lakoon_detection_and_classification

This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3925
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.9024

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	3	0.5621	0.0	0.0	0.0	0.9024
No log	2.0	6	0.5531	0.0	0.0	0.0	0.9024
No log	3.0	9	0.5385	0.0	0.0	0.0	0.9024
No log	4.0	12	0.5115	0.0	0.0	0.0	0.9024
No log	5.0	15	0.4984	0.0	0.0	0.0	0.9024
No log	6.0	18	0.4821	0.0	0.0	0.0	0.9024
No log	7.0	21	0.4703	0.0	0.0	0.0	0.9024
No log	8.0	24	0.4602	0.0	0.0	0.0	0.9024
No log	9.0	27	0.4391	0.0	0.0	0.0	0.9024
No log	10.0	30	0.4144	0.0	0.0	0.0	0.9024
No log	11.0	33	0.3966	0.0	0.0	0.0	0.9024
No log	12.0	36	0.3888	0.0	0.0	0.0	0.9024
No log	13.0	39	0.3883	0.0	0.0	0.0	0.9024
No log	14.0	42	0.3918	0.0	0.0	0.0	0.9024
No log	15.0	45	0.3969	0.0	0.0	0.0	0.9024
No log	16.0	48	0.3991	0.0	0.0	0.0	0.9024
No log	17.0	51	0.3983	0.0	0.0	0.0	0.9024
No log	18.0	54	0.3959	0.0	0.0	0.0	0.9024
No log	19.0	57	0.3932	0.0	0.0	0.0	0.9024
No log	20.0	60	0.3925	0.0	0.0	0.0	0.9024

Framework versions

• Transformers 4.52.2
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1