Rodrigo1771/bioBIT-drugtemist-it-word2vec-75-ner

output

This model is a fine-tuned version of IVN-RIN/bioBIT on the Rodrigo1771/drugtemist-it-75-ner dataset. It achieves the following results on the evaluation set:

• Loss: 0.0080
• Precision: 0.9145
• Recall: 0.9216
• F1: 0.9180
• Accuracy: 0.9986

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.9990	498	0.0059	0.8588	0.9129	0.8850	0.9981
0.0135	2.0	997	0.0052	0.8778	0.9245	0.9005	0.9985
0.0036	2.9990	1495	0.0061	0.8868	0.9177	0.9020	0.9984
0.0022	4.0	1994	0.0059	0.8842	0.9313	0.9071	0.9985
0.0012	4.9990	2492	0.0077	0.8930	0.9206	0.9066	0.9985
0.0006	6.0	2991	0.0074	0.8813	0.9274	0.9038	0.9984
0.0005	6.9990	3489	0.0080	0.8949	0.9235	0.9090	0.9985
0.0002	8.0	3988	0.0080	0.9145	0.9216	0.9180	0.9986
0.0002	8.9990	4486	0.0087	0.9002	0.9255	0.9126	0.9986
0.0001	9.9900	4980	0.0089	0.9065	0.9197	0.9130	0.9985

Framework versions

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