metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
base_model: cmarkea/distilcamembert-base
model-index:
- name: distilcamembert-cae-component
results: []
distilcamembert-cae-component
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: 0.3683
- Precision: 0.9317
- Recall: 0.9303
- F1: 0.9306
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 |
|---|---|---|---|---|---|---|
| 0.6221 | 1.0 | 309 | 0.3860 | 0.9007 | 0.8720 | 0.8761 |
| 0.1723 | 2.0 | 618 | 0.3505 | 0.9233 | 0.9157 | 0.9168 |
| 0.0604 | 3.0 | 927 | 0.3683 | 0.9317 | 0.9303 | 0.9306 |
| 0.0117 | 4.0 | 1236 | 0.4214 | 0.9311 | 0.9303 | 0.9304 |
| 0.0061 | 5.0 | 1545 | 0.4232 | 0.9317 | 0.9303 | 0.9305 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2