hana-64-0.00002

This model is a fine-tuned version of klue/roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3992
• Accuracy: 0.7137
• F1: 0.7114

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: 64
• eval_batch_size: 64
• 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
0.2557	1.0	1097	1.1509	0.7130	0.7101
0.1925	2.0	2194	1.2460	0.7094	0.7082
0.117	3.0	3291	1.3992	0.7137	0.7114

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.2
• Datasets 2.19.1
• Tokenizers 0.19.1