BirdsSpecies_vit_finetune

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1649
• Accuracy: 0.9545

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
0.824	0.9984	468	0.8012	0.9212
0.3097	1.9989	937	0.3637	0.9291
0.2615	2.9995	1406	0.2659	0.9383
0.2235	4.0	1875	0.2108	0.9464
0.1777	4.9984	2343	0.2156	0.9444
0.1927	5.9989	2812	0.2014	0.9453
0.2229	6.9995	3281	0.1893	0.9485
0.1299	8.0	3750	0.1622	0.9555
0.1525	8.9984	4218	0.1548	0.9584
0.1377	9.984	4680	0.1649	0.9545

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1