README.md

metadata

language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:43371
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
widget:
  - source_sentence: ' New Kids on the Block: Step by Step (1990/I)  Step closer to the New Kids on the Block as they share their newest songs, their hottest performances, and their most personal thoughts. Join the guys as they look at where they came from, where they are right now, and where they''re headed - step by step.'
    sentences:
      - Rare
      - Rare
      - thriller
  - source_sentence: ' "Vampirism Bites" (2010)  Vampire fan girl Belle always dreamed of becoming a vampire, and finally got her wish on a blind date. She quickly discovers the life of a vampire is not what books, movies and TV have told her, and learns that Vampirism is not a 24/7 sexual and romantic fantasy. In fact, Vampirism Bites.'
    sentences:
      - thriller
      - comedy
      - Rare
  - source_sentence: ' O Candidato Vieira (2005)  A feature documentary about satirical rock star Manuel Joăo Vieira who ran as a candidate for the Presidency of Portugal in 2001. Altough he didn''t collect the number of signatures needed to officially put him on the ballots, Vieira''s surreal campaign appearances on television talk shows, radio and concerts took the country by storm and left everybody laughing. A political, comedic and musical documentary!'
    sentences:
      - documentary
      - short
      - short
  - source_sentence: ' Ani DiFranco: Live at Babeville (2008)  On September 11 and 12, 2007, Ani DiFranco and her band (Allison Miller on drums, Todd Sickafoose on bass and Mike Dillon on vibes and percussion) played two sold-out shows before a hometown audience in Buffalo, New York. What made those nights so special wasn''t just the music-that''s always special at an Ani show-but the fact that she was playing the inaugural shows in her very own venue, "Babeville". Now the highlights of the two shows are available on a single DVD featuring eighteen songs (two of which have not yet appeared on studio albums), plus bonus sound check and interview footage, all shot in high definition video and 5.1 surround sound. The result is a must-have memento of Ani at her finest-onstage, playing her guitar and singing with the passion, intensity, and joy that have made her a legend.'
    sentences:
      - drama
      - Rare
      - documentary
  - source_sentence: ' "Oliver Twist" (1985)  In a storm, in a workhouse, to a nameless woman, young Oliver Twist is born into parish care where he''s overworked and underfed. As he grows older his adventures take him from the countryside to London, through harsh treatment, kindness, an undertaker, and a thieves'' dens, where he makes friends and enemies. But all the time he is pursued by the mysterious Monks, who hires Fagin to turn Oliver into a thief. Oliver is rescued by chance and kind friends. But it''s a puzzle of legitimacy, inheritance, and identity that Oliver''s friends must attempt to unravel before Monks can destroy Oliver.'
    sentences:
      - documentary
      - drama
      - drama
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.900683492678328
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.601991593837738
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.4642871879513101
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.520057201385498
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.4201015531660693
            name: Cosine Precision
          - type: cosine_recall
            value: 0.5188600940699069
            name: Cosine Recall
          - type: cosine_ap
            value: 0.46368250557502916
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.900683492678328
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 0.6019916534423828
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.4642871879513101
            name: Dot F1
          - type: dot_f1_threshold
            value: 0.5200573205947876
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.4201015531660693
            name: Dot Precision
          - type: dot_recall
            value: 0.5188600940699069
            name: Dot Recall
          - type: dot_ap
            value: 0.4636826492476884
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.900304343816287
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 13.547416687011719
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.45818772856562373
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 15.149662017822266
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.40953003559235857
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.5199667988564051
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.45787992811626
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.900683492678328
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 0.8921977281570435
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.4642871879513101
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 0.979737401008606
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.4201015531660693
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.5188600940699069
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.46368245984449313
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.900683492678328
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 13.547416687011719
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.4642871879513101
            name: Max F1
          - type: max_f1_threshold
            value: 15.149662017822266
            name: Max F1 Threshold
          - type: max_precision
            value: 0.4201015531660693
            name: Max Precision
          - type: max_recall
            value: 0.5199667988564051
            name: Max Recall
          - type: max_ap
            value: 0.4636826492476884
            name: Max Ap
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.6381767038642442
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.3618232961357558
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.6227289495527069
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.6381767038642442
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.6381767038642442
            name: Max Accuracy

