pogny-32-0.0005-all

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: 1.8438
• Accuracy: 0.3031
• F1: 0.1410

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: 0.0005
• 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
1.8721	1.0	2554	1.8518	0.3031	0.1410
1.8559	2.0	5108	1.8497	0.3031	0.1410
1.8463	3.0	7662	1.8438	0.3031	0.1410

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0a0+b5021ba
• Datasets 2.6.2
• Tokenizers 0.14.1