Batch upload part 26

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	0
+5	1
+6	0
+7	0
+8	1
+9	0
+10	1
+11	1
+12	1
+13	0
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	1
+22	1
+23	1
+24	0
+25	1
+26	1
+27	1
+28	0
+29	1
+30	1
+31	0
+32	0
+33	0
+34	0
+35	0
+36	1
+37	1
+38	0
+39	1
+40	1
+41	1
+42	0
+43	1
+44	1
+45	0
+46	0
+47	0
+48	1
+49	1
+50	1
+51	1
+52	1
+53	1
+54	0
+55	1
+56	1
+57	1
+58	0
+59	1
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	1
+69	1
+70	0
+71	1
+72	1
+73	0
+74	1
+75	0
+76	1
+77	0
+78	0
+79	0
+80	0
+81	0
+82	1
+83	0
+84	0
+85	0
+86	0
+87	1
+88	0
+89	1
+90	0
+91	0
+92	1
+93	1
+94	1
+95	0
+96	1
+97	1
+98	0
+99	1
+100	1
+101	1
+102	1
+103	1
+104	1
+105	0
+106	0
+107	1
+108	1
+109	1
+110	1
+111	0
+112	0
+113	1
+114	1
+115	0
+116	0
+117	0
+118	1
+119	1
+120	1
+121	0
+122	1
+123	0
+124	1
+125	1
+126	1
+127	1
+128	0
+129	1
+130	0
+131	1
+132	1
+133	0
+134	1
+135	0
+136	0
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	0
+147	1
+148	1
+149	1
+150	1
+151	1
+152	0
+153	0
+154	1
+155	1
+156	1
+157	1
+158	0
+159	1
+160	1
+161	1
+162	1
+163	1
+164	0
+165	1
+166	1
+167	0
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	1
+175	1
+176	1
+177	0
+178	1
+179	1
+180	0
+181	0
+182	0
+183	1
+184	1
+185	1
+186	0
+187	0
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	0
+195	0
+196	0
+197	1
+198	1
+199	0
+200	0
+201	1
+202	1
+203	1
+204	0
+205	0
+206	1
+207	1
+208	0
+209	1
+210	0
+211	1
+212	1
+213	0
+214	1
+215	0
+216	1
+217	1
+218	1
+219	1
+220	1
+221	0
+222	1
+223	0
+224	1
+225	1
+226	1
+227	1
+228	1
+229	0
+230	1
+231	0
+232	1
+233	1
+234	0
+235	0
+236	1
+237	1
+238	0
+239	0
+240	1
+241	1
+242	1
+243	1
+244	0
+245	1
+246	1
+247	0
+248	1
+249	1
+250	1
+251	1
+252	0
+253	1
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	0
+261	1
+262	1
+263	1
+264	0
+265	1
+266	1
+267	1
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	1
+276	0
+277	1
+278	1
+279	1
+280	1
+281	0
+282	1
+283	1
+284	1
+285	0
+286	1
+287	0
+288	0
+289	0
+290	1
+291	1
+292	1
+293	1
+294	1
+295	0
+296	0
+297	0
+298	1
+299	0
+300	1
+301	1
+302	0
+303	1
+304	1
+305	0
+306	1
+307	1
+308	0
+309	1
+310	1
+311	1
+312	0
+313	1
+314	1
+315	1
+316	1
+317	1
+318	1
+319	0
+320	1
+321	1
+322	1
+323	1
+324	1
+325	1
+326	1
+327	0
+328	0
+329	0
+330	0
+331	1
+332	1
+333	1
+334	1
+335	0
+336	1
+337	1
+338	1
+339	1
+340	1
+341	1
+342	1
+343	1
+344	0
+345	1
+346	0
+347	0
+348	0
+349	1
+350	1
+351	1
+352	0
+353	1
+354	0
+355	0
+356	0
+357	0
+358	1
+359	0
+360	0
+361	0
+362	1
+363	1
+364	0
+365	1
+366	0
+367	0
+368	0
+369	1
+370	0
+371	1
+372	1
+373	1
+374	1
+375	0
+376	0
+377	1
+378	0
+379	0
+380	1
+381	1
+382	0
+383	1
+384	0
+385	0
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	0
+395	1
+396	1
+397	1
+398	0
+399	0
+400	1
+401	1
+402	1
+403	1
+404	1
+405	0
+406	0
+407	1
+408	1
+409	1
+410	0
+411	1
+412	1
+413	1
+414	1
+415	0
+416	0
+417	1
+418	1
+419	1
+420	1
+421	1
+422	1
+423	1
+424	0
+425	0
+426	0
+427	1
+428	0
+429	1
+430	0
+431	1
+432	1
+433	1
+434	1
+435	1
+436	1
+437	0
+438	1
+439	0
+440	0
+441	0
+442	1
+443	1
+444	1
+445	1
+446	1
+447	1
+448	1
+449	1
+450	0
+451	1
+452	1
+453	1
+454	1
+455	1
+456	1
+457	1
+458	0
+459	1
+460	1
+461	1
+462	1
+463	0
+464	0
+465	0
+466	1
+467	1
+468	1
+469	1
+470	0
+471	1
+472	1
+473	1
+474	1
+475	1
+476	1
+477	1
+478	1
+479	1
+480	0
+481	1
+482	1
+483	1
+484	0
+485	1
+486	1
+487	1
+488	1
+489	1
+490	1
+491	1
+492	1
+493	1
+494	0
+495	1
+496	1
+497	1
+498	0
+499	1
+500	1
+501	1
+502	1
+503	0
+504	1
+505	1
+506	0
+507	1
+508	0
+509	0
+510	1
+511	1
+512	0
+513	1
+514	1
+515	1
+516	1
+517	0
+518	1
+519	1
+520	1
+521	1
+522	1
+523	1
+524	1
+525	1
+526	1
+527	1
+528	1
+529	1
+530	1
+531	1
+532	1
+533	0
+534	1
+535	1
+536	1
+537	1
+538	0
+539	1
+540	1
+541	1
+542	1
+543	1
+544	1
+545	1
+546	0
+547	0
+548	0
+549	0
+550	1
+551	1
+552	0
+553	1
+554	0
+555	1
+556	0
+557	1
+558	1
+559	1
+560	1
+561	0
+562	0
+563	0
+564	1
+565	1
+566	1
+567	1
+568	0
+569	0
+570	0
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	0
+578	1
+579	1
+580	1
+581	1
+582	1
+583	1
+584	1
+585	1
+586	0
+587	1
+588	1
+589	1
+590	1
+591	1
+592	1
+593	0
+594	0
+595	1
+596	1
+597	0
+598	1
+599	1
+600	1
+601	1
+602	1
+603	1
+604	1
+605	1
+606	0
+607	1
+608	0
+609	1
+610	1
+611	1
+612	0
+613	1
+614	1
+615	1
+616	1
+617	0
+618	1
+619	1
+620	1
+621	0
+622	1
+623	0
+624	1
+625	0
+626	1
+627	1
+628	1
+629	1
+630	0
+631	1
+632	1
+633	0
+634	0
+635	1
+636	0
+637	1
+638	1
+639	1
+640	1
+641	1
+642	1
+643	1
+644	1
+645	1
+646	1
+647	1
+648	1
+649	0
+650	1
+651	0
+652	0
+653	1
+654	1
+655	1
+656	1
+657	1
+658	1
+659	1
+660	1
+661	1
+662	1
+663	1
+664	1
+665	0
+666	1
+667	0
+668	0
+669	0
+670	1
+671	1
+672	0
+673	1
+674	1
+675	0
+676	1
+677	1
+678	1
+679	1
+680	0
+681	1
+682	1
+683	1
+684	1
+685	0
+686	1
+687	0
+688	1
+689	1
+690	1
+691	1
+692	0
+693	1
+694	0
+695	0
+696	1
+697	1
+698	0
+699	1
+700	0
+701	1
+702	1
+703	0
+704	1
+705	0
+706	0
+707	0
+708	1
+709	1
+710	0
+711	0
+712	1
+713	1
+714	1
+715	1
+716	1
+717	0
+718	1
+719	1
+720	1
+721	1
+722	0
+723	0
+724	1
+725	1
+726	1
+727	1
+728	1
+729	1
+730	1
+731	1
+732	1
+733	0
+734	1
+735	1
+736	1
+737	1
+738	1
+739	1
+740	1
+741	1
+742	1
+743	1
+744	1
+745	0
+746	1
+747	0
+748	1
+749	0
+750	1
+751	1
+752	1
+753	0
+754	1
+755	1
+756	1
+757	1
+758	1
+759	1
+760	1
+761	1
+762	1
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	1
+770	1
+771	1
+772	1
+773	1
+774	1
+775	1
+776	1
+777	1
+778	0
+779	1
+780	0
+781	0
+782	1
+783	0
+784	0
+785	1
+786	1
+787	0
+788	1
+789	1
+790	1
+791	1
+792	1
+793	1
+794	1
+795	1
+796	0
+797	0
+798	1
+799	0
+800	0
+801	0
+802	1
+803	1
+804	0
+805	0
+806	1
+807	0
+808	1
+809	1
+810	1
+811	1
+812	0
+813	1
+814	0
+815	1
+816	0
+817	0
+818	0
+819	1
+820	0
+821	1
+822	0
+823	1
+824	1
+825	1
+826	1
+827	0
+828	0
+829	1
+830	1
+831	1
+832	1
+833	0
+834	1
+835	0
+836	1
+837	1
+838	1
+839	0
+840	0
+841	0
+842	1
+843	1
+844	0
+845	1
+846	1
+847	1
+848	0
+849	1
+850	1
+851	0
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	1
+861	1
+862	0
+863	1
+864	1
+865	1
+866	0
+867	1
+868	1
+869	1
+870	0
+871	1
+872	1
+873	1
+874	0
+875	0
+876	1
+877	0
+878	0
+879	0
+880	1
+881	1
+882	1
+883	1
+884	0
+885	1
+886	1
+887	1
+888	0
+889	1
+890	1
+891	1
+892	0
+893	0
+894	0
+895	0
+896	0
+897	1
+898	1
+899	1
+900	1
+901	1
+902	0
+903	1
+904	1
+905	1
+906	1
+907	1
+908	1
+909	1
+910	0
+911	1
+912	0
+913	0
+914	1
+915	1
+916	1
+917	1
+918	0
+919	1
+920	1
+921	1
+922	1
+923	0
+924	1
+925	1
+926	1
+927	0
+928	1
+929	1
+930	1
+931	0
+932	0
+933	0
+934	0
+935	1
+936	0
+937	0
+938	1
+939	1
+940	1
+941	1
+942	0
+943	0
+944	1
+945	0
+946	1
+947	1
+948	1
+949	1
+950	0
+951	1
+952	1
+953	1
+954	1
+955	1
+956	1
+957	1
+958	1
+959	1
+960	1
+961	1
+962	1
+963	0
+964	0
+965	1
+966	1
+967	1
+968	1
+969	1
+970	1
+971	0
+972	1
+973	1
+974	1
+975	1
+976	1
+977	1
+978	1
+979	1
+980	1
+981	1
+982	0
+983	1
+984	0
+985	1
+986	1
+987	0
+988	1
+989	0
+990	0
+991	1
+992	1
+993	1
+994	0
+995	1
+996	1
+997	1
+998	1
+999	1
+1000	0
+1001	1
+1002	0
+1003	0
+1004	1
+1005	1
+1006	1
+1007	0
+1008	1
+1009	0
+1010	1
+1011	0
+1012	1
+1013	1
+1014	1
+1015	1
+1016	1
+1017	1
+1018	1
+1019	1
+1020	1
+1021	1
+1022	1
+1023	0
+1024	1
+1025	0
+1026	0
+1027	1
+1028	0
+1029	1
+1030	0
+1031	1
+1032	1
+1033	1
+1034	1
+1035	0
+1036	1
+1037	1
+1038	1
+1039	0
+1040	0
+1041	1
+1042	0
+1043	0
+1044	1
+1045	1
+1046	0
+1047	1
+1048	1
+1049	1
+1050	1
+1051	1
+1052	1
+1053	1
+1054	0
+1055	1
+1056	1
+1057	1
+1058	1
+1059	1
+1060	1
+1061	1
+1062	1
+1063	1
+1064	1
+1065	1
+1066	1
+1067	1
+1068	0
+1069	1
+1070	1
+1071	1
+1072	1
+1073	1
+1074	1
+1075	1
+1076	1
+1077	1
+1078	1
+1079	1
+1080	0
+1081	0
+1082	1
+1083	1
+1084	1
+1085	1
+1086	1
+1087	0
+1088	1
+1089	1
+1090	1
+1091	0
+1092	1
+1093	1
+1094	1
+1095	1
+1096	1
+1097	1
+1098	1
+1099	1
+1100	1
+1101	1
+1102	0
+1103	1
+1104	1
+1105	0
+1106	1
+1107	0
+1108	1
+1109	1
+1110	0
+1111	1
+1112	0
+1113	0
+1114	1
+1115	1
+1116	0
+1117	1
+1118	1
+1119	1
+1120	0
+1121	0
+1122	1
+1123	1
+1124	0
+1125	1
+1126	0
+1127	0
+1128	1
+1129	1
+1130	1
+1131	1
+1132	0
+1133	1
+1134	0
+1135	1
+1136	0
+1137	1
+1138	0
+1139	0
+1140	0
+1141	1
+1142	1
+1143	1
+1144	0
+1145	1
+1146	1
+1147	0
+1148	1
+1149	1
+1150	0
+1151	1
+1152	1
+1153	0
+1154	0
+1155	1
+1156	1
+1157	0
+1158	0
+1159	1
+1160	0
+1161	0
+1162	1
+1163	1
+1164	1
+1165	0
+1166	0
+1167	1
+1168	1
+1169	1
+1170	0
+1171	1
+1172	1
+1173	1
+1174	1
+1175	0
+1176	1
+1177	0
+1178	1
+1179	1
+1180	1
+1181	1
+1182	1
+1183	1
+1184	1
+1185	1
+1186	0
+1187	1
+1188	1
+1189	0
+1190	0
+1191	0
+1192	1
+1193	1
+1194	1
+1195	1
+1196	0
+1197	1
+1198	1
+1199	1
+1200	0
+1201	1
+1202	0
+1203	1
+1204	0
+1205	1
+1206	0
+1207	0
+1208	1
+1209	1
+1210	1
+1211	1
+1212	1
+1213	1
+1214	1
+1215	1
+1216	1
+1217	1
+1218	1
+1219	1
+1220	1
+1221	0
+1222	1
+1223	1
+1224	0
+1225	1
+1226	0
+1227	1
+1228	1
+1229	1
+1230	0
+1231	0
+1232	1
+1233	1
+1234	1
+1235	1
+1236	1
+1237	1
+1238	1
+1239	1
+1240	1
+1241	0
+1242	1
+1243	1
+1244	1
+1245	1
+1246	0
+1247	0
+1248	1
+1249	1
+1250	1
+1251	1
+1252	1
+1253	1
+1254	1
+1255	1
+1256	1
+1257	1
+1258	0
+1259	1
+1260	0
+1261	1
+1262	1
+1263	1
+1264	1
+1265	1
+1266	1
+1267	1
+1268	1
+1269	1
+1270	1
+1271	1
+1272	0
+1273	0
+1274	0
+1275	1
+1276	0
+1277	1
+1278	1
+1279	0
+1280	1
+1281	0
+1282	1
+1283	0
+1284	1
+1285	1
+1286	1
+1287	0
+1288	1
+1289	1
+1290	1
+1291	1
+1292	0
+1293	1
+1294	0
+1295	1
+1296	1
+1297	1
+1298	1
+1299	1
+1300	0
+1301	0
+1302	1
+1303	1
+1304	1
+1305	0
+1306	0
+1307	1
+1308	1
+1309	0
+1310	1
+1311	1
+1312	0
+1313	1
+1314	1
+1315	1
+1316	1
+1317	1
+1318	0
+1319	1
+1320	1
+1321	1
+1322	1
+1323	1
+1324	1
+1325	1
+1326	0
+1327	1
+1328	1
+1329	0
+1330	1
+1331	1
+1332	1
+1333	0
+1334	1
+1335	0
+1336	0
+1337	0
+1338	0
+1339	1
+1340	0
+1341	0
+1342	0
+1343	0
+1344	1
+1345	1
+1346	1
+1347	1
+1348	1
+1349	1
+1350	1
+1351	1
+1352	1
+1353	0
+1354	0
+1355	0
+1356	1
+1357	1
+1358	0
+1359	1
+1360	1
+1361	1
+1362	1
+1363	0
+1364	1
+1365	1
+1366	0
+1367	0
+1368	1
+1369	1
+1370	0
+1371	0
+1372	1
+1373	1
+1374	0
+1375	1
+1376	0
+1377	1
+1378	1
+1379	1
+1380	1
+1381	1
+1382	1
+1383	0
+1384	1
+1385	1
+1386	0
+1387	1
+1388	1
+1389	1
+1390	1
+1391	0
+1392	0
+1393	1
+1394	1
+1395	1
+1396	0
+1397	1
+1398	1
+1399	0
+1400	0
+1401	0
+1402	1
+1403	0
+1404	1
+1405	0
+1406	1
+1407	1
+1408	1
+1409	1
+1410	0
+1411	1
+1412	1
+1413	1
+1414	0
+1415	1
+1416	1
+1417	0
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	0
+1428	0
+1429	1
+1430	0
+1431	1
+1432	1
+1433	0
+1434	1
+1435	0
+1436	1
+1437	1
+1438	1
+1439	1
+1440	0
+1441	1
+1442	0
+1443	0
+1444	0
+1445	1
+1446	1
+1447	1
+1448	0
+1449	1
+1450	1
+1451	0
+1452	1
+1453	1
+1454	1
+1455	1
+1456	1
+1457	1
+1458	1
+1459	1
+1460	1
+1461	1
+1462	1
+1463	0
+1464	1
+1465	1
+1466	1
+1467	0
+1468	1
+1469	0
+1470	0
+1471	1
+1472	0
+1473	0
+1474	1
+1475	1
+1476	0
+1477	1
+1478	0
+1479	0
+1480	1
+1481	0
+1482	1
+1483	0
+1484	0
+1485	1
+1486	0
+1487	0
+1488	1
