mlfoundations-cua-dev/qwen2_5vl_7b_lr_1_0e-06_2nodes_z3_offload

qwen2_5vl_7b_easyr1_10k_hard_qwen7b_easy_gta1_4MP_no_resolution_in_prompt_lr_1_0e-06_2nodes_z3_offload

This model is a fine-tuned version of /p/project1/synthlaion/awadalla1/models/Qwen2.5-VL-7B-Instruct on the easyr1-10k-hard-qwen7b-easy-gta1-4MP-no-resolution-in-prompt 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-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 8
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 4.55.0
• Pytorch 2.8.0+cu129
• Datasets 4.0.0
• Tokenizers 0.21.1