|
--- |
|
license: apache-2.0 |
|
base_model: lighteternal/gpt2-finetuned-greek |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2_custom_c_q_and_a |
|
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. --> |
|
|
|
# gpt2_custom_c_q_and_a |
|
|
|
This model is a fine-tuned version of [lighteternal/gpt2-finetuned-greek](https://huggingface.co/lighteternal/gpt2-finetuned-greek) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0467 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.5542 | 4.76 | 100 | 0.7706 | |
|
| 0.4862 | 9.52 | 200 | 0.1913 | |
|
| 0.1955 | 14.29 | 300 | 0.0978 | |
|
| 0.1228 | 19.05 | 400 | 0.0660 | |
|
| 0.0934 | 23.81 | 500 | 0.0527 | |
|
| 0.0792 | 28.57 | 600 | 0.0467 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Tokenizers 0.13.3 |
|
|
