Hugging Face's logo

pkbiswas
/
Llama-3-8B-Summarization-QLoRa

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Llama-3-8B-Summarization-QLoRa / README.md
pkbiswas's picture
pkbiswas
End of training
19c2ce8 verified
preview code
|
raw
history blame contribute delete
1.56 kB
metadata
license: other
library_name: peft
tags:
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - scitldr
model-index:
  - name: Llama-3-8B-Summarization-QLoRa
    results: []

Llama-3-8B-Summarization-QLoRa

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

  • Loss: 2.4051

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

Training results

Training Loss Epoch Step Validation Loss
2.226 0.5020 500 2.3232
2.2207 1.0040 1000 2.3130
1.6901 1.5060 1500 2.4051

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1