metadata

base_model: Nhanvi282/LLaVA_Qwen2.5_0.5b_SigLIPStage2
tags:
  - generated_from_trainer
model-index:
  - name: MoE_LlaVa_Qwen2.5_0.5bx4Top2_SigLIP
    results: []

MoE_LlaVa_Qwen2.5_0.5bx4Top2_SigLIP

This model is a fine-tuned version of Nhanvi282/LLaVA_Qwen2.5_0.5b_SigLIPStage2 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: 2e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 4.0
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.37.0
Pytorch 2.0.1+cu117
Datasets 3.0.1
Tokenizers 0.15.1