bert-mini-hangman

This model is a fine-tuned version of vaibhav9/bert-mini-hangman on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.4192

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.1255	1.0	2609	2.8087
2.1225	2.0	5218	nan
2.1168	3.0	7827	nan
2.1127	4.0	10436	nan
2.1087	5.0	13045	3.4192

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1
• Datasets 2.14.5
• Tokenizers 0.13.3