|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- wiki_qa |
|
model-index: |
|
- name: output |
|
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. --> |
|
|
|
# output |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wiki_qa dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8781 |
|
|
|
## 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.9106 | 0.08 | 200 | 0.7699 | |
|
| 0.9505 | 0.16 | 400 | 0.6965 | |
|
| 0.8446 | 0.24 | 600 | 0.7000 | |
|
| 0.8765 | 0.31 | 800 | 0.6573 | |
|
| 0.7792 | 0.39 | 1000 | 0.7359 | |
|
| 0.9293 | 0.47 | 1200 | 0.6926 | |
|
| 0.9715 | 0.55 | 1400 | 0.7032 | |
|
| 0.8898 | 0.63 | 1600 | 0.7208 | |
|
| 1.0288 | 0.71 | 1800 | 0.6954 | |
|
| 0.7782 | 0.79 | 2000 | 0.6629 | |
|
| 0.9419 | 0.86 | 2200 | 0.7061 | |
|
| 0.7138 | 0.94 | 2400 | 0.7086 | |
|
| 0.9334 | 1.02 | 2600 | 0.6752 | |
|
| 0.9274 | 1.1 | 2800 | 0.7142 | |
|
| 0.7217 | 1.18 | 3000 | 0.7227 | |
|
| 0.74 | 1.26 | 3200 | 0.6896 | |
|
| 0.9408 | 1.34 | 3400 | 0.7039 | |
|
| 0.8503 | 1.41 | 3600 | 0.7456 | |
|
| 0.8816 | 1.49 | 3800 | 0.7226 | |
|
| 0.7751 | 1.57 | 4000 | 0.7182 | |
|
| 0.8669 | 1.65 | 4200 | 0.6904 | |
|
| 1.059 | 1.73 | 4400 | 0.7131 | |
|
| 0.8442 | 1.81 | 4600 | 0.7063 | |
|
| 0.9162 | 1.89 | 4800 | 0.7128 | |
|
| 0.9022 | 1.96 | 5000 | 0.7249 | |
|
| 0.9427 | 2.04 | 5200 | 0.7333 | |
|
| 0.9122 | 2.12 | 5400 | 0.6852 | |
|
| 0.8159 | 2.2 | 5600 | 0.6950 | |
|
| 0.9489 | 2.28 | 5800 | 0.7137 | |
|
| 0.9976 | 2.36 | 6000 | 0.7101 | |
|
| 0.9305 | 2.44 | 6200 | 0.7059 | |
|
| 0.6405 | 2.51 | 6400 | 0.7167 | |
|
| 0.9515 | 2.59 | 6600 | 0.6875 | |
|
| 0.7186 | 2.67 | 6800 | 0.7057 | |
|
| 0.9221 | 2.75 | 7000 | 0.6805 | |
|
| 0.9118 | 2.83 | 7200 | 0.7011 | |
|
| 0.9784 | 2.91 | 7400 | 0.6936 | |
|
| 0.7532 | 2.99 | 7600 | 0.7046 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|