---
library_name: transformers
license: other
base_model: inflatebot/MN-12B-Mag-Mell-R1
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: sft
  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. -->

# sft

This model is a fine-tuned version of [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1) on the kto_rp dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3763
- Rewards/chosen: 0.6433
- Logps/chosen: -219.3819
- Logits/chosen: -923703389.9450
- Rewards/rejected: -1.3013
- Logps/rejected: -231.1543
- Logits/rejected: -831308124.5957
- Rewards/margins: 1.9446
- Kl: 0.0

## 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: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Logps/chosen | Logits/chosen   | Rewards/rejected | Logps/rejected | Logits/rejected | Rewards/margins |     |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:------------:|:---------------:|:----------------:|:--------------:|:---------------:|:---------------:|:---:|
| 0.3079        | 0.8421 | 500  | 0.3781          | 0.8047         | -217.7675    | -922359676.4771 | -1.0247          | -228.3881      | -826945158.3546 | 1.8294          | 0.0 |


### Framework versions

- Transformers 4.55.0
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1