videomae-base-finetuned-sdfvd-subset

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:

• Loss: 0.6996
• Accuracy: 0.5

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: 28

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.2857	8	0.7069	0.5
0.7565	1.2857	16	0.7133	0.5
0.7131	2.2857	24	0.7165	0.4444
0.7131	3.1429	28	0.7159	0.4444

Framework versions

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