Hugging Face's logo

butter-cake
/
llama3_full_three_epoch

Safetensors
llama
trl
sft
Generated from Trainer
Model card Files Community
llama3_full_three_epoch / README.md
butter-cake's picture
butter-cake
End of training
efa9491 verified
preview code
|
raw
history blame contribute delete
1.2 kB
metadata
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama3_full_three_epoch
    results: []

llama3_full_three_epoch

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset.

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: 8
  • seed: 42
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2

Training results

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.0