kamizane/Qwen3.5-0.8B-legal_extraction-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-legal_extraction-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: 0.0734
• —Graft/constrained Ratio: 1.0
• —Graft/constrained Tokens: 38957.0
• —Graft/fallback Samples: 0.0
• —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
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 14
• —gradientaccumulationsteps: 6
• —totaltrainbatch_size: 6
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 4

Training results

Framework versions

• —PEFT 0.20.0
• —Transformers 5.16.1
• —Pytorch 2.11.0+cu128
• —Datasets 4.0.0
• —Tokenizers 0.23.1