|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: GPT2-THESIS |
|
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-THESIS |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9762 |
|
- F1: 0.7492 |
|
- Recall: 0.7492 |
|
- Accuracy: 0.7492 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | F1 | Recall | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:--------:| |
|
| 1.1822 | 1.0 | 1446 | 0.9362 | 0.7065 | 0.7065 | 0.7065 | |
|
| 0.8791 | 2.0 | 2892 | 0.8616 | 0.7303 | 0.7303 | 0.7303 | |
|
| 0.7218 | 3.0 | 4338 | 0.8250 | 0.7406 | 0.7406 | 0.7406 | |
|
| 0.6025 | 4.0 | 5784 | 0.8351 | 0.7509 | 0.7509 | 0.7509 | |
|
| 0.5142 | 5.0 | 7230 | 0.8781 | 0.7477 | 0.7477 | 0.7477 | |
|
| 0.453 | 6.0 | 8676 | 0.8871 | 0.7526 | 0.7526 | 0.7526 | |
|
| 0.3813 | 7.0 | 10122 | 0.9216 | 0.7475 | 0.7475 | 0.7475 | |
|
| 0.3399 | 8.0 | 11568 | 0.9458 | 0.7477 | 0.7477 | 0.7477 | |
|
| 0.3049 | 9.0 | 13014 | 0.9650 | 0.7504 | 0.7504 | 0.7504 | |
|
| 0.2861 | 10.0 | 14460 | 0.9762 | 0.7492 | 0.7492 | 0.7492 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
