Training Loss	Epoch	Step	Validation Loss
4.9675	0.0435	20	4.8181
4.272	0.0871	40	4.0570
3.6898	0.1306	60	3.5712
3.3143	0.1742	80	3.2163
3.0303	0.2177	100	2.9624
2.8546	0.2613	120	2.7811
2.7039	0.3048	140	2.6403
2.559	0.3484	160	2.5206
2.4213	0.3919	180	2.4170
2.348	0.4355	200	2.3301
2.2713	0.4790	220	2.2543
2.2184	0.5226	240	2.1807
2.0808	0.5661	260	2.1157
2.0531	0.6097	280	2.0431
1.9871	0.6532	300	1.9748
1.936	0.6968	320	1.9067
1.8815	0.7403	340	1.8420
1.8133	0.7839	360	1.7902
1.7643	0.8274	380	1.7333
1.6585	0.8710	400	1.6785
1.6465	0.9145	420	1.6133
1.5544	0.9581	440	1.5663
1.5348	1.0016	460	1.5072
1.4016	1.0452	480	1.4577
1.3489	1.0887	500	1.4186
1.2949	1.1323	520	1.3672
1.2179	1.1758	540	1.3171
1.2227	1.2194	560	1.2676
1.1557	1.2629	580	1.2181
1.134	1.3065	600	1.1725
1.0861	1.3500	620	1.1243
1.0583	1.3936	640	1.0730
1.0058	1.4371	660	1.0173
0.9373	1.4807	680	0.9671
0.9298	1.5242	700	0.9267
0.8614	1.5678	720	0.8734
0.8114	1.6113	740	0.8293
0.7695	1.6549	760	0.7900
0.753	1.6984	780	0.7541
0.7132	1.7420	800	0.7042
0.6755	1.7855	820	0.6773
0.6298	1.8291	840	0.6279
0.5957	1.8726	860	0.5947
0.5634	1.9162	880	0.5632
0.5374	1.9597	900	0.5420
0.496	2.0033	920	0.5063
0.4253	2.0468	940	0.4849
0.4213	2.0904	960	0.4649
0.3898	2.1339	980	0.4389
0.3726	2.1775	1000	0.4213
0.3704	2.2210	1020	0.4022
0.3386	2.2646	1040	0.3838
0.3335	2.3081	1060	0.3557
0.3118	2.3517	1080	0.3388
0.2937	2.3952	1100	0.3189
0.2855	2.4388	1120	0.3030
0.2654	2.4823	1140	0.2836
0.245	2.5259	1160	0.2611
0.2416	2.5694	1180	0.2445
0.2165	2.6130	1200	0.2285
0.2068	2.6565	1220	0.2105
0.1961	2.7001	1240	0.1990
0.1923	2.7436	1260	0.1859
0.179	2.7872	1280	0.1750
0.1649	2.8307	1300	0.1649
0.1481	2.8743	1320	0.1572
0.1545	2.9178	1340	0.1471
0.1367	2.9614	1360	0.1367
0.1284	3.0049	1380	0.1302
0.1103	3.0484	1400	0.1241
0.1082	3.0920	1420	0.1171
0.0976	3.1355	1440	0.1120
0.0989	3.1791	1460	0.1056
0.093	3.2226	1480	0.1004
0.0861	3.2662	1500	0.0938
0.0847	3.3097	1520	0.0884
0.0819	3.3533	1540	0.0833
0.0765	3.3968	1560	0.0784
0.0713	3.4404	1580	0.0737
0.0651	3.4839	1600	0.0688
0.065	3.5275	1620	0.0662
0.0629	3.5710	1640	0.0622
0.0588	3.6146	1660	0.0594
0.0577	3.6581	1680	0.0555
0.0524	3.7017	1700	0.0528
0.0503	3.7452	1720	0.0498
0.0464	3.7888	1740	0.0475
0.046	3.8323	1760	0.0451
0.0458	3.8759	1780	0.0426
0.041	3.9194	1800	0.0404
0.0409	3.9630	1820	0.0386
0.0371	4.0065	1840	0.0370
0.0327	4.0501	1860	0.0355
0.033	4.0936	1880	0.0344
0.0319	4.1372	1900	0.0332
0.0318	4.1807	1920	0.0322
0.0298	4.2243	1940	0.0310
0.0291	4.2678	1960	0.0302
0.0288	4.3114	1980	0.0294
0.0275	4.3549	2000	0.0287
0.0284	4.3985	2020	0.0282
0.028	4.4420	2040	0.0277
0.0256	4.4856	2060	0.0272
0.0264	4.5291	2080	0.0268
0.0267	4.5727	2100	0.0265
0.0262	4.6162	2120	0.0262
0.0245	4.6598	2140	0.0260
0.0249	4.7033	2160	0.0258
0.0253	4.7469	2180	0.0257
0.0249	4.7904	2200	0.0256
0.0256	4.8340	2220	0.0256
0.0268	4.8775	2240	0.0255
0.0253	4.9211	2260	0.0255
0.0244	4.9646	2280	0.0255

Framework versions

PEFT 0.15.2
Transformers 4.45.2
Pytorch 2.5.0+cu121
Datasets 3.2.0
Tokenizers 0.20.3

Siqi-Hu/Llama3-8B-lora-generic-epoch-5-labels_40.0-augmented

Llama3-8B-lora-generic-epoch-5-labels_40.0-augmented

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Siqi-Hu/
Llama3-8B-lora-generic-epoch-5-labels_40.0-augmented