recipe-nlg-gpt2-train11_15

This model is a fine-tuned version of gpt2 on the Recipe-NLG dataset.

Model description

TEST MODEL - ABOUT 0.40 EPOCHS OF TRAINING COMPLETED

Intended uses & limitations

Experimenting with GPT-2 for recipe generation.

Training and evaluation data

The RecipeNLG(https://huggingface.co/mbien/recipenlg/) dataset was used for this task.

5% of the dataset was held out for evaluation.

Training procedure

RTX 3090 was used on Vast.AI, training took about 14 hours with a batch size of 8, and f16 enabled.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-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
• lr_scheduler_warmup_steps: 200
• num_epochs: 0.45
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0
• Datasets 2.6.1
• Tokenizers 0.13.2