---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- barc0/induction_20k_gpt4o-mini_generated_problems_seed25.jsonl_messages_format_0.3
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: induction-10k-25seeds-gpt4omini-llama3.1-8b-instruct-lora64_lr2e-4_epoch3
  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. -->

# induction-10k-25seeds-gpt4omini-llama3.1-8b-instruct-lora64_lr2e-4_epoch3

This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/induction_20k_gpt4o-mini_generated_problems_seed25.jsonl_messages_format_0.3 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3479

## 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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.372         | 0.9934 | 75   | 0.3704          |
| 0.3361        | 2.0    | 151  | 0.3516          |
| 0.3346        | 2.9801 | 225  | 0.3479          |


### Framework versions

- PEFT 0.13.0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1