metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- 0.0.2
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: ai-categories-text
results: []
datasets:
- tinutmap/ai-categories-data
ai-categories-text
This model is a fine-tuned version of distilbert-base-uncased on an tinutmap/ai-categories-data 's train dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0037
- Accuracy: 0.9991
- F1: 0.9926
- Precision: 0.9926
- Recall: 0.9926
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1646 | 1.0 | 599 | 0.0271 | 0.9956 | 0.9620 | 0.9834 | 0.9415 |
| 0.0219 | 2.0 | 1198 | 0.0093 | 0.9984 | 0.9862 | 0.9887 | 0.9838 |
| 0.0093 | 3.0 | 1797 | 0.0062 | 0.9989 | 0.9907 | 0.9905 | 0.9908 |
| 0.0054 | 4.0 | 2396 | 0.0048 | 0.9991 | 0.9924 | 0.9919 | 0.9929 |
| 0.0034 | 5.0 | 2995 | 0.0043 | 0.9991 | 0.9928 | 0.9912 | 0.9944 |
| 0.0021 | 6.0 | 3594 | 0.0038 | 0.9992 | 0.9931 | 0.9923 | 0.9940 |
| 0.0017 | 7.0 | 4193 | 0.0038 | 0.9991 | 0.9928 | 0.9933 | 0.9922 |
| 0.0015 | 8.0 | 4792 | 0.0037 | 0.9991 | 0.9926 | 0.9926 | 0.9926 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1