morizon/dpo_visual_llavajp_refmodel

<!-- 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. -->

dpovisualllavajp_refmodel

This model is a fine-tuned version of hibikaze/finetune-llava-v1.5-japanese-gpt2-small_test-checkpoint-1200 on the None dataset.

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-05
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.42.4
• —Pytorch 2.3.1+cu121
• —Datasets 2.20.0
• —Tokenizers 0.19.1