SFT-Qwen2.5-Coder-3B_v1

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7801

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
1.0934	0.2909	20	0.9285
0.8825	0.5818	40	0.8725
0.8459	0.8727	60	0.8423
0.8573	1.16	80	0.8205
0.8109	1.4509	100	0.8079
0.7729	1.7418	120	0.7978
0.7089	2.0291	140	0.7842
0.7298	2.32	160	0.7870
0.6684	2.6109	180	0.7820
0.6122	2.9018	200	0.7801

Framework versions

• PEFT 0.18.0
• Transformers 4.57.1
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1