---
license: other
base_model: meta-llama/Meta-Llama-3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: C020_random_sample_llama3-8b-base_instruct_20240505_135320
  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. -->

# C020_random_sample_llama3-8b-base_instruct_20240505_135320

This model is a fine-tuned version of [./output/training_results/C020_random_sample_llama3-8b-base_pretrain_20240505_135320/](https://huggingface.co/./output/training_results/C020_random_sample_llama3-8b-base_pretrain_20240505_135320/) on the instructions_curated dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8432

## 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: 1.5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_steps: 20
- num_epochs: 4.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8145        | 0.4167 | 20   | 0.8468          |
| 0.7939        | 0.8333 | 40   | 0.8432          |
| 0.4337        | 1.25   | 60   | 0.8653          |
| 0.4546        | 1.6667 | 80   | 0.8524          |
| 0.3886        | 2.0833 | 100  | 0.8477          |
| 0.3963        | 2.5    | 120  | 0.8523          |
| 0.3728        | 2.9167 | 140  | 0.8571          |
| 0.3681        | 3.3333 | 160  | 0.8608          |
| 0.3621        | 3.75   | 180  | 0.8637          |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1