metadata

license: llama3
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: llava-hf/llama3-llava-next-8b-hf
model-index:
  - name: llama3-llava-next-8b-SCAND
    results: []

llama3-llava-next-8b-SCAND

This model is a fine-tuned version of llava-hf/llama3-llava-next-8b-hf on an unknown 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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 3
total_train_batch_size: 96
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.0
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.12.0
Transformers 4.44.0
Pytorch 2.3.0+cu121
Datasets 2.16.1
Tokenizers 0.19.1