| --- |
| base_model: distilbert-base-uncased |
| license: apache-2.0 |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| - f1 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: distilbert |
| 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 |
|
|
| 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: 0.1400 |
| - Accuracy: 0.973 |
| - Precision: 0.974 |
| - Recall: 0.973 |
| - F1: 0.973 |
|
|
| ## 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: 0.0001 |
| - train_batch_size: 16 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 500 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:-----:| |
| | 2.7987 | 1.0 | 114 | 2.0513 | 0.527 | 0.53 | 0.527 | 0.449 | |
| | 1.3683 | 2.0 | 228 | 0.4828 | 0.955 | 0.959 | 0.955 | 0.955 | |
| | 0.4676 | 3.0 | 342 | 0.2051 | 0.949 | 0.936 | 0.949 | 0.94 | |
| | 0.2473 | 4.0 | 456 | 0.1503 | 0.971 | 0.973 | 0.971 | 0.971 | |
| | 0.1912 | 5.0 | 570 | 0.1231 | 0.973 | 0.974 | 0.973 | 0.973 | |
| | 0.1413 | 6.0 | 684 | 0.1538 | 0.971 | 0.972 | 0.971 | 0.971 | |
| | 0.1289 | 7.0 | 798 | 0.1197 | 0.976 | 0.977 | 0.976 | 0.976 | |
| | 0.0951 | 8.0 | 912 | 0.1246 | 0.978 | 0.979 | 0.978 | 0.978 | |
| | 0.0686 | 9.0 | 1026 | 0.1397 | 0.973 | 0.974 | 0.973 | 0.973 | |
| | 0.0518 | 10.0 | 1140 | 0.1400 | 0.973 | 0.974 | 0.973 | 0.973 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.43.3 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.20.0 |
| - Tokenizers 0.19.1 |
|
|