+1489	1
+1490	0
+1491	1
+1492	1
+1493	0
+1494	0
+1495	1
+1496	1
+1497	0
+1498	0
+1499	0
+1500	1
+1501	1
+1502	1
+1503	0
+1504	0
+1505	1
+1506	1
+1507	1
+1508	1
+1509	0
+1510	1
+1511	1
+1512	0
+1513	1
+1514	0
+1515	1
+1516	0
+1517	1
+1518	0
+1519	0
+1520	0
+1521	0
+1522	0
+1523	1
+1524	1
+1525	1
+1526	1
+1527	1
+1528	0
+1529	1
+1530	1
+1531	1
+1532	1
+1533	1
+1534	1
+1535	0
+1536	1
+1537	0
+1538	1
+1539	0
+1540	0
+1541	1
+1542	0
+1543	1
+1544	0
+1545	0
+1546	1
+1547	0
+1548	1
+1549	1
+1550	1
+1551	0
+1552	0
+1553	0
+1554	1
+1555	1
+1556	0
+1557	1
+1558	0
+1559	1
+1560	1
+1561	0
+1562	1
+1563	1
+1564	0
+1565	0
+1566	1
+1567	1
+1568	1
+1569	1
+1570	0
+1571	1
+1572	0
+1573	0
+1574	1
+1575	1
+1576	1
+1577	0
+1578	0
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	1
+1586	1
+1587	1
+1588	1
+1589	1
+1590	0
+1591	1
+1592	1
+1593	0
+1594	1
+1595	1
+1596	1
+1597	0
+1598	0
+1599	1
+1600	0
+1601	1
+1602	1
+1603	0
+1604	0
+1605	0
+1606	1
+1607	1
+1608	0
+1609	1
+1610	0
+1611	1
+1612	1
+1613	1
+1614	1
+1615	1
+1616	1
+1617	0
+1618	1
+1619	1
+1620	0
+1621	0
+1622	1
+1623	1
+1624	0
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	0
+1632	1
+1633	1
+1634	1
+1635	1
+1636	1
+1637	1
+1638	0
+1639	0
+1640	0
+1641	1
+1642	1
+1643	1
+1644	1
+1645	1
+1646	1
+1647	0
+1648	1
+1649	1
+1650	0
+1651	0
+1652	0
+1653	1
+1654	1
+1655	1
+1656	0
+1657	0
+1658	1
+1659	0
+1660	0
+1661	1
+1662	1
+1663	1
+1664	0
+1665	0
+1666	0
+1667	1
+1668	0
+1669	1
+1670	1
+1671	0
+1672	1
+1673	1
+1674	1
+1675	1
+1676	1
+1677	1
+1678	1
+1679	1
+1680	1
+1681	1
+1682	1
+1683	0
+1684	1
+1685	1
+1686	0
+1687	0
+1688	1
+1689	1
+1690	1
+1691	0
+1692	1
+1693	1
+1694	0
+1695	1
+1696	1
+1697	0
+1698	0
+1699	1
+1700	0
+1701	1
+1702	0
+1703	1
+1704	1
+1705	1
+1706	0
+1707	0
+1708	1
+1709	0
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	0
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9221436817257659,
+    "eval_f1": 0.9349736379613357,
+    "eval_loss": 0.6781179308891296,
+    "eval_runtime": 0.6361,
+    "eval_samples": 408,
+    "eval_samples_per_second": 641.363,
+    "eval_steps_per_second": 1.572
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9221436817257659,
+    "eval_f1": 0.9349736379613357,
+    "eval_loss": 0.6781179308891296,
+    "eval_runtime": 0.6361,
+    "eval_samples": 408,
+    "eval_samples_per_second": 641.363,
+    "eval_steps_per_second": 1.572
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/ft/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/ft/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/ft/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/ft/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 2400,
+  "best_metric": 0.9093137254901961,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/checkpoint-2400",
+  "epoch": 30.0,
+  "eval_steps": 100,
+  "global_step": 3450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 9.207517623901367,
+      "learning_rate": 0.00198,
+      "loss": 0.6035,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.8014705882352942,
+      "eval_combined_score": 0.8220945174186179,
+      "eval_f1": 0.8427184466019417,
+      "eval_loss": 0.48600342869758606,
+      "eval_runtime": 0.7317,
+      "eval_samples_per_second": 557.637,
+      "eval_steps_per_second": 1.367,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 2.2224478721618652,
+      "learning_rate": 0.0019956152348614225,
+      "loss": 0.4063,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8820863505604604,
+      "eval_f1": 0.9038785834738617,
+      "eval_loss": 0.35205960273742676,
+      "eval_runtime": 0.6476,
+      "eval_samples_per_second": 630.027,
+      "eval_steps_per_second": 1.544,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.051316261291504,
+      "learning_rate": 0.0019823226955326743,
+      "loss": 0.3156,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8774509803921569,
+      "eval_combined_score": 0.8963526088401462,
+      "eval_f1": 0.9152542372881356,
+      "eval_loss": 0.2953622341156006,
+      "eval_runtime": 0.6404,
+      "eval_samples_per_second": 637.103,
+      "eval_steps_per_second": 1.562,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 2.0906338691711426,
+      "learning_rate": 0.0019602408686963785,
+      "loss": 0.251,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.8823529411764706,
+      "eval_combined_score": 0.9006359300476947,
+      "eval_f1": 0.918918918918919,
+      "eval_loss": 0.2901740074157715,
+      "eval_runtime": 0.6457,
+      "eval_samples_per_second": 631.915,
+      "eval_steps_per_second": 1.549,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 2.9156606197357178,
+      "learning_rate": 0.0019295673304908422,
+      "loss": 0.2437,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9120710784313726,
+      "eval_f1": 0.9270833333333334,
+      "eval_loss": 0.27514174580574036,
+      "eval_runtime": 0.6388,
+      "eval_samples_per_second": 638.745,
+      "eval_steps_per_second": 1.566,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 10.352530479431152,
+      "learning_rate": 0.001890576530999922,
+      "loss": 0.1758,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.916733816814397,
+      "eval_f1": 0.9315068493150684,
+      "eval_loss": 0.3504975140094757,
+      "eval_runtime": 0.6372,
+      "eval_samples_per_second": 640.303,
+      "eval_steps_per_second": 1.569,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 3.138051748275757,
+      "learning_rate": 0.0018436173386234143,
+      "loss": 0.1481,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8651960784313726,
+      "eval_combined_score": 0.8866881894661036,
+      "eval_f1": 0.9081803005008348,
+      "eval_loss": 0.5320879220962524,
+      "eval_runtime": 0.6389,
+      "eval_samples_per_second": 638.555,
+      "eval_steps_per_second": 1.565,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 8.193928718566895,
+      "learning_rate": 0.001789109918592965,
+      "loss": 0.1325,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.916733816814397,
+      "eval_f1": 0.9315068493150684,
+      "eval_loss": 0.4476175606250763,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 641.552,
+      "eval_steps_per_second": 1.572,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 3.793989419937134,
+      "learning_rate": 0.001727541973562826,
+      "loss": 0.0984,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9062594591867621,
+      "eval_f1": 0.9228130360205832,
+      "eval_loss": 0.4270480275154114,
+      "eval_runtime": 0.6368,
+      "eval_samples_per_second": 640.739,
+      "eval_steps_per_second": 1.57,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 4.246761322021484,
+      "learning_rate": 0.001659464379912601,
+      "loss": 0.0718,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9062594591867621,
+      "eval_f1": 0.9228130360205832,
+      "eval_loss": 0.4241102635860443,
+      "eval_runtime": 0.6466,
+      "eval_samples_per_second": 631.011,
+      "eval_steps_per_second": 1.547,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 2.9366676807403564,
+      "learning_rate": 0.0015854862588059726,
+      "loss": 0.0655,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9141027280477408,
+      "eval_f1": 0.928695652173913,
+      "eval_loss": 0.5752078294754028,
+      "eval_runtime": 0.6364,
+      "eval_samples_per_second": 641.102,
+      "eval_steps_per_second": 1.571,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 8.673500061035156,
+      "learning_rate": 0.0015062695261068735,
+      "loss": 0.0697,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9044579681064526,
+      "eval_f1": 0.9192100538599641,
+      "eval_loss": 0.5210642218589783,
+      "eval_runtime": 0.6474,
+      "eval_samples_per_second": 630.222,
+      "eval_steps_per_second": 1.545,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 18.172353744506836,
+      "learning_rate": 0.0014225229699174897,
+      "loss": 0.0368,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.9000596184419714,
+      "eval_f1": 0.9153153153153153,
+      "eval_loss": 0.8053569197654724,
+      "eval_runtime": 0.6382,
+      "eval_samples_per_second": 639.309,
+      "eval_steps_per_second": 1.567,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 6.8164215087890625,
+      "learning_rate": 0.0013349959087290495,
+      "loss": 0.0495,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9085357692565081,
+      "eval_f1": 0.9249146757679181,
+      "eval_loss": 0.613058865070343,
+      "eval_runtime": 0.639,
+      "eval_samples_per_second": 638.527,
+      "eval_steps_per_second": 1.565,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 2.474440097808838,
+      "learning_rate": 0.001244471486928804,
+      "loss": 0.041,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9156447031109264,
+      "eval_f1": 0.9293286219081273,
+      "eval_loss": 0.5219125151634216,
+      "eval_runtime": 0.6342,
+      "eval_samples_per_second": 643.282,
+      "eval_steps_per_second": 1.577,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 1.85358464717865,
+      "learning_rate": 0.0011517596676513472,
+      "loss": 0.0291,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9141027280477408,
+      "eval_f1": 0.928695652173913,
+      "eval_loss": 0.6180567741394043,
+      "eval_runtime": 0.6358,
+      "eval_samples_per_second": 641.685,
+      "eval_steps_per_second": 1.573,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 0.012138199992477894,
+      "learning_rate": 0.001057689985670419,
+      "loss": 0.0245,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9111628637220013,
+      "eval_f1": 0.9252669039145908,
+      "eval_loss": 0.6767077445983887,
+      "eval_runtime": 0.6402,
+      "eval_samples_per_second": 637.327,
+      "eval_steps_per_second": 1.562,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 0.6696063280105591,
+      "learning_rate": 0.0009631041251743559,
+      "loss": 0.0248,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9197434292866082,
+      "eval_f1": 0.9326241134751773,
+      "eval_loss": 0.6179582476615906,
+      "eval_runtime": 0.5873,
+      "eval_samples_per_second": 694.754,
+      "eval_steps_per_second": 1.703,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.008201290853321552,
+      "learning_rate": 0.0008688483888352111,
+      "loss": 0.025,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.906651908075058,
+      "eval_f1": 0.921146953405018,
+      "eval_loss": 0.601223349571228,
+      "eval_runtime": 0.6344,
+      "eval_samples_per_second": 643.157,
+      "eval_steps_per_second": 1.576,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.0032772510312497616,
+      "learning_rate": 0.000775766125554205,
+      "loss": 0.0166,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9175700031344687,
