srikarvar/fine_tuned_model_10

SentenceTransformer based on srikarvar/fine_tuned_model_5

This is a sentence-transformers model finetuned from srikarvar/fine_tuned_model_5 on the json dataset. 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: srikarvar/fine_tuned_model_5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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_10")
# Run inference
sentences = [
    'Once you have completed your library script, you can generate a library card and submit it to the server.',
    'Once your library script is ready, you can create a library card and upload it to the server.',
    "It replaces the document's header.",
]
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

Information Retrieval

• Dataset: e5-cogcache-small-refined
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9821
cosine_accuracy@3	0.9821
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9821
cosine_precision@3	0.3274
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9821
cosine_recall@3	0.9821
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9898
cosine_mrr@10	0.9866
cosine_map@100	0.9866
dot_accuracy@1	0.9821
dot_accuracy@3	0.9821
dot_accuracy@5	1.0
dot_accuracy@10	1.0
dot_precision@1	0.9821
dot_precision@3	0.3274
dot_precision@5	0.2
dot_precision@10	0.1
dot_recall@1	0.9821
dot_recall@3	0.9821
dot_recall@5	1.0
dot_recall@10	1.0
dot_ndcg@10	0.9898
dot_mrr@10	0.9866
dot_map@100	0.9866

Information Retrieval

• Dataset: e5-cogcache-small-refined
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9821
cosine_accuracy@3	0.9821
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9821
cosine_precision@3	0.3274
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9821
cosine_recall@3	0.9821
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9898
cosine_mrr@10	0.9866
cosine_map@100	0.9866
dot_accuracy@1	0.9821
dot_accuracy@3	0.9821
dot_accuracy@5	1.0
dot_accuracy@10	1.0
dot_precision@1	0.9821
dot_precision@3	0.3274
dot_precision@5	0.2
dot_precision@10	0.1
dot_recall@1	0.9821
dot_recall@3	0.9821
dot_recall@5	1.0
dot_recall@10	1.0
dot_ndcg@10	0.9898
dot_mrr@10	0.9866
dot_map@100	0.9866

Training Details

Training Dataset

json

• Dataset: json
• Size: 560 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 560 samples:

  	anchor	positive
  type	string	string
  details	min: 9 tokens mean: 30.23 tokens max: 98 tokens	min: 8 tokens mean: 30.06 tokens max: 98 tokens

• Samples:

  anchor	positive
  It retrieves items from a list.	It selects items from a list.
  The goal of seasoning a cast iron pan is to create a non-stick surface and protect it from rust.	The purpose of seasoning a cast iron pan is to create a non-stick surface and prevent rust.
  The Spark manual covers topics like data analysis, machine learning, graph processing, and stream processing.	The Spark documentation covers topics such as data analysis, machine learning, graph processing, and stream processing.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 1e-05
• warmup_ratio: 0.1
• 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: 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
• learning_rate: 1e-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: 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	e5-cogcache-small-refined_cosine_map@100
0	0	-	0.9777
0.3125	10	0.0118	-
0.625	20	0.0025	-
0.9375	30	0.006	-
1.0	32	-	0.9866
1.25	40	0.0008	-
1.5625	50	0.0005	-
1.875	60	0.0011	-
2.0	64	-	0.9866
2.1875	70	0.0006	-
2.5	80	0.0003	-
2.8125	90	0.001	-
3.0	96	-	0.9866

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}