multilingual-e5-small-finetuned / README.md

Nada-10

Add new SentenceTransformer model.

29e1846 verified over 1 year ago

preview code

raw

history blame contribute delete

15.4 kB

metadata

base_model: intfloat/multilingual-e5-small
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:800
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Can you provide the definition of deaerating chamber?
    sentences:
      - 冷却水中に含まれる泥砂を沈澱させる池。
      - 脱気室の上部にあって、溶存ガスを分離する室。
      - 制御系の状態を変えようとする外的作用。
  - source_sentence: Explain the definition of sodium phosphate dibasic.
    sentences:
      - 作用は、第３リン酸ソーダと同様であるがアルカリ性は弱い。
      - タービン起動停止時または主油ポンプが異常の場合に自動起動し制御油および軸受油を供給するポンプ。
      - 内筒の外側における空気の流れの方向と燃焼の進行する方向とが逆向きになっている燃焼器。
  - source_sentence: 抽気 をどのように定義しますか？
    sentences:
      - 所内電源喪失時に密封油制御装置の電源を確保するための直流電動機駆動の交流発電機。
      - 他に使用する目的で圧縮機の出口側若しくは圧縮過程の途中から気体を抜き出すこと。又はそのようにし て抜き出された気体。
      - >-
        排ガス中の酸素の割合を示すものであり、連続指示ができるためボイラの燃焼管理上重要な計器で、Eco出口のガスO2その他のO２の指示を与える。動作原理は水素との燃焼熱量によって算出される燃焼式、及びO２の磁化率が大きいことを利用した磁気式がある。
  - source_sentence: What is the explanation of outer casing?
    sentences:
      - 二重構造のケーシングで、直接高圧蒸気にふれない外側のケーシング。
      - 伸縮自在継手のことで、タービン低圧排気室と復水器との継目に使用してある。これにより膨張収縮を吸収し本体と管束間の不等の膨張歪を減少する。
      - 操作信号を受けて信号に見合った開度に自動操作される弁。火力発電所弁類名称基準参照。
  - source_sentence: Describe the meaning of diesel generator panel.
    sentences:
      - ユニットのタイプ別にｐＨ、シリカ、電導率、溶存酸素量等の目標値を定めたもの。
      - 取水口などのスクリーンを制御する盤。
      - ディーゼル発電機の制御、操作、監視などを行う盤。

SentenceTransformer based on intfloat/multilingual-e5-small

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-small. 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: intfloat/multilingual-e5-small
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 tokens
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: 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("Nada-10/multilingual-e5-small-finetuned")
# Run inference
sentences = [
    'Describe the meaning of diesel generator panel.',
    'ディーゼル発電機の制御、操作、監視などを行う盤。',
    '取水口などのスクリーンを制御する盤。',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 800 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 7 tokens
mean: 12.91 tokens
max: 29 tokens

min: 8 tokens
mean: 26.73 tokens
max: 86 tokens

	anchor	positive
type	string	string
details	min: 7 tokens mean: 12.91 tokens max: 29 tokens	min: 8 tokens mean: 26.73 tokens max: 86 tokens

Samples:

anchor	positive
`火力発電所の定義を説明してください。`	`石油、石炭、天然ガス、高炉ガスなどのもつ熱エネルギーを利用して発電するプラント。`
`What does the term steam power plant refer to?`	`蒸気タービンにより発電するプラント。`
`ガスタービン発電所の機能は何ですか？`	`ガスタービンにより発電するプラント。`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 1,008 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 7 tokens
mean: 13.45 tokens
max: 29 tokens

min: 8 tokens
mean: 28.35 tokens
max: 123 tokens

	anchor	positive
type	string	string
details	min: 7 tokens mean: 13.45 tokens max: 29 tokens	min: 8 tokens mean: 28.35 tokens max: 123 tokens

Samples:

anchor	positive
`What is the explanation of ash gate?`	`アッシュホッパからクリンカを排出するゲート。`
`クリンカクラッシャをどのように定義しますか？`	`クリンカを適当な大きさに破砕する機械。`
`What is meant by jet pump?`	`圧力水を噴射させクリンカを水力輸送するポンプ。`

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: 16
per_device_eval_batch_size: 16
num_train_epochs: 5
warmup_ratio: 0.2
fp16: 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: 5
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.2
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
eval_on_start: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
2.0	100	0.8734	1.4281
4.0	200	0.3795	1.4617

Framework Versions

Python: 3.11.7
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cpu
Accelerate: 0.32.1
Datasets: 2.20.0
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}
}