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: 1.2337
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: 128
- eval_batch_size: 32
- 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 |
---|---|---|---|
2.3389 | 1.0 | 73 | 1.7400 |
1.8014 | 2.0 | 146 | 1.4690 |
1.634 | 3.0 | 219 | 1.4783 |
1.5461 | 4.0 | 292 | 1.3912 |
1.4706 | 5.0 | 365 | 1.3109 |
1.4161 | 6.0 | 438 | 1.3405 |
1.3664 | 7.0 | 511 | 1.3459 |
1.332 | 8.0 | 584 | 1.2745 |
1.3029 | 9.0 | 657 | 1.2633 |
1.2871 | 10.0 | 730 | 1.2336 |
1.2807 | 11.0 | 803 | 1.2966 |
1.2569 | 12.0 | 876 | 1.1508 |
1.2392 | 13.0 | 949 | 1.2530 |
1.237 | 14.0 | 1022 | 1.2485 |
1.2169 | 15.0 | 1095 | 1.2592 |
1.2272 | 16.0 | 1168 | 1.2337 |
Framework versions
- Transformers 4.19.1
- Pytorch 1.12.0.dev20220513+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.