mini-mlm-tweet-target-imdb
This model is a fine-tuned version of muhtasham/mini-mlm-tweet on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4742
- Accuracy: 0.8324
- F1: 0.9085
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 |
|---|---|---|---|---|---|
| 0.4141 | 0.64 | 500 | 0.2415 | 0.9025 | 0.9487 |
| 0.3008 | 1.28 | 1000 | 0.2407 | 0.9046 | 0.9499 |
| 0.2573 | 1.92 | 1500 | 0.2428 | 0.904 | 0.9496 |
| 0.2164 | 2.56 | 2000 | 0.3198 | 0.8753 | 0.9335 |
| 0.1918 | 3.2 | 2500 | 0.4742 | 0.8324 | 0.9085 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2