---
license: apache-2.0
base_model: jan-hq/LlamaCorn-1.1B-Chat
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- jan-hq/systemchat_binarized
- jan-hq/youtube_transcripts_qa
- jan-hq/youtube_transcripts_qa_ext
model-index:
- name: TinyJensen-1.1B-Chat
  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. -->

# TinyJensen-1.1B-Chat

This model is a fine-tuned version of [jan-hq/LlamaCorn-1.1B-Chat](https://huggingface.co/jan-hq/LlamaCorn-1.1B-Chat) on the jan-hq/systemchat_binarized, the jan-hq/youtube_transcripts_qa and the jan-hq/youtube_transcripts_qa_ext datasets.
It achieves the following results on the evaluation set:
- Loss: 0.8771

## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.8226        | 1.0   | 207  | 0.8232          |
| 0.6608        | 2.0   | 414  | 0.7941          |
| 0.526         | 3.0   | 621  | 0.8186          |
| 0.4388        | 4.0   | 829  | 0.8643          |
| 0.3888        | 4.99  | 1035 | 0.8771          |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0