---
library_name: transformers
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-stem-case-1
  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-stem-case-1

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: 0.0500

## 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: 1e-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: 0.03
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1144        | 1.0   | 2    | 1.2928          |
| 1.1144        | 2.0   | 4    | 0.8673          |
| 1.0902        | 3.0   | 6    | 0.6944          |
| 1.0902        | 4.0   | 8    | 0.4531          |
| 0.5758        | 5.0   | 10   | 0.3128          |
| 0.5758        | 6.0   | 12   | 0.1866          |
| 0.5758        | 7.0   | 14   | 0.1056          |
| 0.1998        | 8.0   | 16   | 0.0681          |
| 0.1998        | 9.0   | 18   | 0.0533          |
| 0.0645        | 10.0  | 20   | 0.0500          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1