resnet-50

This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:

Loss: 0.1129
Accuracy: 0.9672

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 128
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 300

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	333	2.2281	0.3698
2.254	2.0	666	2.0398	0.485
2.254	3.0	999	1.7629	0.5999
2.0306	4.0	1332	1.4352	0.6541
1.707	5.0	1665	1.1485	0.7283
1.707	6.0	1998	0.8991	0.7757
1.3808	7.0	2331	0.7259	0.8118
1.1274	8.0	2664	0.5785	0.8434
1.1274	9.0	2997	0.4903	0.8629
0.9636	10.0	3330	0.4194	0.8832
0.8581	11.0	3663	0.3754	0.891
0.8581	12.0	3996	0.3398	0.8971
0.7848	13.0	4329	0.3043	0.907
0.7276	14.0	4662	0.2837	0.9133
0.7276	15.0	4995	0.2741	0.9127
0.7025	16.0	5328	0.2618	0.9169
0.6684	17.0	5661	0.2495	0.9186
0.6684	18.0	5994	0.2378	0.9251
0.6354	19.0	6327	0.2301	0.9264
0.6175	20.0	6660	0.2237	0.9293
0.6175	21.0	6993	0.2131	0.9321
0.6074	22.0	7326	0.2117	0.9307
0.5897	23.0	7659	0.2101	0.9316
0.5897	24.0	7992	0.1986	0.9357
0.5808	25.0	8325	0.2032	0.9335
0.5654	26.0	8658	0.1944	0.9365
0.5654	27.0	8991	0.1939	0.939
0.5577	28.0	9324	0.1861	0.9393
0.5415	29.0	9657	0.1798	0.9404
0.5415	30.0	9990	0.1782	0.9431
0.5438	31.0	10323	0.1754	0.9424
0.5277	32.0	10656	0.1754	0.9427
0.5277	33.0	10989	0.1739	0.9421
0.5162	34.0	11322	0.1718	0.9439
0.5098	35.0	11655	0.1665	0.945
0.5098	36.0	11988	0.1647	0.9459
0.5087	37.0	12321	0.1621	0.9468
0.4935	38.0	12654	0.1619	0.9458
0.4935	39.0	12987	0.1635	0.9465
0.4941	40.0	13320	0.1597	0.9485
0.49	41.0	13653	0.1566	0.9513
0.49	42.0	13986	0.1575	0.9491
0.4764	43.0	14319	0.1580	0.9482
0.4764	44.0	14652	0.1529	0.9499
0.4764	45.0	14985	0.1551	0.9508
0.4709	46.0	15318	0.1502	0.9514
0.467	47.0	15651	0.1525	0.9499
0.467	48.0	15984	0.1522	0.9504
0.4596	49.0	16317	0.1489	0.9526
0.4523	50.0	16650	0.1478	0.9523
0.4523	51.0	16983	0.1452	0.9546
0.4554	52.0	17316	0.1451	0.9519
0.447	53.0	17649	0.1469	0.9525
0.447	54.0	17982	0.1432	0.9537
0.4395	55.0	18315	0.1437	0.9535
0.4413	56.0	18648	0.1444	0.9532
0.4413	57.0	18981	0.1417	0.9534
0.4433	58.0	19314	0.1385	0.9543
0.433	59.0	19647	0.1427	0.9529
0.433	60.0	19980	0.1398	0.9533
0.4292	61.0	20313	0.1439	0.9539
0.4266	62.0	20646	0.1361	0.956
0.4266	63.0	20979	0.1381	0.9549
0.4243	64.0	21312	0.1361	0.9559
0.4197	65.0	21645	0.1357	0.9546
0.4197	66.0	21978	0.1350	0.9554
0.4218	67.0	22311	0.1334	0.9571
0.4174	68.0	22644	0.1317	0.9583
0.4174	69.0	22977	0.1359	0.9544
0.4156	70.0	23310	0.1350	0.956
0.4152	71.0	23643	0.1328	0.957
0.4152	72.0	23976	0.1314	0.9571
0.4066	73.0	24309	0.1310	0.9556
