---
library_name: transformers
license: llama3.1
base_model: mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: sky-t1-original-plus-oh
  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. -->

# sky-t1-original-plus-oh

This model is a fine-tuned version of [mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini](https://huggingface.co/mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini) on the mlfoundations-dev/sky_t1_original dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4574

## 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- 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: constant
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.5104        | 1.0   | 30   | 0.5004          |
| 0.4439        | 2.0   | 60   | 0.4688          |
| 0.392         | 3.0   | 90   | 0.4574          |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.5.1
- Datasets 3.0.2
- Tokenizers 0.20.3