phi-4-multimodal-instruct-lttc

This model is a fine-tuned version of microsoft/Phi-4-multimodal-instruct on a private dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

  • Finetune on ntnu-smil/LTTC-Train-1764-0520 without giving original question,image
  • Test on ntnu-smil/LTTC-dev-1764-0520

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 4e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 2

Training results

0.806 on Accuracy (abs(prediction-truth label)<= 0.5)

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.6.0+cu124
  • Datasets 3.4.1
  • Tokenizers 0.21.1
Downloads last month
9
Safetensors
Model size
5.57B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ntnu-smil/phi-4-multimodal-instruct-lttc

Finetuned
(30)
this model
Finetunes
1 model

Datasets used to train ntnu-smil/phi-4-multimodal-instruct-lttc