DistilGPT2-Beatles-Lyrics-finetuned

This model is a fine-tuned version of distilgpt2 on the Huggingartists - beatles dataset. It will complete an input prompt with Beatles-like text.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 4
• 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_steps: 100
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.748	1.0	165	2.3732
2.4395	2.0	330	2.1938
2.2968	3.0	495	2.1118
2.2075	4.0	660	2.0721
2.1393	5.0	825	2.0571

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.2.0
• Tokenizers 0.12.1