---
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: zephyr-7b-sft-safe
  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. -->

# zephyr-7b-sft-safe

This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4746

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- 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: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9227        | 0.54  | 100  | 1.3366          |
| 0.3659        | 1.08  | 200  | 1.4554          |
| 0.3187        | 1.62  | 300  | 1.4746          |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2