hana-64-0.005

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: 1.9708
• Accuracy: 0.3096
• F1: 0.1463

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: 0.005
• 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
2.2731	1.0	1097	2.2254	0.3096	0.1463
2.1577	2.0	2194	2.2213	0.2034	0.0687
2.04	3.0	3291	1.9708	0.3096	0.1463

Framework versions

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