Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
beit-base-patch16-224-pt22k-ft22k-finetuning – AI Model by Rocky807 | AlphaNeural AI
You can deploy this model and start earning money today!
Rocky807
/
beit-base-patch16-224-pt22k-ft22k-finetuning
like
0
transformers
tensorboard
safetensors
beit
image-classification
generated_from_trainer
microsoft/beit-base-patch16-224-pt22k-ft22k
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
beit-base-patch16-224-pt22k-ft22k-finetuning
This model is a fine-tuned version of
microsoft/beit-base-patch16-224-pt22k-ft22k
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.2268
Accuracy: 0.921
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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.3814
0.9979
351
0.3500
0.8838
0.3251
1.9986
703
0.2797
0.9042
0.2368
2.9936
1053
0.2436
0.9168
Framework versions
Transformers 4.41.0.dev0
Pytorch 2.2.2
Datasets 2.18.0
Tokenizers 0.19.1
