SPIE_MULTICLASS_CHINA_2_2

This model is a fine-tuned version of Visual-Attention-Network/van-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3552
• Accuracy: 0.8969

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: 2
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7225	0.96	18	1.1618	0.7176
0.9126	1.9733	37	0.6123	0.8403
0.5284	2.9867	56	0.4291	0.875
0.4014	4.0	75	0.3605	0.895
0.3638	4.8	90	0.3552	0.8969

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0