|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: prompt-extend |
|
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. --> |
|
|
|
# prompt-extend |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0437 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- 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_ratio: 0.1 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 6.3538 | 0.32 | 500 | 4.7231 | |
|
| 4.2863 | 0.64 | 1000 | 3.7473 | |
|
| 3.5828 | 0.96 | 1500 | 3.2410 | |
|
| 3.1699 | 1.28 | 2000 | 2.9410 | |
|
| 2.9123 | 1.6 | 2500 | 2.7295 | |
|
| 2.7413 | 1.92 | 3000 | 2.5568 | |
|
| 2.5181 | 2.24 | 3500 | 2.4281 | |
|
| 2.394 | 2.56 | 4000 | 2.3263 | |
|
| 2.3157 | 2.88 | 4500 | 2.2393 | |
|
| 2.1822 | 3.2 | 5000 | 2.1750 | |
|
| 2.091 | 3.52 | 5500 | 2.1231 | |
|
| 2.0489 | 3.84 | 6000 | 2.0844 | |
|
| 1.9873 | 4.16 | 6500 | 2.0609 | |
|
| 1.9335 | 4.48 | 7000 | 2.0487 | |
|
| 1.9307 | 4.8 | 7500 | 2.0437 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
