tiny-mlm-tweet-target-imdb
This model is a fine-tuned version of muhtasham/tiny-mlm-tweet on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4017
- Accuracy: 0.8486
- F1: 0.9181
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 |
---|---|---|---|---|---|
0.5661 | 0.64 | 500 | 0.3869 | 0.8363 | 0.9109 |
0.3798 | 1.28 | 1000 | 0.3730 | 0.8390 | 0.9125 |
0.3283 | 1.92 | 1500 | 0.2422 | 0.9018 | 0.9484 |
0.2926 | 2.56 | 2000 | 0.4156 | 0.8210 | 0.9017 |
0.2713 | 3.2 | 2500 | 0.3951 | 0.8405 | 0.9133 |
0.2519 | 3.84 | 3000 | 0.2170 | 0.9118 | 0.9539 |
0.2329 | 4.48 | 3500 | 0.4214 | 0.8357 | 0.9105 |
0.2074 | 5.12 | 4000 | 0.5114 | 0.8032 | 0.8909 |
0.1898 | 5.75 | 4500 | 0.4017 | 0.8486 | 0.9181 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 3
Dataset used to train muhtasham/tiny-mlm-tweet-target-imdb
Evaluation results
- Accuracy on imdbself-reported0.849
- F1 on imdbself-reported0.918