DistilBertPolitiFact

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

• Loss: 0.7162
• Accuracy: 0.8616

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: 16
• eval_batch_size: 16
• 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
No log	1.0	57	0.3736	0.8428
No log	2.0	114	0.4061	0.8553
No log	3.0	171	0.5411	0.8742
No log	4.0	228	0.5767	0.8491
No log	5.0	285	0.5931	0.8616
No log	6.0	342	0.6440	0.8742
No log	7.0	399	0.6649	0.8742
No log	8.0	456	0.7300	0.8491
0.0548	9.0	513	0.7114	0.8616
0.0548	10.0	570	0.7162	0.8616

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2