ft-lora / README.md
Kota123's picture
starling-7b-raft-ft-adapters
ccc7ff2 verified
metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - generator
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: ft-lora
    results: []

ft-lora

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

  • Loss: 1.0903

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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1399
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • training_steps: 50

Training results

Training Loss Epoch Step Validation Loss
1.8244 0.8696 20 1.6404
1.3653 1.7391 40 1.0903

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1