ComOM-VIDeBERTa-3

This model is a fine-tuned version of Fsoft-AIC/videberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0971
• Precision: 0.1319
• Recall: 0.1029
• F1: 0.1156
• Accuracy: 0.6647

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: 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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	78	1.2306	0.0768	0.0370	0.0499	0.6486
No log	2.0	156	1.1902	0.0755	0.0609	0.0674	0.6407
No log	3.0	234	1.1627	0.0923	0.0679	0.0783	0.6499
No log	4.0	312	1.1489	0.1159	0.0879	0.1000	0.6530
No log	5.0	390	1.1219	0.0997	0.0749	0.0856	0.6529
No log	6.0	468	1.1130	0.1245	0.0879	0.1030	0.6589
1.0673	7.0	546	1.1095	0.1247	0.0919	0.1058	0.6600
1.0673	8.0	624	1.0971	0.1319	0.1029	0.1156	0.6647

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1