finetuned-mlm_small
This model is a fine-tuned version of muhtasham/bert-small-mlm-finetuned-emotion on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.5097
- Accuracy: 0.9084
- F1: 0.9520
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 |
|---|---|---|---|---|---|
| 0.2852 | 2.55 | 500 | 0.1781 | 0.9334 | 0.9656 |
| 0.1243 | 5.1 | 1000 | 0.3215 | 0.9078 | 0.9517 |
| 0.0543 | 7.65 | 1500 | 0.2467 | 0.9378 | 0.9679 |
| 0.0309 | 10.2 | 2000 | 0.7256 | 0.8594 | 0.9244 |
| 0.0199 | 12.76 | 2500 | 0.4230 | 0.9222 | 0.9595 |
| 0.0161 | 15.31 | 3000 | 0.5097 | 0.9084 | 0.9520 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2