metadata
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: FRA_party_tweets_climate
results: []
FRA_party_tweets_climate
This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0826
- Accuracy: 0.9857
- F1 Macro: 0.9853
- Accuracy Balanced: 0.9847
- F1 Micro: 0.9857
- Precision Macro: 0.9858
- Recall Macro: 0.9847
- Precision Micro: 0.9857
- Recall Micro: 0.9857
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 80
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2428 | 1.0 | 628 | 0.0792 | 0.9841 | 0.9836 | 0.9831 | 0.9841 | 0.9842 | 0.9831 | 0.9841 | 0.9841 |
| 0.058 | 2.0 | 1256 | 0.0925 | 0.9809 | 0.9804 | 0.9804 | 0.9809 | 0.9804 | 0.9804 | 0.9809 | 0.9809 |
| 0.0429 | 3.0 | 1884 | 0.0785 | 0.9857 | 0.9852 | 0.9846 | 0.9857 | 0.9859 | 0.9846 | 0.9857 | 0.9857 |
| 0.024 | 4.0 | 2512 | 0.0829 | 0.9857 | 0.9853 | 0.9847 | 0.9857 | 0.9858 | 0.9847 | 0.9857 | 0.9857 |
| 0.0202 | 5.0 | 3140 | 0.0826 | 0.9857 | 0.9853 | 0.9847 | 0.9857 | 0.9858 | 0.9847 | 0.9857 | 0.9857 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0