dl-2-hw-2-bert-finetuned-ner-best-optuna

This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 9.46040946630437e-05
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.295	1.0	313	0.1106	0.8383	0.8899	0.8633	0.9738
0.0866	2.0	626	0.0815	0.8774	0.9143	0.8955	0.9789
0.0496	3.0	939	0.0787	0.8879	0.9170	0.9022	0.9794
0.0334	4.0	1252	0.0807	0.8977	0.9212	0.9093	0.9810
0.0228	5.0	1565	0.0865	0.8912	0.9251	0.9078	0.9809
0.0177	6.0	1878	0.0837	0.9074	0.9221	0.9147	0.9815
0.0142	7.0	2191	0.0880	0.8990	0.9243	0.9115	0.9805
0.0106	8.0	2504	0.0920	0.9121	0.9285	0.9202	0.9820
0.0081	9.0	2817	0.0965	0.9165	0.9315	0.9240	0.9822
0.0068	10.0	3130	0.0995	0.8988	0.9241	0.9113	0.9809
0.0056	11.0	3443	0.0934	0.9044	0.9295	0.9168	0.9823
0.0048	12.0	3756	0.0937	0.9153	0.9310	0.9231	0.9826
0.0041	13.0	4069	0.0988	0.9127	0.9329	0.9227	0.9824
0.003	14.0	4382	0.0988	0.9151	0.9308	0.9229	0.9826
0.0027	15.0	4695	0.0990	0.9121	0.9312	0.9216	0.9826