|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 20230430-001-baseline-mbert-qa-squadv2-ft-clickbait-spoiling |
|
results: [] |
|
datasets: |
|
- Tugay/clickbait-spoiling |
|
- squad_v2 |
|
language: |
|
- id |
|
--- |
|
|
|
<!-- 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. --> |
|
# T-BASELINE001 |
|
# 20230430-001-baseline-mbert-qa-squadv2-ft-clickbait-spoiling |
|
|
|
This model is a fine-tuned version of [intanm/mbert-squadv2](https://huggingface.co/intanm/mbert-squadv2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.8747 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 200 | 2.8065 | |
|
| No log | 2.0 | 400 | 2.8088 | |
|
| 2.5698 | 3.0 | 600 | 3.1652 | |
|
| 2.5698 | 4.0 | 800 | 3.5464 | |
|
| 1.1384 | 5.0 | 1000 | 3.8477 | |
|
| 1.1384 | 6.0 | 1200 | 4.1725 | |
|
| 1.1384 | 7.0 | 1400 | 4.5057 | |
|
| 0.4763 | 8.0 | 1600 | 4.7721 | |
|
| 0.4763 | 9.0 | 1800 | 4.8970 | |
|
| 0.2594 | 10.0 | 2000 | 4.8747 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
