videomae-base-finetuned-emonet-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: 1.9697
• Accuracy: 0.2892

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: 1755

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6831	0.33	586	2.2690	0.0505
1.737	1.33	1172	2.2291	0.3239
1.5042	2.33	1755	2.2894	0.0728

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1