finetuned-base_small
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3962
- Accuracy: 0.8942
- F1: 0.9441
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 |
|---|---|---|---|---|---|
| 0.3459 | 0.64 | 500 | 0.1283 | 0.9505 | 0.9746 |
| 0.2389 | 1.28 | 1000 | 0.1054 | 0.9595 | 0.9793 |
| 0.1927 | 1.92 | 1500 | 0.1447 | 0.9457 | 0.9721 |
| 0.1408 | 2.56 | 2000 | 0.1261 | 0.9594 | 0.9793 |
| 0.1168 | 3.2 | 2500 | 0.3962 | 0.8942 | 0.9441 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2