finetuned-base_medium
This model is a fine-tuned version of google/bert_uncased_L-8_H-512_A-8 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1906
- Accuracy: 0.9568
- F1: 0.9779
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.2292 | 2.55 | 500 | 0.1077 | 0.9633 | 0.9813 |
0.0789 | 5.1 | 1000 | 0.2340 | 0.9386 | 0.9683 |
0.0367 | 7.65 | 1500 | 0.3223 | 0.9299 | 0.9637 |
0.0227 | 10.2 | 2000 | 0.1906 | 0.9568 | 0.9779 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 6
Dataset used to train muhtasham/finetuned-base_medium
Evaluation results
- Accuracy on imdbself-reported0.957
- F1 on imdbself-reported0.978