Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-203/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-203/unigram.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

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

README.md

@@ -0,0 +1,62 @@
+
+---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- autotrain
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: 'search_query: i love autotrain'
+  sentences:
+  - 'search_query: huggingface auto train'
+  - 'search_query: hugging face auto train'
+  - 'search_query: i love autotrain'
+pipeline_tag: sentence-similarity
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Sentence Transformers
+
+## Validation Metrics
+loss: 0.14303971827030182
+
+runtime: 1.4424
+
+samples_per_second: 79.726
+
+steps_per_second: 2.773
+
+: 7.0
+
+## 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 Hugging Face Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'search_query: autotrain',
+    'search_query: auto train',
+    'search_query: i love autotrain',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+```

checkpoint-203/1_Pooling/config.json

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

checkpoint-203/README.md

@@ -0,0 +1,408 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:456
+- loss:SoftmaxLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: not especially natural
+  sentences:
+  - bright
+  - bright
+  - bright
+- source_sentence: くつろいだ感じじゃない
+  sentences:
+  - bright
+  - bright
+  - cozy
+- source_sentence: not especially bright
+  sentences:
+  - bright
+  - cozy
+  - natural
+- source_sentence: 明るくしないで
+  sentences:
+  - cozy
+  - cozy
+  - bright
+- source_sentence: This room feels too cozy I need something more energetic
+  sentences:
+  - cozy
+  - bright
+  - bright
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'This room feels too cozy I need something more energetic',
+    'bright',
+    'cozy',
+]
+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.*
+-->
+
+<!--
+## 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: 456 training samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 456 samples:
+  |         | premise                                                                          | hypothesis                                                                      | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 7.82 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.31 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~17.98%</li><li>1: ~82.02%</li></ul> |
+* Samples:
+  | premise                                                            | hypothesis          | label          |
+  |:-------------------------------------------------------------------|:--------------------|:---------------|
+  | <code>not romantic lighting</code>                                 | <code>bright</code> | <code>1</code> |
+  | <code>These lights are way too bright please turn them down</code> | <code>cozy</code>   | <code>1</code> |
+  | <code>not quite cozy</code>                                        | <code>bright</code> | <code>1</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 115 evaluation samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 115 samples:
+  |         | premise                                                                          | hypothesis                                                                      | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.24 tokens</li><li>max: 17 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.38 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~20.87%</li><li>1: ~79.13%</li></ul> |
+* Samples:
+  | premise                                                                | hypothesis        | label          |
+  |:-----------------------------------------------------------------------|:------------------|:---------------|
+  | <code>not warm</code>                                                  | <code>cozy</code> | <code>0</code> |
+  | <code>In the evening I want lighting that's not bright but cozy</code> | <code>cozy</code> | <code>1</code> |
+  | <code>明るい光は苦手です</code>                                                 | <code>cozy</code> | <code>1</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 32
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 7
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `ddp_find_unused_parameters`: False
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 7
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: False
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: 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
+- `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
+- `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 |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.1724 | 5    | 0.7808        | -               |
+| 0.3448 | 10   | 0.7224        | -               |
+| 0.5172 | 15   | 0.5833        | -               |
+| 0.6897 | 20   | 0.4336        | -               |
+| 0.8621 | 25   | 0.426         | -               |
+| 1.0    | 29   | -             | 0.4209          |
+| 1.0345 | 30   | 0.407         | -               |
+| 1.2069 | 35   | 0.4633        | -               |
+| 1.3793 | 40   | 0.2629        | -               |
+| 1.5517 | 45   | 0.4468        | -               |
+| 1.7241 | 50   | 0.3665        | -               |
+| 1.8966 | 55   | 0.2735        | -               |
+| 2.0    | 58   | -             | 0.3269          |
+| 2.0690 | 60   | 0.2472        | -               |
+| 2.2414 | 65   | 0.2586        | -               |
+| 2.4138 | 70   | 0.2281        | -               |
+| 2.5862 | 75   | 0.3056        | -               |
+| 2.7586 | 80   | 0.2166        | -               |
+| 2.9310 | 85   | 0.2243        | -               |
+| 3.0    | 87   | -             | 0.2471          |
+| 3.1034 | 90   | 0.2233        | -               |
+| 3.2759 | 95   | 0.1625        | -               |
+| 3.4483 | 100  | 0.1718        | -               |
+| 3.6207 | 105  | 0.1728        | -               |
+| 3.7931 | 110  | 0.1949        | -               |
+| 3.9655 | 115  | 0.0891        | -               |
+| 4.0    | 116  | -             | 0.1997          |
+| 4.1379 | 120  | 0.1895        | -               |
+| 4.3103 | 125  | 0.1021        | -               |
+| 4.4828 | 130  | 0.1232        | -               |
+| 4.6552 | 135  | 0.0891        | -               |
+| 4.8276 | 140  | 0.109         | -               |
+| 5.0    | 145  | 0.0879        | 0.1679          |
+| 5.1724 | 150  | 0.0814        | -               |
+| 5.3448 | 155  | 0.1015        | -               |
+| 5.5172 | 160  | 0.0822        | -               |
+| 5.6897 | 165  | 0.1054        | -               |
+| 5.8621 | 170  | 0.1093        | -               |
+| 6.0    | 174  | -             | 0.1479          |
+| 6.0345 | 175  | 0.0911        | -               |
+| 6.2069 | 180  | 0.0804        | -               |
+| 6.3793 | 185  | 0.1063        | -               |
+| 6.5517 | 190  | 0.0821        | -               |
+| 6.7241 | 195  | 0.0988        | -               |
+| 6.8966 | 200  | 0.0691        | -               |
+| 7.0    | 203  | -             | 0.1430          |
+
+
+### Framework Versions
+- Python: 3.10.16
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.0
+- PyTorch: 2.4.0
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers and SoftmaxLoss
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

