|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilBERT_without_preprocessing_grid_search |
|
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. --> |
|
|
|
# distilBERT_without_preprocessing_grid_search |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co./distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8909 |
|
- Precision: 0.8485 |
|
- Recall: 0.8467 |
|
- F1: 0.8467 |
|
- Accuracy: 0.8857 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.9219 | 1.0 | 514 | 0.5751 | 0.8031 | 0.8211 | 0.8091 | 0.8658 | |
|
| 0.4593 | 2.0 | 1028 | 0.5435 | 0.8461 | 0.8372 | 0.8333 | 0.8789 | |
|
| 0.2853 | 3.0 | 1542 | 0.6109 | 0.8362 | 0.8385 | 0.8347 | 0.8794 | |
|
| 0.2159 | 4.0 | 2056 | 0.6320 | 0.8349 | 0.8681 | 0.8492 | 0.8847 | |
|
| 0.1531 | 5.0 | 2570 | 0.6988 | 0.8564 | 0.8532 | 0.8536 | 0.8901 | |
|
| 0.1223 | 6.0 | 3084 | 0.8081 | 0.8447 | 0.8476 | 0.8456 | 0.8833 | |
|
| 0.1073 | 7.0 | 3598 | 0.7644 | 0.8366 | 0.8501 | 0.8425 | 0.8833 | |
|
| 0.0958 | 8.0 | 4112 | 0.8606 | 0.8522 | 0.8468 | 0.8488 | 0.8847 | |
|
| 0.0769 | 9.0 | 4626 | 0.8468 | 0.8475 | 0.8482 | 0.8472 | 0.8857 | |
|
| 0.061 | 10.0 | 5140 | 0.8909 | 0.8485 | 0.8467 | 0.8467 | 0.8857 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
