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-datetime
results: []
herbert-ner-lora-datetime
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: 0.0326
- Precision: 0.5051
- Recall: 0.4902
- F1: 0.4975
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 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 92 | 0.1005 | 0.2308 | 0.0882 | 0.1277 |
| No log | 2.0 | 184 | 0.0583 | 0.4211 | 0.2745 | 0.3323 |
| No log | 3.0 | 276 | 0.0422 | 0.4105 | 0.3824 | 0.3959 |
| No log | 4.0 | 368 | 0.0346 | 0.4899 | 0.4755 | 0.4826 |
| No log | 5.0 | 460 | 0.0326 | 0.5051 | 0.4902 | 0.4975 |
Framework versions
- PEFT 0.12.0
- Transformers 4.50.3
- Pytorch 2.4.1
- Datasets 2.21.0
- Tokenizers 0.21.1