rule_learning_test
This model is a fine-tuned version of bert-base-uncased on the enoriega/odinsynth_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1255
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 1000
- total_train_batch_size: 8000
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1764 | 0.32 | 20 | 0.2303 |
| 0.145 | 0.64 | 40 | 0.1470 |
| 0.129 | 0.96 | 60 | 0.1321 |
| 0.1256 | 1.29 | 80 | 0.1265 |
| 0.1304 | 1.61 | 100 | 0.1252 |
| 0.1235 | 1.93 | 120 | 0.1260 |
| 0.125 | 2.26 | 140 | 0.1261 |
| 0.1263 | 2.58 | 160 | 0.1262 |
| 0.1244 | 2.9 | 180 | 0.1256 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0
- Datasets 2.2.1
- Tokenizers 0.12.1