distilgpt2-finetuned-wikitext2

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.2288

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.4689	1.0	24449	2.3948
2.2998	2.0	48898	2.2660
2.2683	3.0	73347	2.2288

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2