srikarvar/fine_tuned_model_15

SentenceTransformer based on intfloat/multilingual-e5-small

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-small. 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: intfloat/multilingual-e5-small
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• 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': 512, '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})
  (2): Normalize()
)

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("srikarvar/fine_tuned_model_15")
# Run inference
sentences = [
    'Who wrote the book "To Kill a Mockingbird"?',
    'Who wrote the book "1984"?',
    'At what speed does light travel?',
]
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

Binary Classification

• Dataset: pair-class-dev
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8768
cosine_accuracy_threshold	0.8267
cosine_f1	0.897
cosine_f1_threshold	0.8267
cosine_precision	0.881
cosine_recall	0.9136
cosine_ap	0.9301
dot_accuracy	0.8768
dot_accuracy_threshold	0.8267
dot_f1	0.897
dot_f1_threshold	0.8267
dot_precision	0.881
dot_recall	0.9136
dot_ap	0.9301
manhattan_accuracy	0.8732
manhattan_accuracy_threshold	8.953
manhattan_f1	0.893
manhattan_f1_threshold	9.028
manhattan_precision	0.8848
manhattan_recall	0.9012
manhattan_ap	0.9285
euclidean_accuracy	0.8768
euclidean_accuracy_threshold	0.5886
euclidean_f1	0.897
euclidean_f1_threshold	0.5886
euclidean_precision	0.881
euclidean_recall	0.9136
euclidean_ap	0.9301
max_accuracy	0.8768
max_accuracy_threshold	8.953
max_f1	0.897
max_f1_threshold	9.028
max_precision	0.8848
max_recall	0.9136
max_ap	0.9301

Binary Classification

• Dataset: pair-class-test
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8768
cosine_accuracy_threshold	0.8267
cosine_f1	0.897
cosine_f1_threshold	0.8267
cosine_precision	0.881
cosine_recall	0.9136
cosine_ap	0.9301
dot_accuracy	0.8768
dot_accuracy_threshold	0.8267
dot_f1	0.897
dot_f1_threshold	0.8267
dot_precision	0.881
dot_recall	0.9136
dot_ap	0.9301
manhattan_accuracy	0.8732
manhattan_accuracy_threshold	8.953
manhattan_f1	0.893
manhattan_f1_threshold	9.028
manhattan_precision	0.8848
manhattan_recall	0.9012
manhattan_ap	0.9285
euclidean_accuracy	0.8768
euclidean_accuracy_threshold	0.5886
euclidean_f1	0.897
euclidean_f1_threshold	0.5886
euclidean_precision	0.881
euclidean_recall	0.9136
euclidean_ap	0.9301
max_accuracy	0.8768
max_accuracy_threshold	8.953
max_f1	0.897
max_f1_threshold	9.028
max_precision	0.8848
max_recall	0.9136
max_ap	0.9301

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,476 training samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 1000 samples:

  	label	sentence1	sentence2
  type	int	string	string
  details	0: ~40.20% 1: ~59.80%	min: 6 tokens mean: 16.35 tokens max: 98 tokens	min: 4 tokens mean: 16.06 tokens max: 98 tokens

• Samples:

  label	sentence1	sentence2
  1	The ImageNet dataset is used for training models to classify images into various categories.	A model is trained using the ImageNet dataset to classify images into distinct categories.
  1	No, it doesn't exist in version 5.3.1.	Version 5.3.1 does not contain it.
  0	Can you help me with my homework?	Can you do my homework for me?

• Loss: OnlineContrastiveLoss

Evaluation Dataset

Unnamed Dataset

• Size: 276 evaluation samples
• Columns: label, sentence1, and sentence2
• Approximate statistics based on the first 276 samples:

  	label	sentence1	sentence2
  type	int	string	string
  details	0: ~41.30% 1: ~58.70%	min: 6 tokens mean: 15.56 tokens max: 87 tokens	min: 5 tokens mean: 15.34 tokens max: 86 tokens

• Samples:

  label	sentence1	sentence2
  0	What are the challenges of AI in cybersecurity?	How is AI used to enhance cybersecurity?
  1	You can find the SYSTEM log documentation on the main version. Click on the provided link to redirect to the main version of the documentation.	The SYSTEM log documentation can be accessed by clicking on the link which will take you to the main version.
  1	What is the capital of Italy?	Name the capital city of Italy

• Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• gradient_accumulation_steps: 2
• num_train_epochs: 4
• warmup_ratio: 0.1
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• eval_accumulation_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: 1.0
• num_train_epochs: 4
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: False
• fp16: False
• fp16_opt_level: 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_fused
• 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	pair-class-dev_max_ap	pair-class-test_max_ap
0	0	-	-	0.7876	-
0.2564	10	1.5794	-	-	-
0.5128	20	0.8392	-	-	-
0.7692	30	0.7812	-	-	-
1.0	39	-	0.8081	0.9138	-
1.0256	40	0.6505	-	-	-
1.2821	50	0.57	-	-	-
1.5385	60	0.3015	-	-	-
1.7949	70	0.3091	-	-	-
2.0	78	-	0.7483	0.9267	-
2.0513	80	0.3988	-	-	-
2.3077	90	0.1801	-	-	-
2.5641	100	0.1166	-	-	-
2.8205	110	0.1255	-	-	-
3.0	117	-	0.7106	0.9284	-
3.0769	120	0.2034	-	-	-
3.3333	130	0.0329	-	-	-
3.5897	140	0.0805	-	-	-
3.8462	150	0.0816	-	-	-
4.0	156	-	0.6969	0.9301	0.9301

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.0
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.34.2
• Datasets: 2.19.1
• Tokenizers: 0.19.1

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",
}