videomae-base-finetuned-v2

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: 0.3288
• Accuracy: 0.8392

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: 16
• eval_batch_size: 16
• 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: 104

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6414	0.1346	14	0.9173	0.4545
0.6093	1.1346	28	0.6265	0.6364
0.5066	2.1346	42	0.5984	0.6364
0.3898	3.1346	56	0.4570	0.8
0.4321	4.1346	70	0.6020	0.7091
0.2806	5.1346	84	0.4016	0.8364
0.1498	6.1346	98	0.4253	0.8727
0.2482	7.0577	104	0.4269	0.8727

Framework versions

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