580  | 5600  | -             | -0.0060      |
+| 4.2029  | 5800  | -             | -0.0060      |
+| 4.3478  | 6000  | 0.0           | -0.0060      |
+| 4.4928  | 6200  | -             | -0.0059      |
+| 4.6377  | 6400  | -             | -0.0059      |
+| 4.7101  | 6500  | 0.0           | -            |
+| 4.7826  | 6600  | -             | -0.0059      |
+| 4.9275  | 6800  | -             | -0.0059      |
+| 5.0     | 6900  | -             | -0.0059      |
+| 5.0725  | 7000  | 0.0           | -0.0059      |
+| 5.2174  | 7200  | -             | -0.0059      |
+| 5.3623  | 7400  | -             | -0.0059      |
+| 5.4348  | 7500  | 0.0           | -            |
+| 5.5072  | 7600  | -             | -0.0059      |
+| 5.6522  | 7800  | -             | -0.0059      |
+| 5.7971  | 8000  | 0.0           | -0.0059      |
+| 5.9420  | 8200  | -             | -0.0059      |
+| 6.0     | 8280  | -             | -0.0058      |
+| 6.0870  | 8400  | -             | -0.0058      |
+| 6.1594  | 8500  | 0.0           | -            |
+| 6.2319  | 8600  | -             | -0.0058      |
+| 6.3768  | 8800  | -             | -0.0059      |
+| 6.5217  | 9000  | 0.0           | -0.0058      |
+| 6.6667  | 9200  | -             | -0.0058      |
+| 6.8116  | 9400  | -             | -0.0058      |
+| 6.8841  | 9500  | 0.0           | -            |
+| 6.9565  | 9600  | -             | -0.0058      |
+| 7.0     | 9660  | -             | -0.0058      |
+| 7.1014  | 9800  | -             | -0.0058      |
+| 7.2464  | 10000 | 0.0           | -0.0058      |
+| 7.3913  | 10200 | -             | -0.0058      |
+| 7.5362  | 10400 | -             | -0.0058      |
+| 7.6087  | 10500 | 0.0           | -            |
+| 7.6812  | 10600 | -             | -0.0058      |
+| 7.8261  | 10800 | -             | -0.0058      |
+| 7.9710  | 11000 | 0.0           | -0.0058      |
+| 8.0     | 11040 | -             | -0.0058      |
+| 8.1159  | 11200 | -             | -0.0057      |
+| 8.2609  | 11400 | -             | -0.0057      |
+| 8.3333  | 11500 | 0.0           | -            |
+| 8.4058  | 11600 | -             | -0.0058      |
+| 8.5507  | 11800 | -             | -0.0058      |
+| 8.6957  | 12000 | 0.0           | -0.0057      |
+| 8.8406  | 12200 | -             | -0.0058      |
+| 8.9855  | 12400 | -             | -0.0057      |
+| 9.0     | 12420 | -             | -0.0057      |
+| 9.0580  | 12500 | 0.0           | -            |
+| 9.1304  | 12600 | -             | -0.0057      |
+| 9.2754  | 12800 | -             | -0.0057      |
+| 9.4203  | 13000 | 0.0           | -0.0057      |
+| 9.5652  | 13200 | -             | -0.0057      |
+| 9.7101  | 13400 | -             | -0.0057      |
+| 9.7826  | 13500 | 0.0           | -            |
+| 9.8551  | 13600 | -             | -0.0057      |
+| 10.0    | 13800 | -             | -0.0057      |
+| 10.1449 | 14000 | 0.0           | -0.0057      |
+| 10.2899 | 14200 | -             | -0.0057      |
+| 10.4348 | 14400 | -             | -0.0057      |
+| 10.5072 | 14500 | 0.0           | -            |
+| 10.5797 | 14600 | -             | -0.0057      |
+| 10.7246 | 14800 | -             | -0.0057      |
+| 10.8696 | 15000 | 0.0           | -0.0057      |
+| 11.0    | 15180 | -             | -0.0057      |
+| 11.0145 | 15200 | -             | -0.0057      |
+| 11.1594 | 15400 | -             | -0.0057      |
+| 11.2319 | 15500 | 0.0           | -            |
+| 11.3043 | 15600 | -             | -0.0057      |
+| 11.4493 | 15800 | -             | -0.0057      |
+| 11.5942 | 16000 | 0.0           | -0.0057      |
+| 11.7391 | 16200 | -             | -0.0056      |
+| 11.8841 | 16400 | -             | -0.0056      |
+| 11.9565 | 16500 | 0.0           | -            |
+| 12.0    | 16560 | -             | -0.0057      |
+| 12.0290 | 16600 | -             | -0.0056      |
+| 12.1739 | 16800 | -             | -0.0056      |
+| 12.3188 | 17000 | 0.0           | -0.0057      |
