metadata
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
model-index:
- name: 0703-lr5e-05_warm0.1_epoch6
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: 0.92816
0703-lr5e-05_warm0.1_epoch6
This model is a fine-tuned version of yujiepan/bert-base-uncased-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.53258
- Accuracy: 0.92816
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.5 | 391 | 0.4331 | 0.9122 |
| 0.0385 | 1.0 | 782 | 0.3080 | 0.9150 |
| 0.0654 | 1.5 | 1173 | 0.3286 | 0.9164 |
| 0.0636 | 2.0 | 1564 | 0.4296 | 0.9184 |
| 0.0636 | 2.5 | 1955 | 0.5366 | 0.9170 |
| 0.0344 | 3.0 | 2346 | 0.4581 | 0.9172 |
| 0.0285 | 3.5 | 2737 | 0.5553 | 0.9164 |
| 0.0163 | 4.0 | 3128 | 0.5055 | 0.9194 |
| 0.0104 | 4.5 | 3519 | 0.5432 | 0.9264 |
| 0.0104 | 5.0 | 3910 | 0.5357 | 0.9268 |
| 0.0034 | 5.5 | 4301 | 0.5457 | 0.9249 |
| 0.0046 | 6.0 | 4692 | 0.5326 | 0.9282 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1
- Datasets 2.11.0
- Tokenizers 0.13.3