custom_bert

This model is a fine-tuned version of on the eli5_category dataset. It achieves the following results on the evaluation set:

• Loss: 6.7038

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
7.2917	1.0	1326	6.9082
6.8038	2.0	2652	6.8164
6.7413	3.0	3978	6.7508
6.6956	4.0	5304	6.7371
6.6856	5.0	6630	6.7080

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1