TaiGary/Qwen2.5-1.5B-Instruct_rejection_sampling_MATH_training_short_CoT

reject-sampling_8_MATH_training_short_CoT

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the reject-sampling_8_MATH_training_short_CoT dataset. It achieves the following results on the evaluation set:

• Loss: 0.1684

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
0.1755	0.2551	100	0.1783
0.1688	0.5102	200	0.1753
0.1684	0.7653	300	0.1720
0.1183	1.0204	400	0.1734
0.1013	1.2755	500	0.1717
0.1174	1.5306	600	0.1697
0.1391	1.7857	700	0.1684

Framework versions

• Transformers 4.46.1
• Pytorch 2.6.0+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3