chchen's picture
End of training
4c127fd verified
metadata
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
  - llama-factory
  - lora
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Llama-3.1-8B-Instruct-reward-100
    results: []

Llama-3.1-8B-Instruct-reward-100

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_dpo_100 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3586
  • Accuracy: 0.9

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0 9.4889 50 0.3586 0.9

Framework versions

  • PEFT 0.12.0
  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3