metadata
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
model-index:
- name: camembert_question_answering_tools_fr
results: []
camembert_question_answering_tools_fr
This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7647
- 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 | Rate |
|---|---|---|---|---|
| No log | 1.0 | 7 | 4.1015 | 0.0001 |
| No log | 2.0 | 14 | 3.2806 | 0.0001 |
| No log | 3.0 | 21 | 2.9722 | 0.0001 |
| No log | 4.0 | 28 | 2.8707 | 0.0001 |
| No log | 5.0 | 35 | 2.7841 | 0.0001 |
| No log | 6.0 | 42 | 2.7172 | 9e-05 |
| No log | 7.0 | 49 | 2.6598 | 0.0001 |
| No log | 8.0 | 56 | 2.6083 | 0.0001 |
| No log | 9.0 | 63 | 2.5637 | 0.0001 |
| No log | 10.0 | 70 | 2.5213 | 0.0001 |
| No log | 11.0 | 77 | 2.4843 | 0.0001 |
| No log | 12.0 | 84 | 2.4661 | 8e-05 |
| No log | 13.0 | 91 | 2.4349 | 0.0001 |
| No log | 14.0 | 98 | 2.4924 | 0.0001 |
| No log | 15.0 | 105 | 2.3981 | 0.0001 |
| No log | 16.0 | 112 | 2.5037 | 0.0001 |
| No log | 17.0 | 119 | 2.3250 | 0.0001 |
| No log | 18.0 | 126 | 2.4910 | 7e-05 |
| No log | 19.0 | 133 | 2.3392 | 0.0001 |
| No log | 20.0 | 140 | 2.5614 | 0.0001 |
| No log | 21.0 | 147 | 2.3671 | 0.0001 |
| No log | 22.0 | 154 | 3.1649 | 0.0001 |
| No log | 23.0 | 161 | 2.3988 | 0.0001 |
| No log | 24.0 | 168 | 2.7332 | 6e-05 |
| No log | 25.0 | 175 | 2.8618 | 0.0001 |
| No log | 26.0 | 182 | 3.0148 | 0.0001 |
| No log | 27.0 | 189 | 2.7647 | 0.0001 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1