MatBERTNanoQA

This model is a fine-tuned version of Flamenco43/MatBERT on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1722
• F1: 74.5785
• Em: 62.5
• Precision: 0
• Recall: 0

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: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Em	Precision	Recall
1.1937	1.0	1118	1.5914	67.1538	50.0	0	0
1.0172	2.0	2236	1.3482	72.0843	59.6154	0	0
0.8463	3.0	3354	1.2223	74.0304	62.5	0	0
0.7447	4.0	4472	1.1722	74.5785	62.5	0	0

Framework versions

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