asprenger's picture
Model save
bb55cd4 verified
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - generator
model-index:
  - name: Meta-Llama-3-8B-VIGGO-qlora
    results: []

Meta-Llama-3-8B-VIGGO-qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6168

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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
0.5174 0.99 25 0.5002
0.4168 1.98 50 0.4846
0.3898 2.97 75 0.4930
0.3179 4.0 101 0.5523
0.2378 4.95 125 0.6168

Framework versions

  • PEFT 0.10.0
  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.2