metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: bert-base-cased
model-index:
- name: modelo-epico
results: []
modelo-epico
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: 1.2257
- Accuracy: 0.6
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6677 | 0.1 | 5 | 1.5904 | 0.2 |
| 1.6574 | 0.2 | 10 | 1.6043 | 0.2 |
| 1.6257 | 0.3 | 15 | 1.5648 | 0.25 |
| 1.6168 | 0.4 | 20 | 1.5907 | 0.275 |
| 1.569 | 0.5 | 25 | 1.5746 | 0.275 |
| 1.5479 | 0.6 | 30 | 1.5310 | 0.275 |
| 1.5693 | 0.7 | 35 | 1.4761 | 0.35 |
| 1.4442 | 0.8 | 40 | 1.4862 | 0.325 |
| 1.4322 | 0.9 | 45 | 1.4651 | 0.325 |
| 1.4132 | 1.0 | 50 | 1.3922 | 0.25 |
| 1.2111 | 1.1 | 55 | 1.2754 | 0.5 |
| 1.2534 | 1.2 | 60 | 1.3157 | 0.35 |
| 1.3622 | 1.3 | 65 | 1.5002 | 0.275 |
| 1.224 | 1.4 | 70 | 1.6893 | 0.25 |
| 1.3443 | 1.5 | 75 | 1.5709 | 0.325 |
| 1.4062 | 1.6 | 80 | 1.5901 | 0.275 |
| 1.6972 | 1.7 | 85 | 1.6217 | 0.175 |
| 1.5011 | 1.8 | 90 | 1.4320 | 0.3 |
| 1.2093 | 1.9 | 95 | 1.4006 | 0.375 |
| 1.1032 | 2.0 | 100 | 1.4851 | 0.3 |
| 1.1088 | 2.1 | 105 | 1.5357 | 0.225 |
| 1.0199 | 2.2 | 110 | 1.3272 | 0.4 |
| 0.8264 | 2.3 | 115 | 1.2645 | 0.425 |
| 0.882 | 2.4 | 120 | 1.2772 | 0.425 |
| 0.9676 | 2.5 | 125 | 1.2152 | 0.6 |
| 0.9234 | 2.6 | 130 | 1.1970 | 0.55 |
| 0.9638 | 2.7 | 135 | 1.2324 | 0.525 |
| 0.8617 | 2.8 | 140 | 1.2457 | 0.65 |
| 0.783 | 2.9 | 145 | 1.2522 | 0.6 |
| 0.8607 | 3.0 | 150 | 1.1974 | 0.575 |
| 0.6252 | 3.1 | 155 | 1.2007 | 0.6 |
| 0.6922 | 3.2 | 160 | 1.3761 | 0.425 |
| 0.4611 | 3.3 | 165 | 1.1633 | 0.6 |
| 0.534 | 3.4 | 170 | 1.1376 | 0.55 |
| 0.4077 | 3.5 | 175 | 1.1891 | 0.55 |
| 0.4847 | 3.6 | 180 | 1.2391 | 0.55 |
| 0.573 | 3.7 | 185 | 1.3569 | 0.55 |
| 0.4307 | 3.8 | 190 | 1.2758 | 0.55 |
| 0.4476 | 3.9 | 195 | 1.1952 | 0.625 |
| 0.5455 | 4.0 | 200 | 1.1454 | 0.575 |
| 0.3741 | 4.1 | 205 | 1.1856 | 0.6 |
| 0.2889 | 4.2 | 210 | 1.2064 | 0.575 |
| 0.2342 | 4.3 | 215 | 1.1740 | 0.6 |
| 0.1775 | 4.4 | 220 | 1.1550 | 0.575 |
| 0.2052 | 4.5 | 225 | 1.2035 | 0.575 |
| 0.2276 | 4.6 | 230 | 1.1959 | 0.6 |
| 0.17 | 4.7 | 235 | 1.1827 | 0.625 |
| 0.2608 | 4.8 | 240 | 1.2152 | 0.6 |
| 0.3476 | 4.9 | 245 | 1.2261 | 0.6 |
| 0.3617 | 5.0 | 250 | 1.2257 | 0.6 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2