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	0.0056	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
1.194	1.0	12	0.9451	0.0056	777.1506	538.6797	377.0	570.0	0.6614	374.0	0.6561	113.0	114.0	158.0	0.7215	0.7152	84.0	84.0	152.0	0.5526	0.5526	112.0	112.0	142.0	0.7887	0.7887	65.0	67.0	118.0	0.5678	0.5508
0.2945	2.0	24	0.8341	0.0056	685.9408	475.4579	409.0	570.0	0.7175	409.0	0.7175	107.0	107.0	158.0	0.6772	0.6772	118.0	118.0	152.0	0.7763	0.7763	110.0	110.0	142.0	0.7746	0.7746	74.0	74.0	118.0	0.6271	0.6271
0.4134	3.0	36	1.5085	0.0056	1240.4630	859.8234	410.0	570.0	0.7193	410.0	0.7193	100.0	100.0	158.0	0.6329	0.6329	110.0	110.0	152.0	0.7237	0.7237	116.0	116.0	142.0	0.8169	0.8169	84.0	84.0	118.0	0.7119	0.7119
0.461	4.0	48	1.4966	0.0056	1230.7477	853.0893	399.0	570.0	0.7	398.0	0.6982	126.0	127.0	158.0	0.8038	0.7975	101.0	101.0	152.0	0.6645	0.6645	101.0	101.0	142.0	0.7113	0.7113	70.0	70.0	118.0	0.5932	0.5932
0.0011	5.0	60	2.3408	0.0056	1924.8864	1334.2296	387.0	570.0	0.6789	387.0	0.6789	87.0	87.0	158.0	0.5506	0.5506	110.0	110.0	152.0	0.7237	0.7237	108.0	108.0	142.0	0.7606	0.7606	82.0	82.0	118.0	0.6949	0.6949
0.0001	6.0	72	2.2085	0.0056	1816.1275	1258.8437	401.0	570.0	0.7035	401.0	0.7035	113.0	113.0	158.0	0.7152	0.7152	112.0	112.0	152.0	0.7368	0.7368	105.0	105.0	142.0	0.7394	0.7394	71.0	71.0	118.0	0.6017	0.6017
0.0039	7.0	84	2.5338	0.0056	2083.6571	1444.2811	408.0	570.0	0.7158	408.0	0.7158	109.0	109.0	158.0	0.6899	0.6899	117.0	117.0	152.0	0.7697	0.7697	107.0	107.0	142.0	0.7535	0.7535	75.0	75.0	118.0	0.6356	0.6356
0.0	8.0	96	3.2577	0.0056	2678.9232	1856.8880	398.0	570.0	0.6982	398.0	0.6982	105.0	105.0	158.0	0.6646	0.6646	115.0	115.0	152.0	0.7566	0.7566	105.0	105.0	142.0	0.7394	0.7394	73.0	73.0	118.0	0.6186	0.6186
0.0	9.0	108	3.4677	0.0056	2851.5869	1976.5694	398.0	570.0	0.6982	398.0	0.6982	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	10.0	120	3.4773	0.0056	2859.4752	1982.0372	399.0	570.0	0.7	399.0	0.7	112.0	112.0	158.0	0.7089	0.7089	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	11.0	132	3.4894	0.0056	2869.4529	1988.9532	398.0	570.0	0.6982	398.0	0.6982	112.0	112.0	158.0	0.7089	0.7089	114.0	114.0	152.0	0.75	0.75	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	12.0	144	3.5153	0.0056	2890.7667	2003.7268	398.0	570.0	0.6982	398.0	0.6982	112.0	112.0	158.0	0.7089	0.7089	112.0	112.0	152.0	0.7368	0.7368	103.0	103.0	142.0	0.7254	0.7254	71.0	71.0	118.0	0.6017	0.6017
0.0	13.0	156	3.5315	0.0056	2904.0647	2012.9442	396.0	570.0	0.6947	396.0	0.6947	111.0	111.0	158.0	0.7025	0.7025	112.0	112.0	152.0	0.7368	0.7368	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	14.0	168	3.5311	0.0056	2903.7751	2012.7435	399.0	570.0	0.7	399.0	0.7	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	71.0	71.0	118.0	0.6017	0.6017
0.0	15.0	180	3.5053	0.0056	2882.5005	1997.9971	398.0	570.0	0.6982	398.0	0.6982	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	102.0	102.0	142.0	0.7183	0.7183	71.0	71.0	118.0	0.6017	0.6017
