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: 0.0650
• Accuracy: 0.9714

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: 2
• eval_batch_size: 2
• 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: 1200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6019	0.125	150	2.0551	0.2571
1.1869	1.125	300	0.8491	0.7
0.5153	2.125	450	0.3884	0.8143
0.8658	3.125	600	0.7162	0.8286
0.0047	4.125	750	0.1311	0.9286
0.0082	5.125	900	0.1580	0.9571
0.0031	6.125	1050	0.1162	0.9714
0.0026	7.125	1200	0.0650	0.9714

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1