Am09/distilroberta-base-fake_news_detector-Am09

results

This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0022
• Acc: 0.9997
• Precision: 0.9997
• Recall: 0.9997
• F1 score: 0.9997

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Acc	Precision	Recall	F1 score
0.0069	0.0989	100	0.0401	0.9928	0.9927	0.9930	0.9928
0.0262	0.1978	200	0.0143	0.9975	0.9975	0.9975	0.9975
0.0118	0.2967	300	0.0098	0.9983	0.9983	0.9983	0.9983
0.0135	0.3956	400	0.0088	0.9989	0.9989	0.9989	0.9989
0.0163	0.4946	500	0.0136	0.9981	0.9980	0.9981	0.9980
0.0078	0.5935	600	0.0114	0.9986	0.9986	0.9986	0.9986
0.0103	0.6924	700	0.0132	0.9983	0.9983	0.9983	0.9983
0.0041	0.7913	800	0.0122	0.9986	0.9986	0.9986	0.9986
0.0098	0.8902	900	0.0078	0.9989	0.9989	0.9989	0.9989
0.0045	0.9891	1000	0.0047	0.9989	0.9989	0.9989	0.9989

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 3.0.0
• Tokenizers 0.19.1