loha_fine_tuned_boolq

This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5655
• Accuracy: 0.7778
• F1: 0.6806

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
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6686	4.1667	50	0.6058	0.7778	0.6806
0.661	8.3333	100	0.5835	0.7778	0.6806
0.66	12.5	150	0.5765	0.7778	0.6806
0.6685	16.6667	200	0.5708	0.7778	0.6806
0.6634	20.8333	250	0.5677	0.7778	0.6806
0.6573	25.0	300	0.5668	0.7778	0.6806
0.6623	29.1667	350	0.5661	0.7778	0.6806
0.6583	33.3333	400	0.5655	0.7778	0.6806

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.1
• Pytorch 2.1.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1