out – AI Model by nnaatt | AlphaNeural AI

You can deploy this model and start earning money today!

nnaatt/
out

like

0

image-classification

generated_from_trainer

google/vit-base-patch16-224

autotrain_compatible

endpoints_compatible

Views

No views yet

out

This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3251
Accuracy: 0.8761

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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6237	0.99	43	0.5558	0.7302
0.462	1.99	86	0.4139	0.8248
0.4174	2.98	129	0.3704	0.8468
0.4089	4.0	173	0.4138	0.8231
0.3656	4.99	216	0.3322	0.8688
0.3282	5.99	259	0.3251	0.8761
0.3251	6.98	302	0.3296	0.8696
0.3025	8.0	346	0.3221	0.8720
0.2937	8.99	389	0.3218	0.8729
0.2812	9.94	430	0.3219	0.8753

Framework versions

Transformers 4.35.2
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.15.0