cutelemonlili/llama3.2_3b_OpenMathInstruct-2_100k_MATH_training_Qwen2.5-32B-Instruct

MATH_training_Qwen2.5-32B-Instruct

This model is a fine-tuned version of TaiGary/llama3.2_3b_OpenMathInstruct-2_100k on the MATH_training_Qwen2.5-32B-Instruct dataset. It achieves the following results on the evaluation set:

• Loss: 0.2496

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
0.2073	0.2999	200	0.2770
0.2183	0.5997	400	0.2596
0.2086	0.8996	600	0.2451
0.0868	1.1994	800	0.2615
0.0724	1.4993	1000	0.2537
0.0957	1.7991	1200	0.2501

Framework versions

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