llama2-test-sample

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset.

Model description

Created using https://towardsdatascience.com/fine-tune-your-own-llama-2-model-in-a-colab-notebook-df9823a04a32 and https://medium.com/odicis-data-engineering/language-modelling-fine-tuning-the-llama2-46a947b0720d

Intended uses & limitations

practice

Training and evaluation data meta-llama/Llama-2-7b-hf

meta-llama/Llama-2-7b-hf trained with timdettmers/openassistant-guanaco

Training procedure

SFT

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 20

Training results

Framework versions

• Transformers 4.31.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3