|
--- |
|
license: mit |
|
base_model: neuralmind/bert-base-portuguese-cased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: e3_lr2e-05 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# e3_lr2e-05 |
|
|
|
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5721 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.2771 | 0.0707 | 100 | 1.9875 | |
|
| 2.0486 | 0.1414 | 200 | 1.8946 | |
|
| 1.993 | 0.2121 | 300 | 1.8415 | |
|
| 1.9532 | 0.2828 | 400 | 1.8133 | |
|
| 1.9145 | 0.3535 | 500 | 1.7807 | |
|
| 1.8872 | 0.4242 | 600 | 1.7534 | |
|
| 1.8593 | 0.4949 | 700 | 1.7357 | |
|
| 1.8447 | 0.5656 | 800 | 1.7173 | |
|
| 1.8149 | 0.6363 | 900 | 1.7074 | |
|
| 1.7966 | 0.7070 | 1000 | 1.7036 | |
|
| 1.8034 | 0.7777 | 1100 | 1.6883 | |
|
| 1.7854 | 0.8484 | 1200 | 1.6740 | |
|
| 1.7779 | 0.9191 | 1300 | 1.6642 | |
|
| 1.7706 | 0.9897 | 1400 | 1.6582 | |
|
| 1.7723 | 1.0604 | 1500 | 1.6475 | |
|
| 1.746 | 1.1311 | 1600 | 1.6463 | |
|
| 1.7386 | 1.2018 | 1700 | 1.6399 | |
|
| 1.7319 | 1.2725 | 1800 | 1.6385 | |
|
| 1.7292 | 1.3432 | 1900 | 1.6230 | |
|
| 1.7121 | 1.4139 | 2000 | 1.6204 | |
|
| 1.7245 | 1.4846 | 2100 | 1.6152 | |
|
| 1.7159 | 1.5553 | 2200 | 1.6103 | |
|
| 1.7232 | 1.6260 | 2300 | 1.6114 | |
|
| 1.6952 | 1.6967 | 2400 | 1.6099 | |
|
| 1.6944 | 1.7674 | 2500 | 1.6012 | |
|
| 1.6991 | 1.8381 | 2600 | 1.5970 | |
|
| 1.6954 | 1.9088 | 2700 | 1.5933 | |
|
| 1.698 | 1.9795 | 2800 | 1.5918 | |
|
| 1.6857 | 2.0502 | 2900 | 1.5915 | |
|
| 1.6783 | 2.1209 | 3000 | 1.5840 | |
|
| 1.679 | 2.1916 | 3100 | 1.5817 | |
|
| 1.6796 | 2.2623 | 3200 | 1.5835 | |
|
| 1.6709 | 2.3330 | 3300 | 1.5769 | |
|
| 1.6626 | 2.4037 | 3400 | 1.5819 | |
|
| 1.6732 | 2.4744 | 3500 | 1.5824 | |
|
| 1.6726 | 2.5458 | 3600 | 1.5720 | |
|
| 1.6822 | 2.6165 | 3700 | 1.5758 | |
|
| 1.6578 | 2.6872 | 3800 | 1.5739 | |
|
| 1.6756 | 2.7579 | 3900 | 1.5743 | |
|
| 1.6747 | 2.8286 | 4000 | 1.5695 | |
|
| 1.659 | 2.8993 | 4100 | 1.5713 | |
|
| 1.6587 | 2.9700 | 4200 | 1.5750 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|