cutelemonlili/Qwen2.5-3B_MATH_training_response_Qwen2.5-32B-Instruct_common_correct_with_qwen2.5_3b

MATH_training_response_Qwen2.5-32B-Instruct_common_correct_with_qwen2.5_3b

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the MATH_training_response_Qwen2.5-32B-Instruct_common_correct_with_qwen2.5_3b dataset. It achieves the following results on the evaluation set:

• Loss: 0.1437

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
0.1244	0.4283	200	0.1429
0.1083	0.8565	400	0.1296
0.0395	1.2848	600	0.1522
0.0258	1.7131	800	0.1452

Framework versions

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