---
library_name: transformers
license: other
base_model: llava-hf/llava-v1.6-mistral-7b-hf
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: RLAIF-V_Coocur-q0_75
  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. -->

# RLAIF-V_Coocur-q0_75

This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the RLAIF-V_Coocur-q0_75 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0131

## 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1348        | 0.2320 | 50   | 1.1268          |
| 1.08          | 0.4640 | 100  | 1.0813          |
| 1.0619        | 0.6961 | 150  | 1.0556          |
| 1.0468        | 0.9281 | 200  | 1.0335          |
| 0.8999        | 1.1601 | 250  | 1.0276          |
| 0.8818        | 1.3921 | 300  | 1.0166          |
| 0.8729        | 1.6241 | 350  | 1.0092          |
| 0.8653        | 1.8561 | 400  | 1.0026          |
| 0.7781        | 2.0882 | 450  | 1.0152          |
| 0.7742        | 2.3202 | 500  | 1.0131          |
| 0.7689        | 2.5522 | 550  | 1.0138          |
| 0.7824        | 2.7842 | 600  | 1.0129          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.20.3