|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: gpt2-psych_chatbot |
|
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-psych_chatbot |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9593 |
|
|
|
## 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: 0.0002 |
|
- 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 5.8353 | 1.0 | 651 | 4.8999 | |
|
| 4.8713 | 2.0 | 1302 | 4.4407 | |
|
| 4.4876 | 3.0 | 1953 | 4.0638 | |
|
| 3.7647 | 4.0 | 2604 | 3.7308 | |
|
| 3.3969 | 5.0 | 3255 | 3.4360 | |
|
| 3.1115 | 6.0 | 3906 | 3.1895 | |
|
| 2.4283 | 7.0 | 4557 | 2.9595 | |
|
| 2.0813 | 8.0 | 5208 | 2.7442 | |
|
| 1.7785 | 9.0 | 5859 | 2.5330 | |
|
| 1.3337 | 10.0 | 6510 | 2.3619 | |
|
| 1.066 | 11.0 | 7161 | 2.2079 | |
|
| 0.9607 | 12.0 | 7812 | 2.1072 | |
|
| 0.8078 | 13.0 | 8463 | 2.0385 | |
|
| 0.6072 | 14.0 | 9114 | 1.9966 | |
|
| 0.5351 | 15.0 | 9765 | 1.9736 | |
|
| 0.5049 | 16.0 | 10416 | 1.9646 | |
|
| 0.3958 | 17.0 | 11067 | 1.9607 | |
|
| 0.346 | 18.0 | 11718 | 1.9592 | |
|
| 0.3244 | 19.0 | 12369 | 1.9565 | |
|
| 0.2777 | 20.0 | 13020 | 1.9593 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
