|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- generator |
|
|
model-index: |
|
|
- name: gpt2-dp-mod-datasets |
|
|
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-dp-mod-datasets |
|
|
|
|
|
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: 3.1587 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 6.721 | 0.28 | 500 | 5.6661 | |
|
|
| 5.3704 | 0.55 | 1000 | 5.2444 | |
|
|
| 5.0331 | 0.83 | 1500 | 4.9898 | |
|
|
| 4.784 | 1.1 | 2000 | 4.8409 | |
|
|
| 4.6004 | 1.38 | 2500 | 4.7323 | |
|
|
| 4.5032 | 1.65 | 3000 | 4.6355 | |
|
|
| 4.4157 | 1.93 | 3500 | 4.5419 | |
|
|
| 4.2123 | 2.2 | 4000 | 4.5062 | |
|
|
| 4.1323 | 2.48 | 4500 | 4.4562 | |
|
|
| 4.1086 | 2.75 | 5000 | 4.3991 | |
|
|
| 4.0432 | 3.03 | 5500 | 4.3667 | |
|
|
| 3.8085 | 3.3 | 6000 | 4.3636 | |
|
|
| 3.8151 | 3.58 | 6500 | 4.3268 | |
|
|
| 3.7855 | 3.85 | 7000 | 4.2969 | |
|
|
| 3.6519 | 4.13 | 7500 | 4.3076 | |
|
|
| 3.5149 | 4.4 | 8000 | 4.3007 | |
|
|
| 3.5086 | 4.68 | 8500 | 4.2851 | |
|
|
| 3.4995 | 4.95 | 9000 | 4.2743 | |
|
|
| 3.3468 | 5.23 | 9500 | 4.2884 | |
|
|
| 3.3143 | 5.5 | 10000 | 4.2904 | |
|
|
| 3.3138 | 5.78 | 10500 | 4.2893 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.13.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
