distilbert_B001

This model is a fine-tuned version of distilbert-base-uncased on the essay_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.3451
• Accuracy: {'accuracy': 0.5280898876404494}
• Precision: {'precision': 0.19377125850340135}
• Recall: {'recall': 0.2962962962962963}
• F1: {'f1': 0.21358825283243887}

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=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	42	1.6131	{'accuracy': 0.4044943820224719}	{'precision': 0.10313447927199192}	{'recall': 0.2456896551724138}	{'f1': 0.13425925925925927}
No log	2.0	84	1.4558	{'accuracy': 0.4943820224719101}	{'precision': 0.16714285714285715}	{'recall': 0.24942129629629628}	{'f1': 0.19666725679383906}
No log	3.0	126	1.3405	{'accuracy': 0.5730337078651685}	{'precision': 0.20856060606060606}	{'recall': 0.31513409961685823}	{'f1': 0.2357282221467332}
No log	4.0	168	1.3451	{'accuracy': 0.5280898876404494}	{'precision': 0.19377125850340135}	{'recall': 0.2962962962962963}	{'f1': 0.21358825283243887}

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1