metadata
license: apache-2.0
base_model: lmms-lab/llava-onevision-qwen2-7b-ov
tags:
- generated_from_trainer
model-index:
- name: aha
results: []
library_name: peft
language:
- en
pipeline_tag: video-text-to-text
anon for paper submission
This model is a fine-tuned version of lmms-lab/llava-onevision-qwen2-7b-ov on an unknown dataset.
Training and evaluation data
Please check out the dataset for more information.
Training procedure
Please check out our main repository for more information.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1.0
Training results
Framework versions
- PEFT 0.4.0
- Transformers 4.40.0
- Pytorch 2.5.1+cu124
- Datasets 2.16.1
- Tokenizers 0.19.1