tmvar_0.0001_250

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0142
• Precision: 0.8520
• Recall: 0.9027
• F1: 0.8766
• Accuracy: 0.9972

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
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2033	1.0	25	0.0313	0.6273	0.3730	0.4678	0.9899
0.0336	2.0	50	0.0197	0.6723	0.8541	0.7524	0.9946
0.0133	3.0	75	0.0134	0.8763	0.8811	0.8787	0.9969
0.0075	4.0	100	0.0192	0.7110	0.8378	0.7692	0.9952
0.0065	5.0	125	0.0126	0.8681	0.8541	0.8610	0.9969
0.0029	6.0	150	0.0130	0.8513	0.8973	0.8737	0.9974
0.002	7.0	175	0.0121	0.8446	0.8811	0.8624	0.9969
0.0017	8.0	200	0.0103	0.8462	0.8919	0.8684	0.9974
0.0011	9.0	225	0.0148	0.8299	0.8703	0.8496	0.9967
0.0007	10.0	250	0.0150	0.8426	0.8973	0.8691	0.9971
0.0005	11.0	275	0.0142	0.8376	0.8919	0.8639	0.9970
0.0004	12.0	300	0.0142	0.8513	0.8973	0.8737	0.9972
0.0003	13.0	325	0.0143	0.8469	0.8973	0.8714	0.9971
0.0003	14.0	350	0.0142	0.8520	0.9027	0.8766	0.9972

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.2