|
--- |
|
license: mit |
|
base_model: IProject-10/gpt-neo-daily-dialog |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: persona-chat-gpt-neo |
|
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. --> |
|
|
|
# persona-chat-gpt-neo |
|
|
|
This model is a fine-tuned version of [IProject-10/gpt-neo-daily-dialog](https://huggingface.co/IProject-10/gpt-neo-daily-dialog) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3551 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.8898 | 0.9998 | 1117 | 2.0927 | |
|
| 0.7337 | 1.9996 | 2234 | 2.2669 | |
|
| 0.6361 | 2.9993 | 3351 | 2.3551 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
