# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("stephen423/bert-base-cased-wikitext2")
model = AutoModelForMaskedLM.from_pretrained("stephen423/bert-base-cased-wikitext2", device_map="auto")Quick Links
bert-base-cased-wikitext2
This model is a fine-tuned version of bert-base-cased on the wikitext dataset. It achieves the following results on the evaluation set:
- Loss: 6.8630
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.0876 | 1.0 | 2346 | 7.0208 |
| 6.9111 | 2.0 | 4692 | 6.8997 |
| 6.8649 | 3.0 | 7038 | 6.8515 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cpu
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 6
Model tree for stephen423/bert-base-cased-wikitext2
Base model
google-bert/bert-base-cased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="stephen423/bert-base-cased-wikitext2")