roberta-finetuned-WebClassification-v2-smalllinguaENES

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

• Loss: 1.0053
• Accuracy: 0.9355
• F1: 0.9355
• Precision: 0.9355
• Recall: 0.9355

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	16	2.4058	0.1613	0.1613	0.1613	0.1613
No log	2.0	32	2.3931	0.0968	0.0968	0.0968	0.0968
No log	3.0	48	1.9594	0.4516	0.4516	0.4516	0.4516
No log	4.0	64	1.7428	0.6129	0.6129	0.6129	0.6129
No log	5.0	80	1.3781	0.8387	0.8387	0.8387	0.8387
No log	6.0	96	1.0053	0.9355	0.9355	0.9355	0.9355
No log	7.0	112	0.8489	0.8387	0.8387	0.8387	0.8387
No log	8.0	128	0.7135	0.8710	0.8710	0.8710	0.8710
No log	9.0	144	0.6700	0.8710	0.8710	0.8710	0.8710
No log	10.0	160	0.6511	0.9355	0.9355	0.9355	0.9355

Framework versions

• Transformers 4.27.3
• Pytorch 2.0.0+cpu
• Datasets 2.10.1
• Tokenizers 0.13.2