metadata
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: camembert_classification_tools_qlora
results: []
camembert_classification_tools_qlora
This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6740
- Accuracy: 0.425
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 5 | 2.0911 | 0.075 |
| No log | 2.0 | 10 | 2.1007 | 0.05 |
| No log | 3.0 | 15 | 2.1026 | 0.05 |
| No log | 4.0 | 20 | 2.0981 | 0.1 |
| No log | 5.0 | 25 | 2.0945 | 0.125 |
| No log | 6.0 | 30 | 2.0925 | 0.125 |
| No log | 7.0 | 35 | 2.0857 | 0.15 |
| No log | 8.0 | 40 | 2.0703 | 0.175 |
| No log | 9.0 | 45 | 2.0553 | 0.25 |
| No log | 10.0 | 50 | 2.0371 | 0.325 |
| No log | 11.0 | 55 | 2.0138 | 0.325 |
| No log | 12.0 | 60 | 1.9877 | 0.325 |
| No log | 13.0 | 65 | 1.9577 | 0.4 |
| No log | 14.0 | 70 | 1.9285 | 0.4 |
| No log | 15.0 | 75 | 1.9028 | 0.4 |
| No log | 16.0 | 80 | 1.8771 | 0.4 |
| No log | 17.0 | 85 | 1.8537 | 0.4 |
| No log | 18.0 | 90 | 1.8311 | 0.4 |
| No log | 19.0 | 95 | 1.8051 | 0.4 |
| No log | 20.0 | 100 | 1.7835 | 0.425 |
| No log | 21.0 | 105 | 1.7632 | 0.425 |
| No log | 22.0 | 110 | 1.7449 | 0.425 |
| No log | 23.0 | 115 | 1.7284 | 0.425 |
| No log | 24.0 | 120 | 1.7144 | 0.425 |
| No log | 25.0 | 125 | 1.7027 | 0.425 |
| No log | 26.0 | 130 | 1.6925 | 0.425 |
| No log | 27.0 | 135 | 1.6846 | 0.425 |
| No log | 28.0 | 140 | 1.6789 | 0.425 |
| No log | 29.0 | 145 | 1.6753 | 0.425 |
| No log | 30.0 | 150 | 1.6740 | 0.425 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1