Hugging Face's logo

nvl-og
/
llama-3.1-fine-tuned

PEFT
Safetensors
English
Thai
Generated from Trainer
NLP
fine-tuned
conversation ai
chatbot
Model card Files Community
llama-3.1-fine-tuned / README.md
Tanabodee Limpaitoon
Update README.md
3de7acc verified
preview code
|
raw
history blame
1.65 kB
metadata
base_model:
  - meta-llama/Meta-Llama-3.1-8B-Instruct
  - meta-llama/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
  - generated_from_trainer
  - NLP
  - fine-tuned
  - conversation ai
  - chatbot
model-index:
  - name: results
    results: []
datasets:
  - nvl-og/chat
language:
  - en
  - th
metrics:
  - accuracy

results

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 6.1610

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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
14.5596 0.9978 14 9.4378
9.3982 1.9955 28 6.1610

Framework versions

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