SentenceTransformer based on indobenchmark/indobert-base-p2
This is a sentence-transformers model finetuned from indobenchmark/indobert-base-p2. 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: indobenchmark/indobert-base-p2
- Maximum Sequence Length: 75 tokens
- Output Dimensionality: 768 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': 75, 'do_lower_case': False}) with Transformer model: BertModel
(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("Hvare/Athena-indobert-finetuned-indonli")
# Run inference
sentences = [
'Tumenggung Wirapraja setelah mangkat dimakamkan di Kebon Alas Warudoyong, Kecamatan Panumbangan, Kabupaten Ciamis.',
'Tumenggung Wirapraja dikremasi setelah dipastikan mangkat dan abunya kemudian dilarungkan ke Pantai Laut Selatan.',
'Di hari libur ini, Pengunjung semua taman nasional tidak dibebaskan biaya.',
]
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
Semantic Similarity
- Dataset:
sts-dev
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | -0.053 |
spearman_cosine | -0.0611 |
pearson_manhattan | -0.064 |
spearman_manhattan | -0.0684 |
pearson_euclidean | -0.0643 |
spearman_euclidean | -0.0691 |
pearson_dot | -0.0245 |
spearman_dot | -0.0242 |
pearson_max | -0.0245 |
spearman_max | -0.0242 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 10,330 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string int details - min: 11 tokens
- mean: 29.47 tokens
- max: 75 tokens
- min: 6 tokens
- mean: 12.25 tokens
- max: 28 tokens
- 0: ~35.90%
- 1: ~32.00%
- 2: ~32.10%
- Samples:
sentence_0 sentence_1 label "" "Akan ada protes dan hal-hal lain, semua nya sudah direncanakan," "ungkap oposisi kepada El Mundo."
Protes dan hal-hal lain sudah direncanakan.
0
Tak jarang, bangun kesiangan pun jadi alasan untuk tak berolahraga.
Salah satu alasan tidak berolahraga adalah bangun kesiangan.
0
Namun, saingannya Prabowo Subianto juga mendeklarasikan kemenangan, membuat orang Indonesia bingung.
Prabowo menerima bahwa Dia kalah.
2
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 16per_device_eval_batch_size
: 16num_train_epochs
: 1multi_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_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
: 1num_train_epochs
: 1max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_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
: batch_samplermulti_dataset_batch_sampler
: round_robin
Training Logs
Epoch | Step | Training Loss | sts-dev_spearman_max |
---|---|---|---|
0.0991 | 64 | - | -0.0411 |
0.1981 | 128 | - | -0.0426 |
0.2972 | 192 | - | -0.0419 |
0.3963 | 256 | - | -0.0425 |
0.4954 | 320 | - | -0.0384 |
0.5944 | 384 | - | -0.0260 |
0.6935 | 448 | - | -0.0216 |
0.7740 | 500 | 0.0531 | - |
0.7926 | 512 | - | -0.0243 |
0.8916 | 576 | - | -0.0241 |
0.9907 | 640 | - | -0.0242 |
1.0 | 646 | - | -0.0242 |
Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.31.0
- Datasets: 2.19.2
- 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
- 3
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 Hvare/Athena-indobert-finetuned-indonli-SentenceTransformer
Base model
indobenchmark/indobert-base-p2
Finetuned
this model
Evaluation results
- Pearson Cosine on sts devself-reported-0.053
- Spearman Cosine on sts devself-reported-0.061
- Pearson Manhattan on sts devself-reported-0.064
- Spearman Manhattan on sts devself-reported-0.068
- Pearson Euclidean on sts devself-reported-0.064
- Spearman Euclidean on sts devself-reported-0.069
- Pearson Dot on sts devself-reported-0.025
- Spearman Dot on sts devself-reported-0.024
- Pearson Max on sts devself-reported-0.025
- Spearman Max on sts devself-reported-0.024