metadata
library_name: transformers
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: camembert-math-classification
results: []
camembert-math-classification
This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0166
- F1 Macro: 0.9987
- F1 Weighted: 0.9987
- F1 Correct: 1.0
- F1 Partiel: 0.9980
- F1 Incorrect: 0.9980
- Accuracy: 0.9987
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | F1 Correct | F1 Partiel | F1 Incorrect | Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| 0.6561 | 1.0 | 184 | 0.8086 | 0.4912 | 0.4912 | 0.8169 | 0.0204 | 0.6364 | 0.5675 |
| 0.1997 | 2.0 | 368 | 0.1530 | 0.9669 | 0.9669 | 0.9902 | 0.9513 | 0.9592 | 0.9669 |
| 0.0648 | 3.0 | 552 | 0.0360 | 0.9960 | 0.9960 | 1.0 | 0.9940 | 0.9941 | 0.9960 |
| 0.0261 | 4.0 | 736 | 0.0227 | 0.9974 | 0.9974 | 0.9980 | 0.9960 | 0.9980 | 0.9974 |
| 0.0147 | 5.0 | 920 | 0.0166 | 0.9987 | 0.9987 | 1.0 | 0.9980 | 0.9980 | 0.9987 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2