roberta-finetuned-WebClassification-v2-smalllinguaEN

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: 1.5844
• Accuracy: 0.7143
• F1: 0.7143
• Precision: 0.7143
• Recall: 0.7143

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	7	2.3084	0.0714	0.0714	0.0714	0.0714
No log	2.0	14	2.2951	0.2857	0.2857	0.2857	0.2857
No log	3.0	21	2.2725	0.2143	0.2143	0.2143	0.2143
No log	4.0	28	2.0608	0.2143	0.2143	0.2143	0.2143
No log	5.0	35	1.8552	0.3571	0.3571	0.3571	0.3571
No log	6.0	42	1.6846	0.5714	0.5714	0.5714	0.5714
No log	7.0	49	1.5844	0.7143	0.7143	0.7143	0.7143
No log	8.0	56	1.4531	0.7143	0.7143	0.7143	0.7143
No log	9.0	63	1.3746	0.7143	0.7143	0.7143	0.7143
No log	10.0	70	1.3663	0.7143	0.7143	0.7143	0.7143

Framework versions

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