hugsom/ecopromptgenerator

EcoPrompt Generation

This model is a fine-tuned version of gpt2 on an ecoprompt dataset. It achieves the following results on the evaluation set:

• Loss: 2.6718

Model description

Text generation model for generating suitable style cues given the main idea for a prompt.It is performing tasks to fine-tune a GPT-2 language model for text generation using a custom dataset. Dataset is collected and trained by students of College of Engineering Guindy.

• Athiraj V S
• Siva Vignesh S
• Someshwar J

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
4.225	1.0	20473	3.3004
2.9935	2.0	40946	2.7915
2.5083	3.0	61419	2.6718

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1