|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: 2d_psn_1600 |
|
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. --> |
|
|
|
# 2d_psn_1600 |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [ComNum](https://huggingface.co/datasets/abbassix/ComNum) dataset. |
|
This model used 800 samples as training, 200 as validation, and 1200 as test on three epochs. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3675 |
|
- Accuracy: 0.7175 |
|
|
|
This model achieves the following results on the test set: |
|
- Loss: 0.3475 |
|
- Accuracy: 0.7493 |
|
<!-- |
|
{'eval_loss': 0.34749719500541687, 'eval_accuracy': 0.7493, 'eval_runtime': 852.7429, 'eval_samples_per_second': 11.727, 'eval_steps_per_second': 1.466} |
|
--> |
|
## 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: 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: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 200 | 0.3701 | 0.735 | |
|
| No log | 2.0 | 400 | 0.3714 | 0.74 | |
|
| 0.4173 | 3.0 | 600 | 0.3675 | 0.7175 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
