---
library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: llama_8b_lima_40
  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. -->

# llama_8b_lima_40

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the open_webui_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9296

## 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: 6e-06
- train_batch_size: 3
- eval_batch_size: 2
- seed: 66
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 6
- total_train_batch_size: 36
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_ratio: 0.04
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1355        | 0.0494 | 40   | 1.0442          |
| 0.9066        | 0.0987 | 80   | 1.0029          |
| 0.9609        | 0.1481 | 120  | 0.9815          |
| 1.0128        | 0.1974 | 160  | 0.9743          |
| 0.9558        | 0.2468 | 200  | 0.9663          |
| 0.9236        | 0.2962 | 240  | 0.9598          |
| 1.0243        | 0.3455 | 280  | 0.9488          |
| 0.9767        | 0.3949 | 320  | 0.9481          |
| 0.763         | 0.4443 | 360  | 0.9467          |
| 0.944         | 0.4936 | 400  | 0.9442          |
| 0.937         | 0.5430 | 440  | 0.9415          |
| 0.8981        | 0.5923 | 480  | 0.9385          |
| 0.9358        | 0.6417 | 520  | 0.9364          |
| 0.8273        | 0.6911 | 560  | 0.9349          |
| 0.8544        | 0.7404 | 600  | 0.9339          |
| 0.8621        | 0.7898 | 640  | 0.9315          |
| 0.8641        | 0.8392 | 680  | 0.9320          |
| 0.7915        | 0.8885 | 720  | 0.9314          |
| 0.8847        | 0.9379 | 760  | 0.9302          |
| 0.9551        | 0.9872 | 800  | 0.9304          |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3