roberta-base-bne-finetuned-detests-ini

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: 0.9922
• Accuracy: 0.8576

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3505	1.0	153	0.3533	0.8380
0.3031	2.0	306	0.3637	0.8363
0.0623	3.0	459	0.6493	0.8560
0.0011	4.0	612	0.8077	0.8642
0.0003	5.0	765	0.9070	0.8625
0.0002	6.0	918	0.9381	0.8625
0.0002	7.0	1071	0.9621	0.8592
0.0001	8.0	1224	0.9787	0.8592
0.0001	9.0	1377	0.9888	0.8576
0.0001	10.0	1530	0.9922	0.8576

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2