|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- rotten_tomatoes |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-uncased_rotten_tomatoes |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: rotten_tomatoes |
|
type: rotten_tomatoes |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8461538461538461 |
|
--- |
|
|
|
<!-- 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_rotten_tomatoes |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the rotten_tomatoes dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9761 |
|
- Accuracy: 0.8462 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.4293 | 1.0 | 534 | 0.4071 | 0.8349 | |
|
| 0.2313 | 2.0 | 1068 | 0.4994 | 0.8246 | |
|
| 0.1162 | 3.0 | 1602 | 0.7041 | 0.8358 | |
|
| 0.0483 | 4.0 | 2136 | 0.9108 | 0.8462 | |
|
| 0.0187 | 5.0 | 2670 | 0.9761 | 0.8462 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.7.0 |
|
- Tokenizers 0.13.2 |
|
|