0.0	16.0	192	3.5451	0.0056	2915.2903	2020.7253	396.0	570.0	0.6947	396.0	0.6947	111.0	111.0	158.0	0.7025	0.7025	112.0	112.0	152.0	0.7368	0.7368	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	17.0	204	3.5035	0.0056	2881.0363	1996.9822	398.0	570.0	0.6982	398.0	0.6982	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	18.0	216	3.5279	0.0056	2901.1133	2010.8985	397.0	570.0	0.6965	397.0	0.6965	112.0	112.0	158.0	0.7089	0.7089	113.0	113.0	152.0	0.7434	0.7434	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	19.0	228	3.5114	0.0056	2887.5511	2001.4979	398.0	570.0	0.6982	398.0	0.6982	112.0	112.0	158.0	0.7089	0.7089	113.0	113.0	152.0	0.7434	0.7434	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	20.0	240	3.5258	0.0056	2899.3659	2009.6873	398.0	570.0	0.6982	398.0	0.6982	113.0	113.0	158.0	0.7152	0.7152	113.0	113.0	152.0	0.7434	0.7434	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	21.0	252	3.5182	0.0056	2893.1824	2005.4012	398.0	570.0	0.6982	398.0	0.6982	113.0	113.0	158.0	0.7152	0.7152	113.0	113.0	152.0	0.7434	0.7434	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	22.0	264	3.5311	0.0056	2903.7556	2012.7300	399.0	570.0	0.7	399.0	0.7	112.0	112.0	158.0	0.7089	0.7089	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	23.0	276	3.5512	0.0056	2920.2721	2024.1784	397.0	570.0	0.6965	397.0	0.6965	112.0	112.0	158.0	0.7089	0.7089	113.0	113.0	152.0	0.7434	0.7434	101.0	101.0	142.0	0.7113	0.7113	71.0	71.0	118.0	0.6017	0.6017
0.0	24.0	288	3.5225	0.0056	2896.7196	2007.8530	398.0	570.0	0.6982	398.0	0.6982	112.0	112.0	158.0	0.7089	0.7089	113.0	113.0	152.0	0.7434	0.7434	102.0	102.0	142.0	0.7183	0.7183	71.0	71.0	118.0	0.6017	0.6017
0.0	25.0	300	3.5491	0.0056	2918.5535	2022.9871	398.0	570.0	0.6982	398.0	0.6982	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	26.0	312	3.5540	0.0056	2922.6214	2025.8068	397.0	570.0	0.6965	397.0	0.6965	112.0	112.0	158.0	0.7089	0.7089	113.0	113.0	152.0	0.7434	0.7434	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	27.0	324	3.5449	0.0056	2915.1207	2020.6077	397.0	570.0	0.6965	397.0	0.6965	111.0	111.0	158.0	0.7025	0.7025	113.0	113.0	152.0	0.7434	0.7434	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	28.0	336	3.5337	0.0056	2905.8888	2014.2086	400.0	570.0	0.7018	400.0	0.7018	113.0	113.0	158.0	0.7152	0.7152	113.0	113.0	152.0	0.7434	0.7434	104.0	104.0	142.0	0.7324	0.7324	70.0	70.0	118.0	0.5932	0.5932
0.0	29.0	348	3.5339	0.0056	2906.0870	2014.3460	399.0	570.0	0.7	399.0	0.7	113.0	113.0	158.0	0.7152	0.7152	113.0	113.0	152.0	0.7434	0.7434	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	30.0	360	3.5652	0.0056	2931.7771	2032.1530	399.0	570.0	0.7	399.0	0.7	113.0	113.0	158.0	0.7152	0.7152	114.0	114.0	152.0	0.75	0.75	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932
0.0	31.0	372	3.5626	0.0056	2929.6326	2030.6666	399.0	570.0	0.7	399.0	0.7	113.0	113.0	158.0	0.7152	0.7152	113.0	113.0	152.0	0.7434	0.7434	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	32.0	384	3.5552	0.0056	2923.5628	2026.4593	399.0	570.0	0.7	399.0	0.7	112.0	112.0	158.0	0.7089	0.7089	114.0	114.0	152.0	0.75	0.75	103.0	103.0	142.0	0.7254	0.7254	70.0	70.0	118.0	0.5932	0.5932
0.0	33.0	396	3.5880	0.0056	2950.5460	2045.1626	397.0	570.0	0.6965	397.0	0.6965	111.0	111.0	158.0	0.7025	0.7025	114.0	114.0	152.0	0.75	0.75	102.0	102.0	142.0	0.7183	0.7183	70.0	70.0	118.0	0.5932	0.5932

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-kiprk0jk

ARC-Easy_Llama-3.2-1B-kiprk0jk

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-kiprk0jk