roberta-base-finetuned-classifier-roberta1

This model is a fine-tuned version of roberta-base on the lectures dataset. It achieves the following results on the test set:

• Loss: 0.5266
• Precision: 0.9244
• Recall: 0.9200
• F1-score: 0.9198
• Accuracy: 0.92

Model description

The model was trained on a lectures dataset of 1000 rows of data. Hyperparameter tuning was also done to achieve these results.

Intended uses & limitations

More information needed

Training and evaluation data

The dataset was split into 80% training data, 10% validation data and 10% test data. We ensured that each split would have a proportional number of lectures per field.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1-score	Accuracy
No log	1.0	25	0.4560	0.9362	0.93	0.9308	0.93
No log	2.0	50	0.3287	0.9519	0.95	0.9505	0.95

Framework versions

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