qwen2.5-1.5b-diffusion-graph-canvas-inpainting-v1

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7547

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• 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: linear
• lr_scheduler_warmup_steps: 100.0
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
3.0543	0.2722	250	3.1076
2.8852	0.5444	500	2.9352
2.8112	0.8166	750	2.8511
2.6657	1.0882	1000	2.8080
2.7338	1.3604	1250	2.7869
2.6773	1.6326	1500	2.7736
2.8516	1.9048	1750	2.7675
2.6461	2.1764	2000	2.7592
2.7112	2.4486	2250	2.7570
2.6040	2.7208	2500	2.7557
2.7622	2.9930	2750	2.7581
2.7622	3.0	2757	2.7547

Framework versions

• Transformers 5.14.1
• Pytorch 2.12.1+cu130
• Datasets 4.8.5
• Tokenizers 0.22.2