bert-finetuned-gesture-prediction-9-classes

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the validation set:

• Loss: 0.6948
• Accuracy: 0.8332
• Precision: 0.8352
• Recall: 0.8332
• F1: 0.8311

It achieves the following results on the test set:

• Loss: 0.6337
• Accuracy: 0.8297
• Precision: 0.8365
• Recall: 0.8297
• F1: 0.8281

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

The model has been trained with the qfrodicio/gesture-prediction-9-classes dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• weight_decay: 0.01
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.6408	1.0	87	1.0168	0.7110	0.6825	0.7110	0.6559
0.7629	2.0	174	0.7777	0.7977	0.7863	0.7977	0.7856
0.4526	3.0	261	0.6951	0.8263	0.8276	0.8263	0.8199
0.285	4.0	348	0.6948	0.8332	0.8352	0.8332	0.8311
0.1788	5.0	435	0.7196	0.8277	0.8296	0.8277	0.8260
0.1246	6.0	522	0.7677	0.8314	0.8357	0.8314	0.8284
0.0866	7.0	609	0.7865	0.8407	0.8433	0.8407	0.8391
0.0629	8.0	696	0.8168	0.8435	0.8457	0.8435	0.8420
0.0489	9.0	783	0.8292	0.8417	0.8439	0.8417	0.8395
0.0398	10.0	870	0.8391	0.8443	0.8461	0.8443	0.8422

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2