VF_MatSciBERT_ST_1800

This model is a fine-tuned version of m3rg-iitd/matscibert on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1894
• Precision: 0.7360
• Recall: 0.7770
• F1: 0.7560
• Accuracy: 0.9556

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	30	0.3205	0.4448	0.2093	0.2847	0.9095
No log	2.0	60	0.2400	0.6346	0.6075	0.6208	0.9376
No log	3.0	90	0.2236	0.6764	0.7010	0.6885	0.9450
No log	4.0	120	0.1959	0.6664	0.7127	0.6888	0.9453
No log	5.0	150	0.1958	0.7177	0.7514	0.7342	0.9519
No log	6.0	180	0.1802	0.7180	0.7666	0.7415	0.9541
No log	7.0	210	0.1911	0.7316	0.7668	0.7488	0.9546
No log	8.0	240	0.1914	0.7384	0.7711	0.7544	0.9554
No log	9.0	270	0.1873	0.7366	0.7745	0.7551	0.9556
No log	10.0	300	0.1894	0.7360	0.7770	0.7560	0.9556

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1