llama-edu / README.md
LouayYahyaoui's picture
add: llama for education
523c87a verified
metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama-edu
    results: []

llama-edu

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

  • Loss: 0.7934
  • Model Preparation Time: 0.0161

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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 20
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Model Preparation Time
2.2418 1.0256 20 2.0564 0.0161
1.2511 2.0513 40 1.2006 0.0161
0.9906 3.0769 60 0.9552 0.0161
0.8046 4.1026 80 0.8716 0.0161
0.7893 5.1282 100 0.8376 0.0161
0.8012 6.1538 120 0.8167 0.0161
0.7734 7.1795 140 0.8038 0.0161
0.78 8.2051 160 0.7970 0.0161
0.7576 9.2308 180 0.7939 0.0161

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.1.2
  • Datasets 2.21.0
  • Tokenizers 0.19.1