metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: left_padding100model
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: 0.92732
left_padding100model
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: 0.9273
- Loss: 0.7584
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 |
|---|---|---|---|---|
| 0.0209 | 1.0 | 1563 | 0.9263 | 0.5386 |
| 0.0 | 2.0 | 3126 | 0.9284 | 0.6249 |
| 0.016 | 3.0 | 4689 | 0.9166 | 0.6532 |
| 0.0125 | 4.0 | 6252 | 0.9198 | 0.6454 |
| 0.0032 | 5.0 | 7815 | 0.9264 | 0.6582 |
| 0.0139 | 6.0 | 9378 | 0.9260 | 0.6766 |
| 0.0001 | 7.0 | 10941 | 0.9283 | 0.7319 |
| 0.0 | 8.0 | 12504 | 0.9269 | 0.7658 |
| 0.0132 | 9.0 | 14067 | 0.9266 | 0.7416 |
| 0.0 | 10.0 | 15630 | 0.9273 | 0.7584 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1