timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate16

Kartikeya/timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate16

timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate16 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

Public

Parameters

121M

4.9 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: Oct 11, 2025
Updated: Oct 17, 2025
SHA: f0249643

Base models

facebook/timesformer-base-finetuned-k400

Model card

From the Hugging Face model README

timesformer-base-finetuned-k400-finetuned-snapdata_short_classification-sample_rate16

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: 0.6607
Accuracy: 0.6590
0 Precision: 0.7498
0 Recall: 0.3966
0 F1-score: 0.5188
0 Support: 2002.0
1 Precision: 0.6296
1 Recall: 0.8857
1 F1-score: 0.7360
1 Support: 2318.0
Accuracy F1-score: 0.6590
Macro avg Precision: 0.6897
Macro avg Recall: 0.6411
Macro avg F1-score: 0.6274
Macro avg Support: 4320.0
Weighted avg Precision: 0.6853
Weighted avg Recall: 0.6590
Weighted avg F1-score: 0.6353
Weighted avg Support: 4320.0

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: 8
eval_batch_size: 8
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: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 62000
label_smoothing_factor: 0.1

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
0.7164	0.0200	1241	0.6246	0.6813	0.6716	0.6109	0.6398	2002.0	0.6883	0.7420	0.7141	2318.0	0.6813	0.6799	0.6765	0.6770	4320.0	0.6806	0.6813	0.6797	4320.0
0.6897	1.0200	2482	0.6288	0.6803	0.6527	0.6628	0.6577	2002.0	0.7049	0.6954	0.7001	2318.0	0.6803	0.6788	0.6791	0.6789	4320.0	0.6807	0.6803	0.6805	4320.0
0.5827	2.0200	3723	0.6261	0.6676	0.6171	0.7448	0.6750	2002.0	0.7316	0.6009	0.6599	2318.0	0.6676	0.6744	0.6729	0.6674	4320.0	0.6786	0.6676	0.6669	4320.0
0.615	3.0200	4964	0.6607	0.6590	0.7498	0.3966	0.5188	2002.0	0.6296	0.8857	0.7360	2318.0	0.6590	0.6897	0.6411	0.6274	4320.0	0.6853	0.6590	0.6353	4320.0

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: Oct 11, 2025
Updated: Oct 17, 2025