Edit model card

longformer-base-health-fact2

This model is a fine-tuned version of allenai/longformer-base-4096 on the health_fact dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5858
  • Micro F1: 0.8122
  • Macro F1: 0.6830
  • False F1: 0.7941
  • Mixture F1: 0.5015
  • True F1: 0.9234
  • Unproven F1: 0.5128

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 18
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Micro F1 Macro F1 False F1 Mixture F1 True F1 Unproven F1
0.555 1.0 613 0.5243 0.7842 0.5535 0.7698 0.4170 0.8938 0.1333
0.4282 2.0 1226 0.5008 0.8031 0.6393 0.7829 0.4605 0.9199 0.3939
0.2897 3.0 1839 0.5858 0.8122 0.6830 0.7941 0.5015 0.9234 0.5128

Framework versions

  • Transformers 4.19.0.dev0
  • Pytorch 1.11.0a0+17540c5
  • Datasets 2.1.1.dev0
  • Tokenizers 0.12.1
Downloads last month
240
Hosted inference API
Text Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train nbroad/longformer-base-health-fact

Evaluation results