BERT_NewsNLI

This model is a fine-tuned version of vishruthnath/Calc_BERT_ep20 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7262
• F1: {'f1': 0.20879156215833816}
• Accuracy: {'accuracy': 0.20833333333333334}

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: 1e-05
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
No log	1.0	28	0.7071	{'f1': 0.44863239132902055}	{'accuracy': 0.4861111111111111}
No log	2.0	56	0.7148	{'f1': 0.3611111111111111}	{'accuracy': 0.3611111111111111}
No log	3.0	84	0.7216	{'f1': 0.29746179746179746}	{'accuracy': 0.3055555555555556}
No log	4.0	112	0.7247	{'f1': 0.21315721315721317}	{'accuracy': 0.2222222222222222}
No log	5.0	140	0.7262	{'f1': 0.20879156215833816}	{'accuracy': 0.20833333333333334}

Framework versions

• Transformers 4.35.2
• Pytorch 1.12.1+cu113
• Datasets 2.15.0
• Tokenizers 0.15.0