<!-- 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. -->
base-mlm-imdb-target-imdb
This model is a fine-tuned version of muhtasham/base-mlm-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4659
- Accuracy: 0.8918
- F1: 0.9428
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 |
|---|---|---|---|---|---|
| 0.2453 | 0.64 | 500 | 0.1892 | 0.9334 | 0.9656 |
| 0.1764 | 1.28 | 1000 | 0.1267 | 0.9581 | 0.9786 |
| 0.117 | 1.92 | 1500 | 0.1926 | 0.9290 | 0.9632 |
| 0.0727 | 2.56 | 2000 | 0.3109 | 0.9182 | 0.9574 |
| 0.0665 | 3.2 | 2500 | 0.4659 | 0.8918 | 0.9428 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
