metadata

license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large
tags:
  - generated_from_trainer
model-index:
  - name: videomae-large_7class_UCFCrime
    results: []

videomae-large_7class_UCFCrime

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

eval_loss: 2.1295
eval_confusion_matrix: {'confusion_matrix': array([[ 7, 0, 1, 1, 39, 4, 0], [ 47, 42, 1, 0, 110, 43, 0], [ 1, 0, 37, 2, 0, 0, 9], [ 1, 0, 16, 52, 1, 0, 0], [ 4, 0, 1, 1, 107, 22, 7], [ 0, 0, 0, 0, 16, 54, 0], [ 0, 0, 4, 2, 14, 33, 59]])}
eval_runtime: 327.6535
eval_samples_per_second: 2.252
eval_steps_per_second: 1.126
step: 0

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: 2875

Framework versions

Transformers 4.39.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2