MoE_LlaVa_Qwen1.5_0.5bx4Top2_ChartVQA

This model is a fine-tuned version of TienAnh/stage3-moe-ft-llavaqwen1.5-0.5b-vista-5ep_moe_50k 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: 4
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• 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: 6.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• PEFT 0.4.0
• Transformers 4.37.0
• Pytorch 2.0.1+cu117
• Datasets 3.0.0
• Tokenizers 0.15.1