# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("cvnberk/bert-base-uncased-issues-128")
model = AutoModelForMaskedLM.from_pretrained("cvnberk/bert-base-uncased-issues-128", device_map="auto")Quick Links
bert-base-uncased-issues-128
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: 1.2137
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0966 | 1.0 | 291 | 1.6190 |
| 1.6197 | 2.0 | 582 | 1.5317 |
| 1.485 | 3.0 | 873 | 1.4164 |
| 1.3992 | 4.0 | 1164 | 1.4064 |
| 1.3219 | 5.0 | 1455 | 1.3900 |
| 1.2851 | 6.0 | 1746 | 1.2096 |
| 1.2328 | 7.0 | 2037 | 1.3019 |
| 1.2113 | 8.0 | 2328 | 1.2779 |
| 1.1674 | 9.0 | 2619 | 1.2312 |
| 1.1443 | 10.0 | 2910 | 1.1830 |
| 1.1171 | 11.0 | 3201 | 1.1692 |
| 1.1067 | 12.0 | 3492 | 1.2364 |
| 1.0846 | 13.0 | 3783 | 1.1871 |
| 1.0815 | 14.0 | 4074 | 1.1354 |
| 1.054 | 15.0 | 4365 | 1.1771 |
| 1.0565 | 16.0 | 4656 | 1.2137 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 10
Model tree for cvnberk/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="cvnberk/bert-base-uncased-issues-128")