metadata
library_name: peft
license: cc-by-4.0
base_model: pczarnik/herbert-base-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: herbert-ner-lora-numbers
results: []
herbert-ner-lora-numbers
This model is a fine-tuned version of pczarnik/herbert-base-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0518
- Precision: 0.5800
- Recall: 0.7153
- F1: 0.6406
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.2409 | 1.0 | 649 | 0.0738 | 0.4740 | 0.6183 | 0.5366 |
| 0.0761 | 2.0 | 1298 | 0.0631 | 0.5253 | 0.6698 | 0.5888 |
| 0.0658 | 3.0 | 1947 | 0.0550 | 0.5657 | 0.7064 | 0.6283 |
| 0.0581 | 4.0 | 2596 | 0.0523 | 0.5832 | 0.7153 | 0.6425 |
| 0.0565 | 5.0 | 3245 | 0.0518 | 0.5800 | 0.7153 | 0.6406 |
Framework versions
- PEFT 0.12.0
- Transformers 4.50.3
- Pytorch 2.4.1
- Datasets 2.21.0
- Tokenizers 0.21.1