This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 1.2131
eval_ANSWER: {'precision': 0.8539976825028969, 'recall': 0.9020807833537332, 'f1': 0.8773809523809523, 'number': 817}
eval_HEADER: {'precision': 0.6666666666666666, 'recall': 0.47058823529411764, 'f1': 0.5517241379310345, 'number': 119}
eval_QUESTION: {'precision': 0.8663239074550129, 'recall': 0.9387186629526463, 'f1': 0.9010695187165776, 'number': 1077}
eval_overall_precision: 0.8534
eval_overall_recall: 0.8962
eval_overall_f1: 0.8742
eval_overall_accuracy: 0.8048
eval_runtime: 1.2663
eval_samples_per_second: 39.484
eval_steps_per_second: 5.528
step: 0

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 2500
mixed_precision_training: Native AMP

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1

doc2txt/tst_fine-tuning-lilt

tst_fine-tuning-lilt

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Framework versions

doc2txt/
tst_fine-tuning-lilt