pollen-ner-400

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: 0.5198
• Precision: 0.4615
• Recall: 0.5783
• F1: 0.5134

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	50	0.7012	0.3902	0.2068	0.2703
No log	2.0	100	0.6521	0.4251	0.3193	0.3647
No log	3.0	150	0.6239	0.4528	0.4337	0.4431
No log	4.0	200	0.5779	0.468	0.4699	0.4689
No log	5.0	250	0.5643	0.4563	0.5241	0.4879
No log	6.0	300	0.5509	0.4485	0.5422	0.4909
No log	7.0	350	0.5305	0.4621	0.5502	0.5023
No log	8.0	400	0.5256	0.4633	0.5703	0.5113
No log	9.0	450	0.5217	0.4613	0.5743	0.5116
0.9652	10.0	500	0.5198	0.4615	0.5783	0.5134

Framework versions

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