|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-base-uncased-issues-128 |
|
results: [] |
|
--- |
|
|
|
<!-- 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](https://huggingface.co/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 |
|
|