videomae-base-finetuned-ssv2-finetuned-ucfcrime-ep10

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.9717
• eval_accuracy: 0.8004
• eval_runtime: 868.8117
• eval_samples_per_second: 3.177
• eval_steps_per_second: 1.588
• epoch: 0.1
• step: 140

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: 1400

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3