eduviolence-16class-checkpoints-proposed_eventlevel_timesformer_transformer_dynamic

fushipro123/eduviolence-16class-checkpoints-proposed_eventlevel_timesformer_transformer_dynamic

eduviolence-16class-checkpoints-proposed_eventlevel_timesformer_transformer_dynamic is a machine learning model from fushipro123. 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. The card lists the license as cc-by-nc-4.0.

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

Downloads · 30 days

Access

Public

Updated Aug 29, 2026

Parameters

130M

20.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt1 GB · 50%

At a glance

Library: transformers
License: cc-by-nc-4.0
Access: Public
Created: Aug 29, 2026
Updated: Aug 29, 2026
SHA: b429cc35

Base models

facebook/timesformer-base-finetuned-k400

Model card

From the Hugging Face model README

eduviolence-16class-checkpoints-proposed_eventlevel_timesformer_transformer_dynamic

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: 0.8067
Top1 Macro F1: 0.8214
Top1 Acc: 0.8283
Top5 Acc: 0.9849

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.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_steps: 100
num_epochs: 16
mixed_precision_training: Native AMP
label_smoothing_factor: 0.05

Training results

Training Loss	Epoch	Step	Validation Loss	Top1 Acc	Top1 Macro F1	Top5 Acc
4.7151	0.5051	100	1.8794	0.5361	0.5092	0.8705
2.8384	1.0101	200	1.2383	0.6807	0.6466	0.9639
2.0762	1.5152	300	1.0326	0.7470	0.7283	0.9819
1.8073	2.0202	400	0.9434	0.7831	0.7735	0.9789
1.34	2.5253	500	0.9394	0.7440	0.7291	0.9849
1.4339	3.0303	600	0.8556	0.8042	0.7948	0.9849
1.2465	3.5354	700	0.8902	0.7831	0.7791	0.9789
1.0787	4.0404	800	0.8662	0.8163	0.8011	0.9819
0.985	4.5455	900	0.8243	0.8313	0.8233	0.9849
0.9372	5.0505	1000	0.8489	0.8223	0.8134	0.9819
0.8323	5.5051	1100	0.8278	0.8283	0.8170	0.9849
0.7848	5.5051	1200	0.8587	0.7874	0.7982	0.9819
0.877	6.0101	1300	0.8067	0.8214	0.8283	0.9849

Framework versions

Transformers 4.48.3
Pytorch 2.10.0+cu128
Datasets 5.0.0
Tokenizers 0.21.4

Library: transformers
License: cc-by-nc-4.0
Created: Aug 29, 2026
Updated: Aug 29, 2026