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

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the imdb-triplet 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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • imdb-triplet

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}) 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("celik-muhammed/all-MiniLM-L6-v2-finetuned-imdb")
# Run inference
sentences = [
    ' "Oliver Twist" (1985)  In a storm, in a workhouse, to a nameless woman, young Oliver Twist is born into parish care where he\'s overworked and underfed. As he grows older his adventures take him from the countryside to London, through harsh treatment, kindness, an undertaker, and a thieves\' dens, where he makes friends and enemies. But all the time he is pursued by the mysterious Monks, who hires Fagin to turn Oliver into a thief. Oliver is rescued by chance and kind friends. But it\'s a puzzle of legitimacy, inheritance, and identity that Oliver\'s friends must attempt to unravel before Monks can destroy Oliver.',
    'drama',
    'documentary',
]
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

• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9007
cosine_accuracy_threshold	0.602
cosine_f1	0.4643
cosine_f1_threshold	0.5201
cosine_precision	0.4201
cosine_recall	0.5189
cosine_ap	0.4637
dot_accuracy	0.9007
dot_accuracy_threshold	0.602
dot_f1	0.4643
dot_f1_threshold	0.5201
dot_precision	0.4201
dot_recall	0.5189
dot_ap	0.4637
manhattan_accuracy	0.9003
manhattan_accuracy_threshold	13.5474
manhattan_f1	0.4582
manhattan_f1_threshold	15.1497
manhattan_precision	0.4095
manhattan_recall	0.52
manhattan_ap	0.4579
euclidean_accuracy	0.9007
euclidean_accuracy_threshold	0.8922
euclidean_f1	0.4643
euclidean_f1_threshold	0.9797
euclidean_precision	0.4201
euclidean_recall	0.5189
euclidean_ap	0.4637
max_accuracy	0.9007
max_accuracy_threshold	13.5474
max_f1	0.4643
max_f1_threshold	15.1497
max_precision	0.4201
max_recall	0.52
max_ap	0.4637

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.6382
dot_accuracy	0.3618
manhattan_accuracy	0.6227
euclidean_accuracy	0.6382
max_accuracy	0.6382

Training Details

Training Dataset

imdb-triplet

• Dataset: imdb-triplet
• Size: 43,371 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 31 tokens mean: 129.65 tokens max: 256 tokens	min: 3 tokens mean: 3.0 tokens max: 3 tokens

• Samples:

  anchor	positive
  A Metafísica dos Chocolates (1967) Beautiful girls (pre-teens, adolescents, and young women) in street scenes and one of them visiting a chocolate factory, where all the workers are young women, too. A poetic text and an extract from a major Portuguese poet, convey to us the sensual feeling of choosing, unwrapping, and munching chocolate.	short
  Thai Jashe! (2016) Thai Jashe! is an upcoming Gujarati film written and directed by Nirav Barot. It is about the struggles of a middle class man to achieve his goals in the metro-city Ahmedabad. The film stars Manoj Joshi, Malhar Thakar and Monal Gajjar.	drama
  Vuelco (2005) A teenage boy rides out of town to meet a a girl in the countryside. She is deaf, and he explains the different means he uses to get her attention when she has not seen him. Then they say goodbye, with one poignant hug and a desperate yell punctuating their final farewell.	short

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• num_train_epochs: 5
• warmup_ratio: 0.1
• fp16: True
• batch_sampler: no_duplicates
• 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: 256
• per_device_eval_batch_size: 256
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• 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: 5
• 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: 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: round_robin

Training Logs

Epoch	Step	Training Loss	max_accuracy	max_ap
0	0	-	0.6382	0.2004
0.5882	100	1.7867	-	0.3542
1.1765	200	1.3073	-	0.4564
1.7647	300	1.266	-	0.3862
2.3529	400	1.1889	-	0.4011
2.9412	500	1.1554	-	0.4398
3.5294	600	1.1558	-	0.4386
4.1176	700	1.1555	-	0.4566
4.7059	800	1.0835	-	0.4637

Framework Versions

• Python: 3.10.13
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2
• Accelerate: 0.30.1
• Datasets: 2.19.2
• 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}
}