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: 1.1903
• Accuracy: 0.7335

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: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Use 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: 1920
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5817	0.1255	241	0.6961	0.6601
0.4524	1.1255	482	1.1878	0.6009
0.5473	2.1255	723	1.0509	0.6420
0.5044	3.1255	964	1.0045	0.6745
0.7258	4.1255	1205	0.9840	0.6567
0.3606	5.1255	1446	1.0898	0.7377
0.2423	6.1255	1687	1.0520	0.7460
0.3488	7.1214	1920	1.1903	0.7335

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3