metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: spam-detection_m1
results: []
spam-detection_m1
This model is a fine-tuned version of google-bert/bert-base-uncased on an spam-detection dataset. It achieves the following results on the evaluation set:
- Loss: 0.0202
- Accuracy: 0.9967
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 256 | 0.1144 | 0.9919 |
| 0.22 | 2.0 | 512 | 0.0483 | 0.9923 |
| 0.22 | 3.0 | 768 | 0.0321 | 0.9949 |
| 0.0361 | 4.0 | 1024 | 0.0275 | 0.9949 |
| 0.0361 | 5.0 | 1280 | 0.0245 | 0.9952 |
| 0.0233 | 6.0 | 1536 | 0.0232 | 0.9960 |
| 0.0233 | 7.0 | 1792 | 0.0220 | 0.9967 |
| 0.0171 | 8.0 | 2048 | 0.0209 | 0.9967 |
| 0.0171 | 9.0 | 2304 | 0.0211 | 0.9967 |
| 0.0148 | 10.0 | 2560 | 0.0202 | 0.9967 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0