+      "eval_f1": 0.9307282415630551,
+      "eval_loss": 0.5948611497879028,
+      "eval_runtime": 0.6422,
+      "eval_samples_per_second": 635.352,
+      "eval_steps_per_second": 1.557,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.004750708118081093,
+      "learning_rate": 0.0006846901846358999,
+      "loss": 0.0216,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9158926728586172,
+      "eval_f1": 0.9298245614035088,
+      "eval_loss": 0.6154604554176331,
+      "eval_runtime": 0.6436,
+      "eval_samples_per_second": 633.945,
+      "eval_steps_per_second": 1.554,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 4.844301700592041,
+      "learning_rate": 0.0005964354639070397,
+      "loss": 0.0138,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.91986246795538,
+      "eval_f1": 0.9328621908127208,
+      "eval_loss": 0.6498541831970215,
+      "eval_runtime": 0.6386,
+      "eval_samples_per_second": 638.868,
+      "eval_steps_per_second": 1.566,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0014483303530141711,
+      "learning_rate": 0.0005117916184554203,
+      "loss": 0.013,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9160153571918278,
+      "eval_f1": 0.9300699300699301,
+      "eval_loss": 0.735741138458252,
+      "eval_runtime": 0.6403,
+      "eval_samples_per_second": 637.177,
+      "eval_steps_per_second": 1.562,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 1.6116704940795898,
+      "learning_rate": 0.0004315159952270119,
+      "loss": 0.0112,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9221436817257659,
+      "eval_f1": 0.9349736379613357,
+      "eval_loss": 0.6781179308891296,
+      "eval_runtime": 0.6352,
+      "eval_samples_per_second": 642.273,
+      "eval_steps_per_second": 1.574,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 2.125593662261963,
+      "learning_rate": 0.0003563268566987077,
+      "loss": 0.0159,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9182928388746803,
+      "eval_f1": 0.9321739130434783,
+      "eval_loss": 0.6766356825828552,
+      "eval_runtime": 0.6417,
+      "eval_samples_per_second": 635.782,
+      "eval_steps_per_second": 1.558,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.004114523064345121,
+      "learning_rate": 0.0002868969542575783,
+      "loss": 0.0136,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9157691245512289,
+      "eval_f1": 0.9295774647887324,
+      "eval_loss": 0.6465615630149841,
+      "eval_runtime": 0.6381,
+      "eval_samples_per_second": 639.399,
+      "eval_steps_per_second": 1.567,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 0.18351468443870544,
+      "learning_rate": 0.00022384750878852333,
+      "loss": 0.0069,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9111628637220013,
+      "eval_f1": 0.9252669039145908,
+      "eval_loss": 0.680911123752594,
+      "eval_runtime": 0.6404,
+      "eval_samples_per_second": 637.054,
+      "eval_steps_per_second": 1.561,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.019911231473088264,
+      "learning_rate": 0.00016774265232874353,
+      "loss": 0.0088,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.715298056602478,
+      "eval_runtime": 0.641,
+      "eval_samples_per_second": 636.477,
+      "eval_steps_per_second": 1.56,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.0013759591383859515,
+      "learning_rate": 0.00011908438052207082,
+      "loss": 0.0075,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9133428238080312,
+      "eval_f1": 0.9271758436944938,
+      "eval_loss": 0.7201849222183228,
+      "eval_runtime": 0.6457,
+      "eval_samples_per_second": 631.841,
+      "eval_steps_per_second": 1.549,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 10.307768821716309,
+      "learning_rate": 7.830806103584498e-05,
+      "loss": 0.0098,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9133428238080312,
+      "eval_f1": 0.9271758436944938,
+      "eval_loss": 0.7218621969223022,
+      "eval_runtime": 0.6402,
+      "eval_samples_per_second": 637.321,
+      "eval_steps_per_second": 1.562,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 0.003199663246050477,
+      "learning_rate": 4.577853812857102e-05,
+      "loss": 0.003,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9112953692115144,
+      "eval_f1": 0.925531914893617,
+      "eval_loss": 0.7268513441085815,
+      "eval_runtime": 0.6394,
+      "eval_samples_per_second": 638.09,
+      "eval_steps_per_second": 1.564,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.007014700211584568,
+      "learning_rate": 2.178686822255904e-05,
+      "loss": 0.006,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9156447031109264,
+      "eval_f1": 0.9293286219081273,
+      "eval_loss": 0.7328526377677917,
+      "eval_runtime": 0.6433,
+      "eval_samples_per_second": 634.243,
+      "eval_steps_per_second": 1.555,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.006719864904880524,
+      "learning_rate": 6.547715689861789e-06,
+      "loss": 0.002,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9156447031109264,
+      "eval_f1": 0.9293286219081273,
+      "eval_loss": 0.735953688621521,
+      "eval_runtime": 0.6447,
+      "eval_samples_per_second": 632.849,
+      "eval_steps_per_second": 1.551,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.008782410994172096,
+      "learning_rate": 1.97432152599486e-07,
+      "loss": 0.0049,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9156447031109264,
+      "eval_f1": 0.9293286219081273,
+      "eval_loss": 0.7358721494674683,
+      "eval_runtime": 0.6421,
+      "eval_samples_per_second": 635.378,
+      "eval_steps_per_second": 1.557,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.08607926879240119,
+      "train_runtime": 846.8537,
+      "train_samples_per_second": 129.94,
+      "train_steps_per_second": 4.074
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.83610838283264e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

nlu/glue_exp/mrpc/2dr0.15,mlr5e-04,clr2e-03,ep=30.0t=18d21h42m46/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": false,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "value_proj",
+    "output.dense",
+    "intermediate.dense",
+    "attention.output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/2dr0.15,mlr5e-04,clr2e-03,ep=30.0t=18d21h42m46/ft/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

nlu/glue_exp/mrpc/2dr0.15,mlr5e-04,clr2e-03,ep=30.0t=18d21h42m46/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": true,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "value_proj",
+    "output.dense",
+    "intermediate.dense",
+    "attention.output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/2dr0.15,mlr5e-04,clr2e-03,ep=30.0t=18d21h42m46/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f1c3c1ea9f35f09e385b1c8a64610361c9803fd990bbd7537087c3191da820
+size 7449859

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	0
+5	1
+6	0
+7	0
+8	1
+9	0
+10	1
+11	1
+12	1
+13	0
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	1
+22	1
+23	1
+24	0
+25	1
+26	1
+27	1
+28	0
+29	1
+30	1
+31	0
+32	0
+33	0
+34	0
+35	0
+36	1
+37	1
+38	0
+39	1
+40	1
+41	1
+42	0
+43	1
+44	1
+45	0
+46	0
+47	0
+48	1
+49	1
+50	1
+51	1
+52	1
+53	1
+54	0
+55	1
+56	1
+57	1
+58	0
+59	1
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	1
+69	1
+70	0
+71	1
+72	0
+73	0
+74	1
+75	0
+76	1
+77	1
+78	0
+79	0
+80	0
+81	0
+82	1
+83	0
+84	0
+85	0
+86	1
+87	1
+88	0
+89	1
+90	0
+91	0
+92	1
+93	1
+94	1
+95	0
+96	0
+97	1
+98	0
+99	1
+100	1
+101	1
+102	1
+103	1
+104	1
+105	0
+106	0
+107	1
+108	1
+109	1
+110	1
+111	0
+112	0
+113	1
+114	1
+115	0
+116	0
+117	0
+118	1
+119	1
+120	1
+121	0
+122	1
+123	1
+124	1
+125	1
+126	1
+127	1
+128	0
+129	1
+130	0
+131	1
+132	1
+133	0
+134	1
+135	0
+136	1
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	0
+147	1
+148	1
+149	1
+150	1
+151	1
+152	0
+153	0
+154	1
+155	1
+156	1
+157	1
+158	0
+159	1
+160	1
+161	1
+162	1
+163	0
+164	0
+165	1
+166	1
+167	1
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	0
+175	1
+176	1
+177	0
+178	1
+179	1
+180	0
+181	0
+182	1
+183	1
+184	1
+185	1
+186	0
+187	0
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	0
+195	0
+196	0
+197	1
+198	1
+199	1
+200	0
+201	1
+202	1
+203	1
+204	1
+205	0
+206	0
+207	1
+208	0
+209	1
+210	0
+211	0
+212	1
+213	0
+214	1
+215	0
+216	1
+217	1
+218	1
+219	1
+220	1
+221	0
+222	1
+223	0
+224	1
+225	1
+226	1
+227	1
+228	0
+229	0
+230	1
+231	1
+232	1
+233	1
+234	0
+235	1
+236	1
+237	1
+238	0
+239	0
+240	1
+241	1
+242	0
+243	1
+244	0
+245	1
+246	1
+247	0
+248	1
+249	0
+250	1
+251	0
+252	0
+253	1
+254	1
+255	1
+256	1
+257	0
+258	1
+259	1
+260	1
+261	1
+262	1
+263	1
+264	0
+265	1
+266	1
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	0
+276	1
+277	1
+278	0
+279	1
+280	1
+281	0
+282	1
+283	1
+284	1
+285	0
+286	1
+287	0
+288	0
+289	0
+290	0
+291	1
+292	1
+293	1
+294	1
+295	0
+296	0
+297	0
+298	1
+299	0
+300	1
+301	1
+302	0
+303	1
+304	1
+305	0
+306	1
+307	1
+308	0
+309	1
+310	1
+311	1
+312	0
+313	1
+314	1
+315	1
+316	1
+317	1
+318	1
+319	0
+320	1
+321	1
+322	1
+323	1
+324	1
+325	1
+326	1
+327	0
+328	1
+329	0
+330	0
+331	1
+332	1
+333	1
+334	1
+335	0
+336	1
+337	1
+338	1
+339	1
+340	1
+341	1
+342	1
+343	1
+344	0
+345	1
+346	0
+347	0
+348	0
+349	0
+350	1
+351	0
+352	0
+353	1
+354	0
+355	0
+356	0
+357	0
+358	1
+359	0
+360	0
+361	0
+362	0
+363	1
+364	0
+365	1
+366	0
+367	0
+368	0
+369	0
+370	0
+371	1
+372	1
+373	1
+374	1
+375	1
+376	0
+377	1
+378	0
+379	0
+380	1
+381	1
+382	1
+383	1
+384	1
+385	1
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	0
+395	1
+396	1
+397	1
+398	0
+399	0
+400	1
+401	1
+402	1
+403	1
+404	1
+405	0
+406	0
+407	1
+408	1
+409	0
+410	0
+411	0
+412	1
+413	1
+414	1
+415	0
+416	0
+417	1
+418	1
+419	1
+420	1
+421	1
+422	1
+423	1
+424	0
+425	0
+426	0
+427	1
+428	0
+429	1
+430	0
+431	1
+432	1
+433	1
+434	1
+435	1
+436	1
+437	0
+438	1
+439	0
+440	0
+441	0
+442	1
+443	1
+444	1
+445	1
+446	1
+447	1
+448	1
+449	1
+450	0
+451	1
+452	1
+453	1
+454	1
+455	1
+456	1
+457	1
+458	0
+459	1
+460	1
+461	1
+462	1
+463	0
+464	0
+465	0
+466	1
+467	1
+468	1
+469	1
+470	0
+471	1
+472	1
+473	1
+474	1
+475	1
+476	1
+477	1
+478	1
+479	1
+480	0
+481	1
+482	1
+483	1
+484	0
+485	1
+486	1
+487	1
+488	1
+489	1
+490	1
+491	0
+492	1
+493	1
+494	0
+495	1
+496	0
+497	1
+498	0
+499	1
+500	1
+501	1
+502	1
+503	0
+504	1
+505	1
+506	0
+507	1
+508	0
+509	0
+510	1
+511	1
+512	0
+513	1
+514	1
+515	1
+516	1
+517	1
+518	1
+519	1
+520	1
+521	1
+522	1
+523	1
+524	1
+525	1
+526	0
+527	1
+528	1
+529	1
+530	1
+531	1
+532	1
+533	0
+534	1
+535	1
+536	1
+537	1
+538	0
+539	1
+540	1
+541	0
+542	1
+543	1
+544	1
+545	1
+546	1
+547	0
+548	0
+549	0
+550	1
+551	1
+552	0
+553	1
+554	0
+555	1
+556	0