checkpoint-203/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

checkpoint-203/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-203/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9be9d9e76440a3a74ade4f9b4f7c376e404d1f74a579553059d91dc4ef7406
+size 470637416

checkpoint-203/modules.json

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

checkpoint-203/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441fa5024fdadba26b685a511fc33dc3927275f448a1a0273f9d49296a48df9a
+size 940226682

checkpoint-203/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e1dbcbf9ee2884a40d6c1a0fe31161f6bf610443fb0f04cf4e04294a46efc2
+size 13990

checkpoint-203/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9be6dc1393b4eb31d79ee7d8d417bec396842211c6cb2a1bd3a9c7aa5d24d6a
+size 1064

checkpoint-203/sentence_bert_config.json

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

checkpoint-203/special_tokens_map.json

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

checkpoint-203/tokenizer.json

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

checkpoint-203/tokenizer_config.json

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

checkpoint-203/trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": 0.14303971827030182,
+  "best_model_checkpoint": "autotrain-tckj2-dxpo0/checkpoint-203",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 203,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 3.970233678817749,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.7808,
+      "step": 5
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.5622565746307373,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.7224,
+      "step": 10
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 1.819740891456604,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.5833,
+      "step": 15
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.9450643062591553,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.4336,
+      "step": 20
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.2047266960144043,
+      "learning_rate": 1.9560439560439563e-05,
+      "loss": 0.426,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.42094460129737854,
+      "eval_runtime": 1.7024,
+      "eval_samples_per_second": 67.553,
+      "eval_steps_per_second": 2.35,
+      "step": 29
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 1.0075544118881226,
+      "learning_rate": 1.901098901098901e-05,
+      "loss": 0.407,
+      "step": 30
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 2.6184139251708984,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.4633,
+      "step": 35
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 1.3700945377349854,
+      "learning_rate": 1.7912087912087915e-05,
+      "loss": 0.2629,
+      "step": 40
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 1.5076994895935059,
+      "learning_rate": 1.7362637362637363e-05,
+      "loss": 0.4468,
+      "step": 45
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 1.0693202018737793,
+      "learning_rate": 1.6813186813186814e-05,
+      "loss": 0.3665,
+      "step": 50
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 1.7655493021011353,
+      "learning_rate": 1.6263736263736265e-05,
+      "loss": 0.2735,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3269391655921936,
+      "eval_runtime": 1.3905,
+      "eval_samples_per_second": 82.706,
+      "eval_steps_per_second": 2.877,
+      "step": 58
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 1.0194451808929443,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.2472,
+      "step": 60
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 2.360098361968994,
+      "learning_rate": 1.5164835164835166e-05,
+      "loss": 0.2586,
+      "step": 65
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 1.4176146984100342,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 0.2281,
+      "step": 70
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 3.5215818881988525,
+      "learning_rate": 1.4065934065934068e-05,
+      "loss": 0.3056,
+      "step": 75
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 1.205544352531433,
+      "learning_rate": 1.3516483516483519e-05,
+      "loss": 0.2166,
+      "step": 80
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 1.4513664245605469,
+      "learning_rate": 1.296703296703297e-05,
+      "loss": 0.2243,
+      "step": 85
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2470882385969162,
+      "eval_runtime": 1.6355,
+      "eval_samples_per_second": 70.316,
+      "eval_steps_per_second": 2.446,
+      "step": 87
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 1.3780584335327148,
+      "learning_rate": 1.2417582417582419e-05,
+      "loss": 0.2233,
