pogny-32-0.00001

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: 1.2568
• Accuracy: 0.7693
• F1: 0.7674

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: 1e-06
• train_batch_size: 32
• eval_batch_size: 32
• 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
0.1131	1.0	2409	1.2283	0.7675	0.7665
0.1039	2.0	4818	1.2355	0.7690	0.7670
0.0971	3.0	7227	1.2568	0.7693	0.7674

Framework versions

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