|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0407 |
|
- Accuracy: 0.563 |
|
- F1: 0.5630 |
|
- Precision: 0.5631 |
|
- Recall: 0.563 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.0416 | 1.0 | 2500 | 1.0319 | 0.5479 | 0.5347 | 0.5392 | 0.5479 | |
|
| 0.9488 | 2.0 | 5000 | 1.0248 | 0.5594 | 0.5535 | 0.5540 | 0.5594 | |
|
| 0.8759 | 3.0 | 7500 | 1.0407 | 0.563 | 0.5630 | 0.5631 | 0.563 | |
|
| 0.7576 | 4.0 | 10000 | 1.1242 | 0.5553 | 0.5539 | 0.5533 | 0.5553 | |
|
| 0.6735 | 5.0 | 12500 | 1.2117 | 0.5528 | 0.5504 | 0.5500 | 0.5528 | |
|
| 0.5951 | 6.0 | 15000 | 1.2677 | 0.5464 | 0.5442 | 0.5427 | 0.5464 | |
|
| 0.5128 | 7.0 | 17500 | 1.4077 | 0.5401 | 0.5456 | 0.5570 | 0.5401 | |
|
| 0.4343 | 8.0 | 20000 | 1.4986 | 0.5416 | 0.5433 | 0.5458 | 0.5416 | |
|
| 0.3861 | 9.0 | 22500 | 1.5921 | 0.5402 | 0.5436 | 0.5497 | 0.5402 | |
|
| 0.3713 | 10.0 | 25000 | 1.6282 | 0.5376 | 0.5401 | 0.5438 | 0.5376 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
