Update README.md

345c6a8 verified 6 months ago

12.5 kB

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - cross-encoder
  - reranker
  - generated_from_trainer
  - dataset_size:64921
  - loss:BinaryCrossEntropyLoss
base_model: cambridgeltl/SapBERT-from-PubMedBERT-fulltext
pipeline_tag: text-ranking
library_name: sentence-transformers
metrics:
  - map
  - mrr@10
  - ndcg@10
model-index:
  - name: SapBERT trained on NCBI Disease
    results:
      - task:
          type: cross-encoder-reranking
          name: Cross Encoder Reranking
        dataset:
          name: ncbi disease dev
          type: ncbi-disease-dev
        metrics:
          - type: map
            value: 0.981
            name: Map
          - type: mrr@10
            value: 0.9882
            name: Mrr@10
          - type: ndcg@10
            value: 0.9886
            name: Ndcg@10

SapBERT trained on NCBI Disease

This is a Cross Encoder model finetuned from cambridgeltl/SapBERT-from-PubMedBERT-fulltext using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.

Model Details

Model Description

Model Type: Cross Encoder
Base model: cambridgeltl/SapBERT-from-PubMedBERT-fulltext
Maximum Sequence Length: 512 tokens
Number of Output Labels: 1 label
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("cross_encoder_model_id")
# Get scores for pairs of texts
pairs = [
    ['deficiency of hepatic phenylalanine hydroxylase', 'oligophrenia phenylpyruvica'],
    ['Complete hypoxanthine-guanine phosphoribosyl-transferase (HPRT) deficiency', 'gout, hprt-related'],
    ['myotonia levior', 'gne myopathy'],
    ['ischemic heart disease', 'atheroscleroses, coronary'],
    ['Thomsens disease', 'myotonia, generalized'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    'deficiency of hepatic phenylalanine hydroxylase',
    [
        'oligophrenia phenylpyruvica',
        'gout, hprt-related',
        'gne myopathy',
        'atheroscleroses, coronary',
        'myotonia, generalized',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Evaluation

Metrics

Cross Encoder Reranking

Dataset: ncbi-disease-dev

Evaluated with CrossEncoderRerankingEvaluator with these parameters:

{
    "at_k": 10,
    "always_rerank_positives": false
}

Metric	Value
map	0.9810 (+0.5458)
mrr@10	0.9882 (+0.7140)
ndcg@10	0.9886 (+0.4189)

Training Details

Training Dataset

Unnamed Dataset

Size: 64,921 training samples
Columns: query, answer, and label

Approximate statistics based on the first 1000 samples:

	query	answer	label
type	string	string	int
details	min: 1 characters mean: 21.71 characters max: 74 characters	min: 5 characters mean: 27.42 characters max: 124 characters	0: ~50.90% 1: ~49.10%

Samples:

query	answer	label
`deficiency of hepatic phenylalanine hydroxylase`	`oligophrenia phenylpyruvica`	`1`
`Complete hypoxanthine-guanine phosphoribosyl-transferase (HPRT) deficiency`	`gout, hprt-related`	`0`
`myotonia levior`	`gne myopathy`	`0`

Loss: BinaryCrossEntropyLoss with these parameters:

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": 0.9940566420555115
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
warmup_ratio: 0.1
seed: 12
bf16: True
dataloader_num_workers: 4
load_best_model_at_end: 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: 128
per_device_eval_batch_size: 128
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_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: 3
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: 12
data_seed: None
jit_mode_eval: False
bf16: True
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: 4
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}
parallelism_config: 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
project: huggingface
trackio_space_id: trackio
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: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
include_tokens_per_second: False
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	ncbi-disease-dev_ndcg@10
0.0020	1	0.6977	-
0.4921	250	0.5864	-
0.9843	500	0.3563	-
1.4764	750	0.2523	-
1.9685	1000	0.2154	0.9851 (+0.4155)
2.4606	1250	0.1719	-
2.9528	1500	0.1581	-
-1	-1	-	0.9886 (+0.4189)

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.2.0
Transformers: 4.57.3
PyTorch: 2.9.1+cu128
Accelerate: 1.12.0
Datasets: 4.4.2
Tokenizers: 0.22.1

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",
}