+557	1
+558	1
+559	1
+560	1
+561	0
+562	0
+563	0
+564	0
+565	1
+566	1
+567	1
+568	0
+569	0
+570	0
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	1
+578	1
+579	0
+580	1
+581	1
+582	1
+583	1
+584	0
+585	1
+586	0
+587	1
+588	1
+589	1
+590	1
+591	1
+592	1
+593	0
+594	0
+595	1
+596	1
+597	0
+598	1
+599	1
+600	1
+601	1
+602	1
+603	1
+604	1
+605	1
+606	1
+607	0
+608	0
+609	1
+610	1
+611	1
+612	0
+613	1
+614	1
+615	1
+616	1
+617	0
+618	1
+619	1
+620	1
+621	0
+622	0
+623	0
+624	1
+625	0
+626	1
+627	1
+628	0
+629	1
+630	1
+631	1
+632	1
+633	0
+634	0
+635	1
+636	0
+637	1
+638	1
+639	1
+640	1
+641	1
+642	1
+643	1
+644	1
+645	0
+646	1
+647	1
+648	1
+649	1
+650	1
+651	0
+652	0
+653	1
+654	1
+655	1
+656	1
+657	1
+658	1
+659	1
+660	1
+661	1
+662	1
+663	1
+664	1
+665	0
+666	1
+667	0
+668	0
+669	0
+670	1
+671	1
+672	0
+673	1
+674	1
+675	0
+676	1
+677	1
+678	1
+679	1
+680	0
+681	1
+682	0
+683	1
+684	0
+685	0
+686	1
+687	0
+688	0
+689	1
+690	1
+691	1
+692	0
+693	1
+694	1
+695	0
+696	1
+697	1
+698	0
+699	1
+700	0
+701	1
+702	1
+703	1
+704	1
+705	0
+706	0
+707	0
+708	1
+709	1
+710	0
+711	0
+712	1
+713	1
+714	1
+715	1
+716	1
+717	0
+718	0
+719	1
+720	1
+721	1
+722	0
+723	0
+724	1
+725	1
+726	1
+727	1
+728	1
+729	1
+730	1
+731	1
+732	1
+733	0
+734	1
+735	1
+736	1
+737	1
+738	1
+739	1
+740	1
+741	1
+742	1
+743	1
+744	1
+745	0
+746	1
+747	0
+748	1
+749	0
+750	1
+751	1
+752	1
+753	0
+754	1
+755	1
+756	1
+757	1
+758	1
+759	1
+760	1
+761	1
+762	1
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	1
+770	1
+771	0
+772	1
+773	1
+774	1
+775	1
+776	1
+777	1
+778	0
+779	1
+780	0
+781	1
+782	1
+783	0
+784	1
+785	1
+786	1
+787	0
+788	1
+789	1
+790	1
+791	1
+792	1
+793	1
+794	1
+795	1
+796	0
+797	0
+798	1
+799	0
+800	0
+801	0
+802	1
+803	1
+804	0
+805	0
+806	1
+807	0
+808	1
+809	0
+810	1
+811	1
+812	0
+813	1
+814	0
+815	1
+816	1
+817	0
+818	0
+819	1
+820	0
+821	0
+822	1
+823	1
+824	1
+825	1
+826	1
+827	0
+828	0
+829	1
+830	1
+831	1
+832	1
+833	0
+834	1
+835	0
+836	1
+837	1
+838	1
+839	0
+840	0
+841	0
+842	1
+843	1
+844	0
+845	1
+846	1
+847	1
+848	0
+849	1
+850	0
+851	0
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	1
+861	1
+862	1
+863	1
+864	1
+865	0
+866	0
+867	1
+868	1
+869	1
+870	1
+871	0
+872	1
+873	1
+874	0
+875	0
+876	1
+877	0
+878	0
+879	1
+880	1
+881	1
+882	1
+883	1
+884	1
+885	1
+886	1
+887	1
+888	0
+889	1
+890	1
+891	1
+892	0
+893	1
+894	0
+895	0
+896	0
+897	1
+898	1
+899	1
+900	1
+901	1
+902	0
+903	1
+904	1
+905	1
+906	1
+907	1
+908	1
+909	1
+910	0
+911	1
+912	0
+913	0
+914	1
+915	1
+916	1
+917	1
+918	0
+919	1
+920	1
+921	1
+922	1
+923	1
+924	1
+925	1
+926	1
+927	1
+928	1
+929	1
+930	1
+931	0
+932	0
+933	0
+934	0
+935	1
+936	1
+937	0
+938	1
+939	1
+940	1
+941	1
+942	0
+943	1
+944	1
+945	1
+946	1
+947	1
+948	1
+949	1
+950	0
+951	1
+952	1
+953	1
+954	1
+955	1
+956	1
+957	1
+958	1
+959	1
+960	1
+961	1
+962	1
+963	0
+964	0
+965	1
+966	1
+967	1
+968	1
+969	1
+970	1
+971	0
+972	0
+973	1
+974	1
+975	0
+976	1
+977	1
+978	1
+979	1
+980	1
+981	1
+982	0
+983	1
+984	0
+985	1
+986	1
+987	1
+988	1
+989	1
+990	0
+991	1
+992	1
+993	1
+994	0
+995	1
+996	1
+997	1
+998	1
+999	1
+1000	0
+1001	1
+1002	0
+1003	0
+1004	1
+1005	0
+1006	1
+1007	1
+1008	1
+1009	0
+1010	1
+1011	0
+1012	1
+1013	1
+1014	1
+1015	1
+1016	1
+1017	1
+1018	1
+1019	1
+1020	1
+1021	1
+1022	1
+1023	0
+1024	1
+1025	0
+1026	0
+1027	1
+1028	0
+1029	1
+1030	0
+1031	1
+1032	1
+1033	0
+1034	1
+1035	0
+1036	1
+1037	1
+1038	1
+1039	1
+1040	0
+1041	1
+1042	0
+1043	0
+1044	1
+1045	1
+1046	0
+1047	1
+1048	1
+1049	1
+1050	1
+1051	1
+1052	0
+1053	1
+1054	0
+1055	1
+1056	1
+1057	1
+1058	1
+1059	1
+1060	0
+1061	1
+1062	1
+1063	1
+1064	1
+1065	1
+1066	1
+1067	1
+1068	0
+1069	1
+1070	1
+1071	0
+1072	1
+1073	1
+1074	1
+1075	1
+1076	1
+1077	1
+1078	1
+1079	1
+1080	0
+1081	0
+1082	1
+1083	1
+1084	1
+1085	1
+1086	1
+1087	1
+1088	1
+1089	1
+1090	1
+1091	0
+1092	1
+1093	1
+1094	1
+1095	1
+1096	1
+1097	1
+1098	1
+1099	1
+1100	1
+1101	1
+1102	0
+1103	1
+1104	1
+1105	0
+1106	1
+1107	0
+1108	1
+1109	1
+1110	0
+1111	1
+1112	0
+1113	0
+1114	1
+1115	1
+1116	0
+1117	1
+1118	1
+1119	1
+1120	0
+1121	0
+1122	1
+1123	1
+1124	0
+1125	1
+1126	0
+1127	0
+1128	1
+1129	1
+1130	1
+1131	1
+1132	0
+1133	1
+1134	0
+1135	1
+1136	0
+1137	1
+1138	0
+1139	0
+1140	1
+1141	1
+1142	1
+1143	1
+1144	0
+1145	1
+1146	1
+1147	0
+1148	1
+1149	1
+1150	0
+1151	1
+1152	1
+1153	0
+1154	0
+1155	1
+1156	1
+1157	1
+1158	0
+1159	1
+1160	0
+1161	0
+1162	1
+1163	1
+1164	1
+1165	0
+1166	0
+1167	1
+1168	1
+1169	1
+1170	1
+1171	1
+1172	1
+1173	1
+1174	1
+1175	0
+1176	1
+1177	1
+1178	1
+1179	1
+1180	1
+1181	1
+1182	1
+1183	1
+1184	1
+1185	1
+1186	0
+1187	1
+1188	1
+1189	0
+1190	1
+1191	0
+1192	1
+1193	1
+1194	1
+1195	1
+1196	0
+1197	1
+1198	0
+1199	1
+1200	0
+1201	1
+1202	1
+1203	1
+1204	0
+1205	1
+1206	0
+1207	0
+1208	1
+1209	1
+1210	1
+1211	1
+1212	1
+1213	1
+1214	1
+1215	1
+1216	1
+1217	1
+1218	1
+1219	1
+1220	1
+1221	0
+1222	1
+1223	1
+1224	0
+1225	1
+1226	0
+1227	1
+1228	1
+1229	1
+1230	1
+1231	0
+1232	1
+1233	1
+1234	1
+1235	1
+1236	1
+1237	1
+1238	1
+1239	1
+1240	1
+1241	0
+1242	1
+1243	1
+1244	1
+1245	1
+1246	0
+1247	1
+1248	1
+1249	1
+1250	1
+1251	1
+1252	1
+1253	1
+1254	1
+1255	1
+1256	1
+1257	1
+1258	0
+1259	1
+1260	1
+1261	1
+1262	1
+1263	1
+1264	1
+1265	1
+1266	1
+1267	1
+1268	1
+1269	1
+1270	1
+1271	1
+1272	0
+1273	0
+1274	0
+1275	1
+1276	1
+1277	1
+1278	1
+1279	0
+1280	1
+1281	1
+1282	1
+1283	0
+1284	1
+1285	1
+1286	1
+1287	0
+1288	1
+1289	1
+1290	1
+1291	1
+1292	0
+1293	0
+1294	0
+1295	1
+1296	1
+1297	1
+1298	1
+1299	1
+1300	0
+1301	1
+1302	1
+1303	1
+1304	1
+1305	0
+1306	0
+1307	1
+1308	1
+1309	0
+1310	1
+1311	1
+1312	1
+1313	1
+1314	1
+1315	1
+1316	1
+1317	1
+1318	0
+1319	1
+1320	1
+1321	0
+1322	1
+1323	1
+1324	1
+1325	1
+1326	0
+1327	1
+1328	1
+1329	0
+1330	0
+1331	0
+1332	1
+1333	0
+1334	1
+1335	0
+1336	0
+1337	0
+1338	0
+1339	1
+1340	0
+1341	1
+1342	0
+1343	1
+1344	1
+1345	1
+1346	1
+1347	1
+1348	1
+1349	1
+1350	1
+1351	1
+1352	1
+1353	0
+1354	0
+1355	0
+1356	1
+1357	1
+1358	0
+1359	1
+1360	1
+1361	1
+1362	1
+1363	0
+1364	1
+1365	1
+1366	0
+1367	0
+1368	1
+1369	1
+1370	0
+1371	0
+1372	1
+1373	0
+1374	0
+1375	1
+1376	1
+1377	1
+1378	1
+1379	1
+1380	1
+1381	1
+1382	1
+1383	1
+1384	1
+1385	1
+1386	0
+1387	1
+1388	1
+1389	1
+1390	1
+1391	0
+1392	0
+1393	1
+1394	1
+1395	1
+1396	0
+1397	1
+1398	1
+1399	1
+1400	0
+1401	0
+1402	1
+1403	0
+1404	1
+1405	0
+1406	1
+1407	1
+1408	1
+1409	1
+1410	0
+1411	0
+1412	1
+1413	1
+1414	0
+1415	1
+1416	1
+1417	1
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	1
+1428	0
+1429	1
+1430	0
+1431	1
+1432	1
+1433	0
+1434	1
+1435	0
+1436	1
+1437	1
+1438	1
+1439	1
+1440	1
+1441	1
+1442	1
+1443	0
+1444	0
+1445	1
+1446	1
+1447	1
+1448	0
+1449	1
+1450	1
+1451	0
+1452	1
+1453	1
+1454	1
+1455	1
+1456	1
+1457	1
+1458	1
+1459	1
+1460	1
+1461	1
+1462	1
+1463	0
+1464	1
+1465	1
+1466	1
+1467	0
+1468	1
+1469	0
+1470	1
+1471	1
+1472	0
+1473	0
+1474	1
+1475	1
+1476	1
+1477	1
+1478	0
+1479	0
+1480	1
+1481	0
+1482	1
+1483	0
+1484	0
+1485	1
+1486	0
+1487	0
+1488	1
+1489	1
+1490	0
+1491	1
+1492	1
+1493	0
+1494	0
+1495	1
+1496	1
+1497	0
+1498	0
+1499	0
+1500	1
+1501	1
+1502	1
+1503	0
+1504	1
+1505	1
+1506	1
+1507	1
+1508	0
+1509	0
+1510	1
+1511	1
+1512	0
+1513	1
+1514	0
+1515	1
+1516	1
+1517	1
+1518	0
+1519	0
+1520	0
+1521	0
+1522	0
+1523	1
+1524	1
+1525	1
+1526	1
+1527	1
+1528	0
+1529	1
+1530	1
+1531	1
+1532	1
+1533	1
+1534	1
+1535	0
+1536	1
+1537	0
+1538	1
+1539	0
+1540	0
+1541	1
+1542	0
+1543	1
+1544	0
+1545	0
+1546	1
+1547	0
+1548	1
+1549	1
+1550	1
+1551	0
+1552	0
+1553	0
+1554	1
+1555	1
+1556	0
+1557	1
+1558	0
+1559	1
+1560	1
+1561	0
+1562	1
+1563	1
+1564	0
+1565	0
+1566	1
+1567	1
+1568	1
+1569	1
+1570	1
+1571	1
+1572	1
+1573	0
+1574	1
+1575	1
+1576	1
+1577	0
+1578	0
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	1
+1586	0
+1587	1
+1588	1
+1589	1
+1590	0
+1591	1
+1592	1
+1593	0
+1594	1
+1595	1
+1596	1
+1597	0
+1598	1
+1599	0
+1600	0
+1601	1
+1602	1
+1603	1
+1604	1
+1605	0
+1606	1
+1607	1
+1608	0
+1609	1
+1610	0
+1611	1
+1612	1
+1613	1
+1614	1
+1615	1
+1616	1
+1617	0
+1618	1
+1619	1
+1620	0
+1621	0
+1622	1
+1623	1
+1624	0
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	0
+1632	1
+1633	1
+1634	1
+1635	1
+1636	1
+1637	1
+1638	0
+1639	1
+1640	0
+1641	1
+1642	0
+1643	1
+1644	1
+1645	1
+1646	1
+1647	0
+1648	1
+1649	1
+1650	1
+1651	0
+1652	0
+1653	1
+1654	0
+1655	1
+1656	0
+1657	0
+1658	1
+1659	1
+1660	0
+1661	0
+1662	0
+1663	1
+1664	0
+1665	0
+1666	0
+1667	1
+1668	0
+1669	1
+1670	1
+1671	0
+1672	1
+1673	1
+1674	1
+1675	1
+1676	1
+1677	1
+1678	1
+1679	1
+1680	0
+1681	1
+1682	1
+1683	0
+1684	1
+1685	1
+1686	0
+1687	0
+1688	1
+1689	0
+1690	1
+1691	0
+1692	1
+1693	1
+1694	1
+1695	1
+1696	1
+1697	0
+1698	0
+1699	1
+1700	1
+1701	1
+1702	0
+1703	1
+1704	0
+1705	1
+1706	0
+1707	0
+1708	1
+1709	1
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	0
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9219134999132397,
+    "eval_f1": 0.9345132743362832,
+    "eval_loss": 0.2595154941082001,
+    "eval_runtime": 0.5898,
+    "eval_samples": 408,
+    "eval_samples_per_second": 691.796,
+    "eval_steps_per_second": 1.696
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9219134999132397,
+    "eval_f1": 0.9345132743362832,
+    "eval_loss": 0.2595154941082001,
+    "eval_runtime": 0.5898,
+    "eval_samples": 408,
+    "eval_samples_per_second": 691.796,
+    "eval_steps_per_second": 1.696
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.1,
+  "inference_mode": false,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "output.dense",
+    "intermediate.dense",
+    "attention.output.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.1,
+  "inference_mode": true,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "query_proj",
+    "key_proj",
+    "output.dense",
+    "intermediate.dense",
+    "attention.output.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47930f860d8be39f2c438c809db185f97f5606731066f780d7f2159bfbda002
+size 7449859

nlu/glue_exp/mrpc/6dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.9093137254901961,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.1,mlr1e-04,clr1e-03,ep=30.0t=18d22h55m35/checkpoint-400",
+  "epoch": 30.0,
+  "eval_steps": 100,
+  "global_step": 3450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.888801097869873,
+      "learning_rate": 0.00099,
+      "loss": 0.6185,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.7107843137254902,
+      "eval_combined_score": 0.7665367351759982,
+      "eval_f1": 0.822289156626506,
+      "eval_loss": 0.5315333604812622,
+      "eval_runtime": 0.7399,
+      "eval_samples_per_second": 551.463,
+      "eval_steps_per_second": 1.352,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 4.414052486419678,
+      "learning_rate": 0.0009978076174307112,
+      "loss": 0.4311,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8406862745098039,
