metadata
license: apache-2.0
base_model: bert-base-uncased
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: 1.1652
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
- distributed_type: tpu
- 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 |
|---|---|---|---|
| 2.1106 | 1.0 | 291 | 1.6945 |
| 1.6342 | 2.0 | 582 | 1.3698 |
| 1.4812 | 3.0 | 873 | 1.4282 |
| 1.3939 | 4.0 | 1164 | 1.4237 |
| 1.3419 | 5.0 | 1455 | 1.2666 |
| 1.2871 | 6.0 | 1746 | 1.3084 |
| 1.2294 | 7.0 | 2037 | 1.2115 |
| 1.2124 | 8.0 | 2328 | 1.2611 |
| 1.1791 | 9.0 | 2619 | 1.2653 |
| 1.1488 | 10.0 | 2910 | 1.2165 |
| 1.1268 | 11.0 | 3201 | 1.2643 |
| 1.0993 | 12.0 | 3492 | 1.1550 |
| 1.0963 | 13.0 | 3783 | 1.1520 |
| 1.0793 | 14.0 | 4074 | 1.0736 |
| 1.0659 | 15.0 | 4365 | 1.2466 |
| 1.0674 | 16.0 | 4656 | 1.1652 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0