+| 12.4638 | 17200 | -             | -0.0056      |
+| 12.6087 | 17400 | -             | -0.0056      |
+| 12.6812 | 17500 | 0.0           | -            |
+| 12.7536 | 17600 | -             | -0.0056      |
+| 12.8986 | 17800 | -             | -0.0056      |
+| 13.0    | 17940 | -             | -0.0056      |
+| 13.0435 | 18000 | 0.0           | -0.0056      |
+| 13.1884 | 18200 | -             | -0.0056      |
+| 13.3333 | 18400 | -             | -0.0056      |
+| 13.4058 | 18500 | 0.0           | -            |
+| 13.4783 | 18600 | -             | -0.0056      |
+| 13.6232 | 18800 | -             | -0.0056      |
+| 13.7681 | 19000 | 0.0           | -0.0056      |
+| 13.9130 | 19200 | -             | -0.0056      |
+| 14.0    | 19320 | -             | -0.0056      |
+| 14.0580 | 19400 | -             | -0.0056      |
+| 14.1304 | 19500 | 0.0           | -            |
+| 14.2029 | 19600 | -             | -0.0056      |
+| 14.3478 | 19800 | -             | -0.0056      |
+| 14.4928 | 20000 | 0.0           | -0.0056      |
+| 14.6377 | 20200 | -             | -0.0056      |
+| 14.7826 | 20400 | -             | -0.0056      |
+| 14.8551 | 20500 | 0.0           | -            |
+| 14.9275 | 20600 | -             | -0.0056      |
+| 15.0    | 20700 | -             | -0.0056      |
+| 15.0725 | 20800 | -             | -0.0056      |
+| 15.2174 | 21000 | 0.0           | -0.0056      |
+| 15.3623 | 21200 | -             | -0.0056      |
+| 15.5072 | 21400 | -             | -0.0056      |
+| 15.5797 | 21500 | 0.0           | -            |
+| 15.6522 | 21600 | -             | -0.0056      |
+| 15.7971 | 21800 | -             | -0.0056      |
+| 15.9420 | 22000 | 0.0           | -0.0056      |
+| 16.0    | 22080 | -             | -0.0056      |
+| 16.0870 | 22200 | -             | -0.0056      |
+| 16.2319 | 22400 | -             | -0.0056      |
+| 16.3043 | 22500 | 0.0           | -            |
+| 16.3768 | 22600 | -             | -0.0056      |
+| 16.5217 | 22800 | -             | -0.0056      |
+| 16.6667 | 23000 | 0.0           | -0.0056      |
+| 16.8116 | 23200 | -             | -0.0056      |
+| 16.9565 | 23400 | -             | -0.0056      |
+| 17.0    | 23460 | -             | -0.0056      |
+| 17.0290 | 23500 | 0.0           | -            |
+| 17.1014 | 23600 | -             | -0.0056      |
+| 17.2464 | 23800 | -             | -0.0056      |
+| 17.3913 | 24000 | 0.0           | -0.0056      |
+| 17.5362 | 24200 | -             | -0.0056      |
+| 17.6812 | 24400 | -             | -0.0056      |
+| 17.7536 | 24500 | 0.0           | -            |
+| 17.8261 | 24600 | -             | -0.0056      |
+| 17.9710 | 24800 | -             | -0.0056      |
+| 18.0    | 24840 | -             | -0.0056      |
+| 18.1159 | 25000 | 0.0           | -0.0056      |
+| 18.2609 | 25200 | -             | -0.0056      |
+| 18.4058 | 25400 | -             | -0.0056      |
+| 18.4783 | 25500 | 0.0           | -            |
+| 18.5507 | 25600 | -             | -0.0056      |
+| 18.6957 | 25800 | -             | -0.0056      |
+
+</details>
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0
+- Accelerate: 0.34.2
+- Datasets: 3.0.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MSELoss
+```bibtex
+@inproceedings{reimers-2020-multilingual-sentence-bert,
+    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2020",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/2004.09813",
+}
+```
+
+<!--
+## 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.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/kaggle/input/e5-multilingual-fil-model/output/intfloat/multilingual-e5-large",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.45.1",
+    "pytorch": "2.4.0+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c5991279f5e5b9f6da8d59b938e5f2ef7a5dacdade4d886443d0e3239b229d
+size 2239607176

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}