russellyq/output_uni_dpo_mcq_short
04
<!-- 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. -->
outputunidpomcqshort
This model is a fine-tuned version of /home/yanqiao/data_yq/model_weights/Qwen2-VL-2B on the unidpoimageonlymcq_short 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: 6e-06
- trainbatchsize: 2
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lrschedulertype: cosine
- num_epochs: 1.0
Training results
Framework versions
- Transformers 4.54.0
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.4