MiniLM_uncased_classification_tools_classifier-only_fr
This model is a fine-tuned version of microsoft/MiniLM-L12-H384-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0829
- Accuracy: 0.075
- Learning Rate: 0.0001
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: 24
- eval_batch_size: 192
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Rate |
|---|---|---|---|---|---|
| No log | 1.0 | 7 | 2.0791 | 0.125 | 0.0001 |
| No log | 2.0 | 14 | 2.0797 | 0.075 | 0.0001 |
| No log | 3.0 | 21 | 2.0799 | 0.075 | 0.0001 |
| No log | 4.0 | 28 | 2.0804 | 0.075 | 0.0001 |
| No log | 5.0 | 35 | 2.0808 | 0.075 | 0.0001 |
| No log | 6.0 | 42 | 2.0813 | 0.075 | 9e-05 |
| No log | 7.0 | 49 | 2.0818 | 0.075 | 0.0001 |
| No log | 8.0 | 56 | 2.0820 | 0.075 | 0.0001 |
| No log | 9.0 | 63 | 2.0822 | 0.075 | 0.0001 |
| No log | 10.0 | 70 | 2.0827 | 0.075 | 0.0001 |
| No log | 11.0 | 77 | 2.0829 | 0.075 | 0.0001 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1