Qwen3.5-0.8B-IE-GRAFT

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Qwen3.5-0.8B-IE-GRAFT

This model is a fine-tuned version of Qwen/Qwen3.5-0.8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2691
• Graft/constrained Ratio: 0.5172
• Graft/constrained Tokens: 12302.0
• Graft/fallback Samples: 246.0
• Graft/standard Fallback Samples: 0.0

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: 1
• eval_batch_size: 1
• seed: 14
• gradient_accumulation_steps: 6
• total_train_batch_size: 6
• 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: 0.03
• num_epochs: 4

Training results

Framework versions

• PEFT 0.19.1
• Transformers 5.14.1
• Pytorch 2.11.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.2