|
--- |
|
license: apache-2.0 |
|
base_model: google/electra-small-discriminator |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: teacher_electra_small |
|
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. --> |
|
|
|
# teacher_electra_small |
|
|
|
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3884 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 1022 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.8696 | 0.35 | 3000 | 0.5508 | |
|
| 0.5071 | 0.71 | 6000 | 0.4578 | |
|
| 0.448 | 1.06 | 9000 | 0.4210 | |
|
| 0.4084 | 1.41 | 12000 | 0.4109 | |
|
| 0.3878 | 1.77 | 15000 | 0.3913 | |
|
| 0.3832 | 2.12 | 18000 | 0.3884 | |
|
| 0.3529 | 2.47 | 21000 | 0.3900 | |
|
| 0.3492 | 2.83 | 24000 | 0.3884 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|
