<!-- 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-base_base
This model is a fine-tuned version of google/bert_uncased_L-12_H-768_A-12 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3594
- Accuracy: 0.9094
- F1: 0.9525
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: 50
- eval_batch_size: 50
- 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 |
---|---|---|---|---|---|
0.2414 | 1.0 | 500 | 0.1796 | 0.9343 | 0.9660 |
0.1235 | 2.0 | 1000 | 0.2042 | 0.9311 | 0.9643 |
0.0633 | 3.0 | 1500 | 0.3590 | 0.8997 | 0.9472 |
0.0398 | 4.0 | 2000 | 0.3594 | 0.9094 | 0.9525 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2