EthM300/compare3

results

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9157
• Accuracy: 0.8261

Model description

Text binary classification model for classifying the difficulty of quizbowl clues with regard to difficulty 3 (0 - lower, 1 - higher).

Intended uses & limitations

This is part of bigger multiclass classification model intended to classify quizbowl clues based on their difficulties.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	9	0.4593	0.7826
No log	2.0	18	1.0224	0.6522
No log	3.0	27	0.8772	0.7391
No log	4.0	36	0.8555	0.8261
No log	5.0	45	0.8779	0.8261
No log	6.0	54	0.8982	0.8261
No log	7.0	63	0.9113	0.8261
No log	8.0	72	0.9157	0.8261

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0
• Datasets 3.5.0
• Tokenizers 0.21.1