roberta-finetuned-WebClassification-v2-smalllinguaESv2

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: 1.3862
• Accuracy: 0.6909
• F1: 0.6909
• Precision: 0.6909
• Recall: 0.6909

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	28	2.9841	0.2	0.2000	0.2	0.2
No log	2.0	56	2.8109	0.1636	0.1636	0.1636	0.1636
No log	3.0	84	2.5334	0.3455	0.3455	0.3455	0.3455
No log	4.0	112	2.1164	0.5273	0.5273	0.5273	0.5273
No log	5.0	140	1.9152	0.5818	0.5818	0.5818	0.5818
No log	6.0	168	1.6678	0.6182	0.6182	0.6182	0.6182
No log	7.0	196	1.5647	0.6545	0.6545	0.6545	0.6545
No log	8.0	224	1.4473	0.6727	0.6727	0.6727	0.6727
No log	9.0	252	1.3862	0.6909	0.6909	0.6909	0.6909
No log	10.0	280	1.3647	0.6909	0.6909	0.6909	0.6909

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3