learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
num_epochs: 6.0

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Soft Mae	Soft Brier	Student Prelevantmean	Teacher Prelevantmean	Bin F1	Cal Ece	Cal Brier	Cal Auroc	Info Ndcg@p8	Info Pairwiseacc	Num Questions	Num Pairs
1.4630	0.2562	38	1.6236	0.0118	0.2745	0.1130	0.2112	0.3219	0.0	0.1880	0.2632	0.6501	0.7231	0.5022	20	253
1.4647	0.5124	76	1.4833	0.0118	0.2780	0.0988	0.2630	0.3219	0.0196	0.1561	0.2406	0.7067	0.7529	0.5412	20	253
1.3540	0.7686	114	1.3927	0.0118	0.2538	0.0911	0.2544	0.3219	0.0388	0.1448	0.2283	0.7269	0.7593	0.5666	20	253
1.2624	1.0202	152	1.3260	0.0118	0.2510	0.0822	0.3418	0.3219	0.3636	0.0840	0.2040	0.7505	0.8272	0.5878	20	253
1.0723	1.2764	190	1.2256	0.0118	0.2164	0.0723	0.2967	0.3219	0.4173	0.1377	0.1898	0.8163	0.9125	0.6550	20	253
1.0972	1.5327	228	1.1845	0.0118	0.1917	0.0601	0.2804	0.3219	0.4179	0.1355	0.1686	0.8797	0.9242	0.6985	20	253
0.9822	1.7889	266	1.0331	0.0118	0.1486	0.0422	0.2912	0.3219	0.7101	0.1324	0.1347	0.9256	0.9410	0.7235	20	253
0.8903	2.0405	304	1.1172	0.0118	0.1448	0.0459	0.2408	0.3219	0.6538	0.1617	0.1415	0.9456	0.9402	0.7424	20	253
0.7215	2.2967	342	1.0172	0.0118	0.1394	0.0418	0.2594	0.3219	0.6667	0.1463	0.1355	0.9423	0.9605	0.7357	20	253
0.8471	2.5529	380	1.0209	0.0118	0.1308	0.0369	0.3213	0.3219	0.7692	0.1106	0.1168	0.9377	0.9707	0.7518	20	253
0.6506	2.8091	418	1.0449	0.0118	0.1329	0.0376	0.3641	0.3219	0.8367	0.1072	0.1015	0.9474	0.9704	0.7633	20	253
0.5661	3.0607	456	1.1329	0.0118	0.1380	0.0453	0.2453	0.3219	0.6835	0.1539	0.1378	0.9428	0.9620	0.7409	20	253
0.5664	3.3169	494	1.2448	0.0118	0.1287	0.0446	0.2434	0.3219	0.7284	0.1559	0.1307	0.9502	0.9719	0.7567	20	253
0.5569	3.5731	532	1.1311	0.0118	0.1285	0.0447	0.2843	0.3219	0.7543	0.1149	0.1194	0.9404	0.9747	0.7591	20	253
0.6041	3.8293	570	1.1799	0.0118	0.1269	0.0427	0.2981	0.3219	0.7892	0.1011	0.1147	0.9416	0.9740	0.7701	20	253
0.4112	4.0809	608	1.0701	0.0118	0.1191	0.0356	0.2695	0.3219	0.7195	0.1324	0.1192	0.9550	0.9780	0.7744	20	253
0.3449	4.3371	646	1.2107	0.0118	0.1223	0.0354	0.2754	0.3219	0.7368	0.1238	0.1199	0.9520	0.9756	0.7677	20	253
0.3662	4.5933	684	1.1941	0.0118	0.1226	0.0379	0.2682	0.3219	0.7239	0.1396	0.1239	0.9520	0.9756	0.7725	20	253
0.2984	4.8496	722	1.1552	0.0118	0.1202	0.0409	0.2730	0.3219	0.8045	0.1262	0.1196	0.9470	0.9697	0.7642	20	253
0.2803	5.1011	760	1.2322	0.0118	0.1206	0.0357	0.3037	0.3219	0.8132	0.1204	0.1146	0.9470	0.9691	0.7575	20	253
0.3223	5.3574	798	1.0983	0.0118	0.1123	0.0337	0.2953	0.3219	0.8111	0.1083	0.1098	0.9487	0.9692	0.7639	20	253
0.3059	5.6136	836	1.3210	0.0118	0.1299	0.0456	0.2442	0.3219	0.7081	0.1550	0.1330	0.9460	0.9691	0.7524	20	253
0.3294	5.8698	874	1.2119	0.0118	0.1231	0.0404	0.2752	0.3219	0.7931	0.1299	0.1204	0.9472	0.9721	0.7777	20	253
0.2226	6.0	894	1.3327	0.0118	0.1216	0.0397	0.2704	0.3219	0.7910	0.1288	0.1181	0.9502	0.9732	0.7755	20	253

Framework versions

PEFT 0.19.1
Transformers 5.14.1
Pytorch 2.5.1+cu124
Datasets 5.0.0
Tokenizers 0.22.2

daryaZare/iris-olmo-2-1b-multihop-only-k10

iris-olmo-2-1b-multihop-only-k10

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

daryaZare/
iris-olmo-2-1b-multihop-only-k10