pile_t5_base_docstring

This model is a fine-tuned version of EleutherAI/pile-t5-base on the juraj-juraj/python-docstring-human-gpt-generated-mix dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Bleu: 0.0
• Gen Len: 256.0

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: 1e-05
• train_batch_size: 15
• eval_batch_size: 15
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Framework versions

• Transformers 4.39.2
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2