RoBerta_fnir

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

• Loss: 0.0153
• Accuracy: 0.997
• Auc: 0.999
• Precision: 1.0
• Recall: 0.995
• F1: 0.997
• F1-macro: 0.997
• F1-micro: 0.997
• F1-weighted: 0.997

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision	Recall	F1	F1-macro	F1-micro	F1-weighted
0.1507	0.6024	100	0.0360	0.995	0.999	0.996	0.993	0.995	0.995	0.995	0.995
0.0297	1.2048	200	0.0177	0.997	1.0	1.0	0.993	0.997	0.997	0.997	0.997
0.0092	1.8072	300	0.0201	0.997	0.999	1.0	0.993	0.997	0.997	0.997	0.997
0.0097	2.4096	400	0.0185	0.997	1.0	1.0	0.993	0.997	0.997	0.997	0.997
0.0144	3.0120	500	0.0183	0.997	1.0	1.0	0.993	0.997	0.997	0.997	0.997
0.0044	3.6145	600	0.0145	0.997	1.0	1.0	0.995	0.997	0.997	0.997	0.997
0.0078	4.2169	700	0.0152	0.997	1.0	1.0	0.993	0.997	0.997	0.997	0.997
0.0047	4.8193	800	0.0153	0.997	0.999	1.0	0.995	0.997	0.997	0.997	0.997

Framework versions

• Transformers 4.53.0
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2