|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- pubmed-summarization |
|
model-index: |
|
- name: medicare-gpt2-large |
|
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. --> |
|
|
|
# medicare-gpt2-large |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the pubmed-summarization dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.6383 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 256 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.9036 | 0.08 | 500 | 4.2296 | |
|
| 3.7554 | 0.16 | 1000 | 3.3542 | |
|
| 3.2457 | 0.23 | 1500 | 3.0897 | |
|
| 3.065 | 0.31 | 2000 | 2.9694 | |
|
| 2.966 | 0.39 | 2500 | 2.8919 | |
|
| 2.8912 | 0.47 | 3000 | 2.8305 | |
|
| 2.8345 | 0.55 | 3500 | 2.7817 | |
|
| 2.7818 | 0.62 | 4000 | 2.7378 | |
|
| 2.7391 | 0.7 | 4500 | 2.7001 | |
|
| 2.7052 | 0.78 | 5000 | 2.6689 | |
|
| 2.6769 | 0.86 | 5500 | 2.6486 | |
|
| 2.6599 | 0.94 | 6000 | 2.6383 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
|
### Test input samples |
|
diabetes is caused by |
