---
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
tags:
- alignment-handbook
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- jan-hq/bagel_sft_binarized
- jan-hq/dolphin_binarized
- jan-hq/openhermes_binarized
model-index:
- name: LlamaCorn-sft-adapter
  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. -->

# LlamaCorn-sft-adapter

This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co./TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the jan-hq/bagel_sft_binarized, the jan-hq/dolphin_binarized and the jan-hq/openhermes_binarized datasets.
It achieves the following results on the evaluation set:
- Loss: 0.9638

## 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: 7e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.038         | 1.0   | 6606  | 1.0506          |
| 0.876         | 2.0   | 13212 | 0.9648          |
| 0.7713        | 3.0   | 19818 | 0.9638          |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0