flan-t5-small-hallucination-text-classification

This model is a fine-tuned version of google/flan-t5-small on the Hallucination Acceptance Agent Instruction dataset. It achieves the following results on the evaluation set:

• Loss: 0.7901
• Precision: 0.7429
• Recall: 0.7450
• F1: 0.7428
• Accuracy: 0.7450

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: 0.0003
• 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4967	0.4016	100	0.8049	0.7429	0.7349	0.7248	0.7349
0.4829	0.8032	200	0.7162	0.7284	0.7319	0.7261	0.7319
0.3966	1.2048	300	0.8576	0.7526	0.7530	0.7486	0.7530
0.3115	1.6064	400	0.8358	0.7443	0.7450	0.7438	0.7450

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1