cs221-xlnet-large-cased-finetuned-16-epochs

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5366
• Bce Loss: 0.5366

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bce Loss
0.4505	1.0	139	0.5366	0.5366
0.469	2.0	278	0.5445	0.5445

Framework versions

• Transformers 4.47.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.21.0