metadata
library_name: peft
base_model: DeepPavlov/bert-base-bg-cs-pl-ru-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: pollen-ner2-650
results: []
pollen-ner2-650
This model is a fine-tuned version of DeepPavlov/bert-base-bg-cs-pl-ru-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2844
- Precision: 0.6701
- Recall: 0.7871
- F1: 0.7239
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 | 82 | 0.3143 | 0.6285 | 0.7610 | 0.6885 |
| No log | 2.0 | 164 | 0.3069 | 0.6459 | 0.7691 | 0.7021 |
| No log | 3.0 | 246 | 0.2976 | 0.6525 | 0.7691 | 0.7060 |
| No log | 4.0 | 328 | 0.2903 | 0.6672 | 0.7771 | 0.7180 |
| No log | 5.0 | 410 | 0.2978 | 0.6454 | 0.7932 | 0.7117 |
| No log | 6.0 | 492 | 0.2844 | 0.6701 | 0.7871 | 0.7239 |
| 0.6003 | 7.0 | 574 | 0.2880 | 0.6616 | 0.7892 | 0.7198 |
| 0.6003 | 8.0 | 656 | 0.2809 | 0.6638 | 0.7851 | 0.7194 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu128
- Datasets 3.5.0
- Tokenizers 0.21.1