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: cosine
lr_scheduler_warmup_ratio: 0.01
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
0.5128	1.0	9	1.2716	0.0057	1045.6621	724.7978	365.0	570.0	0.6404	365.0	0.6404	66.0	66.0	158.0	0.4177	0.4177	90.0	90.0	152.0	0.5921	0.5921	121.0	121.0	142.0	0.8521	0.8521	88.0	88.0	118.0	0.7458	0.7458
1.0744	2.0	18	1.1638	0.0057	957.0666	663.3880	390.0	570.0	0.6842	388.0	0.6807	89.0	91.0	158.0	0.5759	0.5633	109.0	109.0	152.0	0.7171	0.7171	114.0	114.0	142.0	0.8028	0.8028	76.0	76.0	118.0	0.6441	0.6441
0.0722	3.0	27	0.9485	0.0057	779.9649	540.6305	403.0	570.0	0.7070	403.0	0.7070	112.0	112.0	158.0	0.7089	0.7089	120.0	120.0	152.0	0.7895	0.7895	103.0	103.0	142.0	0.7254	0.7254	68.0	68.0	118.0	0.5763	0.5763
0.0006	4.0	36	1.9392	0.0057	1594.6584	1105.3330	404.0	570.0	0.7088	404.0	0.7088	116.0	116.0	158.0	0.7342	0.7342	106.0	106.0	152.0	0.6974	0.6974	105.0	105.0	142.0	0.7394	0.7394	77.0	77.0	118.0	0.6525	0.6525
0.0016	5.0	45	2.1923	0.0057	1802.7670	1249.5829	404.0	570.0	0.7088	403.0	0.7070	112.0	113.0	158.0	0.7152	0.7089	102.0	102.0	152.0	0.6711	0.6711	106.0	106.0	142.0	0.7465	0.7465	83.0	83.0	118.0	0.7034	0.7034
0.0001	6.0	54	3.0132	0.0057	2477.8389	1717.5071	407.0	570.0	0.7140	407.0	0.7140	104.0	104.0	158.0	0.6582	0.6582	118.0	118.0	152.0	0.7763	0.7763	103.0	103.0	142.0	0.7254	0.7254	82.0	82.0	118.0	0.6949	0.6949
0.0	7.0	63	3.1848	0.0057	2618.9628	1815.3267	399.0	570.0	0.7	399.0	0.7	99.0	99.0	158.0	0.6266	0.6266	117.0	117.0	152.0	0.7697	0.7697	101.0	101.0	142.0	0.7113	0.7113	82.0	82.0	118.0	0.6949	0.6949
0.0	8.0	72	3.3835	0.0057	2782.3849	1928.6022	398.0	570.0	0.6982	398.0	0.6982	102.0	102.0	158.0	0.6456	0.6456	116.0	116.0	152.0	0.7632	0.7632	107.0	107.0	142.0	0.7535	0.7535	73.0	73.0	118.0	0.6186	0.6186
0.0	9.0	81	3.4467	0.0057	2834.3074	1964.5922	401.0	570.0	0.7035	400.0	0.7018	102.0	103.0	158.0	0.6519	0.6456	115.0	115.0	152.0	0.7566	0.7566	107.0	107.0	142.0	0.7535	0.7535	76.0	76.0	118.0	0.6441	0.6441
0.0	10.0	90	3.5037	0.0057	2881.2031	1997.0978	397.0	570.0	0.6965	396.0	0.6947	102.0	103.0	158.0	0.6519	0.6456	111.0	111.0	152.0	0.7303	0.7303	106.0	106.0	142.0	0.7465	0.7465	77.0	77.0	118.0	0.6525	0.6525
0.0	11.0	99	3.4913	0.0057	2871.0161	1990.0367	401.0	570.0	0.7035	400.0	0.7018	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	12.0	108	3.5206	0.0057	2895.1423	2006.7597	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	13.0	117	3.5211	0.0057	2895.5470	2007.0402	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	14.0	126	3.5373	0.0057	2908.8753	2016.2787	401.0	570.0	0.7035	400.0	0.7018	103.0	104.0	158.0	0.6582	0.6519	112.0	112.0	152.0	0.7368	0.7368	108.0	108.0	142.0	0.7606	0.7606	77.0	77.0	118.0	0.6525	0.6525