+      "step": 90
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 1.5511927604675293,
+      "learning_rate": 1.186813186813187e-05,
+      "loss": 0.1625,
+      "step": 95
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 1.3662214279174805,
+      "learning_rate": 1.131868131868132e-05,
+      "loss": 0.1718,
+      "step": 100
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 2.4403982162475586,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.1728,
+      "step": 105
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 1.4150804281234741,
+      "learning_rate": 1.021978021978022e-05,
+      "loss": 0.1949,
+      "step": 110
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 2.6226606369018555,
+      "learning_rate": 9.670329670329671e-06,
+      "loss": 0.0891,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.19967548549175262,
+      "eval_runtime": 1.725,
+      "eval_samples_per_second": 66.667,
+      "eval_steps_per_second": 2.319,
+      "step": 116
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 2.1667020320892334,
+      "learning_rate": 9.120879120879122e-06,
+      "loss": 0.1895,
+      "step": 120
+    },
+    {
+      "epoch": 4.310344827586207,
+      "grad_norm": 1.2279396057128906,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.1021,
+      "step": 125
+    },
+    {
+      "epoch": 4.482758620689655,
+      "grad_norm": 2.164337396621704,
+      "learning_rate": 8.021978021978023e-06,
+      "loss": 0.1232,
+      "step": 130
+    },
+    {
+      "epoch": 4.655172413793103,
+      "grad_norm": 0.4767724573612213,
+      "learning_rate": 7.472527472527473e-06,
+      "loss": 0.0891,
+      "step": 135
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 0.7710694074630737,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.109,
+      "step": 140
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6246473789215088,
+      "learning_rate": 6.373626373626373e-06,
+      "loss": 0.0879,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.16786590218544006,
+      "eval_runtime": 1.7475,
+      "eval_samples_per_second": 65.808,
+      "eval_steps_per_second": 2.289,
+      "step": 145
+    },
+    {
+      "epoch": 5.172413793103448,
+      "grad_norm": 1.7630176544189453,
+      "learning_rate": 5.824175824175825e-06,
+      "loss": 0.0814,
+      "step": 150
+    },
+    {
+      "epoch": 5.344827586206897,
+      "grad_norm": 0.9055896401405334,
+      "learning_rate": 5.274725274725275e-06,
+      "loss": 0.1015,
+      "step": 155
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 1.1590590476989746,
+      "learning_rate": 4.725274725274726e-06,
+      "loss": 0.0822,
+      "step": 160
+    },
+    {
+      "epoch": 5.689655172413794,
+      "grad_norm": 3.4120426177978516,
+      "learning_rate": 4.175824175824177e-06,
+      "loss": 0.1054,
+      "step": 165
+    },
+    {
+      "epoch": 5.862068965517241,
+      "grad_norm": 1.244531273841858,
+      "learning_rate": 3.6263736263736266e-06,
+      "loss": 0.1093,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.14788025617599487,
+      "eval_runtime": 1.4731,
+      "eval_samples_per_second": 78.065,
+      "eval_steps_per_second": 2.715,
+      "step": 174
+    },
+    {
+      "epoch": 6.0344827586206895,
+      "grad_norm": 0.7680085301399231,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.0911,
+      "step": 175
+    },
+    {
+      "epoch": 6.206896551724138,
+      "grad_norm": 1.3764543533325195,
+      "learning_rate": 2.5274725274725274e-06,
+      "loss": 0.0804,
+      "step": 180
+    },
+    {
+      "epoch": 6.379310344827586,
+      "grad_norm": 1.9512306451797485,
+      "learning_rate": 1.9780219780219782e-06,
+      "loss": 0.1063,
+      "step": 185
+    },
+    {
+      "epoch": 6.551724137931035,
+      "grad_norm": 1.7474387884140015,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0821,
+      "step": 190
+    },
+    {
+      "epoch": 6.724137931034483,
+      "grad_norm": 3.119471788406372,
+      "learning_rate": 8.791208791208792e-07,
+      "loss": 0.0988,
+      "step": 195
+    },
+    {
+      "epoch": 6.896551724137931,
+      "grad_norm": 1.1896252632141113,
+      "learning_rate": 3.296703296703297e-07,
+      "loss": 0.0691,
+      "step": 200
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.14303971827030182,
+      "eval_runtime": 1.4807,
+      "eval_samples_per_second": 77.664,
+      "eval_steps_per_second": 2.701,
+      "step": 203
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 203,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-203/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06298f5ab472894f023b5c1cf146845a081b66643e58450305b37ac7a30f28e
+size 5624

