Raffel_bert_emotion_classification

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3423
• Accuracy: 0.9596

I train this model from kaggle dataset, you can access the dataset via this link : https://www.kaggle.com/datasets/abdallahwagih/emotion-dataset

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: 4e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	167	0.1212	0.9579
No log	2.0	334	0.1362	0.9596
0.1622	3.0	501	0.2034	0.9596
0.1622	4.0	668	0.2035	0.9630
0.1622	5.0	835	0.2153	0.9630
0.017	6.0	1002	0.2010	0.9613
0.017	7.0	1169	0.2718	0.9579
0.017	8.0	1336	0.2641	0.9613
0.0099	9.0	1503	0.2524	0.9613
0.0099	10.0	1670	0.2918	0.9579
0.0099	11.0	1837	0.2749	0.9562
0.0029	12.0	2004	0.3133	0.9562
0.0029	13.0	2171	0.2952	0.9579
0.0029	14.0	2338	0.3334	0.9596
0.0022	15.0	2505	0.3286	0.9596
0.0022	16.0	2672	0.3340	0.9596
0.0022	17.0	2839	0.3344	0.9596
0.0013	18.0	3006	0.3395	0.9596
0.0013	19.0	3173	0.3423	0.9596
0.0013	20.0	3340	0.3423	0.9596

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1