10305f89-af2b-4c89-bd89-e15dcf76396a

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0840

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: 0.000217
• train_batch_size: 4
• eval_batch_size: 4
• seed: 170
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	1.2176
0.1094	0.0008	50	0.2146
0.0602	0.0015	100	0.1716
0.0982	0.0023	150	0.1428
0.0527	0.0030	200	0.1390
0.0799	0.0038	250	0.1166
0.0524	0.0046	300	0.1015
0.0451	0.0053	350	0.0918
0.0447	0.0061	400	0.0864
0.0345	0.0069	450	0.0844
0.0348	0.0076	500	0.0840

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1