0.4067	74.0	24642	0.1348	0.9565
0.4067	75.0	24975	0.1288	0.959
0.4104	76.0	25308	0.1303	0.9575
0.4008	77.0	25641	0.1303	0.9577
0.4008	78.0	25974	0.1312	0.9578
0.4009	79.0	26307	0.1291	0.959
0.399	80.0	26640	0.1267	0.9589
0.399	81.0	26973	0.1298	0.9589
0.3897	82.0	27306	0.1302	0.9585
0.4002	83.0	27639	0.1286	0.9578
0.4002	84.0	27972	0.1281	0.9584
0.3942	85.0	28305	0.1282	0.9583
0.3944	86.0	28638	0.1242	0.9596
0.3944	87.0	28971	0.1232	0.9609
0.3872	88.0	29304	0.1283	0.9593
0.3817	89.0	29637	0.1229	0.9602
0.3817	90.0	29970	0.1245	0.9612
0.3838	91.0	30303	0.1213	0.9607
0.3849	92.0	30636	0.1246	0.9586
0.3849	93.0	30969	0.1244	0.9609
0.382	94.0	31302	0.1245	0.9597
0.3807	95.0	31635	0.1220	0.96
0.3807	96.0	31968	0.1241	0.96
0.3773	97.0	32301	0.1244	0.9595
0.3709	98.0	32634	0.1230	0.9599
0.3709	99.0	32967	0.1235	0.9605
0.3768	100.0	33300	0.1245	0.9603
0.3712	101.0	33633	0.1201	0.9622
0.3712	102.0	33966	0.1221	0.9611
0.372	103.0	34299	0.1199	0.9625
0.3692	104.0	34632	0.1231	0.9605
0.3692	105.0	34965	0.1221	0.9604
0.3698	106.0	35298	0.1201	0.9619
0.3631	107.0	35631	0.1208	0.9625
0.3631	108.0	35964	0.1209	0.9611
0.3667	109.0	36297	0.1195	0.9615
0.3646	110.0	36630	0.1205	0.9621
0.3646	111.0	36963	0.1240	0.9601
0.3628	112.0	37296	0.1179	0.9633
0.3566	113.0	37629	0.1191	0.9617
0.3566	114.0	37962	0.1140	0.964
0.3562	115.0	38295	0.1202	0.9619
0.359	116.0	38628	0.1215	0.9605
0.359	117.0	38961	0.1179	0.9632
0.3583	118.0	39294	0.1206	0.9621
0.36	119.0	39627	0.1212	0.961
0.36	120.0	39960	0.1221	0.9592
0.3528	121.0	40293	0.1169	0.9626
0.349	122.0	40626	0.1152	0.9621
0.349	123.0	40959	0.1160	0.9644
0.3524	124.0	41292	0.1173	0.9619
0.3503	125.0	41625	0.1148	0.963
0.3503	126.0	41958	0.1184	0.9629
0.3491	127.0	42291	0.1200	0.9632
0.35	128.0	42624	0.1164	0.963
0.35	129.0	42957	0.1161	0.9629
0.3464	130.0	43290	0.1146	0.9638
0.3426	131.0	43623	0.1161	0.9627
0.3426	132.0	43956	0.1146	0.9634
0.3459	133.0	44289	0.1148	0.9629
0.342	134.0	44622	0.1202	0.9621
0.342	135.0	44955	0.1200	0.9625
0.3424	136.0	45288	0.1160	0.9626
0.3402	137.0	45621	0.1183	0.9618
0.3402	138.0	45954	0.1163	0.963
0.3422	139.0	46287	0.1148	0.9633
0.3411	140.0	46620	0.1194	0.9626
0.3411	141.0	46953	0.1200	0.9621
0.3416	142.0	47286	0.1170	0.962
0.3321	143.0	47619	0.1175	0.963
0.3321	144.0	47952	0.1134	0.9632
0.3357	145.0	48285	0.1149	0.9631
0.3337	146.0	48618	0.1152	0.964
0.3337	147.0	48951	0.1173	0.9635
0.3321	148.0	49284	0.1153	0.9637
0.336	149.0	49617	0.1164	0.9628
0.336	150.0	49950	0.1143	0.9639
0.3384	151.0	50283	0.1130	0.9619
