|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-reporter |
|
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-reporter |
|
|
|
This model is a fine-tuned version of [theta/gpt2-reporter](https://huggingface.co/theta/gpt2-reporter) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4221 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3859 | 0.04 | 400 | 2.4603 | |
|
| 2.3069 | 0.08 | 800 | 2.4777 | |
|
| 2.3114 | 0.13 | 1200 | 2.4806 | |
|
| 2.3152 | 0.17 | 1600 | 2.4774 | |
|
| 2.3362 | 0.21 | 2000 | 2.4760 | |
|
| 2.3354 | 0.25 | 2400 | 2.4728 | |
|
| 2.344 | 0.3 | 2800 | 2.4685 | |
|
| 2.366 | 0.34 | 3200 | 2.4632 | |
|
| 2.3632 | 0.38 | 3600 | 2.4636 | |
|
| 2.3704 | 0.42 | 4000 | 2.4602 | |
|
| 2.3791 | 0.47 | 4400 | 2.4552 | |
|
| 2.3773 | 0.51 | 4800 | 2.4529 | |
|
| 2.391 | 0.55 | 5200 | 2.4475 | |
|
| 2.4486 | 0.59 | 5600 | 2.4379 | |
|
| 2.468 | 0.64 | 6000 | 2.4346 | |
|
| 2.4602 | 0.68 | 6400 | 2.4323 | |
|
| 2.4643 | 0.72 | 6800 | 2.4301 | |
|
| 2.4634 | 0.76 | 7200 | 2.4289 | |
|
| 2.4632 | 0.81 | 7600 | 2.4266 | |
|
| 2.4534 | 0.85 | 8000 | 2.4250 | |
|
| 2.4528 | 0.89 | 8400 | 2.4238 | |
|
| 2.4618 | 0.93 | 8800 | 2.4222 | |
|
| 2.4519 | 0.98 | 9200 | 2.4221 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0+cu116 |
|
- Tokenizers 0.13.2 |
|
|
