|
--- |
|
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: 6.5337 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.1064 | 1.0 | 291 | 1.6942 | |
|
| 1.6327 | 2.0 | 582 | 1.3707 | |
|
| 1.4819 | 3.0 | 873 | 1.4033 | |
|
| 1.3965 | 4.0 | 1164 | 1.4341 | |
|
| 4.5167 | 5.0 | 1455 | 6.2129 | |
|
| 6.1184 | 6.0 | 1746 | 6.2606 | |
|
| 5.9894 | 7.0 | 2037 | 6.2949 | |
|
| 5.9044 | 8.0 | 2328 | 6.3017 | |
|
| 5.8635 | 9.0 | 2619 | 6.3110 | |
|
| 5.8388 | 10.0 | 2910 | 6.4275 | |
|
| 5.793 | 11.0 | 3201 | 6.3408 | |
|
| 5.7428 | 12.0 | 3492 | 6.4123 | |
|
| 5.7203 | 13.0 | 3783 | 6.4774 | |
|
| 5.7021 | 14.0 | 4074 | 6.4178 | |
|
| 5.6754 | 15.0 | 4365 | 6.5968 | |
|
| 5.6586 | 16.0 | 4656 | 6.5337 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.3 |
|
|
