GSM8K-Binary_Llama-3.2-1B-3bfons7b

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9066
• Model Preparation Time: 0.0057
• Mdl: 3237.1033
• Accumulated Loss: 2243.7890
• Correct Preds: 1438.0
• Total Preds: 2475.0
• Accuracy: 0.5810
• Correct Gen Preds: 35.0
• Gen Accuracy: 0.0141
• Correct Gen Preds 34192: 0.0
• Correct Preds 34192: 831.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.6948
• Gen Accuracy 34192: 0.0
• Correct Gen Preds 41568: 28.0
• Correct Preds 41568: 607.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.4791
• Gen Accuracy 41568: 0.0221

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 64
• 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 34192	Correct Preds 34192	Total Labels 34192	Accuracy 34192	Gen Accuracy 34192	Correct Gen Preds 41568	Correct Preds 41568	Total Labels 41568	Accuracy 41568	Gen Accuracy 41568
No log	0	0	1.4656	0.0057	5233.1723	3627.3586	1196.0	2475.0	0.4832	1204.0	0.4865	1196.0	1196.0	1196.0	1.0	1.0	0.0	0.0	1267.0	0.0	0.0
1.2184	1.0	1	1.4656	0.0057	5233.1723	3627.3586	1196.0	2475.0	0.4832	1204.0	0.4865	1196.0	1196.0	1196.0	1.0	1.0	0.0	0.0	1267.0	0.0	0.0
1.2181	2.0	2	4.9971	0.0057	17843.0063	12367.8295	1267.0	2475.0	0.5119	1274.0	0.5147	0.0	0.0	1196.0	0.0	0.0	1266.0	1267.0	1267.0	1.0	0.9992
5.5269	3.0	3	1.0091	0.0057	3603.0026	2497.4111	1267.0	2475.0	0.5119	7.0	0.0028	0.0	0.0	1196.0	0.0	0.0	0.0	1267.0	1267.0	1.0	0.0
1.0263	4.0	4	1.9729	0.0057	7044.4372	4882.8318	1196.0	2475.0	0.4832	8.0	0.0032	0.0	1196.0	1196.0	1.0	0.0	0.0	0.0	1267.0	0.0	0.0
1.6974	5.0	5	1.0763	0.0057	3843.2050	2663.9067	1195.0	2475.0	0.4828	7.0	0.0028	0.0	1195.0	1196.0	0.9992	0.0	0.0	0.0	1267.0	0.0	0.0
0.8356	6.0	6	0.8186	0.0057	2922.9166	2026.0114	1265.0	2475.0	0.5111	7.0	0.0028	0.0	60.0	1196.0	0.0502	0.0	0.0	1205.0	1267.0	0.9511	0.0
0.7306	7.0	7	0.7934	0.0057	2833.1042	1963.7582	1334.0	2475.0	0.5390	7.0	0.0028	0.0	949.0	1196.0	0.7935	0.0	0.0	385.0	1267.0	0.3039	0.0
0.5692	8.0	8	0.7837	0.0057	2798.4240	1939.7197	1320.0	2475.0	0.5333	7.0	0.0028	0.0	1114.0	1196.0	0.9314	0.0	0.0	206.0	1267.0	0.1626	0.0
0.3958	9.0	9	0.7704	0.0057	2750.8055	1906.7131	1410.0	2475.0	0.5697	7.0	0.0028	0.0	1008.0	1196.0	0.8428	0.0	0.0	402.0	1267.0	0.3173	0.0
0.1932	10.0	10	1.0048	0.0057	3587.9800	2486.9982	1330.0	2475.0	0.5374	7.0	0.0028	0.0	1142.0	1196.0	0.9548	0.0	0.0	188.0	1267.0	0.1484	0.0
