windowz_ln_segment_122725

aholk/windowz_ln_segment_122725

windowz_ln_segment_122725 is a machine learning model from aholk. 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.

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

Downloads · 30 days

6% of all-time downloads

All-time downloads

Public

Parameters

544K

13.2 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.2 MB · 99%

At a glance

Library: transformers
Model type: Unet
Access: Public
Created: Jan 6, 2026
Updated: Jan 14, 2026
SHA: fbc7aeca

Model card

From the Hugging Face model README

windowz_ln_segment_122725

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Model Preparation Time: 0.0016
Accuracy: 0.5423
F1: 0.1626
Iou: 0.0940
Per Class Metrics: {0: {'f1': 0.22376, 'iou': 0.12597, 'accuracy': 0.97977}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}
Loss: 4.0417

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 OptimizerNames.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_steps: 1000
num_epochs: 0.02

Training results

Training Loss	Epoch	Step	Model Preparation Time		Class Metrics	Validation Loss
No log	0.0020	1	0.0016	0.0704	{0: {'f1': 0.05871, 'iou': 0.03024, 'accuracy': 0.60575}, 1: {'f1': 0.00033, 'iou': 0.00016, 'accuracy': 0.93957}, 2: {'f1': 0.08581, 'iou': 0.04483, 'accuracy': 0.09702}, 3: {'f1': 0.3423, 'iou': 0.20649, 'accuracy': 0.21595}}	4.0518
No log	0.0040	2	0.0016	0.0706	{0: {'f1': 0.05996, 'iou': 0.03091, 'accuracy': 0.61825}, 1: {'f1': 5e-05, 'iou': 2e-05, 'accuracy': 0.93958}, 2: {'f1': 0.0864, 'iou': 0.04515, 'accuracy': 0.09174}, 3: {'f1': 0.34182, 'iou': 0.20614, 'accuracy': 0.21372}}	4.0489
No log	0.0060	3	0.0016	0.0909	{0: {'f1': 0.20415, 'iou': 0.11368, 'accuracy': 0.9479}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0433
No log	0.0080	4	0.0016	0.0936	{0: {'f1': 0.22142, 'iou': 0.12449, 'accuracy': 0.97471}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0420
No log	0.0100	5	0.0016	0.0940	{0: {'f1': 0.22376, 'iou': 0.12597, 'accuracy': 0.97977}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0417
No log	0.0120	6	0.0016	0.0965	{0: {'f1': 0.23961, 'iou': 0.13611, 'accuracy': 0.9772}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0431
No log	0.0140	7	0.0016	0.0968	{0: {'f1': 0.24112, 'iou': 0.13708, 'accuracy': 0.9754}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08736, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0472
No log	0.0160	8	0.0016	0.096	{0: {'f1': 0.23636, 'iou': 0.13402, 'accuracy': 0.9745}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.93958}, 2: {'f1': 0.08737, 'iou': 0.04568, 'accuracy': 0.04568}, 3: {'f1': 0.33929, 'iou': 0.2043, 'accuracy': 0.2043}}	4.0510

Framework versions

Transformers 4.47.1
Pytorch 2.9.1+cpu
Datasets 4.5.0
Tokenizers 0.21.4

Library: transformers
Type: Unet
Created: Jan 6, 2026
Updated: Jan 14, 2026