metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert_wikitext
results: []
bert_wikitext
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: 2.5739
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: 0.0005
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5777 | 0.3484 | 400 | 2.5606 |
| 3.4402 | 0.6969 | 800 | 3.1688 |
| 3.3722 | 1.0453 | 1200 | 3.2573 |
| 3.1671 | 1.3937 | 1600 | 3.1576 |
| 3.0417 | 1.7422 | 2000 | 3.0741 |
| 2.6817 | 2.0906 | 2400 | 2.8792 |
| 2.5589 | 2.4390 | 2800 | 2.7123 |
| 2.3957 | 2.7875 | 3200 | 2.5590 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1