distilroberta-pr200k-ep20-ag_news

This model is a fine-tuned version of judy93536/distilroberta-pr200k-ep20 on the ag_news dataset. It achieves the following results on the evaluation set:

• Loss: 0.1707
• Accuracy: 0.9436

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: 4.545606711088675e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.28
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1821	1.0	3750	0.1707	0.9436

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3