cutelemonlili/Qwen2.5-7B-Instruct_MATH_training_response_Qwen2.5_7B_only_right

MATH_training_response_Qwen2.5_7B_only_right

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the MATH_training_response_Qwen2.5_7B_only_right dataset. It achieves the following results on the evaluation set:

• Loss: 0.1080

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
0.1325	0.2849	200	0.1213
0.0894	0.5698	400	0.1227
0.0739	0.8547	600	0.1127
0.0561	1.1396	800	0.1148
0.0311	1.4245	1000	0.1148
0.0341	1.7094	1200	0.1096
0.0352	1.9943	1400	0.1079

Framework versions

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