|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: chatbot |
|
|
results: [] |
|
|
datasets: |
|
|
- Anthropic/hh-rlhf |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
<!-- 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 |
|
|
|
|
|
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an Anthropic's HH-RLHF dataset. |
|
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
This model is designed for research purposes only. I highly suggest not to use this in production. |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- num_epochs: 2 |
|
|
|
|
|
### Tensorboard |
|
|
You can view data about this model in [this](https://tensorboard.dev/experiment/lgu6VRXXR1C9lndVzbl3Ng]) tensorboard. |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.13.1+cu116 |
|
|
- Datasets 2.10.1 |
|
|
- Tokenizers 0.13.2 |