0.3345	152.0	50616	0.1147	0.964
0.3345	153.0	50949	0.1148	0.9634
0.334	154.0	51282	0.1159	0.9617
0.3337	155.0	51615	0.1180	0.9633
0.3337	156.0	51948	0.1124	0.9635
0.3323	157.0	52281	0.1173	0.9624
0.3249	158.0	52614	0.1163	0.9615
0.3249	159.0	52947	0.1143	0.9632
0.3306	160.0	53280	0.1117	0.9645
0.3307	161.0	53613	0.1165	0.9637
0.3307	162.0	53946	0.1135	0.9639
0.33	163.0	54279	0.1123	0.9649
0.3254	164.0	54612	0.1152	0.963
0.3254	165.0	54945	0.1120	0.9638
0.3256	166.0	55278	0.1128	0.9641
0.3236	167.0	55611	0.1121	0.9631
0.3236	168.0	55944	0.1136	0.9637
0.3224	169.0	56277	0.1147	0.963
0.325	170.0	56610	0.1130	0.9633
0.325	171.0	56943	0.1124	0.9638
0.3223	172.0	57276	0.1175	0.963
0.3196	173.0	57609	0.1148	0.9629
0.3196	174.0	57942	0.1133	0.9656
0.3168	175.0	58275	0.1136	0.9638
0.3255	176.0	58608	0.1150	0.964
0.3255	177.0	58941	0.1146	0.9637
0.3137	178.0	59274	0.1143	0.9648
0.3133	179.0	59607	0.1141	0.9647
0.3133	180.0	59940	0.1106	0.9644
0.3258	181.0	60273	0.1125	0.9639
0.3233	182.0	60606	0.1128	0.9649
0.3233	183.0	60939	0.1110	0.9642
0.3194	184.0	61272	0.1156	0.9628
0.3178	185.0	61605	0.1109	0.9647
0.3178	186.0	61938	0.1125	0.964
0.3153	187.0	62271	0.1098	0.9661
0.3115	188.0	62604	0.1115	0.9649
0.3115	189.0	62937	0.1146	0.9626
0.3179	190.0	63270	0.1127	0.9644
0.3145	191.0	63603	0.1143	0.9639
0.3145	192.0	63936	0.1128	0.9641
0.3178	193.0	64269	0.1115	0.965
0.3133	194.0	64602	0.1121	0.9652
0.3133	195.0	64935	0.1135	0.9651
0.3107	196.0	65268	0.1134	0.965
0.3098	197.0	65601	0.1138	0.9641
0.3098	198.0	65934	0.1122	0.9644
0.3103	199.0	66267	0.1099	0.9654
0.315	200.0	66600	0.1140	0.965
0.315	201.0	66933	0.1133	0.9661
0.3136	202.0	67266	0.1150	0.9637
0.3117	203.0	67599	0.1153	0.9649
0.3117	204.0	67932	0.1143	0.9652
0.315	205.0	68265	0.1155	0.9632
0.307	206.0	68598	0.1115	0.9636
0.307	207.0	68931	0.1089	0.9655
0.3177	208.0	69264	0.1122	0.9663
0.3082	209.0	69597	0.1097	0.9644
0.3082	210.0	69930	0.1130	0.9647
0.3165	211.0	70263	0.1106	0.9648
0.3107	212.0	70596	0.1118	0.9652
0.3107	213.0	70929	0.1103	0.966
0.3134	214.0	71262	0.1105	0.9656
0.3132	215.0	71595	0.1122	0.9643
0.3132	216.0	71928	0.1150	0.964
0.3076	217.0	72261	0.1121	0.9636
0.3065	218.0	72594	0.1140	0.9644
0.3065	219.0	72927	0.1094	0.9661
0.3126	220.0	73260	0.1114	0.9645
0.3043	221.0	73593	0.1116	0.9649
0.3043	222.0	73926	0.1104	0.9645
0.3072	223.0	74259	0.1107	0.9638
0.3097	224.0	74592	0.1129	0.9642
0.3097	225.0	74925	0.1103	0.9646
0.2967	226.0	75258	0.1128	0.9648
0.3032	227.0	75591	0.1124	0.9643
0.3032	228.0	75924	0.1164	0.9625
