videomae-base-Vsl-Lab-PC-V7

Ham1mad1/videomae-base-Vsl-Lab-PC-V7

videomae-base-Vsl-Lab-PC-V7 is a video classification model from Ham1mad1. 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.

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

Downloads · 30 days

4% of all-time downloads

All-time downloads

346

Public

Parameters

86.2M

13.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

Task: Video Classification
Library: transformers
Model type: videomae
Access: Public
Created: Apr 3, 2024
Updated: Apr 25, 2024
SHA: dfb4b5e6

Model card

From the Hugging Face model README

videomae-base-Vsl-Lab-PC-V7

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.1302
Accuracy: 0.8326

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: 10
eval_batch_size: 10
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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2342	0.02	81	1.2321	0.7854
0.134	1.02	162	1.1259	0.8112
0.0524	2.02	243	1.2486	0.7768
0.0214	3.02	324	1.2101	0.8155
0.0607	4.02	405	1.3376	0.7897
0.0624	5.02	486	1.4538	0.7811
0.013	6.02	567	1.4118	0.7854
0.0545	7.02	648	1.8297	0.7511
0.0834	8.02	729	1.2903	0.7897
0.0261	9.02	810	1.3051	0.7983
0.1063	10.02	891	1.3785	0.7725
0.0011	11.02	972	1.3544	0.7940
0.0002	12.02	1053	1.1987	0.8326
0.0001	13.02	1134	1.1977	0.8283
0.0001	14.02	1215	1.1963	0.8326
0.0001	15.02	1296	1.1962	0.8326
0.0001	16.02	1377	1.1868	0.8369
0.0001	17.02	1458	1.0947	0.8326
0.0001	18.02	1539	1.1421	0.8283
0.007	19.02	1620	1.3070	0.7854
0.0001	20.02	1701	1.1657	0.8155
0.0001	21.02	1782	1.1627	0.8112
0.0001	22.02	1863	1.1432	0.8197
0.0001	23.02	1944	1.1271	0.8155
0.0001	24.02	2025	1.1188	0.8283
0.0957	25.02	2106	1.2623	0.8155
0.0001	26.02	2187	1.0093	0.8498
0.0001	27.02	2268	1.0397	0.8498
0.0001	28.02	2349	1.0425	0.8498
0.0001	29.02	2430	1.0113	0.8369
0.0001	30.02	2511	1.0144	0.8369
0.0001	31.02	2592	1.0132	0.8369
0.0001	32.02	2673	1.0325	0.8326
0.0321	33.02	2754	1.1152	0.8283
0.0001	34.02	2835	1.1767	0.8069
0.0001	35.02	2916	1.1709	0.8112
0.0001	36.02	2997	1.1632	0.8155
0.0001	37.02	3078	1.1567	0.8197
0.0001	38.02	3159	1.1511	0.8197
0.0001	39.02	3240	1.1263	0.8283
0.0001	40.02	3321	1.1233	0.8283
0.0001	41.02	3402	1.1222	0.8326
0.0001	42.02	3483	1.1212	0.8283
0.0001	43.02	3564	1.1206	0.8283
0.0001	44.02	3645	1.1200	0.8283
0.0001	45.02	3726	1.1197	0.8283
0.0001	46.02	3807	1.1243	0.8283
0.0001	47.02	3888	1.1303	0.8326
0.0001	48.02	3969	1.1302	0.8326
0.0001	49.01	4000	1.1302	0.8326

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Video Classification
Library: transformers
Type: videomae
Created: Apr 3, 2024
Updated: Apr 25, 2024