metadata
library_name: transformers
license: apache-2.0
base_model: alex-miller/ODABert
tags:
- generated_from_trainer
model-index:
- name: climate-percentage-regression
results: []
climate-percentage-regression
This model is a fine-tuned version of alex-miller/ODABert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0613
- Mse: 0.0613
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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse |
|---|---|---|---|---|
| 0.066 | 1.0 | 126 | 0.0603 | 0.0603 |
| 0.044 | 2.0 | 252 | 0.0563 | 0.0563 |
| 0.0357 | 3.0 | 378 | 0.0582 | 0.0582 |
| 0.0262 | 4.0 | 504 | 0.0562 | 0.0562 |
| 0.0205 | 5.0 | 630 | 0.0609 | 0.0609 |
| 0.0152 | 6.0 | 756 | 0.0622 | 0.0622 |
| 0.0135 | 7.0 | 882 | 0.0612 | 0.0612 |
| 0.0103 | 8.0 | 1008 | 0.0571 | 0.0571 |
| 0.0097 | 9.0 | 1134 | 0.0617 | 0.0617 |
| 0.0089 | 10.0 | 1260 | 0.0613 | 0.0613 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1