SFT-Qwen2.5-Coder-14B_v1.1st

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-14B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5219

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.8054	0.3035	50	0.7292
0.7371	0.6070	100	0.6630
0.6231	0.9105	150	0.6295
0.5381	1.2124	200	0.5937
0.5883	1.5159	250	0.5661
0.4634	1.8194	300	0.5427
0.4304	2.1214	350	0.5435
0.3941	2.4249	400	0.5298
0.3886	2.7284	450	0.5219

Framework versions

• PEFT 0.18.0
• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1