classla_bcms_BG

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

• Loss: 0.5426
• Accuracy: 0.7701
• F1: 0.6
• Precision: 0.4688
• Recall: 0.8333

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: 8
• eval_batch_size: 8
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	44	0.5137	0.7471	0.5926	0.4444	0.8889
No log	2.0	88	0.4167	0.7931	0.5909	0.5	0.7222
No log	3.0	132	0.6326	0.7241	0.6	0.4286	1.0
No log	4.0	176	0.5422	0.7701	0.6	0.4688	0.8333
No log	5.0	220	0.5426	0.7701	0.6	0.4688	0.8333

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0