|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: distilbert-amazon-shoe-reviews |
|
results: [] |
|
--- |
|
|
|
# distilbert-amazon-shoe-reviews |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on a [subset](https://huggingface.co/datasets/juliensimon/amazon-shoe-reviews) of the [Amazon US reviews](https://huggingface.co/datasets/amazon_us_reviews) dataset. |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9532 |
|
- Accuracy: 0.5779 |
|
- F1: [0.62616119 0.46456105 0.50993865 0.55755123 0.734375 ] |
|
- Precision: [0.62757927 0.46676662 0.49148534 0.58430541 0.72415507] |
|
- Recall: [0.6247495 0.46237624 0.52983172 0.53313982 0.74488753] |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------------------------------------------------------:|:--------------------------------------------------------:|:--------------------------------------------------------:| |
|
| 0.9713 | 1.0 | 2813 | 0.9532 | 0.5779 | [0.62616119 0.46456105 0.50993865 0.55755123 0.734375 ] | [0.62757927 0.46676662 0.49148534 0.58430541 0.72415507] | [0.6247495 0.46237624 0.52983172 0.53313982 0.74488753] | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu102 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