+      "eval_combined_score": 0.8647875816993464,
+      "eval_f1": 0.8888888888888888,
+      "eval_loss": 0.3522834777832031,
+      "eval_runtime": 0.6358,
+      "eval_samples_per_second": 641.674,
+      "eval_steps_per_second": 1.573,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.967780351638794,
+      "learning_rate": 0.0009911613477663372,
+      "loss": 0.3567,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9095183328164307,
+      "eval_f1": 0.9244288224956063,
+      "eval_loss": 0.2889207899570465,
+      "eval_runtime": 0.64,
+      "eval_samples_per_second": 637.536,
+      "eval_steps_per_second": 1.563,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 3.9725353717803955,
+      "learning_rate": 0.0009801204343481893,
+      "loss": 0.3204,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9219134999132397,
+      "eval_f1": 0.9345132743362832,
+      "eval_loss": 0.2595154941082001,
+      "eval_runtime": 0.638,
+      "eval_samples_per_second": 639.458,
+      "eval_steps_per_second": 1.567,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 2.625113010406494,
+      "learning_rate": 0.0009647836652454211,
+      "loss": 0.2895,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9116873065015481,
+      "eval_f1": 0.9263157894736842,
+      "eval_loss": 0.24875514209270477,
+      "eval_runtime": 0.643,
+      "eval_samples_per_second": 634.557,
+      "eval_steps_per_second": 1.555,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 3.1335086822509766,
+      "learning_rate": 0.000945288265499961,
+      "loss": 0.2422,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9125705076551169,
+      "eval_f1": 0.928082191780822,
+      "eval_loss": 0.2661508619785309,
+      "eval_runtime": 0.5898,
+      "eval_samples_per_second": 691.703,
+      "eval_steps_per_second": 1.695,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 6.072702407836914,
+      "learning_rate": 0.0009218086693117072,
+      "loss": 0.2161,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8830396208070005,
+      "eval_f1": 0.9057851239669421,
+      "eval_loss": 0.5397763848304749,
+      "eval_runtime": 0.5899,
+      "eval_samples_per_second": 691.623,
+      "eval_steps_per_second": 1.695,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 6.110560417175293,
+      "learning_rate": 0.0008945549592964825,
+      "loss": 0.2059,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9050299323269131,
+      "eval_f1": 0.9203539823008849,
+      "eval_loss": 0.2758274972438812,
+      "eval_runtime": 0.5882,
+      "eval_samples_per_second": 693.613,
+      "eval_steps_per_second": 1.7,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 3.184335470199585,
+      "learning_rate": 0.000863770986781413,
+      "loss": 0.1761,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.29342126846313477,
+      "eval_runtime": 0.589,
+      "eval_samples_per_second": 692.754,
+      "eval_steps_per_second": 1.698,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.3413187265396118,
+      "learning_rate": 0.0008297321899563005,
+      "loss": 0.153,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9112953692115144,
+      "eval_f1": 0.925531914893617,
+      "eval_loss": 0.3068132698535919,
+      "eval_runtime": 0.5908,
+      "eval_samples_per_second": 690.623,
+      "eval_steps_per_second": 1.693,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 4.26575231552124,
+      "learning_rate": 0.0007927431294029863,
+      "loss": 0.1409,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9140800231531727,
+      "eval_f1": 0.9261992619926199,
+      "eval_loss": 0.3988274931907654,
+      "eval_runtime": 0.5876,
+      "eval_samples_per_second": 694.311,
+      "eval_steps_per_second": 1.702,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 6.83341121673584,
+      "learning_rate": 0.0007531347630534368,
+      "loss": 0.1217,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.39595237374305725,
+      "eval_runtime": 0.5912,
+      "eval_samples_per_second": 690.094,
+      "eval_steps_per_second": 1.691,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 0.6858878135681152,
+      "learning_rate": 0.0007112614849587449,
+      "loss": 0.1018,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9077509052401449,
+      "eval_f1": 0.9233449477351916,
+      "eval_loss": 0.5210728645324707,
+      "eval_runtime": 0.5898,
+      "eval_samples_per_second": 691.751,
+      "eval_steps_per_second": 1.695,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 0.46270978450775146,
+      "learning_rate": 0.0006674979543645248,
+      "loss": 0.0907,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9057225063938619,
+      "eval_f1": 0.9217391304347826,
+      "eval_loss": 0.3946845829486847,
+      "eval_runtime": 0.5902,
+      "eval_samples_per_second": 691.24,
+      "eval_steps_per_second": 1.694,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 4.69882869720459,
+      "learning_rate": 0.000622235743464402,
+      "loss": 0.0914,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.38392478227615356,
+      "eval_runtime": 0.5894,
+      "eval_samples_per_second": 692.224,
+      "eval_steps_per_second": 1.697,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 2.134861469268799,
+      "learning_rate": 0.0005758798338256736,
+      "loss": 0.0728,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9051704014939308,
+      "eval_f1": 0.9206349206349206,
+      "eval_loss": 0.5737729072570801,
+      "eval_runtime": 0.5907,
+      "eval_samples_per_second": 690.651,
+      "eval_steps_per_second": 1.693,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 9.352970123291016,
+      "learning_rate": 0.0005288449928352095,
+      "loss": 0.0603,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9089795008912656,
+      "eval_f1": 0.9233511586452763,
+      "eval_loss": 0.5365409255027771,
+      "eval_runtime": 0.5876,
+      "eval_samples_per_second": 694.305,
+      "eval_steps_per_second": 1.702,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 0.3746854364871979,
+      "learning_rate": 0.00048155206258717795,
+      "loss": 0.0587,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9158926728586172,
+      "eval_f1": 0.9298245614035088,
+      "eval_loss": 0.5017966628074646,
+      "eval_runtime": 0.5883,
+      "eval_samples_per_second": 693.539,
+      "eval_steps_per_second": 1.7,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.7553677558898926,
+      "learning_rate": 0.00043442419441760554,
+      "loss": 0.0534,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9153932035447632,
+      "eval_f1": 0.9288256227758007,
+      "eval_loss": 0.5661107897758484,
+      "eval_runtime": 0.5901,
+      "eval_samples_per_second": 691.376,
+      "eval_steps_per_second": 1.695,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.019641593098640442,
+      "learning_rate": 0.0003878830627771025,
+      "loss": 0.044,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.906651908075058,
+      "eval_f1": 0.921146953405018,
+      "eval_loss": 0.6302050352096558,
+      "eval_runtime": 0.5908,
+      "eval_samples_per_second": 690.615,
+      "eval_steps_per_second": 1.693,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.2956579923629761,
+      "learning_rate": 0.00034234509231794997,
+      "loss": 0.0515,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9074819401444789,
+      "eval_f1": 0.9228070175438596,
+      "eval_loss": 0.5459933280944824,
+      "eval_runtime": 0.5888,
+      "eval_samples_per_second": 692.977,
+      "eval_steps_per_second": 1.698,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 8.15996265411377,
+      "learning_rate": 0.00029821773195351986,
+      "loss": 0.0473,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9067927170868347,
+      "eval_f1": 0.9214285714285714,
+      "eval_loss": 0.5104790925979614,
+      "eval_runtime": 0.5884,
+      "eval_samples_per_second": 693.428,
+      "eval_steps_per_second": 1.7,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.006465388927608728,
+      "learning_rate": 0.00025589580922771014,
+      "loss": 0.0331,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.910759627592044,
+      "eval_f1": 0.9244604316546763,
+      "eval_loss": 0.6315487027168274,
+      "eval_runtime": 0.5913,
+      "eval_samples_per_second": 690.018,
+      "eval_steps_per_second": 1.691,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 30.930089950561523,
+      "learning_rate": 0.00021575799761350595,
+      "loss": 0.0328,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9085651828298887,
+      "eval_f1": 0.9225225225225225,
+      "eval_loss": 0.6286695599555969,
+      "eval_runtime": 0.5886,
+      "eval_samples_per_second": 693.122,
+      "eval_steps_per_second": 1.699,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.47196853160858154,
+      "learning_rate": 0.00017816342834935385,
+      "loss": 0.024,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9217971824609061,
+      "eval_f1": 0.9342806394316163,
+      "eval_loss": 0.5589781403541565,
+      "eval_runtime": 0.5901,
+      "eval_samples_per_second": 691.398,
+      "eval_steps_per_second": 1.695,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.01034663338214159,
+      "learning_rate": 0.00014344847712878915,
+      "loss": 0.0343,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9129505931636568,
+      "eval_f1": 0.926391382405745,
+      "eval_loss": 0.6613860726356506,
+      "eval_runtime": 0.5893,
+      "eval_samples_per_second": 692.302,
+      "eval_steps_per_second": 1.697,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 4.391206741333008,
+      "learning_rate": 0.00011192375439426166,
+      "loss": 0.0376,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.6102422475814819,
+      "eval_runtime": 0.5879,
+      "eval_samples_per_second": 693.969,
+      "eval_steps_per_second": 1.701,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.02129713073372841,
+      "learning_rate": 8.387132616437177e-05,
+      "loss": 0.0182,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9088423831070891,
+      "eval_f1": 0.9230769230769231,
+      "eval_loss": 0.6355468034744263,
+      "eval_runtime": 0.5883,
+      "eval_samples_per_second": 693.533,
+      "eval_steps_per_second": 1.7,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.10591012984514236,
+      "learning_rate": 5.954219026103541e-05,
+      "loss": 0.0199,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.648102879524231,
+      "eval_runtime": 0.5904,
+      "eval_samples_per_second": 691.031,
+      "eval_steps_per_second": 1.694,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.7612121105194092,
+      "learning_rate": 3.915403051792249e-05,
