|
--- |
|
license: apache-2.0 |
|
base_model: google/electra-base-discriminator |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: electra-base-discriminator_flang-bert |
|
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. --> |
|
|
|
# electra-base-discriminator_flang-bert |
|
|
|
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4214 |
|
- Accuracy: 0.8830 |
|
- F1: 0.8826 |
|
- Precision: 0.8829 |
|
- Recall: 0.8830 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.9314 | 1.0 | 91 | 0.8698 | 0.6318 | 0.5743 | 0.6153 | 0.6318 | |
|
| 0.541 | 2.0 | 182 | 0.4762 | 0.8237 | 0.8247 | 0.8338 | 0.8237 | |
|
| 0.3217 | 3.0 | 273 | 0.3709 | 0.8580 | 0.8577 | 0.8576 | 0.8580 | |
|
| 0.2774 | 4.0 | 364 | 0.4027 | 0.8596 | 0.8582 | 0.8589 | 0.8596 | |
|
| 0.2154 | 5.0 | 455 | 0.4351 | 0.8424 | 0.8437 | 0.8537 | 0.8424 | |
|
| 0.1525 | 6.0 | 546 | 0.4732 | 0.8487 | 0.8459 | 0.8492 | 0.8487 | |
|
| 0.1429 | 7.0 | 637 | 0.4214 | 0.8830 | 0.8826 | 0.8829 | 0.8830 | |
|
| 0.1074 | 8.0 | 728 | 0.5150 | 0.8674 | 0.8678 | 0.8695 | 0.8674 | |
|
| 0.1323 | 9.0 | 819 | 0.5122 | 0.8705 | 0.8697 | 0.8708 | 0.8705 | |
|
| 0.117 | 10.0 | 910 | 0.7296 | 0.8268 | 0.8245 | 0.8294 | 0.8268 | |
|
| 0.1041 | 11.0 | 1001 | 0.5587 | 0.8643 | 0.8620 | 0.8648 | 0.8643 | |
|
| 0.0598 | 12.0 | 1092 | 0.6548 | 0.8565 | 0.8564 | 0.8565 | 0.8565 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
