BigTMiami's picture
End of training
2006c17 verified
metadata
license: mit
base_model: BigTMiami/dapt_plus_tapt_helpfulness_base_pretraining_model
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: dapt_plus_tapt_amazon_helpfulness_classification
    results: []

dapt_plus_tapt_amazon_helpfulness_classification

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

  • Loss: 0.3889
  • Accuracy: 0.8696
  • F1 Macro: 0.6767

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: 42
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.06
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro
0.317 1.0 1563 0.3193 0.8668 0.6641
0.2897 2.0 3126 0.3704 0.8702 0.6222
0.2137 3.0 4689 0.3889 0.8696 0.6767

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2