videomae-base-finetuned-ucf101-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: 2.3963
• Accuracy: 0.1154

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 36

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4449	0.3889	14	2.4051	0.0769
2.4615	1.3889	28	2.3911	0.1154
2.4631	2.2222	36	2.3963	0.1154

Framework versions

• Transformers 4.40.1
• Pytorch 2.1.2+rocm6.0
• Datasets 2.19.1
• Tokenizers 0.19.1