metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-large-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-large-csb
results: []
bert-large-csb
This model is a fine-tuned version of google-bert/bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3276
- Accuracy: 0.8637
- F1: 0.8635
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|---|
| 0.4806 | 1.0 | 228 | 0.3276 | 0.8637 | 0.8635 |
| 0.3325 | 2.0 | 456 | 0.3070 | 0.8527 | 0.8530 |
| 0.2308 | 3.0 | 684 | 0.3310 | 0.8593 | 0.8585 |
| 0.1562 | 4.0 | 912 | 0.5863 | 0.8571 | 0.8547 |
| 0.1152 | 5.0 | 1140 | 0.7901 | 0.8462 | 0.8448 |
| 0.0424 | 6.0 | 1368 | 1.0230 | 0.8374 | 0.8342 |
| 0.018 | 7.0 | 1596 | 0.9910 | 0.8505 | 0.8499 |
| 0.0293 | 8.0 | 1824 | 1.1121 | 0.8484 | 0.8471 |
| 0.0075 | 9.0 | 2052 | 1.2002 | 0.8462 | 0.8446 |
| 0.0067 | 10.0 | 2280 | 1.1791 | 0.8440 | 0.8425 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.2.1
- Datasets 4.4.1
- Tokenizers 0.22.1