metadata
license: mit
tags:
- generated_from_trainer
datasets:
- pubmed-summarization
model-index:
- name: medicare-gpt2-large
results: []
medicare-gpt2-large
This model is a fine-tuned version of 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