|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- generator |
|
|
model-index: |
|
|
- name: all-base-rerun-new-loop2 |
|
|
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. --> |
|
|
|
|
|
# all-base-rerun-new-loop2 |
|
|
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 4.0969 |
|
|
|
|
|
## 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: 64 |
|
|
- eval_batch_size: 64 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 1000 |
|
|
- num_epochs: 6 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 6.3479 | 0.29 | 500 | 5.3389 | |
|
|
| 5.0203 | 0.58 | 1000 | 4.9188 | |
|
|
| 4.6949 | 0.87 | 1500 | 4.6855 | |
|
|
| 4.4434 | 1.16 | 2000 | 4.5414 | |
|
|
| 4.2872 | 1.46 | 2500 | 4.4217 | |
|
|
| 4.1743 | 1.75 | 3000 | 4.3230 | |
|
|
| 4.0791 | 2.04 | 3500 | 4.2448 | |
|
|
| 3.8856 | 2.33 | 4000 | 4.2016 | |
|
|
| 3.8509 | 2.62 | 4500 | 4.1489 | |
|
|
| 3.8144 | 2.91 | 5000 | 4.0998 | |
|
|
| 3.6394 | 3.2 | 5500 | 4.0935 | |
|
|
| 3.5747 | 3.49 | 6000 | 4.0638 | |
|
|
| 3.5592 | 3.78 | 6500 | 4.0296 | |
|
|
| 3.4711 | 4.07 | 7000 | 4.0278 | |
|
|
| 3.3061 | 4.37 | 7500 | 4.0241 | |
|
|
| 3.2984 | 4.66 | 8000 | 4.0105 | |
|
|
| 3.2917 | 4.95 | 8500 | 3.9989 | |
|
|
| 3.1462 | 5.24 | 9000 | 4.0090 | |
|
|
| 3.1241 | 5.53 | 9500 | 4.0085 | |
|
|
| 3.1176 | 5.82 | 10000 | 4.0075 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.13.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
