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-69/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-69/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: 0.4411565661430359
+
+runtime: 2.0186
+
+samples_per_second: 90.16
+
+steps_per_second: 5.945
+
+: 3.0
+
+## 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-69/1_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-69/README.md

@@ -0,0 +1,380 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:182
+- loss:SoftmaxLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: 太陽
+  sentences:
+  - bright
+  - natural
+  - bright
+- source_sentence: 明るくない
+  sentences:
+  - cozy
+  - cozy
+  - bright
+- source_sentence: natural
+  sentences:
+  - natural
+  - cozy
+  - natural
+- source_sentence: sunlight
+  sentences:
+  - bright
+  - natural
+  - cozy
+- source_sentence: 日光
+  sentences:
+  - bright
+  - cozy
+  - natural
+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 = [
+    '日光',
+    'natural',
+    'bright',
+]
+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: 182 training samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 182 samples:
+  |         | premise                                                                          | hypothesis                                                                      | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.39 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.36 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~25.27%</li><li>1: ~74.73%</li></ul> |
+* Samples:
+  | premise               | hypothesis          | label          |
+  |:----------------------|:--------------------|:---------------|
+  | <code>bright</code>   | <code>bright</code> | <code>1</code> |
+  | <code>luminous</code> | <code>bright</code> | <code>1</code> |
+  | <code>well-lit</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: 182 evaluation samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 182 samples:
+  |         | premise                                                                          | hypothesis                                                                      | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.39 tokens</li><li>max: 10 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.36 tokens</li><li>max: 4 tokens</li></ul> | <ul><li>0: ~25.27%</li><li>1: ~74.73%</li></ul> |
+* Samples:
+  | premise               | hypothesis          | label          |
+  |:----------------------|:--------------------|:---------------|
+  | <code>bright</code>   | <code>bright</code> | <code>1</code> |
+  | <code>luminous</code> | <code>bright</code> | <code>1</code> |
+  | <code>well-lit</code> | <code>bright</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_eval_batch_size`: 16
+- `learning_rate`: 3e-05
+- `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`: 8
+- `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`: 3e-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`: 3
+- `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 |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.1739 | 4    | 0.7869        | -               |
+| 0.3478 | 8    | 0.7022        | -               |
+| 0.5217 | 12   | 0.6482        | -               |
+| 0.6957 | 16   | 0.5571        | -               |
+| 0.8696 | 20   | 0.5698        | -               |
+| 1.0    | 23   | -             | 0.5250          |
+| 1.0435 | 24   | 0.4771        | -               |
+| 1.2174 | 28   | 0.444         | -               |
+| 1.3913 | 32   | 0.6149        | -               |
+| 1.5652 | 36   | 0.5523        | -               |
+| 1.7391 | 40   | 0.4806        | -               |
+| 1.9130 | 44   | 0.4623        | -               |
+| 2.0    | 46   | -             | 0.4654          |
+| 2.0870 | 48   | 0.4039        | -               |
+| 2.2609 | 52   | 0.47          | -               |
+| 2.4348 | 56   | 0.3878        | -               |
+| 2.6087 | 60   | 0.5158        | -               |
+| 2.7826 | 64   | 0.5203        | -               |
+| 2.9565 | 68   | 0.4446        | -               |
+| 3.0    | 69   | -             | 0.4412          |
+
+
+### 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-69/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-69/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-69/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f531f1b6b1777ecaa3ed1f5e1dcb13b5285ded13de4667c2c369a308622017
+size 470637416

checkpoint-69/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-69/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee8db425650850a8eb75b151178d0623b5f841998d7ec80aeb40266e9762ea0
+size 940226682

checkpoint-69/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928defb185d37229cef46a59a4356e668dd7bab7ed52898f983eea654ae182be
+size 13990

checkpoint-69/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1ba2e1ef1a7931ed9ce00b46e8e8da1deed03835dbf66fa6156db8675a6ef9
+size 1064

checkpoint-69/sentence_bert_config.json

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

checkpoint-69/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-69/tokenizer.json

