metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: left_padding30model
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: 0.93128
left_padding30model
This model is a fine-tuned version of distilbert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.9313
- Loss: 0.6821
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: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.0907 | 1.0 | 1563 | 0.9292 | 0.3495 |
| 0.0396 | 2.0 | 3126 | 0.9298 | 0.3753 |
| 0.0348 | 3.0 | 4689 | 0.9192 | 0.3895 |
| 0.0484 | 4.0 | 6252 | 0.9294 | 0.4647 |
| 0.0175 | 5.0 | 7815 | 0.9284 | 0.5595 |
| 0.0202 | 6.0 | 9378 | 0.9299 | 0.5709 |
| 0.0035 | 7.0 | 10941 | 0.9287 | 0.6317 |
| 0.0 | 8.0 | 12504 | 0.9305 | 0.7006 |
| 0.0045 | 9.0 | 14067 | 0.9310 | 0.6876 |
| 0.0 | 10.0 | 15630 | 0.9313 | 0.6821 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1