README.md

metadata

license: llama2
base_model: TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ
tags:
  - generated_from_trainer
datasets:
  - emotion
model-index:
  - name: llama-2-7B-Guanaco-QLoRA-AWQ
    results: []

llama-2-7B-Guanaco-QLoRA-AWQ

This model is a fine-tuned version of TheBloke/llama-2-7B-Guanaco-QLoRA-AWQ on the emotion dataset.

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	250	1.6793	0.3225	0.2723

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1