metadata

license: llama3
library_name: peft
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - yihanwang617/ultrachat_200k_processed_indicator_0.6_4k
model-index:
  - name: llama-3-qlora-ultrachat-200k-processed-indicator-0.6
    results: []

llama-3-qlora-ultrachat-200k-processed-indicator-0.6

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the yihanwang617/ultrachat_200k_processed_indicator_0.6_4k dataset. It achieves the following results on the evaluation set:

Loss: 1.0235

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: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.008	0.9997	3247	1.0235

Framework versions

PEFT 0.12.0
Transformers 4.40.1
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1