CoolFace
Modelpublic

paulo037/20260503T211947Z-conll03_ner-graft-soft-invalid-b00-2b-10k-19acaa70

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes10downloads
Model Card

<!-- 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. -->

20260503T211947Z-conll03_ner-graft-soft-invalid-b00-2b-10k-19acaa70

This model is a fine-tuned version of Qwen/Qwen3-VL-2B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0052
  • —Graft/constrained Ratio: 1.0
  • —Graft/constrained Tokens: 10821.0
  • —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: 128
  • —totaltrainbatch_size: 128
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.03
  • —num_epochs: 3

Training results

Training LossEpochStepValidation LossRatioTokensSamplesFallback Samples
0.03990.3328260.02591.022433.00.00.0
0.0150.6656520.01051.017626.00.00.0
0.01140.9984780.00641.010821.00.00.0
0.01211.321040.00621.023581.00.00.0
0.00791.65281300.00581.017229.00.00.0
0.01051.98561560.00621.010821.00.00.0
0.00352.30721820.00591.023207.00.00.0
0.00442.642080.00611.016213.00.00.0
0.0032.97282340.00521.010821.00.00.0

Framework versions

  • —PEFT 0.17.1
  • —Transformers 4.57.0
  • —Pytorch 2.11.0a0+eb65b36914.nv26.02
  • —Datasets 4.1.1
  • —Tokenizers 0.22.2