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

checkpoint-69/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-69/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.4411565661430359,
+  "best_model_checkpoint": "autotrain-3c51k-w49bn/checkpoint-69",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 3.44027042388916,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.7869,
+      "step": 4
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 1.9074159860610962,
+      "learning_rate": 2.9516129032258067e-05,
+      "loss": 0.7022,
+      "step": 8
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 3.345827579498291,
+      "learning_rate": 2.758064516129032e-05,
+      "loss": 0.6482,
+      "step": 12
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 2.091654062271118,
+      "learning_rate": 2.5645161290322582e-05,
+      "loss": 0.5571,
+      "step": 16
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.436171054840088,
+      "learning_rate": 2.370967741935484e-05,
+      "loss": 0.5698,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5249526500701904,
+      "eval_runtime": 3.0089,
+      "eval_samples_per_second": 60.487,
+      "eval_steps_per_second": 3.988,
+      "step": 23
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 1.838670015335083,
+      "learning_rate": 2.1774193548387097e-05,
+      "loss": 0.4771,
+      "step": 24
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 1.2238214015960693,
+      "learning_rate": 1.9838709677419355e-05,
+      "loss": 0.444,
+      "step": 28
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 2.102836847305298,
+      "learning_rate": 1.7903225806451616e-05,
+      "loss": 0.6149,
+      "step": 32
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 1.8485645055770874,
+      "learning_rate": 1.596774193548387e-05,
+      "loss": 0.5523,
+      "step": 36
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 2.7359752655029297,
+      "learning_rate": 1.403225806451613e-05,
+      "loss": 0.4806,
+      "step": 40
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 1.4217264652252197,
+      "learning_rate": 1.2096774193548387e-05,
+      "loss": 0.4623,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46536698937416077,
+      "eval_runtime": 3.1677,
+      "eval_samples_per_second": 57.456,
+      "eval_steps_per_second": 3.788,
+      "step": 46
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": 1.995253562927246,
+      "learning_rate": 1.0161290322580644e-05,
+      "loss": 0.4039,
+      "step": 48
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 2.4988834857940674,
+      "learning_rate": 8.225806451612904e-06,
+      "loss": 0.47,
+      "step": 52
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": 1.7685775756835938,
+      "learning_rate": 6.290322580645162e-06,
+      "loss": 0.3878,
+      "step": 56
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 2.7405200004577637,
+      "learning_rate": 4.35483870967742e-06,
+      "loss": 0.5158,
+      "step": 60
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 3.4083738327026367,
+      "learning_rate": 2.4193548387096776e-06,
+      "loss": 0.5203,
+      "step": 64
+    },
+    {
+      "epoch": 2.9565217391304346,
+      "grad_norm": 1.6851589679718018,
+      "learning_rate": 4.838709677419355e-07,
+      "loss": 0.4446,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.4411565661430359,
+      "eval_runtime": 1.7496,
+      "eval_samples_per_second": 104.022,
+      "eval_steps_per_second": 6.859,
+      "step": 69
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 69,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-69/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea6dcc876978d9aca3f5bd72ab2275d18944971f3a2ae08b4f63b216d3d2b51
+size 5624

checkpoint-69/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 sha256:13f531f1b6b1777ecaa3ed1f5e1dcb13b5285ded13de4667c2c369a308622017
+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_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909403.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d0513566d23a8d0a99cede5b363e42bc906e283293a5f98396e007481070bc
-size 4424
+oid sha256:c57b90c01e200d37c17c463d8c1db5b1990d21a65b71c017ae4021c00e5dfeb6
+size 9089

runs/May22_10-23-19_r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g/events.out.tfevents.1747909665.r-nabil-tazi-ambiance-jp1-r4zwxhi9-1b573-rgi0g.149.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac90fb3fe0f7d6046219246eb082070cde829ad41a9c3a72ffc17af3cc93429
+size 354

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 sha256:5ea6dcc876978d9aca3f5bd72ab2275d18944971f3a2ae08b4f63b216d3d2b51
+size 5624

training_params.json

@@ -0,0 +1,33 @@
+{
+    "data_path": "autotrain-3c51k-w49bn/autotrain-data",
+    "model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+    "lr": 3e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "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-3c51k-w49bn",
+    "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