---
datasets:
- mrfakename/refusal
language:
- en
library_name: transformers
pipeline_tag: text-generation
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
---

**I messed up on this model** and forgot to add special tokens for <|im_start|> & <|im_end|> - but it still seems to work fine. If you're having any issues let me know in the Discussions tab and I can retrain it.

<div style="background-color: rgb(255, 241, 209); color: rgb(90, 65, 0); border-radius: 8px; padding: 0.5rem 1rem; ">
  <b>This model is usable, but you can get better results with the fixed latest model!</b> Check out the <a href="https://huggingface.co/mrfakename/refusal" style="color: rgb(90, 65, 0);">latest model</a> instead of using this one!
</div>

---

A tiny 1B model that refuses basically anything you ask it! Trained on the [refusal](https://huggingface.co/datasets/mrfakename/refusal) dataset. Prompt format is ChatML.

Training results:

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.4352        | 0.0580 | 1    | 2.4462          |
| 1.5742        | 0.5217 | 9    | 1.4303          |
| 1.5084        | 1.0435 | 18   | 1.3672          |
| 1.0814        | 1.5217 | 27   | 1.3483          |
| 1.1024        | 2.0435 | 36   | 1.3204          |
| 0.6554        | 2.5217 | 45   | 1.4286          |
| 0.6163        | 3.0435 | 54   | 1.4375          |
| 0.5058        | 3.5072 | 63   | 1.4908          |

Training hyperparemeters:

The following hyperparameters were used during training:
- learning_rate: 0.0002
- 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: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4

Base model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T