roberta-base-bne-finetuned-recores2
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-bne on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.9761
- Accuracy: 0.3113
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6094 | 1.0 | 1047 | 1.6094 | 0.2259 |
| 1.6094 | 2.0 | 2094 | 1.6094 | 0.2121 |
| 1.6094 | 3.0 | 3141 | 1.6094 | 0.2314 |
| 1.6094 | 4.0 | 4188 | 1.6094 | 0.1956 |
| 1.6094 | 5.0 | 5235 | 1.6094 | 0.2121 |
| 1.6121 | 6.0 | 6282 | 1.6094 | 0.1818 |
| 1.6094 | 7.0 | 7329 | 1.6094 | 0.2259 |
| 1.6092 | 8.0 | 8376 | 1.6094 | 0.1736 |
| 1.6094 | 9.0 | 9423 | 1.6094 | 0.1956 |
| 1.6094 | 10.0 | 10470 | 1.6094 | 0.1736 |
| 1.6094 | 11.0 | 11517 | 1.6094 | 0.1983 |
| 1.6094 | 12.0 | 12564 | 1.6094 | 0.2176 |
| 1.6094 | 13.0 | 13611 | 1.6094 | 0.1928 |
| 1.6096 | 14.0 | 14658 | 1.6094 | 0.1846 |
| 1.6145 | 15.0 | 15705 | 1.6094 | 0.2066 |
| 1.6094 | 16.0 | 16752 | 1.6022 | 0.2121 |
| 1.8471 | 17.0 | 17799 | 1.6101 | 0.1763 |
| 2.8148 | 18.0 | 18846 | 2.7585 | 0.2452 |
| 2.5445 | 19.0 | 19893 | 2.4576 | 0.2920 |
| 1.9972 | 20.0 | 20940 | 3.6002 | 0.2865 |
| 1.9844 | 21.0 | 21987 | 5.3809 | 0.3168 |
| 2.849 | 22.0 | 23034 | 7.2230 | 0.3140 |
| 1.4208 | 23.0 | 24081 | 8.0602 | 0.2975 |
| 0.4045 | 24.0 | 25128 | 8.2947 | 0.3058 |
| 0.3052 | 25.0 | 26175 | 8.9761 | 0.3113 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1