Model save

7e03bcb verified about 1 year ago

2 kB

license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: VideoMAE-UnrealFallDataset
    results: []

VideoMAE-UnrealFallDataset

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: 0.1096
Accuracy: 0.9733

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: 8
eval_batch_size: 8
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: 11770

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8643	0.1	1178	2.1285	0.5080
0.743	1.1	2356	1.1040	0.6968
0.2881	2.1	3534	0.4485	0.8779
0.1943	3.1	4712	0.4007	0.8871
0.08	4.1	5890	0.2446	0.9381
0.0666	5.1	7068	0.3504	0.9131
0.0825	6.1	8246	0.2022	0.9470
0.0059	7.1	9424	0.1628	0.9607
0.0648	8.1	10602	0.1387	0.9639
0.002	9.1	11770	0.1096	0.9733

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1