|
|
--- |
|
|
base_model: hf-internal-testing/tiny-albert |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: results |
|
|
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. --> |
|
|
|
|
|
# results |
|
|
|
|
|
This model is a fine-tuned version of [hf-internal-testing/tiny-albert](https://huggingface.co/hf-internal-testing/tiny-albert) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1315 |
|
|
- Accuracy: 0.96 |
|
|
|
|
|
## 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: 0.001 |
|
|
- train_batch_size: 24 |
|
|
- eval_batch_size: 24 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 25.0 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.6937 | 0.1 | 25 | 0.6927 | 0.5115 | |
|
|
| 0.6911 | 0.2 | 50 | 0.6770 | 0.613 | |
|
|
| 0.4988 | 0.3 | 75 | 0.3574 | 0.886 | |
|
|
| 0.2604 | 0.4 | 100 | 0.1720 | 0.9525 | |
|
|
| 0.1758 | 0.5 | 125 | 0.1787 | 0.9435 | |
|
|
| 0.1964 | 0.6 | 150 | 0.1327 | 0.9615 | |
|
|
| 0.1637 | 0.7 | 175 | 0.1269 | 0.9635 | |
|
|
| 0.1453 | 0.8 | 200 | 0.1538 | 0.9565 | |
|
|
| 0.1563 | 0.9 | 225 | 0.1508 | 0.9575 | |
|
|
| 0.1657 | 1.0 | 250 | 0.1315 | 0.96 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.19.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