0.0	15.0	135	3.5497	0.0057	2919.0747	2023.3484	400.0	570.0	0.7018	399.0	0.7	103.0	104.0	158.0	0.6582	0.6519	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	16.0	144	3.5400	0.0057	2911.0814	2017.8079	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	17.0	153	3.5550	0.0057	2923.3854	2026.3364	398.0	570.0	0.6982	397.0	0.6965	102.0	103.0	158.0	0.6519	0.6456	111.0	111.0	152.0	0.7303	0.7303	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	18.0	162	3.5753	0.0057	2940.0777	2037.9065	398.0	570.0	0.6982	397.0	0.6965	102.0	103.0	158.0	0.6519	0.6456	111.0	111.0	152.0	0.7303	0.7303	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	19.0	171	3.5759	0.0057	2940.5951	2038.2652	400.0	570.0	0.7018	399.0	0.7	103.0	104.0	158.0	0.6582	0.6519	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	20.0	180	3.5724	0.0057	2937.7403	2036.2864	401.0	570.0	0.7035	400.0	0.7018	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	21.0	189	3.5773	0.0057	2941.7130	2039.0401	401.0	570.0	0.7035	400.0	0.7018	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	22.0	198	3.5691	0.0057	2934.9847	2034.3764	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	23.0	207	3.5653	0.0057	2931.9084	2032.2441	401.0	570.0	0.7035	400.0	0.7018	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	24.0	216	3.5999	0.0057	2960.3382	2051.9501	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	25.0	225	3.5823	0.0057	2945.8462	2041.9050	402.0	570.0	0.7053	401.0	0.7035	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	78.0	78.0	118.0	0.6610	0.6610
0.0	26.0	234	3.6104	0.0057	2968.9215	2057.8995	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	27.0	243	3.6075	0.0057	2966.5800	2056.2766	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	28.0	252	3.6379	0.0057	2991.5786	2073.6043	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	29.0	261	3.6116	0.0057	2969.9806	2058.6337	400.0	570.0	0.7018	399.0	0.7	103.0	104.0	158.0	0.6582	0.6519	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	30.0	270	3.6136	0.0057	2971.5578	2059.7269	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	31.0	279	3.6217	0.0057	2978.2495	2064.3652	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	32.0	288	3.6315	0.0057	2986.2913	2069.9394	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	33.0	297	3.6548	0.0057	3005.4758	2083.2371	399.0	570.0	0.7	398.0	0.6982	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525
0.0	34.0	306	3.6216	0.0057	2978.1381	2064.2880	402.0	570.0	0.7053	401.0	0.7035	103.0	104.0	158.0	0.6582	0.6519	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	78.0	78.0	118.0	0.6610	0.6610
0.0	35.0	315	3.6415	0.0057	2994.5376	2075.6553	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	112.0	112.0	152.0	0.7368	0.7368	107.0	107.0	142.0	0.7535	0.7535	78.0	78.0	118.0	0.6610	0.6610
0.0	36.0	324	3.6455	0.0057	2997.8203	2077.9307	400.0	570.0	0.7018	399.0	0.7	102.0	103.0	158.0	0.6519	0.6456	113.0	113.0	152.0	0.7434	0.7434	107.0	107.0	142.0	0.7535	0.7535	77.0	77.0	118.0	0.6525	0.6525

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-622krk4g

ARC-Easy_Llama-3.2-1B-622krk4g

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

donoway/
ARC-Easy_Llama-3.2-1B-622krk4g