kuumba_model

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

• Loss: 0.0055
• Mse: 0.0055
• Mae: 0.0547
• R2: 0.9193

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: 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	Mse	Mae	R2
No log	1.0	61	0.0139	0.0139	0.0816	0.7959
No log	2.0	122	0.0093	0.0093	0.0796	0.8629
No log	3.0	183	0.0081	0.0081	0.0711	0.8809
No log	4.0	244	0.0064	0.0064	0.0586	0.9056
No log	5.0	305	0.0055	0.0055	0.0547	0.9193

Framework versions

• Transformers 4.46.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.20.3