|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-shakespeare |
|
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-shakespeare |
|
|
|
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: 2.0269 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 280 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 0.11 | 100 | 2.7142 | |
|
| No log | 0.21 | 200 | 2.4752 | |
|
| No log | 0.32 | 300 | 2.3674 | |
|
| No log | 0.42 | 400 | 2.3177 | |
|
| 2.9171 | 0.53 | 500 | 2.2626 | |
|
| 2.9171 | 0.63 | 600 | 2.2268 | |
|
| 2.9171 | 0.74 | 700 | 2.2035 | |
|
| 2.9171 | 0.84 | 800 | 2.1836 | |
|
| 2.9171 | 0.95 | 900 | 2.1626 | |
|
| 2.5537 | 1.05 | 1000 | 2.1444 | |
|
| 2.5537 | 1.16 | 1100 | 2.1314 | |
|
| 2.5537 | 1.26 | 1200 | 2.1192 | |
|
| 2.5537 | 1.37 | 1300 | 2.1096 | |
|
| 2.5537 | 1.47 | 1400 | 2.0968 | |
|
| 2.4399 | 1.58 | 1500 | 2.0868 | |
|
| 2.4399 | 1.68 | 1600 | 2.0765 | |
|
| 2.4399 | 1.79 | 1700 | 2.0675 | |
|
| 2.4399 | 1.89 | 1800 | 2.0606 | |
|
| 2.4399 | 2.0 | 1900 | 2.0556 | |
|
| 2.4006 | 2.1 | 2000 | 2.0491 | |
|
| 2.4006 | 2.21 | 2100 | 2.0454 | |
|
| 2.4006 | 2.31 | 2200 | 2.0389 | |
|
| 2.4006 | 2.42 | 2300 | 2.0372 | |
|
| 2.4006 | 2.52 | 2400 | 2.0326 | |
|
| 2.3532 | 2.63 | 2500 | 2.0316 | |
|
| 2.3532 | 2.73 | 2600 | 2.0286 | |
|
| 2.3532 | 2.84 | 2700 | 2.0276 | |
|
| 2.3532 | 2.94 | 2800 | 2.0269 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
