Edit model card

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: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, '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("cassador/indobert-snli-v1")
# Run inference
sentences = [
    'Wanita profesional di meja pendaftaran acara sementara pria berjas melihat.',
    'Orang-orang berkumpul untuk sebuah acara.',
    'Ada seorang anak yang tersenyum untuk difoto.',
]
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

Metric Value
pearson_cosine 0.2315
spearman_cosine 0.2318
pearson_manhattan 0.1985
spearman_manhattan 0.2038
pearson_euclidean 0.1987
spearman_euclidean 0.2039
pearson_dot 0.2562
spearman_dot 0.251
pearson_max 0.2562
spearman_max 0.251

Semantic Similarity

Metric Value
pearson_cosine 0.5915
spearman_cosine 0.5979
pearson_manhattan 0.5132
spearman_manhattan 0.5147
pearson_euclidean 0.5943
spearman_euclidean 0.6002
pearson_dot 0.588
spearman_dot 0.5934
pearson_max 0.5943
spearman_max 0.6002

Training Details

Training Dataset

Unnamed Dataset

  • Size: 133,472 training samples
  • Columns: label, kalimat1, and kalimat2
  • Approximate statistics based on the first 1000 samples:
    label kalimat1 kalimat2
    type int string string
    details
    • 0: ~50.00%
    • 1: ~50.00%
    • min: 5 tokens
    • mean: 16.47 tokens
    • max: 48 tokens
    • min: 4 tokens
    • mean: 9.62 tokens
    • max: 22 tokens
  • Samples:
    label kalimat1 kalimat2
    0 Seseorang di atas kuda melompati pesawat yang rusak. Seseorang sedang makan malam, memesan telur dadar.
    1 Seseorang di atas kuda melompati pesawat yang rusak. Seseorang berada di luar ruangan, di atas kuda.
    1 Anak-anak tersenyum dan melambai ke kamera Ada anak-anak yang hadir
  • Loss: SoftmaxLoss

Evaluation Dataset

Unnamed Dataset

  • Size: 6,607 evaluation samples
  • Columns: label, kalimat1, and kalimat2
  • Approximate statistics based on the first 1000 samples:
    label kalimat1 kalimat2
    type int string string
    details
    • 0: ~50.10%
    • 1: ~49.90%
    • min: 5 tokens
    • mean: 16.87 tokens
    • max: 49 tokens
    • min: 3 tokens
    • mean: 9.45 tokens
    • max: 27 tokens
  • Samples:
    label kalimat1 kalimat2
    1 Dua wanita berpelukan sambil memegang paket untuk pergi. Dua wanita memegang paket.
    0 Dua wanita berpelukan sambil memegang paket untuk pergi. Orang-orang berkelahi di luar toko makanan.
    1 Dua anak kecil berbaju biru, satu dengan nomor 9 dan satu dengan nomor 2 berdiri di tangga kayu di kamar mandi dan mencuci tangan di wastafel. Dua anak dengan kaus bernomor mencuci tangan mereka.
  • Loss: SoftmaxLoss

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 32
  • learning_rate: 2e-05
  • num_train_epochs: 2
  • warmup_ratio: 0.1
  • fp16: True

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • 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: 1
  • eval_accumulation_steps: None
  • learning_rate: 2e-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: 2
  • 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: 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
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step sts-dev_spearman_cosine sts-test_spearman_cosine
0 0 0.2318 -
2.0 8342 - 0.5979

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: 2.20.0
  • Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@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",
}
Downloads last month
4
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Examples
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 cassador/indobert-snli-v1

Finetuned
(35)
this model

Evaluation results