metadata

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - africa-intelligence/yahma-alpaca-cleaned-tn
  - africa-intelligence/yahma-alpaca-cleaned-xh
  - africa-intelligence/yahma-alpaca-cleaned-zu
  - africa-intelligence/yahma-alpaca-cleaned-af
  - africa-intelligence/yahma-alpaca-cleaned-en
  - africa-intelligence/yahma-alpaca-cleaned-nso
library_name: peft
license: llama3.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama-8b-south-africa
    results: []

llama-8b-south-africa

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the africa-intelligence/yahma-alpaca-cleaned-tn, the africa-intelligence/yahma-alpaca-cleaned-xh, the africa-intelligence/yahma-alpaca-cleaned-zu, the africa-intelligence/yahma-alpaca-cleaned-af, the africa-intelligence/yahma-alpaca-cleaned-en and the africa-intelligence/yahma-alpaca-cleaned-nso datasets. It achieves the following results on the evaluation set:

Loss: 1.0571

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
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.0962	0.9999	5596	1.0571

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1