DSC_CafeBERT_finetuned

This model is a fine-tuned version of uitnlp/CafeBERT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6959
• Accuracy: 0.7607
• F1 Macro: 0.7630

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: 56
• eval_batch_size: 56
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
No log	1.0	100	0.8844	0.5771	0.5354
No log	2.0	200	0.6934	0.7364	0.7330
No log	3.0	300	0.6959	0.7607	0.7630
No log	4.0	400	0.7903	0.7471	0.7475
0.6318	5.0	500	0.8440	0.7393	0.7383
0.6318	6.0	600	0.9619	0.7286	0.7301

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2