fzwd6666/NLI_multi_new

This model is a fine-tuned version of fzwd6666/Ged_bert_new on an NLI dataset. It achieves the following results on the evaluation set:

{'precision': 0.9647540983606557} {'recall': 0.9755491089929549} {'f1': 0.9701215742839481} {'accuracy': 0.9525523560209425}

Training hyperparameters:

learning_rate: 2e-5 train_batch_size: 8 eval_batch_size: 8 optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08 weight_decay= 0.01

lr_scheduler_type: linear

num_epochs: 3 It achieves the following results on the test set: Incorrect UD Padded: {'precision': 0.6101694915254238} {'recall': 0.6580907244414353} {'f1': 0.6332247557003257} {'accuracy': 0.5230834392206692}

Incorrect UD Unigram: {'precision': 0.6010863005431503} {'recall': 0.6743398781313473} {'f1': 0.635609444798979} {'accuracy': 0.516306649724693}

Incorrect UD Bigram: {'precision': 0.6137841352405722} {'recall': 0.6391333784698714} {'f1': 0.6262023217247098} {'accuracy': 0.5226598898771707}

Incorrect UD All: {'precision': 0.6333333333333333} {'recall': 0.34732566012186866} {'f1': 0.4486226497595103} {'accuracy': 0.46590427784836935}

Incorrect Sentence: {'precision': 0.6519031141868512} {'recall': 0.6377792823290453} {'f1': 0.6447638603696099} {'accuracy': 0.5603557814485387}