big-dfd

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3824
• eval_accuracy: 0.8759
• eval_runtime: 7483.6129
• eval_samples_per_second: 0.632
• eval_steps_per_second: 0.079
• epoch: 2.25
• step: 1029

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
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1372

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1