metadata

license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: roberta-finetuned-sem_eval-rest14-english
    results: []

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