a08fea00-9b38-4942-908a-8b17d69ec9ad

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

• Loss: 0.0022

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• 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	0.0001	1	0.2925
0.0028	0.0057	50	0.0062
0.0002	0.0115	100	0.0040
0.0006	0.0172	150	0.0047
0.0005	0.0229	200	0.0035
0.0003	0.0287	250	0.0031
0.0034	0.0344	300	0.0027
0.0004	0.0402	350	0.0028
0.0003	0.0459	400	0.0027
0.0003	0.0516	450	0.0022
0.0003	0.0574	500	0.0022

Framework versions

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