learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 112
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.001
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Mdl	Accumulated Loss	Correct Preds	Total Preds	Accuracy	Correct Gen Preds	Gen Accuracy	Correct Gen Preds 32	Correct Preds 32	Total Labels 32	Accuracy 32	Gen Accuracy 32	Correct Gen Preds 33	Correct Preds 33	Total Labels 33	Accuracy 33	Gen Accuracy 33	Correct Gen Preds 34	Correct Preds 34	Total Labels 34	Accuracy 34	Gen Accuracy 34	Correct Gen Preds 35	Correct Preds 35	Total Labels 35	Accuracy 35	Gen Accuracy 35
No log	0	0	1.5354	0.0057	1262.6022	875.1692	172.0	570.0	0.3018	170.0	0.2982	154.0	154.0	158.0	0.9747	0.9747	0.0	0.0	152.0	0.0	0.0	15.0	17.0	142.0	0.1197	0.1056	1.0	1.0	118.0	0.0085	0.0085
1.0495	1.0	10	1.1252	0.0057	925.2995	641.3687	365.0	570.0	0.6404	346.0	0.6070	114.0	123.0	158.0	0.7785	0.7215	87.0	90.0	152.0	0.5921	0.5724	90.0	95.0	142.0	0.6690	0.6338	55.0	57.0	118.0	0.4831	0.4661
0.5032	2.0	20	0.9410	0.0057	773.8220	536.3725	390.0	570.0	0.6842	390.0	0.6842	109.0	109.0	158.0	0.6899	0.6899	101.0	101.0	152.0	0.6645	0.6645	108.0	108.0	142.0	0.7606	0.7606	72.0	72.0	118.0	0.6102	0.6102
0.2482	3.0	30	1.2368	0.0057	1017.0858	704.9901	403.0	570.0	0.7070	380.0	0.6667	115.0	123.0	158.0	0.7785	0.7278	101.0	104.0	152.0	0.6842	0.6645	98.0	106.0	142.0	0.7465	0.6901	66.0	70.0	118.0	0.5932	0.5593
0.0062	4.0	40	1.7542	0.0057	1442.5071	999.8697	397.0	570.0	0.6965	364.0	0.6386	102.0	115.0	158.0	0.7278	0.6456	98.0	111.0	152.0	0.7303	0.6447	94.0	101.0	142.0	0.7113	0.6620	70.0	70.0	118.0	0.5932	0.5932
0.0184	5.0	50	2.8819	0.0057	2369.9259	1642.7075	381.0	570.0	0.6684	380.0	0.6667	81.0	82.0	158.0	0.5190	0.5127	109.0	109.0	152.0	0.7171	0.7171	111.0	111.0	142.0	0.7817	0.7817	79.0	79.0	118.0	0.6695	0.6695
0.0001	6.0	60	2.7818	0.0057	2287.5613	1585.6166	395.0	570.0	0.6930	392.0	0.6877	116.0	118.0	158.0	0.7468	0.7342	107.0	108.0	152.0	0.7105	0.7039	104.0	104.0	142.0	0.7324	0.7324	65.0	65.0	118.0	0.5508	0.5508
0.0001	7.0	70	3.0788	0.0057	2531.7691	1754.8886	394.0	570.0	0.6912	371.0	0.6509	99.0	111.0	158.0	0.7025	0.6266	103.0	107.0	152.0	0.7039	0.6776	101.0	107.0	142.0	0.7535	0.7113	68.0	69.0	118.0	0.5847	0.5763
0.418	8.0	80	3.0952	0.0057	2545.3063	1764.2719	393.0	570.0	0.6895	388.0	0.6807	110.0	114.0	158.0	0.7215	0.6962	108.0	108.0	152.0	0.7105	0.7105	103.0	104.0	142.0	0.7324	0.7254	67.0	67.0	118.0	0.5678	0.5678
0.0001	9.0	90	2.8307	0.0057	2327.7607	1613.4808	393.0	570.0	0.6895	387.0	0.6789	115.0	117.0	158.0	0.7405	0.7278	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	63.0	65.0	118.0	0.5508	0.5339
0.0001	10.0	100	2.8407	0.0057	2336.0188	1619.2048	394.0	570.0	0.6912	389.0	0.6825	115.0	117.0	158.0	0.7405	0.7278	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0001	11.0	110	2.9273	0.0057	2407.1993	1668.5434	390.0	570.0	0.6842	384.0	0.6737	113.0	116.0	158.0	0.7342	0.7152	106.0	107.0	152.0	0.7039	0.6974	102.0	103.0	142.0	0.7254	0.7183	63.0	64.0	118.0	0.5424	0.5339
0.0	12.0	120	2.9689	0.0057	2441.4194	1692.2630	393.0	570.0	0.6895	387.0	0.6789	114.0	117.0	158.0	0.7405	0.7215	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	13.0	130	3.0274	0.0057	2489.5532	1725.6268	393.0	570.0	0.6895	387.0	0.6789	114.0	117.0	158.0	0.7405	0.7215	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	14.0	140	3.0474	0.0057	2505.9722	1737.0076	393.0	570.0	0.6895	387.0	0.6789	113.0	116.0	158.0	0.7342	0.7152	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	15.0	150	3.0533	0.0057	2510.8689	1740.4017	394.0	570.0	0.6912	388.0	0.6807	114.0	117.0	158.0	0.7405	0.7215	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	16.0	160	3.0858	0.0057	2537.5315	1758.8828	393.0	570.0	0.6895	388.0	0.6807	113.0	116.0	158.0	0.7342	0.7152	107.0	107.0	152.0	0.7039	0.7039	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	17.0	170	3.1061	0.0057	2554.2536	1770.4737	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	107.0	108.0	152.0	0.7105	0.7039	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	