Hugging Face's logo

ShahlaDnshi96
/
llama-3-8b-QA

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
llama-3-8b-QA / README.md
ShahlaDnshi96's picture
ShahlaDnshi96
Model save
db1593b verified
preview code
|
raw
history blame contribute delete
1.6 kB
metadata
base_model: meta-llama/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama-3-8b-QA
    results: []

llama-3-8b-QA

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

  • Loss: 0.0577

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.5062 0.2034 48 0.4264
0.1255 0.4068 96 0.1244
0.0849 0.6102 144 0.0687
0.0347 0.8136 192 0.0577

Framework versions

  • PEFT 0.13.1
  • Transformers 4.45.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0