metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert_adaptation_vizwiz
results: []
widget:
- text: please [MASK] this shirt.
example_title: Example 1
- text: can you tell me the title of the book? [MASK].
example_title: Example 2
- text: what [MASK] is this?
example_title: Example 3
bert_adaptation_vizwiz
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0994
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 1.4046 | 1.0 | 375 | 1.1987 |
| 1.1951 | 2.0 | 750 | 1.0976 |
| 1.0913 | 3.0 | 1125 | 1.1045 |
| 1.0711 | 4.0 | 1500 | 1.0678 |
| 1.0434 | 5.0 | 1875 | 1.0652 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3