|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: SST2_ELECTRA_5E |
|
|
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. --> |
|
|
|
|
|
# SST2_ELECTRA_5E |
|
|
|
|
|
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: 0.3431 |
|
|
- Accuracy: 0.9267 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 16 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.667 | 0.12 | 50 | 0.5772 | 0.8533 | |
|
|
| 0.4746 | 0.23 | 100 | 0.3421 | 0.9 | |
|
|
| 0.3104 | 0.35 | 150 | 0.2948 | 0.9 | |
|
|
| 0.2315 | 0.46 | 200 | 0.3269 | 0.8867 | |
|
|
| 0.2675 | 0.58 | 250 | 0.2604 | 0.92 | |
|
|
| 0.2467 | 0.69 | 300 | 0.2321 | 0.92 | |
|
|
| 0.2013 | 0.81 | 350 | 0.2959 | 0.92 | |
|
|
| 0.2165 | 0.92 | 400 | 0.2219 | 0.92 | |
|
|
| 0.2524 | 1.04 | 450 | 0.2649 | 0.9133 | |
|
|
| 0.1396 | 1.15 | 500 | 0.2985 | 0.9133 | |
|
|
| 0.152 | 1.27 | 550 | 0.2766 | 0.9267 | |
|
|
| 0.126 | 1.39 | 600 | 0.2657 | 0.9267 | |
|
|
| 0.1545 | 1.5 | 650 | 0.2568 | 0.92 | |
|
|
| 0.184 | 1.62 | 700 | 0.2916 | 0.92 | |
|
|
| 0.198 | 1.73 | 750 | 0.2564 | 0.9267 | |
|
|
| 0.1432 | 1.85 | 800 | 0.2669 | 0.9267 | |
|
|
| 0.1405 | 1.96 | 850 | 0.2466 | 0.9333 | |
|
|
| 0.0969 | 2.08 | 900 | 0.2213 | 0.9467 | |
|
|
| 0.1055 | 2.19 | 950 | 0.2733 | 0.9333 | |
|
|
| 0.0895 | 2.31 | 1000 | 0.3237 | 0.9333 | |
|
|
| 0.118 | 2.42 | 1050 | 0.3666 | 0.9133 | |
|
|
| 0.0775 | 2.54 | 1100 | 0.2783 | 0.94 | |
|
|
| 0.1145 | 2.66 | 1150 | 0.2550 | 0.9267 | |
|
|
| 0.1214 | 2.77 | 1200 | 0.2777 | 0.9267 | |
|
|
| 0.1288 | 2.89 | 1250 | 0.2861 | 0.9267 | |
|
|
| 0.076 | 3.0 | 1300 | 0.3194 | 0.9267 | |
|
|
| 0.0865 | 3.12 | 1350 | 0.3391 | 0.9267 | |
|
|
| 0.0626 | 3.23 | 1400 | 0.3133 | 0.9267 | |
|
|
| 0.0657 | 3.35 | 1450 | 0.3322 | 0.9267 | |
|
|
| 0.0858 | 3.46 | 1500 | 0.2799 | 0.94 | |
|
|
| 0.0823 | 3.58 | 1550 | 0.2731 | 0.94 | |
|
|
| 0.0739 | 3.7 | 1600 | 0.2822 | 0.9333 | |
|
|
| 0.0911 | 3.81 | 1650 | 0.3264 | 0.9267 | |
|
|
| 0.0808 | 3.93 | 1700 | 0.2388 | 0.9467 | |
|
|
| 0.0509 | 4.04 | 1750 | 0.2740 | 0.94 | |
|
|
| 0.0512 | 4.16 | 1800 | 0.3326 | 0.9267 | |
|
|
| 0.0397 | 4.27 | 1850 | 0.3061 | 0.9333 | |
|
|
| 0.0565 | 4.39 | 1900 | 0.2891 | 0.9333 | |
|
|
| 0.0353 | 4.5 | 1950 | 0.3203 | 0.9333 | |
|
|
| 0.0455 | 4.62 | 2000 | 0.3113 | 0.9333 | |
|
|
| 0.0494 | 4.73 | 2050 | 0.3403 | 0.9267 | |
|
|
| 0.0306 | 4.85 | 2100 | 0.3467 | 0.9267 | |
|
|
| 0.0655 | 4.97 | 2150 | 0.3431 | 0.9267 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.23.1 |
|
|
- Pytorch 1.13.0 |
|
|
- Datasets 2.6.1 |
|
|
- Tokenizers 0.13.1 |
|
|
|
