|
--- |
|
license: apache-2.0 |
|
base_model: google/bert_uncased_L-2_H-128_A-2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: tiny-bert-sst2-distilled |
|
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. --> |
|
|
|
# tiny-bert-sst2-distilled |
|
|
|
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1018 |
|
- Accuracy: 0.8211 |
|
|
|
## 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: 6e-05 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 128 |
|
- seed: 33 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.4646 | 1.0 | 527 | 1.1825 | 0.7867 | |
|
| 0.8559 | 2.0 | 1054 | 1.0389 | 0.8085 | |
|
| 0.6569 | 3.0 | 1581 | 1.0545 | 0.8222 | |
|
| 0.5672 | 4.0 | 2108 | 1.0577 | 0.8188 | |
|
| 0.5094 | 5.0 | 2635 | 1.0876 | 0.8211 | |
|
| 0.4717 | 6.0 | 3162 | 1.0979 | 0.8200 | |
|
| 0.4513 | 7.0 | 3689 | 1.1018 | 0.8211 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
