videomae-base-finetuned-rwf2000-subset – AI Model by DanJoshua | AlphaNeural AI

You can deploy this model and start earning money today!

DanJoshua/
videomae-base-finetuned-rwf2000-subset

like

0

video-classification

generated_from_trainer

MCG-NJU/videomae-base

endpoints_compatible

Views

No views yet

videomae-base-finetuned-rwf2000-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: 0.6551
Accuracy: 0.8187

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: 2790

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3956	0.0670	187	0.7066	0.7179
0.4019	1.0670	374	0.6282	0.7115
0.4473	2.0670	561	0.4394	0.7692
0.3309	3.0670	748	0.4782	0.7821
0.4007	4.0670	935	0.4135	0.8462
0.3772	5.0670	1122	0.4329	0.8462
0.4685	6.0670	1309	0.4191	0.8654
0.4056	7.0670	1496	0.5650	0.8013
0.2306	8.0670	1683	0.7093	0.8077
0.304	9.0670	1870	0.3939	0.8782
0.2418	10.0670	2057	0.5525	0.8333
0.2089	11.0670	2244	0.5139	0.8590
0.3158	12.0670	2431	0.5392	0.8590
0.1726	13.0670	2618	0.5430	0.8333
0.2543	14.0616	2790	0.4978	0.8718

Framework versions

Transformers 4.42.4
Pytorch 2.0.1+cu118
Datasets 2.20.0
Tokenizers 0.19.1