You can deploy this model and start earning money today!

alirzb/
WS800_SwinT_42820409

Name: WS800_SwinT_42820409
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

Views

No views yet

WS800_SwinT_42820409

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0091
Accuracy: 1.0

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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
No log	0.96	6	0.6706	0.9625
No log	1.92	12	0.4819	1.0
No log	2.88	18	0.2188	1.0
No log	4.0	25	0.0947	1.0
No log	4.96	31	0.0464	1.0
No log	5.92	37	0.0263	1.0
No log	6.88	43	0.0163	1.0
0.2515	8.0	50	0.0112	1.0
0.2515	8.96	56	0.0103	1.0
0.2515	9.6	60	0.0091	1.0

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0

alirzb/WS800_SwinT_42820409

WS800_SwinT_42820409

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

alirzb/
WS800_SwinT_42820409