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
0.4429	1.0	36	0.6869	0.0056	564.8439	391.5200	430.0	570.0	0.7544	60.0	0.1053	0.0	130.0	158.0	0.8228	0.0	10.0	113.0	152.0	0.7434	0.0658	43.0	108.0	142.0	0.7606	0.3028	7.0	79.0	118.0	0.6695	0.0593
0.1294	2.0	72	0.6837	0.0056	562.2638	389.7316	444.0	570.0	0.7789	0.0	0.0	0.0	119.0	158.0	0.7532	0.0	0.0	126.0	152.0	0.8289	0.0	0.0	111.0	142.0	0.7817	0.0	0.0	88.0	118.0	0.7458	0.0
0.0423	3.0	108	0.9005	0.0056	740.5548	513.3135	418.0	570.0	0.7333	411.0	0.7211	110.0	116.0	158.0	0.7342	0.6962	128.0	128.0	152.0	0.8421	0.8421	102.0	103.0	142.0	0.7254	0.7183	71.0	71.0	118.0	0.6017	0.6017
0.0101	4.0	144	1.1974	0.0056	984.6596	682.5140	429.0	570.0	0.7526	111.0	0.1947	0.0	117.0	158.0	0.7405	0.0	49.0	124.0	152.0	0.8158	0.3224	59.0	109.0	142.0	0.7676	0.4155	3.0	79.0	118.0	0.6695	0.0254
0.0022	5.0	180	1.9793	0.0056	1627.6320	1128.1885	428.0	570.0	0.7509	384.0	0.6737	85.0	112.0	158.0	0.7089	0.5380	118.0	119.0	152.0	0.7829	0.7763	109.0	109.0	142.0	0.7676	0.7676	72.0	88.0	118.0	0.7458	0.6102
0.0004	6.0	216	2.1635	0.0056	1779.1008	1233.1787	440.0	570.0	0.7719	236.0	0.4140	17.0	126.0	158.0	0.7975	0.1076	79.0	118.0	152.0	0.7763	0.5197	92.0	112.0	142.0	0.7887	0.6479	48.0	84.0	118.0	0.7119	0.4068
0.0001	7.0	252	2.1693	0.0056	1783.8703	1236.4847	421.0	570.0	0.7386	266.0	0.4667	11.0	102.0	158.0	0.6456	0.0696	104.0	122.0	152.0	0.8026	0.6842	108.0	112.0	142.0	0.7887	0.7606	43.0	85.0	118.0	0.7203	0.3644
0.0001	8.0	288	2.0189	0.0056	1660.2508	1150.7982	434.0	570.0	0.7614	225.0	0.3947	2.0	119.0	158.0	0.7532	0.0127	80.0	118.0	152.0	0.7763	0.5263	106.0	114.0	142.0	0.8028	0.7465	37.0	83.0	118.0	0.7034	0.3136
0.0007	9.0	324	2.0142	0.0056	1656.3598	1148.1011	433.0	570.0	0.7596	197.0	0.3456	0.0	113.0	158.0	0.7152	0.0	66.0	123.0	152.0	0.8092	0.4342	107.0	114.0	142.0	0.8028	0.7535	24.0	83.0	118.0	0.7034	0.2034
0.0001	10.0	360	1.9393	0.0056	1594.7939	1105.4269	433.0	570.0	0.7596	169.0	0.2965	1.0	129.0	158.0	0.8165	0.0063	56.0	121.0	152.0	0.7961	0.3684	102.0	109.0	142.0	0.7676	0.7183	10.0	74.0	118.0	0.6271	0.0847
0.0	11.0	396	1.9981	0.0056	1643.0903	1138.9034	437.0	570.0	0.7667	205.0	0.3596	3.0	124.0	158.0	0.7848	0.0190	69.0	119.0	152.0	0.7829	0.4539	109.0	113.0	142.0	0.7958	0.7676	24.0	81.0	118.0	0.6864	0.2034
0.0001	12.0	432	2.0404	0.0056	1677.8660	1163.0081	439.0	570.0	0.7702	213.0	0.3737	4.0	126.0	158.0	0.7975	0.0253	72.0	119.0	152.0	0.7829	0.4737	109.0	113.0	142.0	0.7958	0.7676	28.0	81.0	118.0	0.6864	0.2373

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-nwf15c6a

ARC-Easy_Llama-3.2-1B-nwf15c6a

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-nwf15c6a