metadata

language:
  - en
license: apache-2.0
library_name: sentence-transformers
datasets:
  - davanstrien/similarity-dataset-sc2-8b
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:n<1K
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/mpnet-base
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
widget:
  - source_sentence: >-
      Write a Python function that counts the number of even numbers in a given
      list of integers or floats
    sentences:
      - >-
        Write a Python function that returns the number of even numbers in a
        list.
      - >-
        Create a Python function that adds up all the numbers in a given list.
        The function should support lists containing only positive integers.
      - >-
        Write a Python function that converts a JSON string into a Python
        dictionary using the json module and returns it.
  - source_sentence: >-
      Develop a Python function to validate whether a given string represents a
      valid IPv4 address or not.
    sentences:
      - >-
        Create a Python function to validate a string `s` as an IPv4 address.
        The function should return `True` if `s` is a valid IPv4 address, and
        `False` otherwise.
      - >-
        Write a Python function to find the key with the highest value in a
        dictionary. The function should return the value of the key if it exists
      - >-
        Write a Python function that, given a dictionary `d` and an integer `k`,
        returns the sum of the values of the first `k` keys in `d`.
  - source_sentence: >-
      Write a Python function to create a list of numbers with exactly one even
      number and n-1 odd numbers
    sentences:
      - >-
        Write a Python function that returns the number of even numbers in a
        list.
      - >-
        Write a Python function that recursively traverses a given folder
        structure and returns the absolute path of all files that end with
        ".txt".
      - >-
        Write a Python decorator function that overrides the docstring of the
        decorated function, and stores the old docstring and other metadata in a
        `_doc_metadata` attribute of the function.
  - source_sentence: >-
      Implement a Python function that prints the first character of a string
      using its indexing feature. 
    sentences:
      - >-
        Write a Python function that takes a string as a parameter and returns
        the first character of the string.
      - >-
        Write a Python function that checks if the bit at position `bit` is set
        in the given `integer`. This function should return a boolean value.
      - >-
        Write a Python function `floor_division(x: int, y: int) -> int` that
        divides two integers `x` and `y` and returns the largest whole number
        less than or equal to the result.
  - source_sentence: >-
      Write a Python function that takes a MIDI note number and returns the
      corresponding piano key number.
    sentences:
      - >-
        Create a Python function that translates MIDI note numbers into piano
        key numbers, facilitating music generation.
      - >-
        Write a Python function that accepts a dictionary and returns a set of
        distinct values. If a key maps to an empty list, return an empty set.
      - >-
        Write a Python function `join_strings_with_comma(lst)` that takes a list
        of strings and returns a single string with all the strings from the
        list, separated by commas.
pipeline_tag: sentence-similarity
co2_eq_emissions:
  emissions: 2.213004168952992
  energy_consumed: 0.006336878829164133
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: Intel(R) Xeon(R) CPU @ 2.20GHz
  ram_total_size: 62.804237365722656
  hours_used: 0.049
  hardware_used: 1 x NVIDIA L4
model-index:
  - name: MPNet base trained on AllNLI triplets
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: code similarity dev
          type: code-similarity-dev
        metrics:
          - type: cosine_accuracy
            value: 0.934010152284264
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.07106598984771574
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.934010152284264
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.9390862944162437
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.9390862944162437
            name: Max Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.934010152284264
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.07106598984771574
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.934010152284264
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.9390862944162437
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.9390862944162437
            name: Max Accuracy

MPNet base trained on AllNLI triplets

This is a sentence-transformers model finetuned from microsoft/mpnet-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: microsoft/mpnet-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

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: MPNetModel 
  (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("davanstrien/code-prompt-similarity-model")
# Run inference
sentences = [
    'Write a Python function that takes a MIDI note number and returns the corresponding piano key number.',
    'Create a Python function that translates MIDI note numbers into piano key numbers, facilitating music generation.',
    'Write a Python function that accepts a dictionary and returns a set of distinct values. If a key maps to an empty list, return an empty set.',
]
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

Triplet

Dataset: code-similarity-dev
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.934
dot_accuracy	0.0711
manhattan_accuracy	0.934
euclidean_accuracy	0.9391
max_accuracy	0.9391

Triplet

Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.934
dot_accuracy	0.0711
manhattan_accuracy	0.934
euclidean_accuracy	0.9391
max_accuracy	0.9391

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 10
warmup_ratio: 0.1
bf16: True
batch_sampler: no_duplicates

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
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: 10
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: True
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	loss	code-similarity-dev_max_accuracy	max_accuracy
0	0	-	-	0.8680	-
2.0	100	0.6379	0.1845	0.9340	-
4.0	200	0.0399	0.1577	0.9543	-
6.0	300	0.0059	0.1577	0.9543	-
8.0	400	0.0018	0.1662	0.9492	-
10.0	500	0.0009	0.1643	0.9391	0.9391

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.006 kWh
Carbon Emitted: 0.002 kg of CO2
Hours Used: 0.049 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA L4
CPU Model: Intel(R) Xeon(R) CPU @ 2.20GHz
RAM Size: 62.80 GB

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0+cu121
Accelerate: 0.30.1
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}
}