|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imdb |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_imdb_padding50model |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: imdb |
|
type: imdb |
|
config: plain_text |
|
split: test |
|
args: plain_text |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.93044 |
|
--- |
|
|
|
<!-- 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_imdb_padding50model |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7456 |
|
- Accuracy: 0.9304 |
|
|
|
## 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: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.239 | 1.0 | 1563 | 0.2904 | 0.9081 | |
|
| 0.1693 | 2.0 | 3126 | 0.2311 | 0.9272 | |
|
| 0.1117 | 3.0 | 4689 | 0.3226 | 0.9248 | |
|
| 0.0626 | 4.0 | 6252 | 0.3785 | 0.9226 | |
|
| 0.0467 | 5.0 | 7815 | 0.4768 | 0.9175 | |
|
| 0.0292 | 6.0 | 9378 | 0.4735 | 0.9241 | |
|
| 0.0294 | 7.0 | 10941 | 0.5132 | 0.9261 | |
|
| 0.0207 | 8.0 | 12504 | 0.5925 | 0.9162 | |
|
| 0.0229 | 9.0 | 14067 | 0.5995 | 0.9240 | |
|
| 0.0076 | 10.0 | 15630 | 0.6841 | 0.9224 | |
|
| 0.0125 | 11.0 | 17193 | 0.6141 | 0.9272 | |
|
| 0.0046 | 12.0 | 18756 | 0.6427 | 0.9293 | |
|
| 0.007 | 13.0 | 20319 | 0.6095 | 0.9284 | |
|
| 0.0051 | 14.0 | 21882 | 0.7158 | 0.9250 | |
|
| 0.0037 | 15.0 | 23445 | 0.7008 | 0.9268 | |
|
| 0.0023 | 16.0 | 25008 | 0.7489 | 0.9280 | |
|
| 0.0023 | 17.0 | 26571 | 0.7541 | 0.9282 | |
|
| 0.0001 | 18.0 | 28134 | 0.7298 | 0.9299 | |
|
| 0.0013 | 19.0 | 29697 | 0.7388 | 0.9304 | |
|
| 0.001 | 20.0 | 31260 | 0.7456 | 0.9304 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|