|
--- |
|
license: apache-2.0 |
|
base_model: distilgpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: my_awesome_eli5_clm-model |
|
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. --> |
|
|
|
# my_awesome_eli5_clm-model |
|
|
|
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.7706 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 4.0085 | 0.13 | 500 | 3.8586 | |
|
| 3.9418 | 0.25 | 1000 | 3.8368 | |
|
| 3.9257 | 0.38 | 1500 | 3.8236 | |
|
| 3.9012 | 0.51 | 2000 | 3.8139 | |
|
| 3.9131 | 0.63 | 2500 | 3.8052 | |
|
| 3.8947 | 0.76 | 3000 | 3.7976 | |
|
| 3.8943 | 0.88 | 3500 | 3.7912 | |
|
| 3.8809 | 1.01 | 4000 | 3.7887 | |
|
| 3.8243 | 1.14 | 4500 | 3.7877 | |
|
| 3.8251 | 1.26 | 5000 | 3.7854 | |
|
| 3.822 | 1.39 | 5500 | 3.7824 | |
|
| 3.8141 | 1.52 | 6000 | 3.7808 | |
|
| 3.8243 | 1.64 | 6500 | 3.7785 | |
|
| 3.8108 | 1.77 | 7000 | 3.7762 | |
|
| 3.8059 | 1.89 | 7500 | 3.7755 | |
|
| 3.7984 | 2.02 | 8000 | 3.7765 | |
|
| 3.7866 | 2.15 | 8500 | 3.7747 | |
|
| 3.7761 | 2.27 | 9000 | 3.7746 | |
|
| 3.7764 | 2.4 | 9500 | 3.7727 | |
|
| 3.779 | 2.53 | 10000 | 3.7727 | |
|
| 3.7744 | 2.65 | 10500 | 3.7719 | |
|
| 3.7685 | 2.78 | 11000 | 3.7708 | |
|
| 3.7694 | 2.9 | 11500 | 3.7706 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
