learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 200898
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
5.8984	0.25	5	4.0714	0.7181	0.7712	0.6838	0.3667	0.6735	0.7736	0.7688
5.6719	0.5	10	6.2693	0.5621	0.4185	0.6752	0.4667	0.6463	0.4313	0.4281
5.2305	0.75	15	4.5066	0.7185	0.6169	0.7350	0.3	0.7279	0.6299	0.6119
5.1992	1.0	20	6.6786	0.6155	0.3968	0.5043	0.2333	0.5578	0.3967	0.3774
4.6914	1.25	25	4.2652	0.6791	0.6058	0.8547	0.5333	0.7755	0.6546	0.6006
5.502	1.5	30	5.2347	0.6561	0.3689	0.8803	0.6	0.7823	0.5389	0.4455
3.4502	1.75	35	3.5784	0.7469	0.8360	0.3846	0.0	0.5102	0.7762	0.6165
5.2627	2.0	40	4.2228	0.6933	0.8123	0.3419	0.0333	0.4694	0.6964	0.5135
3.1973	2.25	45	5.3446	0.6755	0.2890	0.8718	0.5333	0.7891	0.5648	0.4090
4.0469	2.5	50	4.2192	0.7407	0.7712	0.4017	0.0	0.5238	0.6747	0.4665
3.9707	2.75	55	3.8095	0.7679	0.7963	0.4615	0.0	0.5714	0.7283	0.5078
3.1924	3.0	60	3.7982	0.7736	0.7982	0.4701	0.0	0.5782	0.7291	0.5047

leobianco/npov_RM_google_S200898_LLM_false_STRUCT_true_epo3_lr2e-4_r8_2602251535

npov_RM_google_S200898_LLM_false_STRUCT_true_epo3_lr2e-4_r8_2602251535