UWNSL/Llama-3.2-3B-Instruct_Long_CoT

MATH_training_Qwen_QwQ_32B_Preview

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the MATH_training_Qwen_QwQ_32B_Preview dataset. It achieves the following results on the evaluation set:

• Loss: 0.3727

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: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 16
• 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
0.3483	0.5988	200	0.3796
0.2544	1.1976	400	0.3797
0.2508	1.7964	600	0.3729

Framework versions

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