BigTMiami's picture
End of training
9c97e98 verified
metadata
license: mit
base_model: BigTMiami/micro_base_help_tapt_pretrain_model
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: micro_base_help_class_tapt_seed_0
    results: []

micro_base_help_class_tapt_seed_0

This model is a fine-tuned version of BigTMiami/micro_base_help_tapt_pretrain_model on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4322
  • Accuracy: 0.8648
  • F1 Macro: 0.6284

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: 0
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro
0.3129 1.0 313 0.4102 0.8568 0.4902
0.2957 2.0 626 0.3787 0.8588 0.5080
0.2515 3.0 939 0.4483 0.8614 0.6406
0.1744 4.0 1252 0.5208 0.8552 0.5978
0.1379 5.0 1565 0.7543 0.861 0.5924
0.1142 6.0 1878 0.8998 0.8534 0.6123

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2