ft_outputs_VIT – AI Model by jym02 | AlphaNeural AI

You can deploy this model and start earning money today!

jym02/
ft_outputs_VIT

like

0

image-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

ft_outputs_VIT

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

Loss: 0.4763
Mse: 0.4763
Rmse: 0.6901
Mae: 0.5614

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: 0
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Rmse	Mae
1.5236	0.24	40	0.5961	0.5961	0.7721	0.6121
0.744	0.48	80	0.5046	0.5046	0.7104	0.5766
0.7042	0.73	120	0.7303	0.7303	0.8546	0.6874
0.6464	0.97	160	0.5121	0.5121	0.7156	0.5672
0.5731	1.21	200	0.5052	0.5052	0.7108	0.5773
0.5585	1.45	240	0.6825	0.6825	0.8261	0.6646
0.6561	1.7	280	0.5252	0.5252	0.7247	0.5821
0.5569	1.94	320	0.5195	0.5195	0.7207	0.5825
0.5179	2.18	360	0.4983	0.4983	0.7059	0.5691
0.5308	2.42	400	0.5014	0.5014	0.7081	0.5678
0.5462	2.67	440	0.4963	0.4963	0.7045	0.5705
0.5499	2.91	480	0.4772	0.4772	0.6908	0.5621

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.3.2
Tokenizers 0.15.2