Tombiczek/all-MiniLM-L6-v2_fine-tuned-cosqa

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 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': 256, 'do_lower_case': False, 'architecture': '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("Tombiczek/all-MiniLM-L6-v2_fine-tuned-cosqa")
# Run inference
sentences = [
    'python qpushbutton resize in grid layout',
    'def resize(self, width, height):\n        """\n        Pyqt specific resize callback.\n        """\n        if not self.fbo:\n            return\n\n        # pyqt reports sizes in actual buffer size\n        self.width = width // self.widget.devicePixelRatio()\n        self.height = height // self.widget.devicePixelRatio()\n        self.buffer_width = width\n        self.buffer_height = height\n\n        super().resize(width, height)',
    'def __delitem__(self, resource):\n        """Remove resource instance from internal cache"""\n        self.__caches[type(resource)].pop(resource.get_cache_internal_key(), None)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5830, 0.0179],
#         [0.5830, 1.0000, 0.1409],
#         [0.0179, 0.1409, 1.0000]])

Evaluation

Metrics

Information Retrieval

• Dataset: cosqa-valid
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.802
cosine_accuracy@3	0.964
cosine_accuracy@5	0.992
cosine_accuracy@10	0.998
cosine_precision@10	0.0998
cosine_recall@10	0.998
cosine_ndcg@10	0.9137
cosine_mrr@10	0.8851
cosine_map@100	0.8852

Training Details

Training Dataset

Unnamed Dataset

• Size: 9,008 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 6 tokens mean: 9.61 tokens max: 23 tokens	min: 38 tokens mean: 87.19 tokens max: 256 tokens

• Samples:

  sentence_0	sentence_1
  python save ndarray to json	def deserialize_ndarray_npy(d): """ Deserializes a JSONified :obj:numpy.ndarray that was created using numpy's :obj:save function. Args: d (:obj:dict): A dictionary representation of an :obj:ndarray object, created using :obj:numpy.save. Returns: An :obj:ndarray object. """ with io.BytesIO() as f: f.write(json.loads(d['npy']).encode('latin-1')) f.seek(0) return np.load(f)
  python delay between loop	def seconds(num): """ Pause for this many seconds """ now = pytime.time() end = now + num until(end)
  python how to read a text file to dict	def read_dict_from_file(file_path): """ Read a dictionary of strings from a file """ with open(file_path) as file: lines = file.read().splitlines() obj = {} for line in lines: key, value = line.split(':', maxsplit=1) obj[key] = eval(value) return obj

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 10
• fp16: True
• 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: 10
• 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
• 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: 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}
• parallelism_config: 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
• project: huggingface
• trackio_space_id: trackio
• 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
• hub_revision: None
• 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
• include_tokens_per_second: False
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	cosqa-valid_cosine_ndcg@10
0.8881	500	0.0925	-
1.0	563	-	0.8889
1.7762	1000	0.0536	-
2.0	1126	-	0.8955
2.6643	1500	0.0419	-
3.0	1689	-	0.8999
3.5524	2000	0.0365	-
4.0	2252	-	0.9087
4.4405	2500	0.0308	-
5.0	2815	-	0.9060
5.3286	3000	0.0283	-
6.0	3378	-	0.9085
6.2167	3500	0.0263	-
7.0	3941	-	0.9116
7.1048	4000	0.0227	-
7.9929	4500	0.0234	-
8.0	4504	-	0.9119
8.8810	5000	0.0214	-
9.0	5067	-	0.9066
9.7691	5500	0.0216	-
10.0	5630	-	0.9137

Framework Versions

• Python: 3.10.18
• Sentence Transformers: 5.1.2
• Transformers: 4.57.1
• PyTorch: 2.9.0
• Accelerate: 1.11.0
• Datasets: 4.3.0
• Tokenizers: 0.22.1

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}
}