finetuned-mlm_mini
This model is a fine-tuned version of muhtasham/bert-mini-mlm-finetuned-emotion on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.6338
- Accuracy: 0.8618
- F1: 0.9257
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 |
|---|---|---|---|---|---|
| 0.3398 | 2.55 | 500 | 0.2366 | 0.9032 | 0.9491 |
| 0.2028 | 5.1 | 1000 | 0.2750 | 0.8956 | 0.9449 |
| 0.1382 | 7.65 | 1500 | 0.2798 | 0.9034 | 0.9492 |
| 0.0899 | 10.2 | 2000 | 0.4193 | 0.882 | 0.9373 |
| 0.0624 | 12.76 | 2500 | 0.5203 | 0.864 | 0.9270 |
| 0.0417 | 15.31 | 3000 | 0.6338 | 0.8618 | 0.9257 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2