ViViT_wlasl_100_200ep_coR_

Shawon16/ViViT_wlasl_100_200ep_coR_

ViViT_wlasl_100_200ep_coR_ is a video classification model from Shawon16. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

463

Public

Parameters

88.7M

15.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors355 MB · 89%

At a glance

Task: Video Classification
Library: transformers
License: mit
Model type: vivit
Access: Public
Created: Dec 2, 2025
Updated: Dec 2, 2025
SHA: 01f3d0ce

Base models

google/vivit-b-16x2-kinetics400

Model card

From the Hugging Face model README

ViViT_wlasl_100_200ep_coR_

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.6046
Accuracy: 0.6716

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
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 36000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
18.8652	0.005	180	4.6810	0.0148
18.549	1.0050	360	4.6061	0.0325
18.0062	2.0050	540	4.5292	0.0414
17.0211	3.0050	721	4.3745	0.0710
15.802	4.005	901	4.1370	0.1036
14.0884	5.0050	1081	3.8357	0.1746
12.1547	6.0050	1261	3.5013	0.2633
10.1205	7.0050	1442	3.1863	0.3284
8.1175	8.005	1622	2.8482	0.3757
6.3088	9.0050	1802	2.5647	0.4704
4.6768	10.0050	1982	2.2896	0.5030
3.2458	11.0050	2163	2.0975	0.5444
2.2535	12.005	2343	1.9396	0.5799
1.428	13.0050	2523	1.7295	0.6006
0.8599	14.0050	2703	1.6543	0.6183
0.5308	15.0050	2884	1.5458	0.6124
0.3372	16.005	3064	1.5154	0.6095
0.1854	17.0050	3244	1.5216	0.6302
0.1656	18.0050	3424	1.4448	0.6361
0.0996	19.0050	3605	1.4351	0.6538
0.1046	20.005	3785	1.4932	0.6479
0.1091	21.0050	3965	1.2451	0.6893
0.0605	22.0050	4145	1.3669	0.6716
0.1048	23.0050	4326	1.3276	0.6982
0.0915	24.005	4506	1.3500	0.6746
0.0642	25.0050	4686	1.4862	0.6065
0.1054	26.0050	4866	1.6206	0.6154
0.1265	27.0050	5047	1.4605	0.6420
0.0877	28.005	5227	1.5949	0.6331
0.1579	29.0050	5407	1.5345	0.6450
0.1928	30.0050	5587	1.6247	0.6450
0.11	31.0050	5768	1.6054	0.6450
0.0869	32.005	5948	1.5318	0.6538
0.1257	33.0050	6128	1.7027	0.6420
0.1298	34.0050	6308	1.5279	0.6479
0.1271	35.0050	6489	1.5453	0.6420
0.1827	36.005	6669	1.7248	0.6391
0.0853	37.0050	6849	1.5689	0.6746
0.1227	38.0050	7029	1.8474	0.6065
0.1244	39.0050	7210	1.7365	0.6538
0.1471	40.005	7390	1.6086	0.6538
0.1105	41.0050	7570	1.7311	0.6509
0.1412	42.0050	7750	1.6021	0.6686
0.0758	43.0050	7931	1.6046	0.6716

Framework versions

Transformers 4.46.1
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.1

Task: Video Classification
Library: transformers
Type: vivit
License: mit
Created: Dec 2, 2025
Updated: Dec 2, 2025