| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: distilbert-base-uncased |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: db_himp_4.2 |
| 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. --> |
|
|
| # db_himp_4.2 |
|
|
| 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: 0.6350 |
| - Accuracy: 0.9290 |
| - F1 Weighted: 0.9284 |
| - F1 Macro: 0.9315 |
| - Precision Weighted: 0.9289 |
| - Recall Weighted: 0.9290 |
| - Precision Macro: 0.9297 |
| - Recall Macro: 0.9339 |
|
|
| ## 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: 2.5e-05 |
| - train_batch_size: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 0.1 |
| - num_epochs: 9 |
| - label_smoothing_factor: 0.05 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Macro | Precision Weighted | Recall Weighted | Precision Macro | Recall Macro | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:------------------:|:---------------:|:---------------:|:------------:| |
| | 1.3724 | 1.0 | 772 | 1.0129 | 0.8106 | 0.8086 | 0.8082 | 0.8128 | 0.8106 | 0.8117 | 0.8114 | |
| | 0.8057 | 2.0 | 1544 | 0.7635 | 0.8810 | 0.8796 | 0.8828 | 0.8818 | 0.8810 | 0.8815 | 0.8872 | |
| | 0.6641 | 3.0 | 2316 | 0.7049 | 0.9038 | 0.9027 | 0.9052 | 0.9038 | 0.9038 | 0.9043 | 0.9081 | |
| | 0.5781 | 4.0 | 3088 | 0.6703 | 0.9156 | 0.9152 | 0.9181 | 0.9163 | 0.9156 | 0.9181 | 0.9195 | |
| | 0.5372 | 5.0 | 3860 | 0.6480 | 0.9226 | 0.9219 | 0.9248 | 0.9225 | 0.9226 | 0.9229 | 0.9277 | |
| | 0.5081 | 6.0 | 4632 | 0.6425 | 0.9253 | 0.9248 | 0.9275 | 0.9256 | 0.9253 | 0.9259 | 0.9300 | |
| | 0.4850 | 7.0 | 5404 | 0.6362 | 0.9280 | 0.9276 | 0.9305 | 0.9282 | 0.9280 | 0.9297 | 0.9320 | |
| | 0.4638 | 8.0 | 6176 | 0.6352 | 0.9288 | 0.9283 | 0.9312 | 0.9288 | 0.9288 | 0.9298 | 0.9334 | |
| | 0.4603 | 9.0 | 6948 | 0.6350 | 0.9290 | 0.9284 | 0.9315 | 0.9289 | 0.9290 | 0.9297 | 0.9339 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.12.1 |
| - Pytorch 2.11.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
|
|