+      "loss": 0.0159,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9067927170868347,
+      "eval_f1": 0.9214285714285714,
+      "eval_loss": 0.6390443444252014,
+      "eval_runtime": 0.5903,
+      "eval_samples_per_second": 691.183,
+      "eval_steps_per_second": 1.694,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 10.649272918701172,
+      "learning_rate": 2.288926906428551e-05,
+      "loss": 0.0293,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.6445656418800354,
+      "eval_runtime": 0.5881,
+      "eval_samples_per_second": 693.802,
+      "eval_steps_per_second": 1.7,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.10578522831201553,
+      "learning_rate": 1.089343411127952e-05,
+      "loss": 0.0155,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.6314123272895813,
+      "eval_runtime": 0.5881,
+      "eval_samples_per_second": 693.8,
+      "eval_steps_per_second": 1.7,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.03251971676945686,
+      "learning_rate": 3.2738578449308944e-06,
+      "loss": 0.0225,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.6310741305351257,
+      "eval_runtime": 0.5913,
+      "eval_samples_per_second": 690.021,
+      "eval_steps_per_second": 1.691,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.031257763504981995,
+      "learning_rate": 9.8716076299743e-08,
+      "loss": 0.0225,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9069325238992394,
+      "eval_f1": 0.9217081850533808,
+      "eval_loss": 0.6320057511329651,
+      "eval_runtime": 0.5902,
+      "eval_samples_per_second": 691.241,
+      "eval_steps_per_second": 1.694,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.1233423205735027,
+      "train_runtime": 750.3445,
+      "train_samples_per_second": 146.653,
+      "train_steps_per_second": 4.598
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.83610838283264e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	0
+5	1
+6	0
+7	0
+8	1
+9	0
+10	1
+11	1
+12	1
+13	0
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	1
+22	1
+23	1
+24	0
+25	1
+26	1
+27	1
+28	0
+29	1
+30	1
+31	0
+32	0
+33	0
+34	0
+35	0
+36	1
+37	1
+38	0
+39	1
+40	1
+41	1
+42	0
+43	1
+44	1
+45	0
+46	0
+47	0
+48	1
+49	1
+50	1
+51	1
+52	1
+53	1
+54	0
+55	1
+56	1
+57	1
+58	0
+59	1
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	1
+69	1
+70	0
+71	1
+72	0
+73	0
+74	1
+75	0
+76	1
+77	1
+78	0
+79	0
+80	0
+81	0
+82	1
+83	0
+84	0
+85	0
+86	1
+87	1
+88	0
+89	1
+90	0
+91	0
+92	1
+93	1
+94	1
+95	0
+96	0
+97	1
+98	0
+99	1
+100	1
+101	1
+102	1
+103	1
+104	1
+105	0
+106	0
+107	1
+108	1
+109	1
+110	1
+111	0
+112	0
+113	1
+114	1
+115	0
+116	0
+117	0
+118	1
+119	1
+120	1
+121	0
+122	1
+123	1
+124	1
+125	1
+126	1
+127	1
+128	0
+129	1
+130	0
+131	1
+132	1
+133	0
+134	1
+135	0
+136	1
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	0
+147	1
+148	1
+149	1
+150	1
+151	1
+152	0
+153	0
+154	1
+155	1
+156	1
+157	1
+158	0
+159	1
+160	1
+161	1
+162	1
+163	0
+164	0
+165	1
+166	1
+167	1
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	0
+175	1
+176	1
+177	0
+178	1
+179	1
+180	0
+181	0
+182	1
+183	1
+184	1
+185	1
+186	0
+187	0
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	0
+195	0
+196	0
+197	1
+198	1
+199	1
+200	0
+201	1
+202	1
+203	1
+204	1
+205	0
+206	0
+207	1
+208	0
+209	1
+210	0
+211	0
+212	1
+213	0
+214	1
+215	0
+216	1
+217	1
+218	1
+219	1
+220	1
+221	0
+222	1
+223	0
+224	1
+225	1
+226	1
+227	1
+228	0
+229	0
+230	1
+231	1
+232	1
+233	1
+234	0
+235	1
+236	1
+237	1
+238	0
+239	0
+240	1
+241	1
+242	0
+243	1
+244	0
+245	1
+246	1
+247	0
+248	1
+249	0
+250	1
+251	0
+252	0
+253	1
+254	1
+255	1
+256	1
+257	0
+258	1
+259	1
+260	1
+261	1
+262	1
+263	1
+264	0
+265	1
+266	1
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	0
+276	1
+277	1
+278	0
+279	1
+280	1
+281	0
+282	1
+283	1
+284	1
+285	0
+286	1
+287	0
+288	0
+289	0
+290	0
+291	1
+292	1
+293	1
+294	1
+295	0
+296	0
+297	0
+298	1
+299	0
+300	1
+301	1
+302	0
+303	1
+304	1
+305	0
+306	1
+307	1
+308	0
+309	1
+310	1
+311	1
+312	0
+313	1
+314	1
+315	1
+316	1
+317	1
+318	1
+319	0
+320	1
+321	1
+322	1
+323	1
+324	1
+325	1
+326	1
+327	0
+328	1
+329	0
+330	0
+331	1
+332	1
+333	1
+334	1
+335	0
+336	1
+337	1
+338	1
+339	1
+340	1
+341	1
+342	1
+343	1
+344	0
+345	1
+346	0
+347	0
+348	0
+349	0
+350	1
+351	0
+352	0
+353	1
+354	0
+355	0
+356	0
+357	0
+358	1
+359	0
+360	0
+361	0
+362	0
+363	1
+364	0
+365	1
+366	0
+367	0
+368	0
+369	0
+370	0
+371	1
+372	1
+373	1
+374	1
+375	1
+376	0
+377	1
+378	0
+379	0
+380	1
+381	1
+382	1
+383	1
+384	1
+385	1
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	0
+395	1
+396	1
+397	1
+398	0
+399	0
+400	1
+401	1
+402	1
+403	1
+404	1
+405	0
+406	0
+407	1
+408	1
+409	0
+410	0
+411	0
+412	1
+413	1
+414	1
+415	0
+416	0
+417	1
+418	1
+419	1
+420	1
+421	1
+422	1
+423	1
+424	0
+425	0
+426	0
+427	1
+428	0
+429	1
+430	0
+431	1
+432	1
+433	1
+434	1
+435	1
+436	1
+437	0
+438	1
+439	0
+440	0
+441	0
+442	1
+443	1
+444	1
+445	1
+446	1
+447	1
+448	1
+449	1
+450	0
+451	1
+452	1
+453	1
+454	1
+455	1
+456	1
+457	1
+458	0
+459	1
+460	1
+461	1
+462	1
+463	0
+464	0
+465	0
+466	1
+467	1
+468	1
+469	1
+470	0
+471	1
+472	1
+473	1
+474	1
+475	1
+476	1
+477	1
+478	1
+479	1
+480	0
+481	1
+482	1
+483	1
+484	0
+485	1
+486	1
+487	1
+488	1
+489	1
+490	1
+491	0
+492	1
+493	1
+494	0
+495	1
+496	0
+497	1
+498	0
+499	1
+500	1
+501	1
+502	1
+503	0
+504	1
+505	1
+506	0
+507	1
+508	0
+509	0
+510	1
+511	1
+512	0
+513	1
+514	1
+515	1
+516	1
+517	1
+518	1
+519	1
+520	1
+521	1
+522	1
+523	1
+524	1
+525	1
+526	0
+527	1
+528	1
+529	1
+530	1
+531	1
+532	1
+533	0
+534	1
+535	1
+536	1
+537	1
+538	0
+539	1
+540	1
+541	0
+542	1
+543	1
+544	1
+545	1
+546	1
+547	0
+548	0
+549	0
+550	1
+551	1
+552	0
+553	1
+554	0
+555	1
+556	0
+557	1
+558	1
+559	1
+560	1
+561	0
+562	0
+563	0
+564	0
+565	1
+566	1
+567	1
+568	0
+569	0
+570	0
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	1
+578	1
+579	0
+580	1
+581	1
+582	1
+583	1
+584	0
+585	1
+586	0
+587	1
+588	1
+589	1
+590	1
+591	1
+592	1
+593	0
+594	0
+595	1
+596	1
+597	0
+598	1
+599	1
+600	1
+601	1
+602	1
+603	1
+604	1
+605	1
+606	1
+607	0
+608	0
+609	1
+610	1
+611	1
+612	0
+613	1
+614	1
+615	1
+616	1
+617	0
+618	1
+619	1
+620	1
+621	0
+622	0
+623	0
+624	1
+625	0
+626	1
+627	1
+628	0
+629	1
+630	1
+631	1
+632	1
+633	0
+634	0
+635	1
+636	0
+637	1
+638	1
+639	1
+640	1
+641	1
+642	1
+643	1
+644	1
+645	0
+646	1
+647	1
+648	1
+649	1
+650	1
+651	0
+652	0
+653	1
+654	1
+655	1
+656	1
+657	1
+658	1
+659	1
+660	1
+661	1
+662	1
+663	1
+664	1
+665	0
+666	1
+667	0
+668	0
+669	0
+670	1
+671	1
+672	0
+673	1
+674	1
+675	0
+676	1
+677	1
+678	1
+679	1
+680	0
+681	1
+682	0
+683	1
+684	0
+685	0
+686	1
+687	0
+688	0
+689	1
+690	1
+691	1
+692	0
+693	1
+694	1
+695	0
+696	1
+697	1
+698	0
+699	1
+700	0
+701	1
+702	1
+703	1
+704	1
+705	0
+706	0
+707	0
+708	1
+709	1
+710	0
+711	0
+712	1
+713	1
+714	1
+715	1
+716	1
+717	0
+718	0
+719	1
+720	1
+721	1
+722	0
+723	0
+724	1
+725	1
+726	1
+727	1
+728	1
+729	1
+730	1
+731	1
+732	1
+733	0
+734	1
+735	1
+736	1
+737	1
+738	1
+739	1
+740	1
+741	1
+742	1
+743	1
+744	1
+745	0
+746	1
+747	0
+748	1
+749	0
+750	1
+751	1
+752	1
+753	0
+754	1
+755	1
+756	1
+757	1
+758	1
+759	1
+760	1
+761	1
+762	1
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	1
+770	1
+771	0
+772	1
+773	1
+774	1
+775	1
+776	1
+777	1
+778	0
+779	1
+780	0
+781	1
+782	1
+783	0
+784	1
+785	1
+786	1
+787	0
+788	1
+789	1
+790	1
+791	1
+792	1
+793	1
+794	1
+795	1
+796	0
+797	0
+798	1
+799	0
+800	0
+801	0
+802	1
+803	1
+804	0
+805	0
+806	1
+807	0
+808	1
+809	0
+810	1
+811	1
+812	0
+813	1
+814	0
+815	1
+816	1
+817	0
+818	0
+819	1
+820	0
+821	0
+822	1
+823	1
+824	1
+825	1
+826	1
+827	0
+828	0
+829	1
+830	1
+831	1
+832	1
+833	0
+834	1
+835	0
+836	1
+837	1
+838	1
+839	0
+840	0
+841	0
+842	1
+843	1
+844	0
+845	1
+846	1
+847	1
+848	0
+849	1
+850	0
+851	0
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	1
+861	1
+862	1
+863	1
+864	1
+865	0
+866	0
+867	1
+868	1
+869	1
+870	1
+871	0
+872	1
+873	1
+874	0
+875	0
+876	1
+877	0
+878	0
+879	1
+880	1
+881	1
+882	1
+883	1
+884	1
+885	1
+886	1
+887	1
+888	0
+889	1
+890	1
+891	1
+892	0
+893	1
+894	0
+895	0
+896	0
+897	1
+898	1
+899	1
+900	1
+901	1
+902	0
+903	1
+904	1
+905	1
+906	1
+907	1
+908	1
+909	1
+910	0
+911	1
+912	0
+913	0
+914	1
+915	1
+916	1
+917	1
+918	0
+919	1
+920	1
+921	1
+922	1
+923	1
+924	1
+925	1
+926	1
+927	1
+928	1
+929	1
+930	1
+931	0
+932	0
+933	0
+934	0
+935	1
+936	1
+937	0
+938	1
+939	1
+940	1
+941	1
+942	0
+943	1
+944	1
+945	1
+946	1
+947	1
+948	1
+949	1
+950	0
+951	1
+952	1
+953	1
+954	1
+955	1
+956	1
+957	1
+958	1
+959	1
+960	1
+961	1
+962	1
+963	0
+964	0
+965	1
+966	1
+967	1
+968	1
+969	1
+970	1
+971	0
+972	0
+973	1
+974	1
+975	0
+976	1
+977	1
+978	1
+979	1
+980	1
+981	1
+982	0
+983	1
+984	0
+985	1
+986	1
+987	1
+988	1
+989	1
+990	0
+991	1
+992	1
+993	1
+994	0
+995	1
+996	1
+997	1
+998	1
+999	1
+1000	0
+1001	1
+1002	0
+1003	0
+1004	1
+1005	0
+1006	1
+1007	1
+1008	1
+1009	0
+1010	1
+1011	0
+1012	1
+1013	1
+1014	1
+1015	1
+1016	1
+1017	1
+1018	1
+1019	1
+1020	1
+1021	1
+1022	1
+1023	0
+1024	1
+1025	0
+1026	0
+1027	1
+1028	0
+1029	1
+1030	0
+1031	1
+1032	1
+1033	0
+1034	1
+1035	0
+1036	1
+1037	1
+1038	1
+1039	1
+1040	0
+1041	1
+1042	0
+1043	0
+1044	1
+1045	1
+1046	0
+1047	1
+1048	1
+1049	1
+1050	1
+1051	1
+1052	0
+1053	1
+1054	0
+1055	1
+1056	1
+1057	1
+1058	1
+1059	1
+1060	0
+1061	1
+1062	1
+1063	1
+1064	1
+1065	1
+1066	1
+1067	1
+1068	0
+1069	1
+1070	1
+1071	0
+1072	1
+1073	1
+1074	1
+1075	1
+1076	1
+1077	1
+1078	1
+1079	1
+1080	0
+1081	0
+1082	1
+1083	1
+1084	1
+1085	1
+1086	1
+1087	1
+1088	1
+1089	1
+1090	1
+1091	0
+1092	1
+1093	1
+1094	1
+1095	1
+1096	1
+1097	1
+1098	1
+1099	1
+1100	1
+1101	1
+1102	0
+1103	1
+1104	1
+1105	0
+1106	1
+1107	0
+1108	1
+1109	1
+1110	0
+1111	1
+1112	0
+1113	0
+1114	1
+1115	1
+1116	0
+1117	1
+1118	1
+1119	1
+1120	0
+1121	0
+1122	1
+1123	1
+1124	0
+1125	1
+1126	0
+1127	0
+1128	1
+1129	1
+1130	1
+1131	1
+1132	0
+1133	1
+1134	0
+1135	1
+1136	0
+1137	1
+1138	0
+1139	0
+1140	1
+1141	1
+1142	1
+1143	1
+1144	0
+1145	1
+1146	1
+1147	0
+1148	1
+1149	1
+1150	0
+1151	1
+1152	1
+1153	0
+1154	0
+1155	1
+1156	1
+1157	1
+1158	0
+1159	1
+1160	0
+1161	0
+1162	1
+1163	1
+1164	1
+1165	0
+1166	0
+1167	1
+1168	1
+1169	1
+1170	1
+1171	1
+1172	1
+1173	1
+1174	1
+1175	0
+1176	1
+1177	1
+1178	1
+1179	1
+1180	1
+1181	1
+1182	1
+1183	1
+1184	1
+1185	1
+1186	0
+1187	1
+1188	1
+1189	0
+1190	1
+1191	0
+1192	1
+1193	1
+1194	1
+1195	1
+1196	0
+1197	1
+1198	0
+1199	1
+1200	0
+1201	1
+1202	1
+1203	1
+1204	0
+1205	1
+1206	0
+1207	0
+1208	1
+1209	1
+1210	1
+1211	1
+1212	1
+1213	1
+1214	1
+1215	1
+1216	1
+1217	1
+1218	1
+1219	1
+1220	1
+1221	0
+1222	1
+1223	1
+1224	0
+1225	1
+1226	0
+1227	1
+1228	1
+1229	1
+1230	1
+1231	0
+1232	1
+1233	1
+1234	1
+1235	1
+1236	1
+1237	1
+1238	1
+1239	1
+1240	1
+1241	0
+1242	1
+1243	1
+1244	1
+1245	1
+1246	0
+1247	1
