|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: robbertfinetuned0906 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# robbertfinetuned0906 |
|
|
|
This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5859 |
|
- Precision: 0.7151 |
|
- Recall: 0.7079 |
|
- F1: 0.7115 |
|
- Accuracy: 0.9186 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.046 | 1.0 | 580 | 0.5770 | 0.6912 | 0.6633 | 0.6769 | 0.9102 | |
|
| 0.0405 | 2.0 | 1160 | 0.5704 | 0.6996 | 0.6835 | 0.6914 | 0.9133 | |
|
| 0.0346 | 3.0 | 1740 | 0.5786 | 0.6951 | 0.7201 | 0.7074 | 0.9130 | |
|
| 0.0242 | 4.0 | 2320 | 0.5453 | 0.7098 | 0.7216 | 0.7157 | 0.9186 | |
|
| 0.0184 | 5.0 | 2900 | 0.6058 | 0.7118 | 0.7036 | 0.7077 | 0.9189 | |
|
| 0.0087 | 6.0 | 3480 | 0.5859 | 0.7151 | 0.7079 | 0.7115 | 0.9186 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|