---
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- generated_from_trainer
model-index:
- name: spin-v-iter0-v2
  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. -->

# spin-v-iter0-v2

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 None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0054
- Rewards/real: -1.6431
- Rewards/generated: -16.4195
- Rewards/accuracies: 1.0
- Rewards/margins: 14.7764
- Logps/generated: -257.4886
- Logps/real: -151.0967
- Logits/generated: -2.5437
- Logits/real: -2.1952

## 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: 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
| 0.0106        | 0.64  | 100  | 0.0084          | -0.8594      | -11.5552          | 0.9992             | 10.6958         | -208.8447       | -143.2594  | -2.7086          | -2.4488     |
| 0.002         | 1.27  | 200  | 0.0057          | -0.9375      | -14.1180          | 1.0                | 13.1805         | -234.4735       | -144.0411  | -2.6005          | -2.2709     |
| 0.0007        | 1.91  | 300  | 0.0054          | -1.6431      | -16.4195          | 1.0                | 14.7764         | -257.4886       | -151.0967  | -2.5437          | -2.1952     |


### Framework versions

- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2