learning_rate: 3e-05
train_batch_size: 60
eval_batch_size: 60
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 240
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
lr_scheduler_warmup_steps: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	72	0.6554	0.6588	0.6020	0.9368	0.7330
No log	2.0	144	0.4637	0.7838	0.7997	0.7573	0.7779
No log	3.0	216	0.4541	0.7931	0.7745	0.8271	0.7999
No log	4.0	288	0.4764	0.7982	0.7630	0.8652	0.8109
No log	5.0	360	0.4254	0.8129	0.8037	0.8280	0.8157
No log	6.0	432	0.4175	0.8224	0.8329	0.8066	0.8196
1.8208	7.0	504	0.4262	0.8259	0.8251	0.8271	0.8261
1.8208	8.0	576	0.4154	0.8296	0.8376	0.8178	0.8276
1.8208	9.0	648	0.4140	0.8310	0.8400	0.8178	0.8287
1.8208	10.0	720	0.4235	0.8254	0.8241	0.8275	0.8258

sms112/bact_roberta_base_essentiality_Network

bact_roberta_base_essentiality_Network