metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: albert_model
results: []
albert_model
This model is a fine-tuned version of 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