metadata

base_model: intfloat/multilingual-e5-small
datasets: []
language: []
library_name: sentence-transformers
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
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:916
  - loss:OnlineContrastiveLoss
widget:
  - source_sentence: Ways to enhance memory retention
    sentences:
      - How to improve memory?
      - What is the currency of China?
      - How do I replace a flat tire?
  - source_sentence: Why it's essential to maintain a balanced diet
    sentences:
      - What is the importance of a balanced diet?
      - What is the population of Canada?
      - How to create a website from scratch?
  - source_sentence: What is the chemical formula for methanol?
    sentences:
      - What is the highest mountain in North America?
      - What are the advantages of electric cars over gasoline vehicles?
      - What is the chemical formula for ethanol?
  - source_sentence: How is photosynthesis carried out?
    sentences:
      - What is the currency of the United States?
      - What is the capital of Norway?
      - How does photosynthesis work?
  - source_sentence: How is the weather today?
    sentences:
      - Who invented the airplane?
      - What is the weather like today?
      - Who was the first female Prime Minister of the UK?
model-index:
  - name: SentenceTransformer based on intfloat/multilingual-e5-small
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: pair class dev
          type: pair-class-dev
        metrics:
          - type: cosine_accuracy
            value: 0.9388646288209607
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.7886800765991211
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.9411764705882353
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.7886800765991211
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.9572649572649573
            name: Cosine Precision
          - type: cosine_recall
            value: 0.9256198347107438
            name: Cosine Recall
          - type: cosine_ap
            value: 0.973954773457217
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.9388646288209607
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 0.7886800765991211
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.9411764705882353
            name: Dot F1
          - type: dot_f1_threshold
            value: 0.7886800765991211
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.9572649572649573
            name: Dot Precision
          - type: dot_recall
            value: 0.9256198347107438
            name: Dot Recall
          - type: dot_ap
            value: 0.973954773457217
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.9388646288209607
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 10.132380485534668
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.9411764705882353
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 10.132380485534668
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.9572649572649573
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.9256198347107438
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.9728889947842537
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.9388646288209607
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 0.6500871777534485
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.9411764705882353
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 0.6500871777534485
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.9572649572649573
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.9256198347107438
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.973954773457217
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.9388646288209607
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 10.132380485534668
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.9411764705882353
            name: Max F1
          - type: max_f1_threshold
            value: 10.132380485534668
            name: Max F1 Threshold
          - type: max_precision
            value: 0.9572649572649573
            name: Max Precision
          - type: max_recall
            value: 0.9256198347107438
            name: Max Recall
          - type: max_ap
            value: 0.973954773457217
            name: Max Ap
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: pair class test
          type: pair-class-test
        metrics:
          - type: cosine_accuracy
            value: 0.9388646288209607
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.8207830190658569
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.9421487603305785
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.8207830190658569
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.9421487603305785
            name: Cosine Precision
          - type: cosine_recall
            value: 0.9421487603305785
            name: Cosine Recall
          - type: cosine_ap
            value: 0.9731728800864022
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.9388646288209607
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 0.8207829594612122
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.9421487603305785
            name: Dot F1
          - type: dot_f1_threshold
            value: 0.8207829594612122
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.9421487603305785
            name: Dot Precision
          - type: dot_recall
            value: 0.9421487603305785
            name: Dot Recall
          - type: dot_ap
            value: 0.9731728800864022
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.9344978165938864
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 9.387104988098145
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.9382716049382717
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 9.516077041625977
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.9344262295081968
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.9421487603305785
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.9720713665843098
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.9388646288209607
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 0.5986893177032471
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.9421487603305785
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 0.5986893177032471
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.9421487603305785
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.9421487603305785
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.9731728800864022
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.9388646288209607
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 9.387104988098145
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.9421487603305785
            name: Max F1
          - type: max_f1_threshold
            value: 9.516077041625977
            name: Max F1 Threshold
          - type: max_precision
            value: 0.9421487603305785
            name: Max Precision
          - type: max_recall
            value: 0.9421487603305785
            name: Max Recall
          - type: max_ap
            value: 0.9731728800864022
            name: Max Ap

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/fine_tuned_model_1")
# Run inference
sentences = [
    'How is the weather today?',
    'What is the weather like today?',
    'Who was the first female Prime Minister of the UK?',
]
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

