learning_rate: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 130104
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 32
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_ratio: 0.1
num_epochs: 3.0

Training Loss	Epoch	Step	Validation Loss	Roc Auc	Best Threshold	Tpr At Best Threshold	Fpr At Best Threshold	Accuracy At Best Threshold	Avg Score True Positives	Avg Score True Negatives
No log	0	0	5.5312	0.5	inf	0.0	0.0	0.2041	0.5	0.5
5.0282	0.3571	5	4.2946	0.7469	0.9161	0.5299	0.1333	0.5986	0.9167	0.8907
4.7456	0.7143	10	3.8355	0.7289	0.8376	0.6239	0.2	0.6599	0.8404	0.7973
2.8018	1.0714	15	3.6978	0.8597	0.8754	0.9316	0.3	0.8844	0.9058	0.8285
2.687	1.4286	20	3.0175	0.8833	0.8702	0.8034	0.1667	0.8095	0.9112	0.7111
2.5198	1.7857	25	2.7490	0.8689	0.8675	0.9060	0.3333	0.8571	0.9487	0.5250
1.27	2.1429	30	2.2480	0.9305	0.8783	0.9316	0.2	0.9048	0.9484	0.4454
1.273	2.5	35	3.2225	0.9292	0.9607	0.9231	0.2	0.8980	0.9772	0.5644
1.5885	2.8571	40	2.2930	0.9265	0.9289	0.7350	0.0	0.7891	0.9020	0.3850

leobianco/npov_RM_google_S130104_LLM_false_STRUCT_false_epo3_lr1e-3_r8_2602241629

npov_RM_google_S130104_LLM_false_STRUCT_false_epo3_lr1e-3_r8_2602241629