learning_rate: 1.104443959321486e-05
train_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.028463177944518272
num_epochs: 10/20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Micro	F1 Macro	Precision Micro	Precision Macro	Recall Micro	Recall Macro	Roc Auc	Hamming Loss
0.3554	1.0	715	0.1938	0.3307	0.7853	0.7036	0.8032	0.7617	0.7682	0.6709	0.8645	0.0724
0.189	2.0	1430	0.1506	0.4245	0.8249	0.7751	0.8478	0.8394	0.8032	0.7304	0.8866	0.0587
0.127	3.0	2145	0.1407	0.4448	0.8349	0.8068	0.8443	0.8265	0.8257	0.7920	0.8970	0.0563
0.1068	4.0	2860	0.1358	0.472	0.8468	0.8191	0.8564	0.8590	0.8375	0.7925	0.9041	0.0522
0.0825	5.0	3575	0.1359	0.4752	0.8457	0.8233	0.8675	0.8485	0.8249	0.8019	0.8993	0.0519
0.0688	6.0	4290	0.1332	0.4763	0.8517	0.8326	0.8613	0.8541	0.8423	0.8144	0.9070	0.0505
0.0543	7.0	5005	0.1369	0.4869	0.8503	0.8194	0.8775	0.8640	0.8247	0.7832	0.9004	0.0500
0.0435	8.0	5720	0.1395	0.4891	0.8555	0.8342	0.8680	0.8640	0.8435	0.8088	0.9084	0.0491
0.0381	9.0	6435	0.1441	0.4795	0.8524	0.8334	0.8686	0.8546	0.8367	0.8142	0.9052	0.0499
0.0289	10.0	7150	0.1531	0.4645	0.8527	0.8318	0.8432	0.8427	0.8624	0.8255	0.9145	0.0513

elfsmo/XLM-Roberta-large-SDGs-Oplib-Elsevier-Pruned

XLM-Roberta-large-SDGs-Oplib-Elsevier-Pruned