tapt_amazon_helpfulness_classification

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

• Loss: 0.3873
• Accuracy: 0.87
• F1 Macro: 0.6868

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
0.3226	1.0	1563	0.3149	0.8688	0.6717
0.2854	2.0	3126	0.3745	0.8682	0.6249
0.2016	3.0	4689	0.3873	0.87	0.6868

Framework versions

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