|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- contratos_tceal |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: ner-bert-large-cased-pt-contratos_tceal |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: contratos_tceal |
|
type: contratos_tceal |
|
config: contratos_tceal |
|
split: validation |
|
args: contratos_tceal |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9134177215189874 |
|
- name: Recall |
|
type: recall |
|
value: 0.9168996188055909 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9151553582752061 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9556322655972385 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ner-bert-large-cased-pt-contratos_tceal |
|
|
|
This model was trained from scratch on the contratos_tceal dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3141 |
|
- Precision: 0.9134 |
|
- Recall: 0.9169 |
|
- F1: 0.9152 |
|
- Accuracy: 0.9556 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 252 | 0.2193 | 0.9026 | 0.8948 | 0.8987 | 0.9488 | |
|
| 0.2496 | 2.0 | 504 | 0.2110 | 0.8957 | 0.9098 | 0.9027 | 0.9494 | |
|
| 0.2496 | 3.0 | 756 | 0.2098 | 0.9166 | 0.9105 | 0.9136 | 0.9531 | |
|
| 0.1666 | 4.0 | 1008 | 0.2063 | 0.9221 | 0.9146 | 0.9183 | 0.9559 | |
|
| 0.1666 | 5.0 | 1260 | 0.2165 | 0.9219 | 0.9146 | 0.9182 | 0.9562 | |
|
| 0.1255 | 6.0 | 1512 | 0.2143 | 0.9175 | 0.9133 | 0.9154 | 0.9555 | |
|
| 0.1255 | 7.0 | 1764 | 0.2278 | 0.9181 | 0.9146 | 0.9164 | 0.9559 | |
|
| 0.092 | 8.0 | 2016 | 0.2404 | 0.9188 | 0.9174 | 0.9181 | 0.9561 | |
|
| 0.092 | 9.0 | 2268 | 0.2538 | 0.9133 | 0.9100 | 0.9117 | 0.9533 | |
|
| 0.069 | 10.0 | 2520 | 0.2654 | 0.9132 | 0.9118 | 0.9125 | 0.9543 | |
|
| 0.069 | 11.0 | 2772 | 0.2796 | 0.9085 | 0.9133 | 0.9109 | 0.9527 | |
|
| 0.0498 | 12.0 | 3024 | 0.2827 | 0.9130 | 0.9149 | 0.9139 | 0.9552 | |
|
| 0.0498 | 13.0 | 3276 | 0.2869 | 0.9127 | 0.9144 | 0.9135 | 0.9557 | |
|
| 0.0397 | 14.0 | 3528 | 0.2993 | 0.9123 | 0.9093 | 0.9108 | 0.9546 | |
|
| 0.0397 | 15.0 | 3780 | 0.2951 | 0.9056 | 0.9144 | 0.9100 | 0.9547 | |
|
| 0.0312 | 16.0 | 4032 | 0.2989 | 0.9092 | 0.9136 | 0.9114 | 0.9566 | |
|
| 0.0312 | 17.0 | 4284 | 0.3104 | 0.9115 | 0.9113 | 0.9114 | 0.9554 | |
|
| 0.0257 | 18.0 | 4536 | 0.3098 | 0.9143 | 0.9161 | 0.9152 | 0.9564 | |
|
| 0.0257 | 19.0 | 4788 | 0.3129 | 0.9141 | 0.9166 | 0.9154 | 0.9556 | |
|
| 0.0207 | 20.0 | 5040 | 0.3141 | 0.9134 | 0.9169 | 0.9152 | 0.9556 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
