<!-- 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. -->
medium-vanilla-target-imdb
This model is a fine-tuned version of google/bert_uncased_L-8_H-512_A-8 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.4330
- Accuracy: 0.8964
- F1: 0.9454
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 |
---|---|---|---|---|---|
0.3068 | 0.64 | 500 | 0.2373 | 0.9061 | 0.9507 |
0.2143 | 1.28 | 1000 | 0.1204 | 0.9534 | 0.9761 |
0.1655 | 1.92 | 1500 | 0.1557 | 0.942 | 0.9701 |
0.1107 | 2.56 | 2000 | 0.2791 | 0.9268 | 0.9620 |
0.0905 | 3.2 | 2500 | 0.4330 | 0.8964 | 0.9454 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2