---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model-index:
- name: tiny_llama_instruct_generation
  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. -->

# tiny_llama_instruct_generation

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 generator dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0919

## 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: 0.0002
- 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: constant
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.3923        | 0.04  | 20   | 2.3466          |
| 2.2664        | 0.08  | 40   | 2.2596          |
| 2.1909        | 0.12  | 60   | 2.1966          |
| 2.1885        | 0.16  | 80   | 2.1737          |
| 2.1536        | 0.2   | 100  | 2.1553          |
| 2.1255        | 0.24  | 120  | 2.1426          |
| 2.1298        | 0.29  | 140  | 2.1318          |
| 2.0497        | 0.33  | 160  | 2.1242          |
| 2.0967        | 0.37  | 180  | 2.1198          |
| 2.1252        | 0.41  | 200  | 2.1160          |
| 2.1051        | 0.45  | 220  | 2.1139          |
| 2.0848        | 0.49  | 240  | 2.1121          |
| 2.1562        | 0.53  | 260  | 2.1104          |
| 2.1043        | 0.57  | 280  | 2.1088          |
| 2.0865        | 0.61  | 300  | 2.1075          |
| 2.0729        | 0.65  | 320  | 2.1065          |
| 2.1046        | 0.69  | 340  | 2.1059          |
| 2.1398        | 0.73  | 360  | 2.1050          |
| 2.0928        | 0.78  | 380  | 2.1035          |
| 2.1055        | 0.82  | 400  | 2.1027          |
| 2.0327        | 0.86  | 420  | 2.1017          |
| 2.0904        | 0.9   | 440  | 2.1012          |
| 2.0922        | 0.94  | 460  | 2.1006          |
| 2.0911        | 0.98  | 480  | 2.0997          |
| 2.1063        | 1.02  | 500  | 2.0994          |
| 2.1296        | 1.06  | 520  | 2.0993          |
| 2.1051        | 1.1   | 540  | 2.0986          |
| 2.0919        | 1.14  | 560  | 2.0982          |
| 2.0608        | 1.18  | 580  | 2.0977          |
| 2.0865        | 1.22  | 600  | 2.0966          |
| 2.0912        | 1.27  | 620  | 2.0962          |
| 2.0858        | 1.31  | 640  | 2.0962          |
| 2.0914        | 1.35  | 660  | 2.0961          |
| 2.0542        | 1.39  | 680  | 2.0951          |
| 2.0939        | 1.43  | 700  | 2.0948          |
| 2.0707        | 1.47  | 720  | 2.0942          |
| 2.1158        | 1.51  | 740  | 2.0944          |
| 2.079         | 1.55  | 760  | 2.0941          |
| 2.0232        | 1.59  | 780  | 2.0935          |
| 2.0954        | 1.63  | 800  | 2.0934          |
| 2.079         | 1.67  | 820  | 2.0939          |
| 2.0747        | 1.71  | 840  | 2.0932          |
| 2.0881        | 1.76  | 860  | 2.0926          |
| 2.0319        | 1.8   | 880  | 2.0928          |
| 2.1047        | 1.84  | 900  | 2.0922          |
| 2.0383        | 1.88  | 920  | 2.0923          |
| 2.0602        | 1.92  | 940  | 2.0923          |
| 2.0902        | 1.96  | 960  | 2.0919          |
| 2.0845        | 2.0   | 980  | 2.0919          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1