Edit model card

roberta-finetuned-sem_eval-rest14-english

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

  • Loss: 0.0813
  • F1: 0.5700
  • Roc Auc: 0.8939
  • Accuracy: 0.7312
  • Hamming Loss: 0.0225

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: 2e-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
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy Hamming Loss
No log 1.0 381 0.1438 0.1120 0.6888 0.33 0.044
0.2014 2.0 762 0.1059 0.3044 0.7981 0.5587 0.0317
0.1093 3.0 1143 0.0914 0.3720 0.8325 0.6275 0.0278
0.0809 4.0 1524 0.0823 0.4290 0.8656 0.6913 0.0244
0.0809 5.0 1905 0.0862 0.4307 0.8680 0.6963 0.0251
0.06 6.0 2286 0.0811 0.4674 0.8714 0.7013 0.0239
0.0466 7.0 2667 0.0842 0.5041 0.8714 0.7 0.0248
0.0365 8.0 3048 0.0821 0.5351 0.8846 0.7137 0.0238
0.0365 9.0 3429 0.0815 0.5375 0.8857 0.7212 0.0234
0.0299 10.0 3810 0.0812 0.5551 0.8918 0.7312 0.0222
0.0236 11.0 4191 0.0815 0.5537 0.8940 0.7338 0.0222
0.0195 12.0 4572 0.0813 0.5700 0.8939 0.7312 0.0225
0.0195 13.0 4953 0.0829 0.5641 0.8955 0.7362 0.022
0.018 14.0 5334 0.0829 0.5662 0.8946 0.7338 0.0221
0.0157 15.0 5715 0.0824 0.5698 0.8980 0.7362 0.0217

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
5
Safetensors
Model size
125M params
Tensor type
F32
·

Finetuned from