Edit model card

stage3-moe-ft-llavaqwen1.5-0.5b-vista-5ep_moe-halongfil

This model is a fine-tuned version of Nhanvi282/stage2-llavaqwen1.5-0.5B-vista-5ep-halong 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: 4.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.37.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.21.0
  • Tokenizers 0.15.1
Downloads last month
2
Safetensors
Model size
1.03B params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Nhanvi282/stage3-moe-ft-llavaqwen1.5-0.5b-vista-5ep-halongfil