+1248	1
+1249	1
+1250	1
+1251	1
+1252	1
+1253	1
+1254	1
+1255	1
+1256	1
+1257	1
+1258	0
+1259	1
+1260	1
+1261	1
+1262	1
+1263	1
+1264	1
+1265	1
+1266	1
+1267	1
+1268	1
+1269	1
+1270	1
+1271	1
+1272	0
+1273	0
+1274	0
+1275	1
+1276	1
+1277	1
+1278	1
+1279	0
+1280	1
+1281	1
+1282	1
+1283	0
+1284	1
+1285	1
+1286	1
+1287	0
+1288	1
+1289	1
+1290	1
+1291	1
+1292	0
+1293	0
+1294	0
+1295	1
+1296	1
+1297	1
+1298	1
+1299	1
+1300	0
+1301	1
+1302	1
+1303	1
+1304	1
+1305	0
+1306	0
+1307	1
+1308	1
+1309	0
+1310	1
+1311	1
+1312	1
+1313	1
+1314	1
+1315	1
+1316	1
+1317	1
+1318	0
+1319	1
+1320	1
+1321	0
+1322	1
+1323	1
+1324	1
+1325	1
+1326	0
+1327	1
+1328	1
+1329	0
+1330	0
+1331	0
+1332	1
+1333	0
+1334	1
+1335	0
+1336	0
+1337	0
+1338	0
+1339	1
+1340	0
+1341	1
+1342	0
+1343	1
+1344	1
+1345	1
+1346	1
+1347	1
+1348	1
+1349	1
+1350	1
+1351	1
+1352	1
+1353	0
+1354	0
+1355	0
+1356	1
+1357	1
+1358	0
+1359	1
+1360	1
+1361	1
+1362	1
+1363	0
+1364	1
+1365	1
+1366	0
+1367	0
+1368	1
+1369	1
+1370	0
+1371	0
+1372	1
+1373	0
+1374	0
+1375	1
+1376	1
+1377	1
+1378	1
+1379	1
+1380	1
+1381	1
+1382	1
+1383	1
+1384	1
+1385	1
+1386	0
+1387	1
+1388	1
+1389	1
+1390	1
+1391	0
+1392	0
+1393	1
+1394	1
+1395	1
+1396	0
+1397	1
+1398	1
+1399	1
+1400	0
+1401	0
+1402	1
+1403	0
+1404	1
+1405	0
+1406	1
+1407	1
+1408	1
+1409	1
+1410	0
+1411	0
+1412	1
+1413	1
+1414	0
+1415	1
+1416	1
+1417	1
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	1
+1428	0
+1429	1
+1430	0
+1431	1
+1432	1
+1433	0
+1434	1
+1435	0
+1436	1
+1437	1
+1438	1
+1439	1
+1440	1
+1441	1
+1442	1
+1443	0
+1444	0
+1445	1
+1446	1
+1447	1
+1448	0
+1449	1
+1450	1
+1451	0
+1452	1
+1453	1
+1454	1
+1455	1
+1456	1
+1457	1
+1458	1
+1459	1
+1460	1
+1461	1
+1462	1
+1463	0
+1464	1
+1465	1
+1466	1
+1467	0
+1468	1
+1469	0
+1470	1
+1471	1
+1472	0
+1473	0
+1474	1
+1475	1
+1476	1
+1477	1
+1478	0
+1479	0
+1480	1
+1481	0
+1482	1
+1483	0
+1484	0
+1485	1
+1486	0
+1487	0
+1488	1
+1489	1
+1490	0
+1491	1
+1492	1
+1493	0
+1494	0
+1495	1
+1496	1
+1497	0
+1498	0
+1499	0
+1500	1
+1501	1
+1502	1
+1503	0
+1504	1
+1505	1
+1506	1
+1507	1
+1508	0
+1509	0
+1510	1
+1511	1
+1512	0
+1513	1
+1514	0
+1515	1
+1516	1
+1517	1
+1518	0
+1519	0
+1520	0
+1521	0
+1522	0
+1523	1
+1524	1
+1525	1
+1526	1
+1527	1
+1528	0
+1529	1
+1530	1
+1531	1
+1532	1
+1533	1
+1534	1
+1535	0
+1536	1
+1537	0
+1538	1
+1539	0
+1540	0
+1541	1
+1542	0
+1543	1
+1544	0
+1545	0
+1546	1
+1547	0
+1548	1
+1549	1
+1550	1
+1551	0
+1552	0
+1553	0
+1554	1
+1555	1
+1556	0
+1557	1
+1558	0
+1559	1
+1560	1
+1561	0
+1562	1
+1563	1
+1564	0
+1565	0
+1566	1
+1567	1
+1568	1
+1569	1
+1570	1
+1571	1
+1572	1
+1573	0
+1574	1
+1575	1
+1576	1
+1577	0
+1578	0
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	1
+1586	0
+1587	1
+1588	1
+1589	1
+1590	0
+1591	1
+1592	1
+1593	0
+1594	1
+1595	1
+1596	1
+1597	0
+1598	1
+1599	0
+1600	0
+1601	1
+1602	1
+1603	1
+1604	1
+1605	0
+1606	1
+1607	1
+1608	0
+1609	1
+1610	0
+1611	1
+1612	1
+1613	1
+1614	1
+1615	1
+1616	1
+1617	0
+1618	1
+1619	1
+1620	0
+1621	0
+1622	1
+1623	1
+1624	0
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	0
+1632	1
+1633	1
+1634	1
+1635	1
+1636	1
+1637	1
+1638	0
+1639	1
+1640	0
+1641	1
+1642	0
+1643	1
+1644	1
+1645	1
+1646	1
+1647	0
+1648	1
+1649	1
+1650	1
+1651	0
+1652	0
+1653	1
+1654	0
+1655	1
+1656	0
+1657	0
+1658	1
+1659	1
+1660	0
+1661	0
+1662	0
+1663	1
+1664	0
+1665	0
+1666	0
+1667	1
+1668	0
+1669	1
+1670	1
+1671	0
+1672	1
+1673	1
+1674	1
+1675	1
+1676	1
+1677	1
+1678	1
+1679	1
+1680	0
+1681	1
+1682	1
+1683	0
+1684	1
+1685	1
+1686	0
+1687	0
+1688	1
+1689	0
+1690	1
+1691	0
+1692	1
+1693	1
+1694	1
+1695	1
+1696	1
+1697	0
+1698	0
+1699	1
+1700	1
+1701	1
+1702	0
+1703	1
+1704	0
+1705	1
+1706	0
+1707	0
+1708	1
+1709	1
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	0
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9219134999132397,
+    "eval_f1": 0.9345132743362832,
+    "eval_loss": 0.2595154941082001,
+    "eval_runtime": 0.6585,
+    "eval_samples": 408,
+    "eval_samples_per_second": 619.56,
+    "eval_steps_per_second": 1.519
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9093137254901961,
+    "eval_combined_score": 0.9219134999132397,
+    "eval_f1": 0.9345132743362832,
+    "eval_loss": 0.2595154941082001,
+    "eval_runtime": 0.6585,
+    "eval_samples": 408,
+    "eval_samples_per_second": 619.56,
+    "eval_steps_per_second": 1.519
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": false,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "key_proj",
+    "query_proj",
+    "attention.output.dense",
+    "intermediate.dense",
+    "output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": true,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "value_proj",
+    "key_proj",
+    "query_proj",
+    "attention.output.dense",
+    "intermediate.dense",
+    "output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47930f860d8be39f2c438c809db185f97f5606731066f780d7f2159bfbda002
+size 7449859

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.9093137254901961,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.15,mlr1e-04,clr1e-03,ep=30.0t=18d23h08m30/checkpoint-400",
+  "epoch": 30.0,
+  "eval_steps": 100,
+  "global_step": 3450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.888801097869873,
+      "learning_rate": 0.00099,
+      "loss": 0.6185,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.7107843137254902,
+      "eval_combined_score": 0.7665367351759982,
+      "eval_f1": 0.822289156626506,
+      "eval_loss": 0.5315333604812622,
+      "eval_runtime": 0.6819,
+      "eval_samples_per_second": 598.305,
+      "eval_steps_per_second": 1.466,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 4.414052486419678,
+      "learning_rate": 0.0009978076174307112,
+      "loss": 0.4311,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8406862745098039,
+      "eval_combined_score": 0.8647875816993464,
+      "eval_f1": 0.8888888888888888,
+      "eval_loss": 0.3522834777832031,
+      "eval_runtime": 0.5912,
+      "eval_samples_per_second": 690.18,
+      "eval_steps_per_second": 1.692,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.967780351638794,
+      "learning_rate": 0.0009911613477663372,
+      "loss": 0.3567,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9095183328164307,
+      "eval_f1": 0.9244288224956063,
+      "eval_loss": 0.2889207899570465,
+      "eval_runtime": 0.5884,
+      "eval_samples_per_second": 693.412,
+      "eval_steps_per_second": 1.7,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 3.9725353717803955,
+      "learning_rate": 0.0009801204343481893,
+      "loss": 0.3204,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9219134999132397,
+      "eval_f1": 0.9345132743362832,
+      "eval_loss": 0.2595154941082001,
+      "eval_runtime": 0.5886,
+      "eval_samples_per_second": 693.195,
+      "eval_steps_per_second": 1.699,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 2.625113010406494,
+      "learning_rate": 0.0009647836652454211,
+      "loss": 0.2895,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9116873065015481,
+      "eval_f1": 0.9263157894736842,
+      "eval_loss": 0.24875514209270477,
+      "eval_runtime": 0.5875,
+      "eval_samples_per_second": 694.524,
+      "eval_steps_per_second": 1.702,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 3.1335086822509766,
+      "learning_rate": 0.000945288265499961,
+      "loss": 0.2422,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9125705076551169,
+      "eval_f1": 0.928082191780822,
+      "eval_loss": 0.2661508619785309,
+      "eval_runtime": 0.5892,
+      "eval_samples_per_second": 692.497,
+      "eval_steps_per_second": 1.697,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 6.072702407836914,
+      "learning_rate": 0.0009218086693117072,
+      "loss": 0.2161,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8830396208070005,
+      "eval_f1": 0.9057851239669421,
+      "eval_loss": 0.5397763848304749,
+      "eval_runtime": 0.5875,
+      "eval_samples_per_second": 694.483,
+      "eval_steps_per_second": 1.702,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 6.110560417175293,
+      "learning_rate": 0.0008945549592964825,
+      "loss": 0.2059,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9050299323269131,
+      "eval_f1": 0.9203539823008849,
+      "eval_loss": 0.2758274972438812,
+      "eval_runtime": 0.5879,
+      "eval_samples_per_second": 694.053,
+      "eval_steps_per_second": 1.701,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 3.184335470199585,
+      "learning_rate": 0.000863770986781413,
+      "loss": 0.1761,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.29342126846313477,
+      "eval_runtime": 0.5877,
+      "eval_samples_per_second": 694.206,
+      "eval_steps_per_second": 1.701,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.3413187265396118,
+      "learning_rate": 0.0008297321899563005,
+      "loss": 0.153,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9112953692115144,
+      "eval_f1": 0.925531914893617,
+      "eval_loss": 0.3068132698535919,
+      "eval_runtime": 0.5875,
+      "eval_samples_per_second": 694.509,
+      "eval_steps_per_second": 1.702,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 4.26575231552124,
+      "learning_rate": 0.0007927431294029863,
+      "loss": 0.1409,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9140800231531727,
+      "eval_f1": 0.9261992619926199,
+      "eval_loss": 0.3988274931907654,
+      "eval_runtime": 0.588,
+      "eval_samples_per_second": 693.92,
+      "eval_steps_per_second": 1.701,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 6.83341121673584,
+      "learning_rate": 0.0007531347630534368,
+      "loss": 0.1217,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.39595237374305725,
+      "eval_runtime": 0.5884,
+      "eval_samples_per_second": 693.384,
+      "eval_steps_per_second": 1.699,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 0.6858878135681152,
+      "learning_rate": 0.0007112614849587449,
+      "loss": 0.1018,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9077509052401449,
+      "eval_f1": 0.9233449477351916,
+      "eval_loss": 0.5210728645324707,
+      "eval_runtime": 0.5874,
+      "eval_samples_per_second": 694.532,
+      "eval_steps_per_second": 1.702,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 0.46270978450775146,
+      "learning_rate": 0.0006674979543645248,
+      "loss": 0.0907,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9057225063938619,
+      "eval_f1": 0.9217391304347826,
+      "eval_loss": 0.3946845829486847,
+      "eval_runtime": 0.5898,
+      "eval_samples_per_second": 691.704,
+      "eval_steps_per_second": 1.695,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 4.69882869720459,
+      "learning_rate": 0.000622235743464402,
