ft-videomae-ucf101

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on the aisuko/funsd-layoutlmv3 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0175
• Accuracy: 1.0

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 150
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2154	0.5	75	0.1093	0.9857
0.0519	1.5	150	0.0175	1.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0