learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2222	1.0	625	0.1697	0.7831	0.8251	0.8036	0.9644
0.1152	2.0	1250	0.1097	0.8572	0.8980	0.8771	0.9761
0.1038	3.0	1875	0.0852	0.8754	0.9152	0.8948	0.9790
0.0519	4.0	2500	0.0816	0.8875	0.9202	0.9036	0.9805
0.0456	5.0	3125	0.0844	0.8861	0.9187	0.9021	0.9799
0.0393	6.0	3750	0.0813	0.9007	0.9206	0.9105	0.9818
0.0301	7.0	4375	0.0821	0.8997	0.9270	0.9131	0.9813
0.0238	8.0	5000	0.0825	0.9090	0.9266	0.9177	0.9825
0.0184	9.0	5625	0.0859	0.8995	0.9249	0.9120	0.9810
0.0213	10.0	6250	0.0863	0.9074	0.9266	0.9169	0.9821
0.0190	11.0	6875	0.0876	0.9101	0.9280	0.9189	0.9822
0.0172	12.0	7500	0.0893	0.9115	0.9261	0.9188	0.9825
0.0139	13.0	8125	0.0899	0.9064	0.9290	0.9176	0.9822
0.0113	14.0	8750	0.0906	0.9092	0.9297	0.9193	0.9825
0.0093	15.0	9375	0.0922	0.9110	0.9300	0.9204	0.9826
0.0119	16.0	10000	0.0925	0.9073	0.9295	0.9183	0.9821
0.0102	17.0	10625	0.0967	0.9093	0.9278	0.9185	0.9824
0.0093	18.0	11250	0.0959	0.9049	0.9293	0.9170	0.9822

Akzium/bge-small-en-v1.5-finetuned-ner

bge-small-en-v1.5-finetuned-ner