metadata

base_model: intfloat/multilingual-e5-small
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:546
  - loss:TripletLoss
widget:
  - source_sentence: How to cook a turkey?
    sentences:
      - How to make a turkey sandwich?
      - World's biggest desert by area
      - Steps to roast a turkey
  - source_sentence: What is the best way to learn a new language?
    sentences:
      - Author of the play 'Hamlet'
      - What is the fastest way to travel?
      - How can I effectively learn a new language?
  - source_sentence: Who wrote 'To Kill a Mockingbird'?
    sentences:
      - Who wrote 'The Great Gatsby'?
      - How can I effectively save money?
      - Author of 'To Kill a Mockingbird'
  - source_sentence: Who was the first person to climb Mount Everest?
    sentences:
      - Steps to visit the Great Wall of China
      - Who was the first person to climb K2?
      - First climber to reach the summit of Everest
  - source_sentence: What is the capital city of Canada?
    sentences:
      - First circumnavigator of the globe
      - What is the capital of Canada?
      - What is the capital city of Australia?
model-index:
  - name: SentenceTransformer based on intfloat/multilingual-e5-small
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: triplet validation
          type: triplet-validation
        metrics:
          - type: cosine_accuracy
            value: 0.9836065573770492
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.01639344262295082
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.9836065573770492
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.9836065573770492
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.9836065573770492
            name: Max Accuracy

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("srikarvar/multilingual-e5-small-triplet-final-2")
# Run inference
sentences = [
    'What is the capital city of Canada?',
    'What is the capital of Canada?',
    'What is the capital city of Australia?',
]
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

Triplet

Dataset: triplet-validation
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9836
dot_accuracy	0.0164
manhattan_accuracy	0.9836
euclidean_accuracy	0.9836
max_accuracy	0.9836

Training Details

Training Dataset

Unnamed Dataset

Size: 546 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 10.78 tokens max: 22 tokens	min: 4 tokens mean: 9.52 tokens max: 19 tokens	min: 6 tokens mean: 10.75 tokens max: 22 tokens

Samples:

anchor	positive	negative
`What is the capital of Brazil?`	`Capital city of Brazil`	`What is the capital of Argentina?`
`How do I install Python on my computer?`	`How do I set up Python on my PC?`	`How do I uninstall Python on my computer?`
`How do I apply for a credit card?`	`How do I get a credit card?`	`How do I cancel a credit card?`

Loss: TripletLoss with these parameters:

{
    "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
    "triplet_margin": 0.7
}

Evaluation Dataset

Unnamed Dataset

Size: 61 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 7 tokens mean: 10.66 tokens max: 16 tokens	min: 5 tokens mean: 9.43 tokens max: 14 tokens	min: 6 tokens mean: 10.54 tokens max: 17 tokens

Samples:

anchor	positive	negative
`How to create a podcast?`	`Steps to start a podcast`	`How to create a vlog?`
`How many states are there in the USA?`	`Total number of states in the United States`	`How many provinces are there in Canada?`
`What is the population of India?`	`How many people live in India?`	`What is the population of China?`

Loss: TripletLoss with these parameters:

{
    "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
    "triplet_margin": 0.7
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
gradient_accumulation_steps: 2
learning_rate: 3e-06
weight_decay: 0.01
num_train_epochs: 22
lr_scheduler_type: cosine
warmup_steps: 50
load_best_model_at_end: True
optim: adamw_torch_fused

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 2
eval_accumulation_steps: None
learning_rate: 3e-06
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 22
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 50
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: 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: True
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_fused
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: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	triplet-validation_max_accuracy
1.0	9	-	0.6381	-
1.1111	10	0.6743	-	-
2.0	18	-	0.6262	-
2.2222	20	0.6608	-	-
3.0	27	-	0.6066	-
3.3333	30	0.6517	-	-
4.0	36	-	0.5795	-
4.4444	40	0.6288	-	-
5.0	45	-	0.5453	-
5.5556	50	0.5934	-	-
6.0	54	-	0.5052	-
6.6667	60	0.5708	-	-
7.0	63	-	0.4652	-
7.7778	70	0.5234	-	-
8.0	72	-	0.4270	-
8.8889	80	0.5041	-	-
9.0	81	-	0.3918	-
10.0	90	0.4666	0.3589	-
11.0	99	-	0.3292	-
11.1111	100	0.4554	-	-
12.0	108	-	0.3029	-
12.2222	110	0.4208	-	-
13.0	117	-	0.2797	-
13.3333	120	0.4076	-	-
14.0	126	-	0.2607	-
14.4444	130	0.3958	-	-
15.0	135	-	0.2471	-
15.5556	140	0.3881	-	-
16.0	144	-	0.2365	-
16.6667	150	0.3595	-	-
17.0	153	-	0.2286	-
17.7778	160	0.354	-	-
18.0	162	-	0.2232	-
18.8889	170	0.3506	-	-
19.0	171	-	0.2199	-
20.0	180	0.3555	0.2182	-
21.0	189	-	0.2175	-
21.1111	190	0.3526	-	-
22.0	198	-	0.2174	0.9836

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.32.1
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",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification}, 
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}