Edit model card

balanced-augmented-roberta-gest-pred-seqeval-partialmatch-2

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

  • Loss: 0.4965
  • Precision: 0.9214
  • Recall: 0.9180
  • F1: 0.9135
  • Accuracy: 0.9012

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
3.0873 1.0 52 2.5606 0.1508 0.1205 0.1095 0.3096
2.2599 2.0 104 1.8545 0.3409 0.3827 0.3343 0.5265
1.7149 3.0 156 1.4711 0.5470 0.5222 0.4715 0.6087
1.3056 4.0 208 1.0879 0.6500 0.6103 0.5886 0.6919
0.9978 5.0 260 1.0036 0.7039 0.6766 0.6497 0.7221
0.7532 6.0 312 0.7722 0.7356 0.7552 0.7286 0.7842
0.5945 7.0 364 0.6766 0.8316 0.7902 0.7790 0.8053
0.473 8.0 416 0.5994 0.8602 0.8248 0.8224 0.8406
0.3762 9.0 468 0.5572 0.8725 0.8743 0.8600 0.8593
0.2943 10.0 520 0.5767 0.8893 0.8714 0.8659 0.8593
0.251 11.0 572 0.5480 0.8892 0.8765 0.8667 0.8633
0.2074 12.0 624 0.5652 0.8960 0.8866 0.8757 0.8714
0.1714 13.0 676 0.5254 0.9172 0.9087 0.9019 0.8875
0.1523 14.0 728 0.5788 0.9217 0.8900 0.8918 0.8790
0.1309 15.0 780 0.5209 0.9205 0.9141 0.9080 0.8961
0.1187 16.0 832 0.5030 0.9163 0.9138 0.9073 0.8961
0.1065 17.0 884 0.5449 0.9278 0.9212 0.9153 0.8986
0.0923 18.0 936 0.4965 0.9214 0.9180 0.9135 0.9012
0.0894 19.0 988 0.5171 0.9236 0.9189 0.9148 0.9007
0.0869 20.0 1040 0.5211 0.9245 0.9214 0.9159 0.9027

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.1+cu116
  • Datasets 2.11.0
  • Tokenizers 0.13.2

LICENSE

Copyright (c) 2014, Universidad Carlos III de Madrid. Todos los derechos reservados. Este software es propiedad de la Universidad Carlos III de Madrid, grupo de investigación Robots Sociales. La Universidad Carlos III de Madrid es titular en exclusiva de los derechos de propiedad intelectual de este software. Queda prohibido cualquier uso indebido o no autorizado, entre estos, a título enunciativo pero no limitativo, la reproducción, fijación, distribución, comunicación pública, ingeniería inversa y/o transformación sobre dicho software, ya sea total o parcialmente, siendo el responsable del uso indebido o no autorizado también responsable de las consecuencias legales que pudieran derivarse de sus actos.

Downloads last month
10

Dataset used to train Jsevisal/balanced-augmented-roberta-gest-pred-seqeval-partialmatch-2