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-ner2-600
results: []
pollen-ner2-600
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: 0.3100
- Precision: 0.6451
- Recall: 0.7590
- F1: 0.6974
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 | 75 | 0.3387 | 0.6186 | 0.7329 | 0.6710 |
| No log | 2.0 | 150 | 0.3311 | 0.6181 | 0.7410 | 0.6740 |
| No log | 3.0 | 225 | 0.3248 | 0.6336 | 0.7430 | 0.6839 |
| No log | 4.0 | 300 | 0.3310 | 0.6120 | 0.7570 | 0.6768 |
| No log | 5.0 | 375 | 0.3218 | 0.6326 | 0.7570 | 0.6892 |
| No log | 6.0 | 450 | 0.3154 | 0.6342 | 0.7590 | 0.6910 |
| 0.65 | 7.0 | 525 | 0.3154 | 0.6332 | 0.7590 | 0.6904 |
| 0.65 | 8.0 | 600 | 0.3125 | 0.6396 | 0.7590 | 0.6942 |
| 0.65 | 9.0 | 675 | 0.3085 | 0.6449 | 0.7550 | 0.6957 |
| 0.65 | 10.0 | 750 | 0.3100 | 0.6451 | 0.7590 | 0.6974 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu128
- Datasets 3.5.0
- Tokenizers 0.21.1