pollen-ner-350

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: 0.7599
• Precision: 0.3086
• Recall: 0.1004
• F1: 0.1515

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: 5e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	44	0.9983	0.0	0.0	0.0
No log	2.0	88	0.9593	0.1818	0.0040	0.0079
No log	3.0	132	0.9094	0.2222	0.0080	0.0155
No log	4.0	176	0.8783	0.2647	0.0181	0.0338
No log	5.0	220	0.8430	0.1961	0.0201	0.0364
No log	6.0	264	0.8117	0.2809	0.0502	0.0852
No log	7.0	308	0.7908	0.2992	0.0763	0.1216
No log	8.0	352	0.7762	0.3	0.0904	0.1389
No log	9.0	396	0.7612	0.3020	0.0904	0.1391
No log	10.0	440	0.7599	0.3086	0.1004	0.1515

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.7.0+cu128
• Datasets 3.5.0
• Tokenizers 0.21.1