ComNumPNdistilBERTv0

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

ComNumPNdistilBERT

This model is a fine-tuned version of distilbert-base-uncased on a subset (800 samples as training and 200 samples as validation) of the This model is a fine-tuned version of distilbert-base-uncased on a subset (800 samples as training and 200 samples as validation) of the ComNum dataset. We just separated a numeral into digits as a reframing before tokenizing them. For example '1871' becomes '1 8 7 1'. It achieves the following results on the evaluation subset:

• Loss: 0.3672
• Accuracy: 0.75

It achieves the following results on the test set:

• Loss: 0.3833
• Accuracy: 0.7413

<!-- {'eval_loss': 0.383272260427475, 'eval_accuracy': 0.7413, 'eval_runtime': 381.4396, 'eval_samples_per_second': 26.216, 'eval_steps_per_second': 3.277} -->

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0