learning_rate: 0.0006174293063066378
train_batch_size: 16
eval_batch_size: 32
seed: 130104
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 32
total_eval_batch_size: 64
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: 15.0

Training results

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	1.2592	0.4586	0.5026	0.9296	0.8409	0.7473	0.5864	0.5913
0.4487	0.5882	20	0.9393	0.7517	0.6516	0.9789	0.5455	0.8548	0.8450	0.7068
0.6523	1.1765	40	0.8086	0.8510	0.7592	0.8451	0.2273	0.8280	0.8708	0.4310
1.8125	1.7647	60	1.2938	0.8765	0.9923	0.7535	0.1136	0.7849	0.9834	0.7823
0.1971	2.3529	80	1.1667	0.8339	0.5687	0.8169	0.25	0.8011	0.7598	0.3157
1.0371	2.9412	100	0.9195	0.8094	0.7896	0.8099	0.2727	0.7903	0.8775	0.5184
0.6328	3.5294	120	0.9378	0.8971	0.9775	0.8310	0.1364	0.8387	0.9533	0.5406
0.1332	4.1176	140	0.9581	0.8857	0.7680	0.8310	0.2045	0.8226	0.8508	0.2809
0.0580	4.7059	160	1.3505	0.8752	0.3698	0.8310	0.1818	0.8280	0.7819	0.2023
0.0025	5.2941	180	2.1579	0.8796	0.9866	0.9648	0.3409	0.8925	0.9941	0.7516
0.2951	5.8824	200	0.9745	0.8783	0.9627	0.7535	0.1364	0.7796	0.8705	0.3184
0.2604	6.4706	220	1.6551	0.8939	0.8193	0.8028	0.1364	0.8172	0.8181	0.1970
0.0080	7.0588	240	1.8263	0.8525	0.9585	0.7606	0.1818	0.7742	0.8370	0.2950
0.0196	7.6471	260	1.8269	0.8600	0.9979	0.7887	0.2045	0.7903	0.9214	0.4739
0.0439	8.2353	280	2.1334	0.8856	0.9970	0.9014	0.2045	0.8763	0.9296	0.3125
1.0725	8.8235	300	1.8254	0.8812	0.9934	0.8169	0.1818	0.8172	0.8934	0.3415
0.0004	9.4118	320	1.7214	0.8600	0.9944	0.8169	0.2273	0.8065	0.9004	0.4122
0.0000	10.0	340	1.9074	0.8671	0.9954	0.8592	0.2273	0.8387	0.9302	0.4206
0.0000	10.5882	360	1.9057	0.8768	0.9696	0.8521	0.2273	0.8333	0.8926	0.3417
0.0000	11.1765	380	1.9765	0.8827	0.9953	0.8028	0.1818	0.8065	0.8625	0.2983
0.0001	11.7647	400	1.9267	0.8837	0.9989	0.8028	0.1818	0.8065	0.8820	0.3254
0.0000	12.3529	420	1.9024	0.8834	0.9995	0.8028	0.1818	0.8065	0.8923	0.3368
0.0092	12.9412	440	1.9313	0.8800	0.9995	0.8028	0.1818	0.8065	0.8915	0.3337
0.0013	13.5294	460	1.9567	0.8786	0.9997	0.8028	0.1818	0.8065	0.8991	0.3441
0.0000	14.1176	480	1.9513	0.8800	0.9995	0.8028	0.1818	0.8065	0.8981	0.3403
0.0001	14.7059	500	1.9504	0.8795	0.9997	0.8028	0.1818	0.8065	0.8981	0.3409
0.0000	15.0	510	1.9397	0.8799	0.9997	0.8028	0.1818	0.8065	0.8987	0.3415

Framework versions

PEFT 0.20.0
Transformers 5.14.1
Pytorch 2.11.0+cu130
Datasets 5.0.1
Tokenizers 0.22.2

leobianco/bosch_RM_google_S130104_LLM_false_STRUCT_false_epo15_lr6.2e-04_r8_2608191212

bosch_RM_google_S130104_LLM_false_STRUCT_false_epo15_lr6.2e-04_r8_2608191212

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

leobianco/
bosch_RM_google_S130104_LLM_false_STRUCT_false_epo15_lr6.2e-04_r8_2608191212