roberta-base-bne-finetuned_personality_multi

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: 2.3709
• Accuracy: 0.5130

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: 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	Accuracy
2.2576	1.0	125	2.2755	0.2340
2.0409	2.0	250	2.1425	0.2974
1.6358	3.0	375	1.8730	0.4403
1.3553	4.0	500	1.7443	0.5032
0.9201	5.0	625	1.7165	0.5055
0.5199	6.0	750	1.7476	0.5107
0.5588	7.0	875	1.7758	0.5153
0.2079	8.0	1000	1.7964	0.5251
0.2685	9.0	1125	1.8886	0.5187
0.1261	10.0	1250	1.9463	0.5199
0.1105	11.0	1375	2.0337	0.5222
0.1572	12.0	1500	2.1206	0.5084
0.0643	13.0	1625	2.1815	0.5182
0.0174	14.0	1750	2.2412	0.5176
0.0266	15.0	1875	2.2741	0.5112
0.0447	16.0	2000	2.3089	0.5159
0.02	17.0	2125	2.3401	0.5135
0.0414	18.0	2250	2.3504	0.5159
0.0122	19.0	2375	2.3661	0.5130
0.0154	20.0	2500	2.3709	0.5130

Framework versions

• Transformers 4.19.3
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1