KarelDO/gpt2.CEBaB_confounding.uniform.absa.5-class.seed_43

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

gpt2.CEBaBconfounding.uniform.absa.5-class.seed43

This model is a fine-tuned version of gpt2 on the OpenTable OPENTABLE-ABSA dataset. It achieves the following results on the evaluation set:

• —Loss: 0.3820
• —Accuracy: 0.8654
• —Macro-f1: 0.8612
• —Weighted-macro-f1: 0.8650

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
• —trainbatchsize: 32
• —evalbatchsize: 32
• —seed: 43
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 5.0

Training results

Framework versions

• —Transformers 4.18.0
• —Pytorch 1.10.2+cu102
• —Datasets 2.5.2
• —Tokenizers 0.12.1