|
--- |
|
license: mit |
|
base_model: pdelobelle/robbert-v2-dutch-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: robbert_seed37_1311 |
|
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. --> |
|
|
|
# robbert_seed37_1311 |
|
|
|
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: 0.3848 |
|
- Precisions: 0.8521 |
|
- Recall: 0.8198 |
|
- F-measure: 0.8327 |
|
- Accuracy: 0.9441 |
|
|
|
## 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: 7.5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 37 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 14 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:| |
|
| 0.4569 | 1.0 | 236 | 0.2571 | 0.7110 | 0.7130 | 0.7092 | 0.9217 | |
|
| 0.222 | 2.0 | 472 | 0.2286 | 0.7904 | 0.7574 | 0.7685 | 0.9313 | |
|
| 0.1311 | 3.0 | 708 | 0.2412 | 0.8047 | 0.7810 | 0.7875 | 0.9359 | |
|
| 0.0813 | 4.0 | 944 | 0.2755 | 0.8019 | 0.7775 | 0.7886 | 0.9354 | |
|
| 0.0552 | 5.0 | 1180 | 0.3120 | 0.8499 | 0.7793 | 0.8032 | 0.9409 | |
|
| 0.0323 | 6.0 | 1416 | 0.3536 | 0.8350 | 0.7955 | 0.8099 | 0.9402 | |
|
| 0.0212 | 7.0 | 1652 | 0.3789 | 0.8448 | 0.7817 | 0.8092 | 0.9405 | |
|
| 0.0154 | 8.0 | 1888 | 0.3835 | 0.8419 | 0.7780 | 0.7971 | 0.9385 | |
|
| 0.0119 | 9.0 | 2124 | 0.3906 | 0.8583 | 0.7812 | 0.8058 | 0.9388 | |
|
| 0.0081 | 10.0 | 2360 | 0.3910 | 0.8477 | 0.7874 | 0.8062 | 0.9424 | |
|
| 0.0052 | 11.0 | 2596 | 0.3839 | 0.8642 | 0.8087 | 0.8298 | 0.9431 | |
|
| 0.0046 | 12.0 | 2832 | 0.3848 | 0.8521 | 0.8198 | 0.8327 | 0.9441 | |
|
| 0.0018 | 13.0 | 3068 | 0.4017 | 0.8450 | 0.8125 | 0.8240 | 0.9438 | |
|
| 0.0014 | 14.0 | 3304 | 0.4060 | 0.8571 | 0.8088 | 0.8265 | 0.9441 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|