metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: disaster-tweet-teacher
results: []
disaster-tweet-teacher
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4062
- Accuracy: 0.811
- Auc: 0.905
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
|---|---|---|---|---|---|
| 0.5137 | 1.0 | 263 | 0.4356 | 0.793 | 0.892 |
| 0.4518 | 2.0 | 526 | 0.3996 | 0.827 | 0.9 |
| 0.421 | 3.0 | 789 | 0.4352 | 0.804 | 0.9 |
| 0.4128 | 4.0 | 1052 | 0.4023 | 0.818 | 0.902 |
| 0.4055 | 5.0 | 1315 | 0.4191 | 0.8 | 0.902 |
| 0.3988 | 6.0 | 1578 | 0.4112 | 0.809 | 0.901 |
| 0.4007 | 7.0 | 1841 | 0.4376 | 0.804 | 0.903 |
| 0.3911 | 8.0 | 2104 | 0.4066 | 0.809 | 0.904 |
| 0.3966 | 9.0 | 2367 | 0.4185 | 0.811 | 0.904 |
| 0.3909 | 10.0 | 2630 | 0.4062 | 0.811 | 0.905 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0