vit-base-patch16-224-in21k-gpt2-finetuned-to-pokemon-descriptions-oak

This model is a fine-tuned version of tkarr/vit-base-patch16-224-in21k-gpt2-finetuned-to-pokemon-descriptions on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0586

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0693	1.0	3208	0.0671
0.063	2.0	6416	0.0620
0.0562	3.0	9624	0.0592
0.0534	4.0	12832	0.0586

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2