2025-06-07_19-28-29 – AI Model by Jedrzej-Smok | AlphaNeural AI

You can deploy this model and start earning money today!

Jedrzej-Smok/
2025-06-07_19-28-29

like

0

generated_from_trainer

endpoints_compatible

Views

No views yet

2025-06-07_19-28-29

This model is a fine-tuned version of nvidia/mit-b0 on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.6029
Mean Iou: 0.4567
Mean Accuracy: 0.8572
Overall Accuracy: 0.8319
Per Category Iou: [0.8292291767303844, 0.08412248019936341]
Per Category Accuracy: [0.8309502163983278, 0.8833557881645766]

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: 6e-05
train_batch_size: 16
eval_batch_size: 16
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: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.6868	3.3333	20	0.6029	0.4567	0.8572	0.8319	[0.8292291767303844, 0.08412248019936341]	[0.8309502163983278, 0.8833557881645766]

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1