variant-tapt_freeze_llrd-LR_2e-05

This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext on the Mardiyyah/TAPT_Variant_FT dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4408
  • Accuracy: 0.7208

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 3407
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.06
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.6327 1.0 19 1.6173 0.7107
1.5988 2.0 38 1.5820 0.7121
1.5615 3.0 57 1.5136 0.7221
1.5289 4.0 76 1.4800 0.7179
1.5178 5.0 95 1.4445 0.7289
1.4878 6.0 114 1.4360 0.7259
1.4812 7.0 133 1.4790 0.7208
1.4423 8.0 152 1.4385 0.7298
1.4869 9.0 171 1.4737 0.7273
1.4432 10.0 190 1.4679 0.7239
1.4259 11.0 209 1.3732 0.7280
1.4123 12.0 228 1.3996 0.7269
1.4365 13.0 247 1.3973 0.7317
1.4018 14.0 266 1.4079 0.7268
1.4105 15.0 285 1.3483 0.7309
1.409 16.0 304 1.4483 0.7189
1.4064 17.0 323 1.4226 0.7286
1.3731 18.0 342 1.3888 0.7275
1.4023 19.0 361 1.4027 0.7239
1.393 20.0 380 1.4187 0.7259

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.21.0
Downloads last month
2
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Mardiyyah/variant-tapt_freeze_llrd-LR_2e-05