0.3063	229.0	76257	0.1131	0.9635
0.2994	230.0	76590	0.1077	0.9668
0.2994	231.0	76923	0.1114	0.9663
0.2996	232.0	77256	0.1107	0.9664
0.3044	233.0	77589	0.1125	0.9652
0.3044	234.0	77922	0.1130	0.9656
0.3051	235.0	78255	0.1147	0.9644
0.298	236.0	78588	0.1123	0.9655
0.298	237.0	78921	0.1108	0.966
0.3113	238.0	79254	0.1110	0.9649
0.3078	239.0	79587	0.1122	0.9658
0.3078	240.0	79920	0.1108	0.9653
0.3073	241.0	80253	0.1134	0.9662
0.3031	242.0	80586	0.1118	0.9655
0.3031	243.0	80919	0.1105	0.9657
0.3039	244.0	81252	0.1144	0.9643
0.2995	245.0	81585	0.1144	0.9639
0.2995	246.0	81918	0.1147	0.9644
0.3066	247.0	82251	0.1127	0.9651
0.2997	248.0	82584	0.1111	0.964
0.2997	249.0	82917	0.1102	0.9664
0.3004	250.0	83250	0.1132	0.9649
0.3051	251.0	83583	0.1123	0.9655
0.3051	252.0	83916	0.1128	0.9643
0.3022	253.0	84249	0.1117	0.9653
0.2976	254.0	84582	0.1135	0.9644
0.2976	255.0	84915	0.1100	0.9673
0.3	256.0	85248	0.1124	0.9657
0.3038	257.0	85581	0.1096	0.9659
0.3038	258.0	85914	0.1114	0.9649
0.3008	259.0	86247	0.1105	0.9662
0.3019	260.0	86580	0.1095	0.9652
0.3019	261.0	86913	0.1107	0.9657
0.3023	262.0	87246	0.1108	0.9659
0.3004	263.0	87579	0.1114	0.9662
0.3004	264.0	87912	0.1098	0.9654
0.2977	265.0	88245	0.1138	0.9667
0.3009	266.0	88578	0.1112	0.9654
0.3009	267.0	88911	0.1095	0.9656
0.3017	268.0	89244	0.1144	0.9643
0.3037	269.0	89577	0.1112	0.9666
0.3037	270.0	89910	0.1106	0.9653
0.3021	271.0	90243	0.1130	0.9648
0.3007	272.0	90576	0.1104	0.9674
0.3007	273.0	90909	0.1129	0.9636
0.3052	274.0	91242	0.1125	0.9652
0.3024	275.0	91575	0.1109	0.9657
0.3024	276.0	91908	0.1136	0.9653
0.2973	277.0	92241	0.1096	0.9661
0.3014	278.0	92574	0.1122	0.9657
0.3014	279.0	92907	0.1114	0.9667
0.2992	280.0	93240	0.1151	0.9652
0.297	281.0	93573	0.1087	0.9663
0.297	282.0	93906	0.1138	0.9641
0.2977	283.0	94239	0.1125	0.9659
0.2962	284.0	94572	0.1115	0.9659
0.2962	285.0	94905	0.1144	0.9629
0.2958	286.0	95238	0.1110	0.9658
0.2934	287.0	95571	0.1112	0.9667
0.2934	288.0	95904	0.1145	0.9641
0.2984	289.0	96237	0.1141	0.9654
0.2968	290.0	96570	0.1134	0.9653
0.2968	291.0	96903	0.1098	0.9661
0.2995	292.0	97236	0.1148	0.9646
0.3	293.0	97569	0.1117	0.9656
0.3	294.0	97902	0.1137	0.9652
0.2946	295.0	98235	0.1111	0.9658
0.2962	296.0	98568	0.1112	0.9654
0.2962	297.0	98901	0.1134	0.9664
0.3025	298.0	99234	0.1143	0.9638
0.3002	299.0	99567	0.1133	0.9648
0.3002	300.0	99900	0.1129	0.9672

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

jialicheng/cifar10_resnet-50

resnet-50

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions