metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: robbert2809_lrate10
results: []
robbert2809_lrate10
This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3760
- Precision: 0.7615
- Recall: 0.7517
- F1: 0.7566
- Accuracy: 0.8990
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 118 | 0.4116 | 0.7166 | 0.7104 | 0.7135 | 0.8906 |
| No log | 2.0 | 236 | 0.3760 | 0.7615 | 0.7517 | 0.7566 | 0.8990 |
| No log | 3.0 | 354 | 0.4114 | 0.7428 | 0.7692 | 0.7558 | 0.9019 |
| No log | 4.0 | 472 | 0.4230 | 0.7881 | 0.7844 | 0.7862 | 0.9131 |
| 0.1527 | 5.0 | 590 | 0.4550 | 0.7858 | 0.7716 | 0.7786 | 0.9092 |
| 0.1527 | 6.0 | 708 | 0.4553 | 0.7876 | 0.8019 | 0.7947 | 0.9188 |
| 0.1527 | 7.0 | 826 | 0.4824 | 0.7864 | 0.8001 | 0.7932 | 0.9181 |
| 0.1527 | 8.0 | 944 | 0.4973 | 0.7922 | 0.7978 | 0.7950 | 0.9196 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3