surya-narayanan/gpt2-XKTV

results

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6075
• Accuracy: 0.8594
• F1: 0.8544

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.8332	1.0	2537	0.6640	0.8093	0.7980
0.4568	2.0	5074	0.6026	0.8459	0.8396
0.19	3.0	7611	0.5569	0.8641	0.8580

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2