metadata
language:
- en
license: apache-2.0
base_model: bert-base-uncased
tags:
- mhs
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_base_uncased
results: []
bert_base_uncased
This model is a fine-tuned version of bert-base-uncased on the WP dataset. It achieves the following results on the evaluation set:
- Loss: 0.5591
- Accuracy: 0.8500
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 23 | 0.5552 | 0.8250 |
| No log | 2.0 | 46 | 0.4623 | 0.8250 |
| No log | 3.0 | 69 | 0.5304 | 0.8250 |
| No log | 4.0 | 92 | 0.5741 | 0.8500 |
| No log | 5.0 | 115 | 0.5591 | 0.8500 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0