peft-FT-2.5-Coder-32b

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-32B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7838

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
1.1544	0.25	50	1.0288
1.0177	0.5	100	0.8956
0.943	0.75	150	0.8172
0.8269	1.0	200	0.7838

Framework versions

• PEFT 0.17.1
• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1