metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-issues-128
results: []
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: 1.2512
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0978 | 1.0 | 291 | 1.7077 |
| 1.6399 | 2.0 | 582 | 1.4279 |
| 1.4845 | 3.0 | 873 | 1.3755 |
| 1.3998 | 4.0 | 1164 | 1.3708 |
| 1.3393 | 5.0 | 1455 | 1.1966 |
| 1.2848 | 6.0 | 1746 | 1.2787 |
| 1.238 | 7.0 | 2037 | 1.2609 |
| 1.1969 | 8.0 | 2328 | 1.2159 |
| 1.1648 | 9.0 | 2619 | 1.1781 |
| 1.1419 | 10.0 | 2910 | 1.2104 |
| 1.1296 | 11.0 | 3201 | 1.2160 |
| 1.1048 | 12.0 | 3492 | 1.1685 |
| 1.0803 | 13.0 | 3783 | 1.2540 |
| 1.0778 | 14.0 | 4074 | 1.1658 |
| 1.0641 | 15.0 | 4365 | 1.1269 |
| 1.0616 | 16.0 | 4656 | 1.2512 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1