cutelemonlili/Qwen2.5-Math-7B-Instruct_MATH_training_Qwen_QwQ_32B_Preview

MATH_training_Qwen_QwQ_32B_Preview

This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B-Instruct on the MATH_training_Qwen_QwQ_32B_Preview dataset. It achieves the following results on the evaluation set:

• Loss: 0.2995

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: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 8
• total_eval_batch_size: 4
• 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
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.2734	0.2999	200	0.3187
0.2738	0.5997	400	0.2967
0.3223	0.8996	600	0.2878
0.1772	1.1994	800	0.3054
0.1444	1.4993	1000	0.3005
0.1154	1.7991	1200	0.2998

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3