0.0723	11.0	11	0.9755	0.0057	3483.1862	2414.3607	1351.0	2475.0	0.5459	8.0	0.0032	0.0	1075.0	1196.0	0.8988	0.0	1.0	276.0	1267.0	0.2178	0.0008
0.0181	12.0	12	0.9066	0.0057	3237.1033	2243.7890	1438.0	2475.0	0.5810	35.0	0.0141	0.0	831.0	1196.0	0.6948	0.0	28.0	607.0	1267.0	0.4791	0.0221
0.0044	13.0	13	1.4092	0.0057	5031.9556	3487.8858	1386.0	2475.0	0.56	100.0	0.0404	28.0	1040.0	1196.0	0.8696	0.0234	65.0	346.0	1267.0	0.2731	0.0513
0.0006	14.0	14	2.0506	0.0057	7321.8602	5075.1267	1376.0	2475.0	0.5560	335.0	0.1354	228.0	1132.0	1196.0	0.9465	0.1906	100.0	244.0	1267.0	0.1926	0.0789
0.0002	15.0	15	2.6608	0.0057	9500.8931	6585.5173	1357.0	2475.0	0.5483	678.0	0.2739	557.0	1173.0	1196.0	0.9808	0.4657	114.0	184.0	1267.0	0.1452	0.0900
0.0001	16.0	16	3.1937	0.0057	11403.7545	7904.4803	1343.0	2475.0	0.5426	981.0	0.3964	856.0	1185.0	1196.0	0.9908	0.7157	118.0	158.0	1267.0	0.1247	0.0931
0.0001	17.0	17	3.6210	0.0057	12929.2533	8961.8755	1331.0	2475.0	0.5378	1158.0	0.4679	1030.0	1186.0	1196.0	0.9916	0.8612	121.0	145.0	1267.0	0.1144	0.0955
0.0001	18.0	18	3.9355	0.0057	14052.2862	9740.3026	1324.0	2475.0	0.5349	1247.0	0.5038	1122.0	1187.0	1196.0	0.9925	0.9381	118.0	137.0	1267.0	0.1081	0.0931
0.0	19.0	19	4.1504	0.0057	14819.8661	10272.3484	1325.0	2475.0	0.5354	1291.0	0.5216	1159.0	1187.0	1196.0	0.9925	0.9691	124.0	138.0	1267.0	0.1089	0.0979
0.0	20.0	20	4.2889	0.0057	15314.2863	10615.0543	1323.0	2475.0	0.5345	1301.0	0.5257	1169.0	1187.0	1196.0	0.9925	0.9774	124.0	136.0	1267.0	0.1073	0.0979
0.0	21.0	21	4.3808	0.0057	15642.3416	10842.4450	1323.0	2475.0	0.5345	1311.0	0.5297	1178.0	1187.0	1196.0	0.9925	0.9849	126.0	136.0	1267.0	0.1073	0.0994
0.0	22.0	22	4.4451	0.0057	15871.9519	11001.5987	1326.0	2475.0	0.5358	1323.0	0.5345	1183.0	1187.0	1196.0	0.9925	0.9891	131.0	139.0	1267.0	0.1097	0.1034
0.0	23.0	23	4.4902	0.0057	16033.0571	11113.2683	1327.0	2475.0	0.5362	1327.0	0.5362	1183.0	1187.0	1196.0	0.9925	0.9891	135.0	140.0	1267.0	0.1105	0.1066
0.0	24.0	24	4.5216	0.0057	16145.1152	11190.9411	1329.0	2475.0	0.5370	1330.0	0.5374	1183.0	1187.0	1196.0	0.9925	0.9891	138.0	142.0	1267.0	0.1121	0.1089
0.0	25.0	25	4.5424	0.0057	16219.4313	11242.4531	1330.0	2475.0	0.5374	1331.0	0.5378	1183.0	1187.0	1196.0	0.9925	0.9891	139.0	143.0	1267.0	0.1129	0.1097
0.0	26.0	26	4.5522	0.0057	16254.5512	11266.7964	1331.0	2475.0	0.5378	1332.0	0.5382	1183.0	1187.0	1196.0	0.9925	0.9891	140.0	144.0	1267.0	0.1137	0.1105
