metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_trainer
model-index:
- name: geoplantbert_fill_mask_model
results: []
geoplantbert_fill_mask_model
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6236
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: 4
- eval_batch_size: 4
- seed: 123
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1929 | 1.0 | 46127 | 3.3831 |
| 3.2569 | 2.0 | 92254 | 2.9780 |
| 2.9787 | 3.0 | 138381 | 2.7813 |
| 2.8294 | 4.0 | 184508 | 2.6708 |
| 2.7486 | 5.0 | 230635 | 2.6236 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0