|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-uncased__sst2__train-8-5 |
|
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. --> |
|
|
|
# distilbert-base-uncased__sst2__train-8-5 |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6920 |
|
- Accuracy: 0.5129 |
|
|
|
## 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: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7057 | 1.0 | 3 | 0.6848 | 0.75 | |
|
| 0.6681 | 2.0 | 6 | 0.6875 | 0.5 | |
|
| 0.6591 | 3.0 | 9 | 0.6868 | 0.25 | |
|
| 0.6052 | 4.0 | 12 | 0.6943 | 0.25 | |
|
| 0.557 | 5.0 | 15 | 0.7078 | 0.25 | |
|
| 0.4954 | 6.0 | 18 | 0.7168 | 0.25 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.15.0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.2 |
|
- Tokenizers 0.10.3 |
|
|