learning_rate: 2e-05
train_batch_size: 32
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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.4689	1.0	822	1.9415	0.6058	0.6051
1.1999	2.0	1644	1.7062	0.6584	0.6575
0.9192	3.0	2466	1.7341	0.6725	0.6724
0.7188	4.0	3288	2.0076	0.6793	0.6793
0.4309	5.0	4110	2.5662	0.6805	0.6805
0.2596	6.0	4932	3.2284	0.6826	0.6827
0.1609	7.0	5754	4.2233	0.6882	0.6883
0.1436	8.0	6576	4.9898	0.6891	0.6892
0.0947	9.0	7398	5.1743	0.6980	0.6982
0.0757	10.0	8220	5.2247	0.6977	0.6979

Inori612/Sleep_NEW_xlm-roberta-large

Sleep_NEW_xlm-roberta-large