You can deploy this model and start earning money today!

Seba42/
cifar100-butterfly-demo

Name: cifar100-butterfly-demo
Availability: InStock

Views

No views yet

cifar100-butterfly-demo

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

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 64
eval_batch_size: 64
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_ratio: 0.01
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.4272	1.0	782	3.4173	0.1836
3.13	2.0	1564	3.1456	0.2398
2.9701	3.0	2346	3.0407	0.264
2.7407	4.0	3128	2.9624	0.2742
2.5488	5.0	3910	2.9198	0.2884
2.4276	6.0	4692	2.9361	0.2964
2.2345	7.0	5474	2.9901	0.2967
2.0829	8.0	6256	3.0555	0.2905
1.9186	9.0	7038	3.1012	0.2903
1.8801	10.0	7820	3.1115	0.2904