learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use 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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
0.7005	1.0	173	0.6933	0.2773	0.1919	0.5
0.6977	2.0	346	0.6933	0.3813	0.3081	0.5
0.7042	3.0	519	0.6871	0.5362	0.5533	0.5554
0.6959	4.0	692	0.6933	0.4990	0.5355	0.5345
0.6861	5.0	865	0.6828	0.4914	0.5789	0.5624
0.6868	6.0	1038	0.6820	0.4907	0.5816	0.5636
0.7039	7.0	1211	0.6863	0.4931	0.5725	0.5592
0.6772	8.0	1384	0.6879	0.4882	0.5519	0.5449
0.6854	9.0	1557	0.6891	0.4962	0.5450	0.5416
0.6804	10.0	1730	0.6900	0.4938	0.5412	0.5382

usyk/roberta_sharetask-finetuned_on_codemixed

roberta_sharetask-finetuned_on_codemixed