|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: aochildes_gutenberg_fixed_log_rarity-mixed-seed |
|
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. --> |
|
|
|
# aochildes_gutenberg_fixed_log_rarity-mixed-seed |
|
|
|
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: 4.1457 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 6.3592 | 0.29 | 500 | 5.3385 | |
|
| 5.0519 | 0.59 | 1000 | 4.9203 | |
|
| 4.7218 | 0.88 | 1500 | 4.6948 | |
|
| 4.4531 | 1.17 | 2000 | 4.5553 | |
|
| 4.3081 | 1.47 | 2500 | 4.4381 | |
|
| 4.201 | 1.76 | 3000 | 4.3366 | |
|
| 4.0871 | 2.05 | 3500 | 4.2702 | |
|
| 3.9013 | 2.35 | 4000 | 4.2246 | |
|
| 3.88 | 2.64 | 4500 | 4.1727 | |
|
| 3.8385 | 2.93 | 5000 | 4.1257 | |
|
| 3.6438 | 3.23 | 5500 | 4.1265 | |
|
| 3.5973 | 3.52 | 6000 | 4.0988 | |
|
| 3.5805 | 3.81 | 6500 | 4.0654 | |
|
| 3.4762 | 4.11 | 7000 | 4.0753 | |
|
| 3.3279 | 4.4 | 7500 | 4.0724 | |
|
| 3.3237 | 4.69 | 8000 | 4.0616 | |
|
| 3.3081 | 4.99 | 8500 | 4.0509 | |
|
| 3.1497 | 5.28 | 9000 | 4.0682 | |
|
| 3.1439 | 5.57 | 9500 | 4.0663 | |
|
| 3.1428 | 5.87 | 10000 | 4.0656 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|