0.0	27.0	27	4.5629	0.0057	16292.5871	11293.1608	1332.0	2475.0	0.5382	1334.0	0.5390	1182.0	1186.0	1196.0	0.9916	0.9883	143.0	146.0	1267.0	0.1152	0.1129
0.0	28.0	28	4.5677	0.0057	16309.7312	11305.0442	1332.0	2475.0	0.5382	1334.0	0.5390	1183.0	1187.0	1196.0	0.9925	0.9891	142.0	145.0	1267.0	0.1144	0.1121
0.0	29.0	29	4.5732	0.0057	16329.2607	11318.5810	1333.0	2475.0	0.5386	1335.0	0.5394	1183.0	1187.0	1196.0	0.9925	0.9891	143.0	146.0	1267.0	0.1152	0.1129
0.0	30.0	30	4.5757	0.0057	16338.4857	11324.9753	1333.0	2475.0	0.5386	1336.0	0.5398	1183.0	1186.0	1196.0	0.9916	0.9891	144.0	147.0	1267.0	0.1160	0.1137
0.0	31.0	31	4.5783	0.0057	16347.4855	11331.2135	1333.0	2475.0	0.5386	1336.0	0.5398	1183.0	1186.0	1196.0	0.9916	0.9891	144.0	147.0	1267.0	0.1160	0.1137
0.0	32.0	32	4.5766	0.0057	16341.7025	11327.2050	1334.0	2475.0	0.5390	1337.0	0.5402	1183.0	1186.0	1196.0	0.9916	0.9891	145.0	148.0	1267.0	0.1168	0.1144
0.0	33.0	33	4.5759	0.0057	16338.9663	11325.3084	1335.0	2475.0	0.5394	1339.0	0.5410	1184.0	1186.0	1196.0	0.9916	0.9900	146.0	149.0	1267.0	0.1176	0.1152
0.0	34.0	34	4.5764	0.0057	16340.7048	11326.5134	1332.0	2475.0	0.5382	1336.0	0.5398	1183.0	1185.0	1196.0	0.9908	0.9891	144.0	147.0	1267.0	0.1160	0.1137
0.0	35.0	35	4.5782	0.0057	16347.3521	11331.1210	1333.0	2475.0	0.5386	1339.0	0.5410	1185.0	1186.0	1196.0	0.9916	0.9908	145.0	147.0	1267.0	0.1160	0.1144
0.0	36.0	36	4.5762	0.0057	16340.1836	11326.1522	1333.0	2475.0	0.5386	1337.0	0.5402	1184.0	1186.0	1196.0	0.9916	0.9900	144.0	147.0	1267.0	0.1160	0.1137
0.0	37.0	37	4.5778	0.0057	16345.7491	11330.0099	1333.0	2475.0	0.5386	1337.0	0.5402	1183.0	1185.0	1196.0	0.9908	0.9891	145.0	148.0	1267.0	0.1168	0.1144
0.0	38.0	38	4.5758	0.0057	16338.7762	11325.1766	1335.0	2475.0	0.5394	1339.0	0.5410	1183.0	1186.0	1196.0	0.9916	0.9891	147.0	149.0	1267.0	0.1176	0.1160
0.0	39.0	39	4.5744	0.0057	16333.6144	11321.5988	1334.0	2475.0	0.5390	1338.0	0.5406	1183.0	1185.0	1196.0	0.9908	0.9891	146.0	149.0	1267.0	0.1176	0.1152
0.0	40.0	40	4.5746	0.0057	16334.3188	11322.0870	1334.0	2475.0	0.5390	1337.0	0.5402	1183.0	1186.0	1196.0	0.9916	0.9891	145.0	148.0	1267.0	0.1168	0.1144
0.0	41.0	41	4.5741	0.0057	16332.7662	11321.0109	1335.0	2475.0	0.5394	1339.0	0.5410	1183.0	1185.0	1196.0	0.9908	0.9891	147.0	150.0	1267.0	0.1184	0.1160
0.0	42.0	42	4.5751	0.0057	16336.1639	11323.3659	1334.0	2475.0	0.5390	1338.0	0.5406	1183.0	1185.0	1196.0	0.9908	0.9891	146.0	149.0	1267.0	0.1176	0.1152

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1