aczhu/qwen_reason

reason

This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the bespoke_reasoning_17k dataset. It achieves the following results on the evaluation set:

• Loss: 0.4530

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 7
• gradient_accumulation_steps: 2
• total_train_batch_size: 14
• total_eval_batch_size: 7
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4968	0.4653	500	0.4815
0.4717	0.9307	1000	0.4591
0.3426	1.3955	1500	0.4593
0.3598	1.8609	2000	0.4531

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0