shirzady1934/bert-riddle-finetuned_3choice

bert_base_uncased

This model is a fine-tuned version of bert-base-uncased on the word-puzzle dataset. It achieves the following results on the evaluation set:

• Loss: 0.4856
• Accuracy: 0.8500

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• 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	Accuracy
No log	1.0	23	1.0218	0.6000
No log	2.0	46	0.6112	0.7250
No log	3.0	69	0.4168	0.875
No log	4.0	92	0.4505	0.8500
No log	5.0	115	0.4856	0.8500

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0