Hugging Face's logo

nikolamilosevic
/
SCIFACT_xlm_roberta_large

Text Classification
Transformers
PyTorch
English
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
SCIFACT_xlm_roberta_large / README.md
nikolamilosevic's picture
nikolamilosevic
Adding right widget
09ff730
preview code
|
raw
history blame
4.23 kB
metadata
license: mit
base_model: xlm-roberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: SCIFACT_inference_model
    results: []
datasets:
  - allenai/scifact
language:
  - en
widget:
  - text: >-
      [CLS]A country's Vaccine Alliance (GAVI) eligibility is indictivate of
      accelerated adoption of the Hub vaccine.[SEP]Accelerating Policy Decisions
      to Adopt Haemophilus influenzae Type b Vaccine: A Global, Multivariable
      Analysis BACKGROUND Adoption of new and underutilized vaccines by national
      immunization programs is an essential step towards reducing child
      mortality. Policy decisions to adopt new vaccines in high mortality
      countries often lag behind decisions in high-income countries. Using the
      case of Haemophilus influenzae type b (Hib) vaccine, this paper endeavors
      to explain these delays through the analysis of country-level economic,
      epidemiological, programmatic and policy-related factors, as well as the
      role of the Global Alliance for Vaccines and Immunisation (GAVI Alliance).
      METHODS AND FINDINGS Data for 147 countries from 1990 to 2007 were
      analyzed in accelerated failure time models to identify factors that are
      associated with the time to decision to adopt Hib vaccine. In
      multivariable models that control for Gross National Income, region, and
      burden of Hib disease, the receipt of GAVI support speeded the time to
      decision by a factor of 0.37 (95% CI 0.18-0.76), or 63%. The presence of
      two or more neighboring country adopters accelerated decisions to adopt by
      a factor of 0.50 (95% CI 0.33-0.75). For each 1% increase in vaccine
      price, decisions to adopt are delayed by a factor of 1.02 (95% CI
      1.00-1.04). Global recommendations and local studies were not associated
      with time to decision.CONCLUSIONS This study substantiates previous
      findings related to vaccine price and presents new evidence to suggest
      that GAVI eligibility is associated with accelerated decisions to adopt
      Hib vaccine. The influence of neighboring country decisions was also
      highly significant, suggesting that approaches to support the adoption of
      new vaccines should consider supply- and demand-side factors. 
library_name: transformers

SCIFACT_inference_model

This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2496
  • Accuracy: 0.8819

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 3
  • eval_batch_size: 3
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 378 1.0485 0.4724
1.0382 2.0 756 1.3964 0.6063
0.835 3.0 1134 0.9168 0.8268
0.6801 4.0 1512 0.7524 0.8425
0.6801 5.0 1890 1.0672 0.8346
0.4291 6.0 2268 0.9599 0.8425
0.2604 7.0 2646 0.8691 0.8661
0.1932 8.0 3024 1.3162 0.8268
0.1932 9.0 3402 1.3200 0.8583
0.0974 10.0 3780 1.1566 0.8740
0.1051 11.0 4158 1.1568 0.8819
0.0433 12.0 4536 1.2013 0.8661
0.0433 13.0 4914 1.1557 0.8819
0.034 14.0 5292 1.3044 0.8661
0.0303 15.0 5670 1.2496 0.8819

Framework versions

  • Transformers 4.34.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.14.6
  • Tokenizers 0.14.1