|
|
--- |
|
|
license: mit |
|
|
base_model: openai-community/gpt2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: chatbot_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. --> |
|
|
|
|
|
# chatbot_model |
|
|
|
|
|
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 5.4551 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 1 |
|
|
- num_epochs: 1 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 6.3724 | 0.06 | 50 | 6.1788 | |
|
|
| 6.286 | 0.12 | 100 | 6.0336 | |
|
|
| 6.1512 | 0.18 | 150 | 5.9263 | |
|
|
| 6.0683 | 0.24 | 200 | 5.8277 | |
|
|
| 5.986 | 0.3 | 250 | 5.7590 | |
|
|
| 5.9205 | 0.36 | 300 | 5.7009 | |
|
|
| 5.8265 | 0.42 | 350 | 5.6524 | |
|
|
| 5.7699 | 0.47 | 400 | 5.6017 | |
|
|
| 5.8097 | 0.53 | 450 | 5.5629 | |
|
|
| 5.7624 | 0.59 | 500 | 5.5347 | |
|
|
| 5.689 | 0.65 | 550 | 5.5032 | |
|
|
| 5.7271 | 0.71 | 600 | 5.4836 | |
|
|
| 5.6464 | 0.77 | 650 | 5.4660 | |
|
|
| 5.6965 | 0.83 | 700 | 5.4632 | |
|
|
| 5.5684 | 0.89 | 750 | 5.4594 | |
|
|
| 5.6917 | 0.95 | 800 | 5.4551 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
