mi-clase-antes-clase
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1648
- Accuracy: 0.47
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
- 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 | Accuracy |
|---|---|---|---|---|
| 1.5671 | 1.0 | 38 | 1.7266 | 0.2 |
| 1.3401 | 2.0 | 76 | 1.4448 | 0.38 |
| 1.1463 | 3.0 | 114 | 1.2995 | 0.44 |
| 0.9089 | 4.0 | 152 | 1.2523 | 0.48 |
| 0.573 | 5.0 | 190 | 1.5740 | 0.41 |
| 0.3689 | 6.0 | 228 | 1.5738 | 0.52 |
| 0.4487 | 7.0 | 266 | 1.7316 | 0.5 |
| 0.3233 | 8.0 | 304 | 1.8300 | 0.5 |
| 0.023 | 9.0 | 342 | 2.0170 | 0.5 |
| 0.0186 | 10.0 | 380 | 2.1648 | 0.47 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.2.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ctutiven/mi-clase-antes-clase
Base model
google-bert/bert-base-cased