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: 0.5280
• Accuracy: 0.8051

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: 1300

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5307	0.1008	131	0.5135	0.7897
0.7467	1.1008	262	0.4954	0.7863
0.5834	2.1008	393	0.5522	0.7419
0.5894	3.1008	524	0.5229	0.8171
0.536	4.1008	655	0.4529	0.8154
0.5135	5.1008	786	0.4495	0.8205
0.4498	6.1008	917	0.5333	0.8034
0.5968	7.1008	1048	0.5310	0.8205
0.5063	8.1008	1179	0.5089	0.8137
0.4491	9.0931	1300	0.5280	0.8051

Framework versions

• Transformers 4.42.4
• Pytorch 2.0.1+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1