shakespearean-lm

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.4100

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: 0.0001
• 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
4.9075	0.53	500	4.6423
4.6274	1.06	1000	4.5136
4.4057	1.59	1500	4.4582
4.3596	2.12	2000	4.4350
4.2589	2.65	2500	4.4163

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1