qwen2_vl-72b_full-sft_m3cot+llava-reasoner_v2

This model is a fine-tuned version of /mnt/zhangh/sicong/vl3_data/checkpoints/Qwen/Qwen2-VL-72B-Instruct on the m3cot+llava-reasoner_v2 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: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 32
  • total_train_batch_size: 128
  • total_eval_batch_size: 256
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1.0

Training results

Framework versions

  • Transformers 4.46.0
  • Pytorch 2.5.0
  • Datasets 2.21.0
  • Tokenizers 0.20.3
Downloads last month
236
Safetensors
Model size
73.4B params
Tensor type
BF16
·
Inference Examples
Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for mm-o1/Qwen2VL-72B-sft-v2

Base model

Qwen/Qwen2-VL-72B
Finetuned
(4)
this model