metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: bert-base-uncased
model-index:
- name: bert-base-uncased-finetuned-imdb
results: []
bert-base-uncased-finetuned-imdb
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2082
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-06
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 60 | 6.8866 |
| No log | 2.0 | 120 | 4.1530 |
| No log | 3.0 | 180 | 2.8300 |
| No log | 4.0 | 240 | 2.1248 |
| No log | 5.0 | 300 | 1.7365 |
| No log | 6.0 | 360 | 1.5032 |
| No log | 7.0 | 420 | 1.3602 |
| No log | 8.0 | 480 | 1.2720 |
| 3.649 | 9.0 | 540 | 1.2241 |
| 3.649 | 10.0 | 600 | 1.2082 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2