Hemg/Birds-Species-classification

Source: 🤗image-classificationapache-2.086M params346 MBsafetensors✓ 30 checksumsupdated 971d ago

Birds-Species-classification

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: 0.1943
Accuracy: 0.9527

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: 0.0005
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: 16
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.2759	0.99	68	3.4103	0.86
1.7015	1.99	137	0.7510	0.8945
0.566	3.0	206	0.5793	0.8664
0.4301	4.0	275	0.4694	0.8909
0.3603	4.99	343	0.3995	0.9036
0.3032	5.99	412	0.3757	0.9036
0.2632	7.0	481	0.3843	0.9059
0.2211	8.0	550	0.3490	0.9123
0.1929	8.99	618	0.3618	0.9045
0.1645	9.99	687	0.2970	0.9241
0.1621	11.0	756	0.2874	0.93
0.1337	12.0	825	0.2705	0.9391
0.1238	12.99	893	0.2231	0.9436
0.1096	13.99	962	0.2440	0.9441
0.0979	15.0	1031	0.2371	0.9423
0.0808	15.83	1088	0.1943	0.9527

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Seed this model

Have the files? Submit a torrent.

Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from , and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Hemg/Birds-Species-classification ./model-folder