README.md

metadata

library_name: transformers
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: windowz_test
    results: []

windowz_test

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

• Model Preparation Time: 0.001
• Accuracy: 0.9678
• F1: 0.9630
• Iou: 0.9377
• Loss: 0.1675

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Model Preparation Time		Validation Loss
1.0939	0.0501	257	0.001	0.5935	1.0369
1.0201	0.1003	514	0.001	0.6796	0.9606
0.9555	0.1504	771	0.001	0.7692	0.8134
0.8988	0.2005	1028	0.001	0.8883	0.4634
0.8663	0.2507	1285	0.001	0.9029	0.3463
0.8516	0.3008	1542	0.001	0.8728	0.3075
0.7798	0.3510	1799	0.001	0.9528	0.7747
0.7601	0.4011	2056	0.001	0.8082	0.5655
0.7723	0.4512	2313	0.001	0.9550	0.3013
0.7258	0.5014	2570	0.001	0.9673	0.1914
0.7085	0.5515	2827	0.001	0.9377	0.1675
0.7058	0.6016	3084	0.001	0.9406	0.2294
0.7008	0.6518	3341	0.001	0.9189	0.2342
0.6691	0.7019	3598	0.001	0.9404	0.2161

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.1+cu124
• Datasets 2.21.0
• Tokenizers 0.20.3