|
--- |
|
license: mit |
|
base_model: camembert-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: camembert_question_answering_tools_fr |
|
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. --> |
|
|
|
# camembert_question_answering_tools_fr |
|
|
|
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8470 |
|
- Learning Rate: 0.0 |
|
|
|
## 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 | 4.1208 | 0.0001 | |
|
| No log | 2.0 | 14 | 3.2825 | 0.0001 | |
|
| No log | 3.0 | 21 | 3.0182 | 0.0001 | |
|
| No log | 4.0 | 28 | 2.8863 | 0.0001 | |
|
| No log | 5.0 | 35 | 2.8072 | 0.0001 | |
|
| No log | 6.0 | 42 | 2.7408 | 9e-05 | |
|
| No log | 7.0 | 49 | 2.6830 | 0.0001 | |
|
| No log | 8.0 | 56 | 2.6311 | 0.0001 | |
|
| No log | 9.0 | 63 | 2.5832 | 0.0001 | |
|
| No log | 10.0 | 70 | 2.5409 | 0.0001 | |
|
| No log | 11.0 | 77 | 2.5002 | 0.0001 | |
|
| No log | 12.0 | 84 | 2.4644 | 8e-05 | |
|
| No log | 13.0 | 91 | 2.6593 | 0.0001 | |
|
| No log | 14.0 | 98 | 3.1933 | 0.0001 | |
|
| No log | 15.0 | 105 | 2.8660 | 0.0001 | |
|
| No log | 16.0 | 112 | 2.8877 | 0.0001 | |
|
| No log | 17.0 | 119 | 2.8835 | 0.0001 | |
|
| No log | 18.0 | 126 | 3.1413 | 7e-05 | |
|
| No log | 19.0 | 133 | 2.3645 | 0.0001 | |
|
| No log | 20.0 | 140 | 2.6474 | 0.0001 | |
|
| No log | 21.0 | 147 | 2.6844 | 0.0001 | |
|
| No log | 22.0 | 154 | 2.6115 | 0.0001 | |
|
| No log | 23.0 | 161 | 2.6331 | 0.0001 | |
|
| No log | 24.0 | 168 | 2.6264 | 6e-05 | |
|
| No log | 25.0 | 175 | 2.8091 | 0.0001 | |
|
| No log | 26.0 | 182 | 3.0149 | 0.0001 | |
|
| No log | 27.0 | 189 | 3.1302 | 0.0001 | |
|
| No log | 28.0 | 196 | 3.3069 | 0.0001 | |
|
| No log | 29.0 | 203 | 2.9019 | 0.0001 | |
|
| No log | 30.0 | 210 | 2.9813 | 5e-05 | |
|
| No log | 31.0 | 217 | 3.0455 | 0.0000 | |
|
| No log | 32.0 | 224 | 2.5279 | 0.0000 | |
|
| No log | 33.0 | 231 | 2.3590 | 0.0000 | |
|
| No log | 34.0 | 238 | 2.1238 | 0.0000 | |
|
| No log | 35.0 | 245 | 2.0876 | 0.0000 | |
|
| No log | 36.0 | 252 | 2.2768 | 4e-05 | |
|
| No log | 37.0 | 259 | 2.1171 | 0.0000 | |
|
| No log | 38.0 | 266 | 2.0958 | 0.0000 | |
|
| No log | 39.0 | 273 | 2.1616 | 0.0000 | |
|
| No log | 40.0 | 280 | 2.0285 | 0.0000 | |
|
| No log | 41.0 | 287 | 1.8582 | 0.0000 | |
|
| No log | 42.0 | 294 | 1.7696 | 3e-05 | |
|
| No log | 43.0 | 301 | 1.6826 | 0.0000 | |
|
| No log | 44.0 | 308 | 2.1097 | 0.0000 | |
|
| No log | 45.0 | 315 | 1.8101 | 0.0000 | |
|
| No log | 46.0 | 322 | 1.8781 | 0.0000 | |
|
| No log | 47.0 | 329 | 1.6785 | 0.0000 | |
|
| No log | 48.0 | 336 | 1.7334 | 2e-05 | |
|
| No log | 49.0 | 343 | 1.7917 | 0.0000 | |
|
| No log | 50.0 | 350 | 1.6310 | 0.0000 | |
|
| No log | 51.0 | 357 | 1.5047 | 0.0000 | |
|
| No log | 52.0 | 364 | 1.6845 | 0.0000 | |
|
| No log | 53.0 | 371 | 1.6887 | 0.0000 | |
|
| No log | 54.0 | 378 | 1.6869 | 1e-05 | |
|
| No log | 55.0 | 385 | 1.6888 | 0.0000 | |
|
| No log | 56.0 | 392 | 1.7991 | 0.0000 | |
|
| No log | 57.0 | 399 | 1.8191 | 5e-06 | |
|
| No log | 58.0 | 406 | 1.8621 | 0.0000 | |
|
| No log | 59.0 | 413 | 1.8628 | 0.0000 | |
|
| No log | 60.0 | 420 | 1.8470 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
