|
--- |
|
license: mit |
|
base_model: camembert-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: VogagenRelation |
|
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. --> |
|
|
|
# VogagenRelation |
|
|
|
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4869 |
|
- Accuracy: 0.9016 |
|
- Precision: 0.8671 |
|
- Recall: 0.9484 |
|
- F1: 0.9060 |
|
|
|
## 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 |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| No log | 0.21 | 100 | 0.6272 | 0.6729 | 0.6415 | 0.7828 | 0.7051 | |
|
| No log | 0.42 | 200 | 0.4933 | 0.7799 | 0.7406 | 0.8609 | 0.7962 | |
|
| No log | 0.62 | 300 | 0.4114 | 0.8431 | 0.8087 | 0.8984 | 0.8512 | |
|
| No log | 0.83 | 400 | 0.4483 | 0.8384 | 0.8054 | 0.8922 | 0.8466 | |
|
| 0.5445 | 1.04 | 500 | 0.4149 | 0.8525 | 0.7971 | 0.9453 | 0.8649 | |
|
| 0.5445 | 1.25 | 600 | 0.4221 | 0.8532 | 0.8038 | 0.9344 | 0.8642 | |
|
| 0.5445 | 1.46 | 700 | 0.4022 | 0.8712 | 0.8728 | 0.8688 | 0.8708 | |
|
| 0.5445 | 1.66 | 800 | 0.4083 | 0.8509 | 0.8013 | 0.9328 | 0.8621 | |
|
| 0.5445 | 1.87 | 900 | 0.4272 | 0.8704 | 0.8455 | 0.9062 | 0.8748 | |
|
| 0.3857 | 2.08 | 1000 | 0.3800 | 0.8759 | 0.8501 | 0.9125 | 0.8802 | |
|
| 0.3857 | 2.29 | 1100 | 0.4684 | 0.8673 | 0.8357 | 0.9141 | 0.8731 | |
|
| 0.3857 | 2.49 | 1200 | 0.4754 | 0.8634 | 0.8207 | 0.9297 | 0.8718 | |
|
| 0.3857 | 2.7 | 1300 | 0.4392 | 0.8681 | 0.8294 | 0.9266 | 0.8753 | |
|
| 0.3857 | 2.91 | 1400 | 0.5272 | 0.8470 | 0.7803 | 0.9656 | 0.8631 | |
|
| 0.2687 | 3.12 | 1500 | 0.3529 | 0.9016 | 0.8693 | 0.9453 | 0.9057 | |
|
| 0.2687 | 3.33 | 1600 | 0.3857 | 0.8899 | 0.8499 | 0.9469 | 0.8958 | |
|
| 0.2687 | 3.53 | 1700 | 0.3852 | 0.9016 | 0.8836 | 0.925 | 0.9038 | |
|
| 0.2687 | 3.74 | 1800 | 0.4860 | 0.8829 | 0.8365 | 0.9516 | 0.8904 | |
|
| 0.2687 | 3.95 | 1900 | 0.4014 | 0.9001 | 0.8657 | 0.9469 | 0.9045 | |
|
| 0.1785 | 4.16 | 2000 | 0.4295 | 0.8993 | 0.8655 | 0.9453 | 0.9037 | |
|
| 0.1785 | 4.37 | 2100 | 0.4592 | 0.8977 | 0.8550 | 0.9578 | 0.9035 | |
|
| 0.1785 | 4.57 | 2200 | 0.4392 | 0.9055 | 0.8844 | 0.9328 | 0.9080 | |
|
| 0.1785 | 4.78 | 2300 | 0.4659 | 0.9024 | 0.8759 | 0.9375 | 0.9057 | |
|
| 0.1785 | 4.99 | 2400 | 0.4059 | 0.9110 | 0.9021 | 0.9219 | 0.9119 | |
|
| 0.1098 | 5.2 | 2500 | 0.4869 | 0.9016 | 0.8671 | 0.9484 | 0.9060 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
