roberta-base-bne-finetuned_personality_multi_3

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

• Loss: 2.1145
• Accuracy: 0.4847

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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	Accuracy
2.2498	1.0	63	2.2799	0.2236
2.3044	2.0	126	2.1644	0.2980
1.9017	3.0	189	1.9934	0.4127
2.2281	4.0	252	1.8517	0.4501
1.2955	5.0	315	1.7588	0.4870
1.221	6.0	378	1.7269	0.4888
1.1381	7.0	441	1.7617	0.4888
0.8415	8.0	504	1.8101	0.4853
0.6696	9.0	567	1.8325	0.4928
0.6646	10.0	630	1.8707	0.4841
0.3758	11.0	693	1.8766	0.4876
0.3477	12.0	756	1.9171	0.4905
0.2854	13.0	819	1.9203	0.4980
0.2713	14.0	882	2.0089	0.4813
0.3434	15.0	945	2.0130	0.4905
0.0758	16.0	1008	2.0230	0.4922
0.2518	17.0	1071	2.0793	0.4824
0.0783	18.0	1134	2.0920	0.4830
0.0933	19.0	1197	2.1067	0.4836
0.184	20.0	1260	2.1145	0.4847

Framework versions

• Transformers 4.19.4
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1