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: 1.1704
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 |
|---|---|---|---|
| 2.1081 | 1.0 | 291 | 1.6857 |
| 1.6343 | 2.0 | 582 | 1.3655 |
| 1.4792 | 3.0 | 873 | 1.4230 |
| 1.3974 | 4.0 | 1164 | 1.4269 |
| 1.343 | 5.0 | 1455 | 1.2747 |
| 1.2834 | 6.0 | 1746 | 1.3208 |
| 1.2318 | 7.0 | 2037 | 1.2150 |
| 1.21 | 8.0 | 2328 | 1.2872 |
| 1.1781 | 9.0 | 2619 | 1.2658 |
| 1.1488 | 10.0 | 2910 | 1.2139 |
| 1.1253 | 11.0 | 3201 | 1.2613 |
| 1.0972 | 12.0 | 3492 | 1.1637 |
| 1.0928 | 13.0 | 3783 | 1.1443 |
| 1.0773 | 14.0 | 4074 | 1.0640 |
| 1.0645 | 15.0 | 4365 | 1.2635 |
| 1.0652 | 16.0 | 4656 | 1.1704 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1