finetuned-climategpt-7b

This model is a fine-tuned version of eci-io/climategpt-7b on the Science Feedback dataset (https://huggingface.co/datasets/Joon007/science-feedback).

Model description

More info coming soon

Intended uses & limitations

More info coming soon

Training and evaluation data

More info coming soon

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.00085
• 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: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.0.1+cu118
• Datasets 3.0.1
• Tokenizers 0.20.0