mvit_v1_b_Kinetics400_transf_b_rwf2000

DanJoshua/mvit_v1_b_Kinetics400_transf_b_rwf2000

mvit_v1_b_Kinetics400_transf_b_rwf2000 is a machine learning model from DanJoshua. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Aug 23, 2024

Parameters

36.7M

880 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors147 MB · 100%

At a glance

Library: transformers
Access: Public
Created: Aug 23, 2024
Updated: Aug 23, 2024
SHA: 24257042

Model card

From the Hugging Face model README

mvit_v1_b_Kinetics400_transf_b_rwf2000

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

Loss: 0.3804
Accuracy: 0.8938
F1: 0.8934
Precision: 0.8988

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: 1e-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
training_steps: 1900

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.501	0.1	190	0.5517	0.8	0.7985	0.8095
0.3591	1.1	380	0.3550	0.8688	0.8686	0.8702
0.2248	2.1	570	0.3302	0.8938	0.8937	0.8938
0.3274	3.1	760	0.3629	0.875	0.8748	0.8771
0.512	4.1	950	0.3528	0.8938	0.8937	0.8943
0.2008	5.1	1140	0.3804	0.8938	0.8934	0.8988

Framework versions

Transformers 4.44.2
Pytorch 2.0.1+cu118
Datasets 2.21.0
Tokenizers 0.19.1

Library: transformers
Created: Aug 23, 2024
Updated: Aug 23, 2024