checkpoint-203/unigram.json

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

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.0",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9be9d9e76440a3a74ade4f9b4f7c376e404d1f74a579553059d91dc4ef7406
+size 470637416

modules.json

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

runs/May22_12-44-19_r-nabil-tazi-ambiance-jp1-o73hkamg-cf8c1-dzdsf/events.out.tfevents.1747917864.r-nabil-tazi-ambiance-jp1-o73hkamg-cf8c1-dzdsf.105.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54330c0e3cab50284e54362e4b2b478178eec0bcf9dcbe05ab53499e5eaf9bf
-size 12834
+oid sha256:3811da47384377061822a0469b5675bf5a43cbd933251c8a5e6a3b6a3dce7d59
+size 14996

runs/May22_12-44-19_r-nabil-tazi-ambiance-jp1-o73hkamg-cf8c1-dzdsf/events.out.tfevents.1747918599.r-nabil-tazi-ambiance-jp1-o73hkamg-cf8c1-dzdsf.105.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e0d0a65bfc69f3261c2b7932f7293080702d8f69dd1366e04a47bb725ddbae
+size 359

sentence_bert_config.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06298f5ab472894f023b5c1cf146845a081b66643e58450305b37ac7a30f28e
+size 5624

training_params.json

@@ -0,0 +1,33 @@
+{
+    "data_path": "autotrain-tckj2-dxpo0/autotrain-data",
+    "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+    "lr": 2e-05,
+    "epochs": 7,
+    "max_seq_length": 256,
+    "batch_size": 16,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "logging_steps": -1,
+    "project_name": "autotrain-tckj2-dxpo0",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "nabil-tazi",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01,
+    "trainer": "pair_class",
+    "sentence1_column": "autotrain_sentence1",
+    "sentence2_column": "autotrain_sentence2",
+    "sentence3_column": "autotrain_sentence3",
+    "target_column": "autotrain_target"
+}

unigram.json

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