Hugging Face's logo

dhanishetty
/
Llama-3-8B-Adapters

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Llama-3-8B-Adapters / README.md
dhanishetty's picture
dhanishetty
dhanishetty/llama_adapters
a35a022 verified
preview code
|
raw
history blame contribute delete
2.03 kB
metadata
base_model: meta-llama/Meta-Llama-3-8B
library_name: peft
license: llama3
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama-qLoRA
    results: []

Visualize in Weights & Biases

llama-qLoRA

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9713

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-06
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: inverse_sqrt
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.9835 0.3350 500 2.0047
1.97 0.6700 1000 1.9901
1.9764 1.0050 1500 1.9838
1.9714 1.3400 2000 1.9799
1.9547 1.6750 2500 1.9770
1.981 2.0101 3000 1.9747
1.9841 2.3451 3500 1.9729
1.9469 2.6801 4000 1.9713

Framework versions

  • PEFT 0.12.0
  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1