|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: distilcamembert-cae-no-thinking |
|
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. --> |
|
|
|
# distilcamembert-cae-no-thinking |
|
|
|
This model is a fine-tuned version of [cmarkea/distilcamembert-base](https://huggingface.co/cmarkea/distilcamembert-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5464 |
|
- Precision: 0.7959 |
|
- Recall: 0.7848 |
|
- F1: 0.7869 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:| |
|
| 1.1607 | 1.0 | 40 | 0.9958 | 0.6444 | 0.4684 | 0.3248 | |
|
| 1.0099 | 2.0 | 80 | 0.9761 | 0.6090 | 0.5316 | 0.4480 | |
|
| 0.6294 | 3.0 | 120 | 0.6770 | 0.8067 | 0.7215 | 0.7542 | |
|
| 0.3294 | 4.0 | 160 | 0.5464 | 0.7959 | 0.7848 | 0.7869 | |
|
| 0.1986 | 5.0 | 200 | 0.5440 | 0.7882 | 0.7722 | 0.7785 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
