中文Sign up

abdiharyadi/wos_flat_1782296044

🤗 Hugging Face sourcetext-classificationapache-2.0110M params438 MBsafetensors✓ 7 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo abdiharyadi/wos_flat_1782296044 ./model-folder
Needs a seeder →

wos_flat_1782296044

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4062
  • Accuracy: 0.8069
  • Precision Macro: 0.7929
  • Recall Macro: 0.7801
  • F1 Macro: 0.7828

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: 3e-05
  • train_batch_size: 12
  • eval_batch_size: 12
  • seed: 120
  • 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: 500
  • num_epochs: 38

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Macro Recall Macro F1 Macro
2.6446 1.0 2506 1.2083 0.7443 0.7249 0.6978 0.6884
0.9237 2.0 5012 0.9532 0.7873 0.7664 0.7543 0.7506
0.6276 3.0 7518 0.9017 0.8055 0.7912 0.7777 0.7792
0.4547 4.0 10024 0.9464 0.8049 0.7950 0.7814 0.7833
0.3283 5.0 12530 1.0243 0.8053 0.7946 0.7848 0.7861
0.2433 6.0 15036 1.1270 0.8058 0.7931 0.7814 0.7812
0.1726 7.0 17542 1.1630 0.8028 0.7955 0.7814 0.7845
0.1169 8.0 20048 1.3213 0.8036 0.7950 0.7779 0.7824
0.0813 9.0 22554 1.4062 0.8069 0.7929 0.7801 0.7828

Framework versions

  • Transformers 5.12.1
  • Pytorch 2.10.0+cu128
  • Datasets 5.0.0
  • Tokenizers 0.22.2