learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Micro F1	Macro F1	Weighted F1	Precision	Recall	Hamming Loss	Jaccard
0.1817	1.0	7266	0.1734	0.7425	0.8805	0.7538	0.8778	0.8979	0.8639	0.0289	0.8571
0.1601	2.0	14532	0.1606	0.7639	0.8918	0.7849	0.8904	0.8959	0.8878	0.0266	0.8698
0.1354	3.0	21798	0.1527	0.7753	0.8965	0.8083	0.8956	0.8997	0.8933	0.0254	0.8773
0.1238	4.0	29064	0.1517	0.7772	0.8978	0.8205	0.8968	0.8953	0.9003	0.0253	0.8796
0.1163	5.0	36330	0.1517	0.7809	0.8989	0.8329	0.8981	0.9014	0.8965	0.0249	0.8818

arfabae/xlm_roberta_allergy

xlm_roberta_allergy