<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
finetuned-self_mlm_medium
This model is a fine-tuned version of muhtasham/bert-medium-mlm-finetuned-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3215
- Accuracy: 0.9130
- F1: 0.9545
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: 32
- eval_batch_size: 32
- 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 |
---|---|---|---|---|---|
0.2916 | 0.64 | 500 | 0.2293 | 0.9087 | 0.9522 |
0.1969 | 1.28 | 1000 | 0.1605 | 0.9442 | 0.9713 |
0.1511 | 1.92 | 1500 | 0.1787 | 0.9406 | 0.9694 |
0.1046 | 2.56 | 2000 | 0.2280 | 0.9379 | 0.9680 |
0.0852 | 3.2 | 2500 | 0.3215 | 0.9130 | 0.9545 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2