metadata
library_name: transformers
base_model: adalbertojunior/distilbert-portuguese-cased
tags:
- generated_from_trainer
model-index:
- name: e500_lr2e-05
results: []
e500_lr2e-05
This model is a fine-tuned version of adalbertojunior/distilbert-portuguese-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3316
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: 2e-05
- train_batch_size: 200
- eval_batch_size: 400
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.8051 | 1.5385 | 100 | 5.4555 |
| 5.0899 | 3.0769 | 200 | 4.5164 |
| 4.3939 | 4.6154 | 300 | 3.9739 |
| 3.948 | 6.1538 | 400 | 3.6053 |
| 3.6364 | 7.6923 | 500 | 3.3412 |
| 3.391 | 9.2308 | 600 | 3.1273 |
| 3.2013 | 10.7692 | 700 | 2.9847 |
| 3.0531 | 12.3077 | 800 | 2.7862 |
| 2.9261 | 13.8462 | 900 | 2.7109 |
| 2.8132 | 15.3846 | 1000 | 2.5933 |
| 2.698 | 16.9231 | 1100 | 2.5080 |
| 2.614 | 18.4615 | 1200 | 2.4453 |
| 2.5423 | 20.0 | 1300 | 2.3267 |
| 2.4675 | 21.5385 | 1400 | 2.2761 |
| 2.4105 | 23.0769 | 1500 | 2.2385 |
| 2.3405 | 24.6154 | 1600 | 2.1717 |
| 2.2862 | 26.1538 | 1700 | 2.1134 |
| 2.2324 | 27.6923 | 1800 | 2.0816 |
| 2.1954 | 29.2308 | 1900 | 2.0319 |
| 2.145 | 30.7692 | 2000 | 1.9917 |
| 2.1001 | 32.3077 | 2100 | 1.9738 |
| 2.0688 | 33.8462 | 2200 | 1.9215 |
| 2.024 | 35.3846 | 2300 | 1.8910 |
| 1.99 | 36.9231 | 2400 | 1.8697 |
| 1.9524 | 38.4615 | 2500 | 1.8273 |
| 1.9288 | 40.0 | 2600 | 1.7972 |
| 1.8957 | 41.5385 | 2700 | 1.7696 |
| 1.8713 | 43.0769 | 2800 | 1.7486 |
| 1.8427 | 44.6154 | 2900 | 1.7461 |
| 1.8155 | 46.1538 | 3000 | 1.6993 |
| 1.7914 | 47.6923 | 3100 | 1.6781 |
| 1.766 | 49.2308 | 3200 | 1.6483 |
| 1.738 | 50.7692 | 3300 | 1.6227 |
| 1.7167 | 52.3077 | 3400 | 1.5883 |
| 1.6781 | 53.8462 | 3500 | 1.5695 |
| 1.658 | 55.3846 | 3600 | 1.5469 |
| 1.6276 | 56.9231 | 3700 | 1.5451 |
| 1.6131 | 58.4615 | 3800 | 1.5046 |
| 1.5916 | 60.0 | 3900 | 1.4997 |
| 1.5746 | 61.5385 | 4000 | 1.4709 |
| 1.5638 | 63.0769 | 4100 | 1.4615 |
| 1.5395 | 64.6154 | 4200 | 1.4542 |
| 1.5291 | 66.1538 | 4300 | 1.4323 |
| 1.5115 | 67.6923 | 4400 | 1.4036 |
| 1.4885 | 69.2308 | 4500 | 1.3822 |
| 1.4706 | 70.7692 | 4600 | 1.3732 |
| 1.4611 | 72.3077 | 4700 | 1.3625 |
| 1.4393 | 73.8462 | 4800 | 1.3662 |
| 1.4321 | 75.3846 | 4900 | 1.3556 |
| 1.4108 | 76.9231 | 5000 | 1.3566 |
| 1.4054 | 78.4615 | 5100 | 1.2953 |
| 1.3863 | 80.0 | 5200 | 1.3333 |
| 1.3674 | 81.5385 | 5300 | 1.3210 |
| 1.3578 | 83.0769 | 5400 | 1.3029 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1