rgai_emotion_recognition

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

• Loss: 1.3077
• Accuracy: 0.5813

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: 2e-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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0698	1.0	25	2.0921	0.1125
1.973	2.0	50	1.9930	0.1938
1.8091	3.0	75	1.8374	0.3937
1.5732	4.0	100	1.6804	0.475
1.4087	5.0	125	1.5660	0.5125
1.2653	6.0	150	1.4769	0.5375
1.1443	7.0	175	1.4084	0.55
0.9888	8.0	200	1.3633	0.5625
0.9029	9.0	225	1.3305	0.55
0.8372	10.0	250	1.3077	0.5813
0.7569	11.0	275	1.2983	0.5625
0.6886	12.0	300	1.2806	0.5687
0.6216	13.0	325	1.2718	0.5687
0.6385	14.0	350	1.2700	0.5563
0.6029	15.0	375	1.2693	0.5625

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3