Debk/Oriya_paraphrase-multilingual-MiniLM-L12-v2_odien

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from 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
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Debk/Oriya_paraphrase-multilingual-MiniLM-L12-v2_odien")
# Run inference
sentences = [
    "For I will defend this city, to save it, for mine own sake, and for my servant David's sake.",
    'ମୁଁ ଏହି ନଗରକୁ ରକ୍ଷା କରିବି। ମାେ ନିଜ ସକାେଶ ଓ ମାରେ ଦାସ ଦାଉଦ ନିମନ୍ତେ ମୁଁ ଏ ନଗରକୁ ସୁରକ୍ଷା ଦବେି।"',
    'ସେଠାକାର ଲୋକମାନଙ୍କୁ ଆଶ୍ୱାସନା ଦେଇ ପ୍ରଧାନମନ୍ତ୍ରୀ କହିଥିଲେ ଯେ ସେମାନଙ୍କୁ ସବୁପ୍ରକାରର ସହାୟତା ଯୋଗାଇ ଦିଆଯିବ ।',
]
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]

Evaluation

Metrics

Semantic Similarity

• Dataset: dev-evaluation
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan

Training Details

Training Dataset

Unnamed Dataset

• Size: 69,370 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 3 tokens mean: 29.5 tokens max: 128 tokens	min: 3 tokens mean: 41.43 tokens max: 128 tokens	min: 0.9 mean: 0.9 max: 0.9

• Samples:

  sentence_0	sentence_1	label
  “Wishing our most beloved & widely respected Atal Ji a happy birthday.	“ଆମର ଅତ୍ୟନ୍ତ ପ୍ରିୟ ଓ ସ୍ନେହର ଆଦରଣୀୟ ଅଟଳ ଜୀଙ୍କୁ ଜନ୍ମ ଦିନର ଶୁଭେଚ୍ଛା ।	0.9
  The project is also an example of environment friendly development.	ଏହି ପରିଯୋଜନା ପରିବେଶ ଅନୁକୂଳ ବିକାଶର ଏକ ଉଦାହରଣ ମଧ୍ୟ ।	0.9
  Old as the hills	ପାହାଡ଼ ପ୍ର ପୁରୁଣା	0.9

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• 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: 3
• 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: 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: round_robin

Training Logs

Epoch	Step	Training Loss	dev-evaluation_spearman_cosine
0.1153	500	0.1806	-
0.2306	1000	0.0047	nan
0.3459	1500	0.0013	-
0.4613	2000	0.0006	nan
0.5766	2500	0.0003	-
0.6919	3000	0.0002	nan
0.8072	3500	0.0001	-
0.9225	4000	0.0001	nan
1.0	4336	-	nan
1.0378	4500	0.0	-
1.1531	5000	0.0	nan
1.2685	5500	0.0	-
1.3838	6000	0.0	nan
1.4991	6500	0.0	-
1.6144	7000	0.0	nan
1.7297	7500	0.0	-
1.8450	8000	0.0	nan
1.9603	8500	0.0	-
2.0	8672	-	nan
2.0756	9000	0.0	nan
2.1910	9500	0.0	-
2.3063	10000	0.0	nan
2.4216	10500	0.0	-
2.5369	11000	0.0	nan
2.6522	11500	0.0	-
2.7675	12000	0.0	nan
2.8828	12500	0.0	-
2.9982	13000	0.0	nan
3.0	13008	-	nan

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.47.1
• PyTorch: 2.5.1+cu121
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@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",
}