liar_binaryclassifier_bert_cased

This model is a fine-tuned version of bert-base-cased on the liar dataset. It achieves the following results on the evaluation set:

• Loss: 0.6331
• Model Preparation Time: 0.0032
• Accuracy: 0.6486

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: 3e-06
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Accuracy
0.6826	1.0	461	0.6477	0.0032	0.6117
0.6435	2.0	922	0.6267	0.0032	0.6356
0.6131	3.0	1383	0.6302	0.0032	0.6529
0.5809	4.0	1844	0.6233	0.0032	0.6508
0.5658	5.0	2305	0.6331	0.0032	0.6486

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1