roberta-base-bne-finetuned_personality_multi_2

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: 2.2983
• Accuracy: 0.5429

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
2.3256	1.0	125	2.2642	0.2161
1.815	2.0	250	1.9569	0.3919
1.614	3.0	375	1.7264	0.5014
1.1718	4.0	500	1.6387	0.5239
1.135	5.0	625	1.6259	0.5245
0.5637	6.0	750	1.6443	0.5372
0.3672	7.0	875	1.7146	0.5326
0.3249	8.0	1000	1.8099	0.5297
0.1791	9.0	1125	1.8888	0.5285
0.2175	10.0	1250	1.9228	0.5326
0.0465	11.0	1375	1.9753	0.5435
0.1154	12.0	1500	2.1102	0.5256
0.0745	13.0	1625	2.1319	0.5429
0.0281	14.0	1750	2.1743	0.5360
0.0173	15.0	1875	2.2087	0.5441
0.0269	16.0	2000	2.2456	0.5424
0.0107	17.0	2125	2.2685	0.5458
0.0268	18.0	2250	2.2893	0.5383
0.0245	19.0	2375	2.2943	0.5418
0.0156	20.0	2500	2.2983	0.5429

Framework versions

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