emotion_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: 1.3105
• Accuracy: 0.5188

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0819	1.0	10	2.0549	0.2375
2.0249	2.0	20	1.9696	0.3625
1.8988	3.0	30	1.8123	0.3937
1.7331	4.0	40	1.6707	0.4375
1.5894	5.0	50	1.5504	0.4938
1.4997	6.0	60	1.4963	0.5188
1.424	7.0	70	1.4749	0.4688
1.3576	8.0	80	1.4223	0.5125
1.2986	9.0	90	1.3850	0.5312
1.2358	10.0	100	1.3588	0.5375
1.2052	11.0	110	1.3226	0.55
1.1699	12.0	120	1.3446	0.525
1.1334	13.0	130	1.3223	0.525
1.1178	14.0	140	1.3089	0.575
1.1062	15.0	150	1.2776	0.5625

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Tokenizers 0.20.3