<!-- 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. -->
distilcamembert-cae-thinking
This model is a fine-tuned version of cmarkea/distilcamembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8373
- Precision: 0.7054
- Recall: 0.7089
- F1: 0.7057
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.1608 | 1.0 | 40 | 1.0292 | 0.1963 | 0.4430 | 0.2720 |
| 0.894 | 2.0 | 80 | 0.9292 | 0.6253 | 0.6203 | 0.5821 |
| 0.5266 | 3.0 | 120 | 0.8919 | 0.6564 | 0.6709 | 0.6485 |
| 0.2895 | 4.0 | 160 | 0.8319 | 0.7049 | 0.6835 | 0.6886 |
| 0.1669 | 5.0 | 200 | 0.8373 | 0.7054 | 0.7089 | 0.7057 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
