timesformer-base-finetuned-k400-finetuned-MicroLens_classification

Kartikeya/timesformer-base-finetuned-k400-finetuned-MicroLens_classification

timesformer-base-finetuned-k400-finetuned-MicroLens_classification is a video classification model from Kartikeya. 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 cc-by-nc-4.0.

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

Downloads · 30 days

6% of all-time downloads

All-time downloads

102

Public

Parameters

121M

3.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors485 MB · 100%

At a glance

Task: Video Classification
Library: transformers
License: cc-by-nc-4.0
Model type: timesformer
Access: Public
Created: Sep 3, 2025
Updated: Sep 7, 2025
SHA: 3fe2b687

Base models

facebook/timesformer-base-finetuned-k400

Model card

From the Hugging Face model README

timesformer-base-finetuned-k400-finetuned-MicroLens_classification

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6900
Accuracy: 0.5327
0 Precision: 0.5219
0 Recall: 0.8770
0 F1-score: 0.6544
0 Support: 88401.0
1 Precision: 0.5927
1 Recall: 0.1822
1 F1-score: 0.2787
1 Support: 86829.0
Accuracy F1-score: 0.5327
Macro avg Precision: 0.5573
Macro avg Recall: 0.5296
Macro avg F1-score: 0.4666
Macro avg Support: 175230.0
Weighted avg Precision: 0.5570
Weighted avg Recall: 0.5327
Weighted avg F1-score: 0.4682
Weighted avg Support: 175230.0

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: 16
eval_batch_size: 16
seed: 42
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: 11600

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	0 Precision	0 Recall	0 F1-score	0 Support	1 Precision	1 Recall	1 F1-score	1 Support	Accuracy F1-score	Macro avg Precision	Macro avg Recall	Macro avg F1-score	Macro avg Support	Weighted avg Precision	Weighted avg Recall	Weighted avg F1-score	Weighted avg Support
0.6962	0.05	580	0.6924	0.5439	0.5404	0.6402	0.5861	88401.0	0.5489	0.4457	0.4920	86829.0	0.5439	0.5447	0.5430	0.5390	175230.0	0.5446	0.5439	0.5395	175230.0
0.7128	1.05	1160	0.6996	0.4982	0.5020	0.6570	0.5691	88401.0	0.4908	0.3366	0.3993	86829.0	0.4982	0.4964	0.4968	0.4842	175230.0	0.4965	0.4982	0.4850	175230.0
0.7141	2.0501	1741	0.7067	0.5070	0.5611	0.1043	0.1759	88401.0	0.5014	0.9170	0.6483	86829.0	0.5070	0.5313	0.5106	0.4121	175230.0	0.5315	0.5070	0.4100	175230.0
0.7048	3.0501	2322	0.6925	0.5304	0.5485	0.3911	0.4566	88401.0	0.5202	0.6722	0.5865	86829.0	0.5304	0.5344	0.5317	0.5216	175230.0	0.5345	0.5304	0.5210	175230.0
0.6834	4.05	2902	0.6919	0.5342	0.5977	0.2343	0.3366	88401.0	0.5185	0.8395	0.6410	86829.0	0.5342	0.5581	0.5369	0.4888	175230.0	0.5585	0.5342	0.4875	175230.0
0.6908	5.0501	3483	0.6900	0.5327	0.5219	0.8770	0.6544	88401.0	0.5927	0.1822	0.2787	86829.0	0.5327	0.5573	0.5296	0.4666	175230.0	0.5570	0.5327	0.4682	175230.0

Framework versions

Transformers 4.46.3
Pytorch 2.0.0+cu117
Datasets 3.1.0
Tokenizers 0.20.3

Task: Video Classification
Library: transformers
Type: timesformer
License: cc-by-nc-4.0
Created: Sep 3, 2025
Updated: Sep 7, 2025