18.0	180	3.1204	0.0057	2566.0528	1778.6522	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	107.0	108.0	152.0	0.7105	0.7039	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	19.0	190	3.1196	0.0057	2565.3768	1778.1837	392.0	570.0	0.6877	386.0	0.6772	113.0	116.0	158.0	0.7342	0.7152	106.0	107.0	152.0	0.7039	0.6974	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	20.0	200	3.1321	0.0057	2575.6468	1785.3023	390.0	570.0	0.6842	384.0	0.6737	112.0	115.0	158.0	0.7278	0.7089	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	21.0	210	3.1534	0.0057	2593.1725	1797.4502	391.0	570.0	0.6860	386.0	0.6772	113.0	115.0	158.0	0.7278	0.7152	106.0	107.0	152.0	0.7039	0.6974	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	22.0	220	3.1442	0.0057	2585.5666	1792.1782	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	23.0	230	3.1591	0.0057	2597.8408	1800.6860	392.0	570.0	0.6877	386.0	0.6772	113.0	116.0	158.0	0.7342	0.7152	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	24.0	240	3.1706	0.0057	2607.2820	1807.2301	391.0	570.0	0.6860	385.0	0.6754	111.0	114.0	158.0	0.7215	0.7025	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	25.0	250	3.1782	0.0057	2613.5598	1811.5816	391.0	570.0	0.6860	385.0	0.6754	111.0	114.0	158.0	0.7215	0.7025	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	26.0	260	3.1695	0.0057	2606.4207	1806.6332	393.0	570.0	0.6895	387.0	0.6789	114.0	117.0	158.0	0.7405	0.7215	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	27.0	270	3.1835	0.0057	2617.9143	1814.5999	393.0	570.0	0.6895	388.0	0.6807	115.0	117.0	158.0	0.7405	0.7278	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	28.0	280	3.1995	0.0057	2631.0951	1823.7361	391.0	570.0	0.6860	385.0	0.6754	113.0	116.0	158.0	0.7342	0.7152	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	29.0	290	3.2063	0.0057	2636.6248	1827.5690	392.0	570.0	0.6877	386.0	0.6772	113.0	116.0	158.0	0.7342	0.7152	106.0	107.0	152.0	0.7039	0.6974	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	30.0	300	3.2030	0.0057	2633.9546	1825.7182	390.0	570.0	0.6842	384.0	0.6737	112.0	115.0	158.0	0.7278	0.7089	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	31.0	310	3.2200	0.0057	2647.9446	1835.4153	390.0	570.0	0.6842	384.0	0.6737	112.0	115.0	158.0	0.7278	0.7089	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	32.0	320	3.2230	0.0057	2650.4148	1837.1275	391.0	570.0	0.6860	385.0	0.6754	112.0	115.0	158.0	0.7278	0.7089	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	66.0	67.0	118.0	0.5678	0.5593
0.0	33.0	330	3.2226	0.0057	2650.0326	1836.8627	392.0	570.0	0.6877	387.0	0.6789	111.0	114.0	158.0	0.7215	0.7025	108.0	108.0	152.0	0.7105	0.7105	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	34.0	340	3.2358	0.0057	2660.8781	1844.3802	391.0	570.0	0.6860	385.0	0.6754	113.0	116.0	158.0	0.7342	0.7152	105.0	106.0	152.0	0.6974	0.6908	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	35.0	350	3.2371	0.0057	2661.9610	1845.1308	392.0	570.0	0.6877	387.0	0.6789	112.0	115.0	158.0	0.7278	0.7089	107.0	107.0	152.0	0.7039	0.7039	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	36.0	360	3.2345	0.0057	2659.8829	1843.6904	392.0	570.0	0.6877	386.0	0.6772	113.0	116.0	158.0	0.7342	0.7152	106.0	107.0	152.0	0.7039	0.6974	102.0	103.0	142.0	0.7254	0.7183	65.0	66.0	118.0	0.5593	0.5508
0.0	37.0	370	3.2478	0.0057	2670.7641	1851.2326	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	105.0	106.0	152.0	0.6974	0.6908	103.0	104.0	142.0	0.7324	0.7254	66.0	67.0	118.0	0.5678	0.5593
0.0	38.0	380	3.2443	0.0057	2667.8917	1849.2416	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508
0.0	39.0	390	3.2590	0.0057	2680.0247	1857.6515	392.0	570.0	0.6877	386.0	0.6772	112.0	115.0	158.0	0.7278	0.7089	106.0	107.0	152.0	0.7039	0.6974	103.0	104.0	142.0	0.7324	0.7254	65.0	66.0	118.0	0.5593	0.5508

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

donoway/ARC-Easy_Llama-3.2-1B-nuliteno

ARC-Easy_Llama-3.2-1B-nuliteno

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-nuliteno