Dataset: pair-class-dev
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9389
cosine_accuracy_threshold	0.7887
cosine_f1	0.9412
cosine_f1_threshold	0.7887
cosine_precision	0.9573
cosine_recall	0.9256
cosine_ap	0.974
dot_accuracy	0.9389
dot_accuracy_threshold	0.7887
dot_f1	0.9412
dot_f1_threshold	0.7887
dot_precision	0.9573
dot_recall	0.9256
dot_ap	0.974
manhattan_accuracy	0.9389
manhattan_accuracy_threshold	10.1324
manhattan_f1	0.9412
manhattan_f1_threshold	10.1324
manhattan_precision	0.9573
manhattan_recall	0.9256
manhattan_ap	0.9729
euclidean_accuracy	0.9389
euclidean_accuracy_threshold	0.6501
euclidean_f1	0.9412
euclidean_f1_threshold	0.6501
euclidean_precision	0.9573
euclidean_recall	0.9256
euclidean_ap	0.974
max_accuracy	0.9389
max_accuracy_threshold	10.1324
max_f1	0.9412
max_f1_threshold	10.1324
max_precision	0.9573
max_recall	0.9256
max_ap	0.974

Binary Classification

Dataset: pair-class-test
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9389
cosine_accuracy_threshold	0.8208
cosine_f1	0.9421
cosine_f1_threshold	0.8208
cosine_precision	0.9421
cosine_recall	0.9421
cosine_ap	0.9732
dot_accuracy	0.9389
dot_accuracy_threshold	0.8208
dot_f1	0.9421
dot_f1_threshold	0.8208
dot_precision	0.9421
dot_recall	0.9421
dot_ap	0.9732
manhattan_accuracy	0.9345
manhattan_accuracy_threshold	9.3871
manhattan_f1	0.9383
manhattan_f1_threshold	9.5161
manhattan_precision	0.9344
manhattan_recall	0.9421
manhattan_ap	0.9721
euclidean_accuracy	0.9389
euclidean_accuracy_threshold	0.5987
euclidean_f1	0.9421
euclidean_f1_threshold	0.5987
euclidean_precision	0.9421
euclidean_recall	0.9421
euclidean_ap	0.9732
max_accuracy	0.9389
max_accuracy_threshold	9.3871
max_f1	0.9421
max_f1_threshold	9.5161
max_precision	0.9421
max_recall	0.9421
max_ap	0.9732

Training Details

Training Dataset

Unnamed Dataset

Size: 916 training samples
Columns: label, sentence2, and sentence1
Approximate statistics based on the first 1000 samples:
label sentence2 sentence1
type int string string
details
0: ~49.56%
1: ~50.44%

min: 4 tokens
mean: 10.32 tokens
max: 22 tokens

min: 6 tokens
mean: 10.92 tokens
max: 22 tokens

	label	sentence2	sentence1
type	int	string	string
details	0: ~49.56% 1: ~50.44%	min: 4 tokens mean: 10.32 tokens max: 22 tokens	min: 6 tokens mean: 10.92 tokens max: 22 tokens

Samples:

label	sentence2	sentence1
`1`	`What are the potential side effects of this medication?`	`What are the side effects of this drug?`
`0`	`How to fix a torn pocket?`	`How to fix a broken zipper?`
`0`	`How to make a chocolate chip cookie dough?`	`How to bake a chocolate chip cookie?`

Loss: OnlineContrastiveLoss

Evaluation Dataset

Unnamed Dataset

Size: 229 evaluation samples
Columns: label, sentence2, and sentence1
Approximate statistics based on the first 1000 samples:
label sentence2 sentence1
type int string string
details
0: ~47.16%
1: ~52.84%

min: 4 tokens
mean: 9.95 tokens
max: 16 tokens

min: 6 tokens
mean: 10.81 tokens
max: 20 tokens

	label	sentence2	sentence1
type	int	string	string
details	0: ~47.16% 1: ~52.84%	min: 4 tokens mean: 9.95 tokens max: 16 tokens	min: 6 tokens mean: 10.81 tokens max: 20 tokens

Samples:

label	sentence2	sentence1
`0`	`What methods are used to measure a nation's GDP?`	`How is the GDP of a country measured?`
`0`	`What is the currency of Japan?`	`What is the currency of China?`
`1`	`Steps to cultivate tomatoes at home`	`How to grow tomatoes in a garden?`

Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
gradient_accumulation_steps: 2
weight_decay: 0.01
num_train_epochs: 8
warmup_ratio: 0.1
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

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: 5e-05
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 8
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: 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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	pair-class-dev_max_ap	pair-class-test_max_ap
0	0	-	-	0.7130	-
0.6897	10	3.0972	-	-	-
1.0345	15	-	0.8033	0.9272	-
1.3448	20	1.0451	-	-	-
2.0345	30	0.5786	0.4910	0.9680	-
2.6897	40	0.2996	-	-	-
3.0345	45	-	0.4487	0.9731	-
3.3448	50	0.0901	-	-	-
4.0345	60	0.067	0.4115	0.9732	-
4.6897	70	0.0729	-	-	-
5.0345	75	-	0.4543	0.9727	-
5.3448	80	0.0453	-	-	-
6.0345	90	0.0637	0.4249	0.9736	-
6.6897	100	0.0388	-	-	-
7.0345	105	-	0.4223	0.9740	-
7.3448	110	0.0382	-	-	-
7.4828	112	-	0.4226	0.9740	0.9732

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",
}