|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: albert_model |
|
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. --> |
|
|
|
# albert_model |
|
|
|
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8674 |
|
- Accuracy: 0.9010 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 334 | 0.3206 | 0.8666 | |
|
| 0.4327 | 2.0 | 668 | 0.4502 | 0.8906 | |
|
| 0.3178 | 3.0 | 1002 | 0.4517 | 0.8951 | |
|
| 0.3178 | 4.0 | 1336 | 0.5688 | 0.9025 | |
|
| 0.1649 | 5.0 | 1670 | 0.6359 | 0.8996 | |
|
| 0.0707 | 6.0 | 2004 | 0.7573 | 0.8906 | |
|
| 0.0707 | 7.0 | 2338 | 0.8200 | 0.8906 | |
|
| 0.0216 | 8.0 | 2672 | 0.7581 | 0.9010 | |
|
| 0.0168 | 9.0 | 3006 | 0.7530 | 0.9130 | |
|
| 0.0168 | 10.0 | 3340 | 0.8194 | 0.9055 | |
|
| 0.0075 | 11.0 | 3674 | 0.8633 | 0.9010 | |
|
| 0.0037 | 12.0 | 4008 | 0.8079 | 0.9145 | |
|
| 0.0037 | 13.0 | 4342 | 0.8283 | 0.9115 | |
|
| 0.0018 | 14.0 | 4676 | 0.8508 | 0.9055 | |
|
| 0.0003 | 15.0 | 5010 | 0.8674 | 0.9010 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
