# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("frahman/bert-base-uncased-issues-128")
model = AutoModelForMaskedLM.from_pretrained("frahman/bert-base-uncased-issues-128")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: 1.2551
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 |
|---|---|---|---|
| 2.0984 | 1.0 | 291 | 1.7081 |
| 1.6512 | 2.0 | 582 | 1.4289 |
| 1.4854 | 3.0 | 873 | 1.3845 |
| 1.3924 | 4.0 | 1164 | 1.3844 |
| 1.3375 | 5.0 | 1455 | 1.1944 |
| 1.2969 | 6.0 | 1746 | 1.2848 |
| 1.2443 | 7.0 | 2037 | 1.2678 |
| 1.1998 | 8.0 | 2328 | 1.2151 |
| 1.1805 | 9.0 | 2619 | 1.1638 |
| 1.1396 | 10.0 | 2910 | 1.2131 |
| 1.1333 | 11.0 | 3201 | 1.1966 |
| 1.0974 | 12.0 | 3492 | 1.1687 |
| 1.0822 | 13.0 | 3783 | 1.2283 |
| 1.0736 | 14.0 | 4074 | 1.1640 |
| 1.0595 | 15.0 | 4365 | 1.1207 |
| 1.0515 | 16.0 | 4656 | 1.2551 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="frahman/bert-base-uncased-issues-128")