<!-- 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_tiny
This model is a fine-tuned version of muhtasham/bert-tiny-mlm-finetuned-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3339
- Accuracy: 0.8796
- F1: 0.9359
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 |
---|---|---|---|---|---|
0.4424 | 2.55 | 500 | 0.4640 | 0.7962 | 0.8865 |
0.2846 | 5.1 | 1000 | 0.2852 | 0.8825 | 0.9376 |
0.2288 | 7.65 | 1500 | 0.3233 | 0.8667 | 0.9286 |
0.1833 | 10.2 | 2000 | 0.3351 | 0.8774 | 0.9347 |
0.1477 | 12.76 | 2500 | 0.3339 | 0.8796 | 0.9359 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2