<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 1.2480
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 |
---|---|---|---|
2.0972 | 1.0 | 291 | 1.7066 |
1.6391 | 2.0 | 582 | 1.4318 |
1.4844 | 3.0 | 873 | 1.3734 |
1.3997 | 4.0 | 1164 | 1.3806 |
1.3398 | 5.0 | 1455 | 1.1957 |
1.2846 | 6.0 | 1746 | 1.2837 |
1.2379 | 7.0 | 2037 | 1.2665 |
1.1969 | 8.0 | 2328 | 1.2154 |
1.1651 | 9.0 | 2619 | 1.1756 |
1.1415 | 10.0 | 2910 | 1.2114 |
1.1296 | 11.0 | 3201 | 1.2138 |
1.1047 | 12.0 | 3492 | 1.1655 |
1.0802 | 13.0 | 3783 | 1.2566 |
1.0775 | 14.0 | 4074 | 1.1650 |
1.0645 | 15.0 | 4365 | 1.1294 |
1.062 | 16.0 | 4656 | 1.2480 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.11.0
- Datasets 1.16.1
- Tokenizers 0.10.3