LorMolf/mnrl-octopus-overlap-roberta-base

SentenceTransformer based on FacebookAI/roberta-base

This is a sentence-transformers model finetuned from FacebookAI/roberta-base. It maps sentences & paragraphs to a 768-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: FacebookAI/roberta-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("LorMolf/mnrl-octopus-overlap-roberta-base")
# Run inference
sentences = [
    "What's the proper way to set up a 'Coffee Break' event starting at 2023-09-05-15-00 and finishing at 2023-09-05-15-15?",
    'def create_calendar_event(title, start_time, end_time):\n    """\n    Schedules a new event in the calendar.\n\n    Parameters:\n    - title (str): Event title.\n    - start_time (str): Event start time as a string in ISO 8601 format "YYYY-MM-DD-HH-MM". For example, "2022-12-31-23-59" for 11:59 PM on December 31, 2022.\n    - end_time (str): Event end time as a string in ISO 8601 format "YYYY-MM-DD-HH-MM". Must be after start_time. For example, "2023-01-01-00-00" for 12:00 AM on January 1, 2023.\n\n    Returns:\n    """',
    'def send_email(recipient, title, content):\n    """\n    Sends an email to a specified recipient with a given title and content.\n\n    Parameters:\n    - recipient (str): The email address of the recipient.\n    - title (str): The subject line of the email. This is a brief summary or title of the email\'s purpose or content.\n    - content (str): The main body text of the email. It contains the primary message, information, or content that is intended to be communicated to the recipient.\n\n    Returns:\n    """',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Device Aware Information Retrieval

• Dataset: dev
• Evaluated with src.port.retrieval_evaluator.DeviceAwareInformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.9231
cosine_accuracy@3	0.9744
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9231
cosine_precision@3	0.3248
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9231
cosine_recall@3	0.9744
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@1	0.9231
cosine_ndcg@3	0.9554
cosine_ndcg@5	0.9654
cosine_ndcg@10	0.9654
cosine_mrr@10	0.9538
cosine_map@100	0.9538

Training Details

Training Dataset

Unnamed Dataset

• Size: 480 training samples
• Columns: sentence_0, sentence_1, and sentence_2
• Approximate statistics based on the first 480 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  details	min: 9 tokens mean: 22.01 tokens max: 44 tokens	min: 73 tokens mean: 113.7 tokens max: 195 tokens	min: 73 tokens mean: 114.92 tokens max: 195 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  How do I disable the Do Not Disturb feature on my device?	def enable_do_not_disturb(enabled): """ Toggles the Do Not Disturb mode on or off. Parameters: - enabled (bool): True to enable, False to disable Do Not Disturb mode. Returns: """	def make_phone_call(phone_number): """ Initiates a phone call to the given phone number. It can handle both international and domestic numbers. Parameters: - phone_number (str): phone number of the contact. The phone number should be provided in a standard format, preferably in E.164 format (e.g., +12345678900 for an international format). Returns: """
  Please send a text to 'John Smith' saying 'Meeting is rescheduled to 3 PM, let everyone know.'	def send_text_message(contact_name, message): """ Sends a text message to the specified contact. Parameters: - contact_name (str): The name of the recipient contact. - message (str): The content of the message to be sent. This is what the recipient will receive. Returns: """	def take_a_photo(camera): """ Captures a photo using the specified camera and resolution settings. Parameters: - camera (str): Specifies the camera to use. Can be 'front' or 'back'. The default is 'back'. Returns: - str: The string contains the file path of the captured photo if successful, or an error message if not. Example: '/storage/emulated/0/Pictures/MyApp/IMG_20240310_123456.jpg' """
  Could you create a contact for my boss, Mr. David Anderson? His contact number is +12347654321.	def create_contact(name, phone_number): """ Creates a new contact entry in the device's address book. Parameters: - name (str): Full name of the contact. This should include first and last name. - phone_number (str): phone number of the contact. The phone number should be provided in a standard format, preferably in E.164 format (e.g., +12345678900 for an international format). Returns: """	def play_video_on_nest_hub(video_service, video_name): """ Streams video on a Google Nest Hub device from a specified service. Parameters: - video_service (str): Video streaming service name. - video_name (str): Video playlist name to play. Returns: """

• 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: 2
• per_device_eval_batch_size: 2
• num_train_epochs: 1
• 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: 2
• per_device_eval_batch_size: 2
• 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: 1.0
• num_train_epochs: 1
• 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: 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}
• tp_size: 0
• 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
• 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	dev_cosine_ndcg@10
-1	-1	0.3941
0.2	48	0.8413
0.4	96	0.9286
0.6	144	0.9554
0.8	192	0.9654
1.0	240	0.9654

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 4.0.2
• Transformers: 4.51.2
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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}
}