---
base_model: dmis-lab/selfbiorag_7b
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- HuggingFaceH4/deita-10k-v0-sft
model-index:
- name: selfbiorag-7b-wo-live_qa-iter-sft-step1
  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. -->

# selfbiorag-7b-wo-live_qa-iter-sft-step1

This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1582

## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.2659        | 0.91  | 5    | 1.2054          |
| 1.0094        | 2.0   | 11   | 1.1690          |
| 0.8249        | 2.73  | 15   | 1.1582          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2