---
base_model: save_model/llama3-2k-spa_1
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- datasets/training-llama3-2k-spa_2
model-index:
- name: llama3-2k-spa_2
  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. -->

# llama3-2k-spa_2

This model is a fine-tuned version of [save_model/llama3-2k-spa_1](https://huggingface.co/save_model/llama3-2k-spa_1) on the datasets/training-llama3-2k-spa_2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9255
- Rewards/chosen: -7.0304
- Rewards/rejected: -7.9655
- Rewards/accuracies: 0.6667
- Rewards/margins: 0.9351
- Rewards/mix Margin: 0.9351
- Logps/rejected: -380.0901
- Logps/chosen: -401.9111
- Logits/rejected: -0.3285
- Logits/chosen: -0.3819

## 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: 5e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Rewards/mix Margin | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:------------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.3277        | 0.8   | 1000 | 0.9255          | -7.0304        | -7.9655          | 0.6667             | 0.9351          | 0.9351             | -380.0901      | -401.9111    | -0.3285         | -0.3819       |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2