SentenceTransformer based on srikarvar/fine_tuned_model_5
This is a sentence-transformers model finetuned from srikarvar/fine_tuned_model_5 on the json dataset. 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: srikarvar/fine_tuned_model_5
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 384 tokens
- Similarity Function: Cosine Similarity
- Training Dataset:
- json
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 ๐ค Hub
model = SentenceTransformer("srikarvar/fine_tuned_model_16")
# Run inference
sentences = [
'Two kinds of cooking methods exist, baking and frying.',
'There are two types of cooking methods, baking and frying.',
'The purpose of the given recipe is to provide instructions for making lasagna.',
]
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
Information Retrieval
- Dataset:
e5-cogcache-small-refined
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.9643 |
cosine_accuracy@3 | 1.0 |
cosine_accuracy@5 | 1.0 |
cosine_accuracy@10 | 1.0 |
cosine_precision@1 | 0.9643 |
cosine_precision@3 | 0.3333 |
cosine_precision@5 | 0.2 |
cosine_precision@10 | 0.1 |
cosine_recall@1 | 0.9643 |
cosine_recall@3 | 1.0 |
cosine_recall@5 | 1.0 |
cosine_recall@10 | 1.0 |
cosine_ndcg@10 | 0.9845 |
cosine_mrr@10 | 0.9792 |
cosine_map@100 | 0.9792 |
dot_accuracy@1 | 0.9643 |
dot_accuracy@3 | 1.0 |
dot_accuracy@5 | 1.0 |
dot_accuracy@10 | 1.0 |
dot_precision@1 | 0.9643 |
dot_precision@3 | 0.3333 |
dot_precision@5 | 0.2 |
dot_precision@10 | 0.1 |
dot_recall@1 | 0.9643 |
dot_recall@3 | 1.0 |
dot_recall@5 | 1.0 |
dot_recall@10 | 1.0 |
dot_ndcg@10 | 0.9845 |
dot_mrr@10 | 0.9792 |
dot_map@100 | 0.9792 |
Information Retrieval
- Dataset:
e5-cogcache-small-refined
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.9643 |
cosine_accuracy@3 | 1.0 |
cosine_accuracy@5 | 1.0 |
cosine_accuracy@10 | 1.0 |
cosine_precision@1 | 0.9643 |
cosine_precision@3 | 0.3333 |
cosine_precision@5 | 0.2 |
cosine_precision@10 | 0.1 |
cosine_recall@1 | 0.9643 |
cosine_recall@3 | 1.0 |
cosine_recall@5 | 1.0 |
cosine_recall@10 | 1.0 |
cosine_ndcg@10 | 0.9845 |
cosine_mrr@10 | 0.9792 |
cosine_map@100 | 0.9792 |
dot_accuracy@1 | 0.9643 |
dot_accuracy@3 | 1.0 |
dot_accuracy@5 | 1.0 |
dot_accuracy@10 | 1.0 |
dot_precision@1 | 0.9643 |
dot_precision@3 | 0.3333 |
dot_precision@5 | 0.2 |
dot_precision@10 | 0.1 |
dot_recall@1 | 0.9643 |
dot_recall@3 | 1.0 |
dot_recall@5 | 1.0 |
dot_recall@10 | 1.0 |
dot_ndcg@10 | 0.9845 |
dot_mrr@10 | 0.9792 |
dot_map@100 | 0.9792 |
Training Details
Training Dataset
json
- Dataset: json
- Size: 560 training samples
- Columns:
anchor
andpositive
- Approximate statistics based on the first 560 samples:
anchor positive type string string details - min: 9 tokens
- mean: 30.72 tokens
- max: 98 tokens
- min: 8 tokens
- mean: 30.52 tokens
- max: 98 tokens
- Samples:
anchor positive The function assists in the preprocessing of the whole module in one go.
The function helps preprocess your entire module at once.
The
num_threads
parameter determines the quantity of threads used when downloading and processing the data locally.The
num_threads
parameter specifies the number of threads when downloading and processing the data locally.The
map()
function can be used to apply transformations to all elements of a model.The
map()
function can apply transforms over an entire model. - Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: epochper_device_train_batch_size
: 16per_device_eval_batch_size
: 16num_train_epochs
: 5warmup_ratio
: 0.1batch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: epochprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 5max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falsebatch_sampler
: no_duplicatesmulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | e5-cogcache-small-refined_cosine_map@100 |
---|---|---|---|
0 | 0 | - | 0.9702 |
0.3125 | 10 | 0.0171 | - |
0.625 | 20 | 0.0042 | - |
0.9375 | 30 | 0.0011 | - |
1.0 | 32 | - | 0.9792 |
1.25 | 40 | 0.0062 | - |
1.5625 | 50 | 0.0001 | - |
1.875 | 60 | 0.0002 | - |
2.0 | 64 | - | 0.9792 |
2.1875 | 70 | 0.0001 | - |
2.5 | 80 | 0.0005 | - |
2.8125 | 90 | 0.0001 | - |
3.0 | 96 | - | 0.9792 |
3.125 | 100 | 0.0001 | - |
3.4375 | 110 | 0.0002 | - |
3.75 | 120 | 0.0001 | - |
4.0 | 128 | - | 0.9792 |
4.0625 | 130 | 0.0001 | - |
4.375 | 140 | 0.0 | - |
4.6875 | 150 | 0.0001 | - |
5.0 | 160 | 0.0001 | 0.9792 |
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.1.0
- Transformers: 4.41.2
- PyTorch: 2.1.2+cu121
- Accelerate: 0.34.2
- 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}
}
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for srikarvar/fine_tuned_model_16
Base model
intfloat/multilingual-e5-small
Finetuned
srikarvar/fine_tuned_model_5
Evaluation results
- Cosine Accuracy@1 on e5 cogcache small refinedself-reported0.964
- Cosine Accuracy@3 on e5 cogcache small refinedself-reported1.000
- Cosine Accuracy@5 on e5 cogcache small refinedself-reported1.000
- Cosine Accuracy@10 on e5 cogcache small refinedself-reported1.000
- Cosine Precision@1 on e5 cogcache small refinedself-reported0.964
- Cosine Precision@3 on e5 cogcache small refinedself-reported0.333
- Cosine Precision@5 on e5 cogcache small refinedself-reported0.200
- Cosine Precision@10 on e5 cogcache small refinedself-reported0.100
- Cosine Recall@1 on e5 cogcache small refinedself-reported0.964
- Cosine Recall@3 on e5 cogcache small refinedself-reported1.000