+      "loss": 0.0914,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.38392478227615356,
+      "eval_runtime": 0.6664,
+      "eval_samples_per_second": 612.263,
+      "eval_steps_per_second": 1.501,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 2.134861469268799,
+      "learning_rate": 0.0005758798338256736,
+      "loss": 0.0728,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9051704014939308,
+      "eval_f1": 0.9206349206349206,
+      "eval_loss": 0.5737729072570801,
+      "eval_runtime": 0.6723,
+      "eval_samples_per_second": 606.827,
+      "eval_steps_per_second": 1.487,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 9.352970123291016,
+      "learning_rate": 0.0005288449928352095,
+      "loss": 0.0603,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9089795008912656,
+      "eval_f1": 0.9233511586452763,
+      "eval_loss": 0.5365409255027771,
+      "eval_runtime": 0.6822,
+      "eval_samples_per_second": 598.047,
+      "eval_steps_per_second": 1.466,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 0.3746854364871979,
+      "learning_rate": 0.00048155206258717795,
+      "loss": 0.0587,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9158926728586172,
+      "eval_f1": 0.9298245614035088,
+      "eval_loss": 0.5017966628074646,
+      "eval_runtime": 0.5893,
+      "eval_samples_per_second": 692.375,
+      "eval_steps_per_second": 1.697,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.7553677558898926,
+      "learning_rate": 0.00043442419441760554,
+      "loss": 0.0534,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9153932035447632,
+      "eval_f1": 0.9288256227758007,
+      "eval_loss": 0.5661107897758484,
+      "eval_runtime": 0.5877,
+      "eval_samples_per_second": 694.263,
+      "eval_steps_per_second": 1.702,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.019641593098640442,
+      "learning_rate": 0.0003878830627771025,
+      "loss": 0.044,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.906651908075058,
+      "eval_f1": 0.921146953405018,
+      "eval_loss": 0.6302050352096558,
+      "eval_runtime": 0.6823,
+      "eval_samples_per_second": 597.972,
+      "eval_steps_per_second": 1.466,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.2956579923629761,
+      "learning_rate": 0.00034234509231794997,
+      "loss": 0.0515,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9074819401444789,
+      "eval_f1": 0.9228070175438596,
+      "eval_loss": 0.5459933280944824,
+      "eval_runtime": 0.6659,
+      "eval_samples_per_second": 612.749,
+      "eval_steps_per_second": 1.502,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 8.15996265411377,
+      "learning_rate": 0.00029821773195351986,
+      "loss": 0.0473,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9067927170868347,
+      "eval_f1": 0.9214285714285714,
+      "eval_loss": 0.5104790925979614,
+      "eval_runtime": 1.4693,
+      "eval_samples_per_second": 277.683,
+      "eval_steps_per_second": 0.681,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.006465388927608728,
+      "learning_rate": 0.00025589580922771014,
+      "loss": 0.0331,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.910759627592044,
+      "eval_f1": 0.9244604316546763,
+      "eval_loss": 0.6315487027168274,
+      "eval_runtime": 0.6759,
+      "eval_samples_per_second": 603.659,
+      "eval_steps_per_second": 1.48,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 30.930089950561523,
+      "learning_rate": 0.00021575799761350595,
+      "loss": 0.0328,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9085651828298887,
+      "eval_f1": 0.9225225225225225,
+      "eval_loss": 0.6286695599555969,
+      "eval_runtime": 0.5907,
+      "eval_samples_per_second": 690.714,
+      "eval_steps_per_second": 1.693,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.47196853160858154,
+      "learning_rate": 0.00017816342834935385,
+      "loss": 0.024,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9217971824609061,
+      "eval_f1": 0.9342806394316163,
+      "eval_loss": 0.5589781403541565,
+      "eval_runtime": 0.588,
+      "eval_samples_per_second": 693.889,
+      "eval_steps_per_second": 1.701,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.01034663338214159,
+      "learning_rate": 0.00014344847712878915,
+      "loss": 0.0343,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9129505931636568,
+      "eval_f1": 0.926391382405745,
+      "eval_loss": 0.6613860726356506,
+      "eval_runtime": 0.5914,
+      "eval_samples_per_second": 689.866,
+      "eval_steps_per_second": 1.691,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 4.391206741333008,
+      "learning_rate": 0.00011192375439426166,
+      "loss": 0.0376,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.6102422475814819,
+      "eval_runtime": 0.6755,
+      "eval_samples_per_second": 603.964,
+      "eval_steps_per_second": 1.48,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.02129713073372841,
+      "learning_rate": 8.387132616437177e-05,
+      "loss": 0.0182,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9088423831070891,
+      "eval_f1": 0.9230769230769231,
+      "eval_loss": 0.6355468034744263,
+      "eval_runtime": 0.6769,
+      "eval_samples_per_second": 602.705,
+      "eval_steps_per_second": 1.477,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.10591012984514236,
+      "learning_rate": 5.954219026103541e-05,
+      "loss": 0.0199,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.648102879524231,
+      "eval_runtime": 0.6669,
+      "eval_samples_per_second": 611.751,
+      "eval_steps_per_second": 1.499,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.7612121105194092,
+      "learning_rate": 3.915403051792249e-05,
+      "loss": 0.0159,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9067927170868347,
+      "eval_f1": 0.9214285714285714,
+      "eval_loss": 0.6390443444252014,
+      "eval_runtime": 0.6798,
+      "eval_samples_per_second": 600.179,
+      "eval_steps_per_second": 1.471,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 10.649272918701172,
+      "learning_rate": 2.288926906428551e-05,
+      "loss": 0.0293,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.6445656418800354,
+      "eval_runtime": 0.6809,
+      "eval_samples_per_second": 599.226,
+      "eval_steps_per_second": 1.469,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.10578522831201553,
+      "learning_rate": 1.089343411127952e-05,
+      "loss": 0.0155,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.6314123272895813,
+      "eval_runtime": 0.6592,
+      "eval_samples_per_second": 618.9,
+      "eval_steps_per_second": 1.517,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.03251971676945686,
+      "learning_rate": 3.2738578449308944e-06,
+      "loss": 0.0225,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.6310741305351257,
+      "eval_runtime": 0.6693,
+      "eval_samples_per_second": 609.608,
+      "eval_steps_per_second": 1.494,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.031257763504981995,
+      "learning_rate": 9.8716076299743e-08,
+      "loss": 0.0225,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9069325238992394,
+      "eval_f1": 0.9217081850533808,
+      "eval_loss": 0.6320057511329651,
+      "eval_runtime": 0.6845,
+      "eval_samples_per_second": 596.08,
+      "eval_steps_per_second": 1.461,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.1233423205735027,
+      "train_runtime": 972.4494,
+      "train_samples_per_second": 113.158,
+      "train_steps_per_second": 3.548
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.83610838283264e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	0
+5	1
+6	0
+7	0
+8	1
+9	0
+10	1
+11	1
+12	1
+13	0
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	1
+22	1
+23	1
+24	0
+25	1
+26	1
+27	1
+28	0
+29	1
+30	1
+31	0
+32	0
+33	0
+34	0
+35	0
+36	1
+37	1
+38	0
+39	1
+40	1
+41	1
+42	0
+43	1
+44	1
+45	0
+46	0
+47	0
+48	1
+49	1
+50	1
+51	1
+52	1
+53	1
+54	0
+55	1
+56	1
+57	1
+58	0
+59	1
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	1
+69	1
+70	0
+71	1
+72	1
+73	0
+74	1
+75	0
+76	1
+77	0
+78	1
+79	0
+80	0
+81	0
+82	1
+83	0
+84	0
+85	0
+86	0
+87	1
+88	0
+89	1
+90	0
+91	0
+92	1
+93	1
+94	1
+95	0
+96	1
+97	1
+98	0
+99	1
+100	1
+101	1
+102	1
+103	1
+104	1
+105	0
+106	0
+107	1
+108	1
+109	1
+110	1
+111	0
+112	0
+113	1
+114	1
+115	0
+116	0
+117	0
+118	1
+119	1
+120	1
+121	0
+122	1
+123	1
+124	1
+125	1
+126	1
+127	1
+128	0
+129	1
+130	0
+131	1
+132	1
+133	0
+134	1
+135	0
+136	0
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	0
+147	1
+148	1
+149	1
+150	0
+151	1
+152	0
+153	0
+154	1
+155	1
+156	1
+157	1
+158	0
+159	1
+160	1
+161	1
+162	1
+163	1
+164	0
+165	1
+166	1
+167	0
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	1
+175	1
+176	1
+177	0
+178	1
+179	1
+180	0
+181	0
+182	1
+183	1
+184	1
+185	1
+186	0
+187	0
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	0
+195	1
+196	0
+197	1
+198	1
+199	0
+200	0
+201	1
+202	1
+203	1
+204	1
+205	0
+206	1
+207	1
+208	0
+209	1
+210	0
+211	1
+212	1
+213	0
+214	1
+215	0
+216	1
+217	1
+218	1
+219	1
+220	1
+221	0
+222	1
+223	0
+224	1
+225	1
+226	1
+227	1
+228	0
+229	0
+230	1
+231	1
+232	1
+233	1
+234	0
+235	1
+236	1
+237	1
+238	0
+239	0
+240	1
+241	1
+242	0
+243	1
+244	0
+245	1
+246	1
+247	0
+248	1
+249	1
+250	1
+251	0
+252	0
+253	1
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	0
+261	1
+262	1
+263	1
+264	0
+265	1
+266	1
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	1
+276	1
+277	1
+278	1
+279	1
+280	1
+281	0
+282	1
+283	1
+284	1
+285	0
+286	1
+287	0
+288	0
+289	0
+290	0
+291	1
+292	1
+293	1
+294	1
+295	1
+296	0
+297	0
+298	1
+299	0
+300	1
+301	1
+302	0
+303	1
+304	1
+305	0
+306	1
+307	1
+308	1
+309	1
+310	1
+311	1
+312	0
+313	1
+314	1
+315	1
+316	1
+317	1
+318	1
+319	0
+320	1
+321	1
+322	1
+323	1
+324	1
+325	1
+326	1
+327	0
+328	0
+329	0
+330	0
+331	0
+332	1
+333	1
+334	1
+335	0
+336	1
+337	1
+338	1
+339	1
+340	1
+341	1
+342	1
+343	1
+344	0
+345	1
+346	0
+347	0
+348	0
+349	0
+350	1
+351	0
+352	0
+353	1
+354	0
+355	0
+356	0
+357	0
+358	1
+359	0
+360	0
+361	0
+362	1
+363	1
+364	0
+365	1
+366	0
+367	0
+368	0
+369	1
+370	0
+371	1
+372	1
+373	1
+374	1
+375	0
+376	1
+377	1
+378	1
+379	0
+380	1
+381	1
+382	0
+383	1
+384	1
+385	0
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	0
+395	1
+396	1
+397	1
+398	0
+399	0
+400	1
+401	1
+402	1
+403	1
+404	1
+405	1
+406	0
+407	1
+408	1
+409	1
+410	0
+411	1
+412	1
+413	1
+414	1
+415	0
+416	1
+417	1
+418	1
+419	1
+420	1
+421	1
+422	1
+423	1
+424	0
+425	0
+426	0
+427	1
+428	0
+429	1
+430	0
+431	1
+432	1
+433	1
+434	1
+435	1
+436	1
+437	0
+438	1
+439	0
+440	0
+441	0
+442	1
+443	1
+444	1
+445	1
+446	1
+447	1
+448	1
+449	1
+450	0
+451	1
+452	1
+453	1
+454	1
+455	0
+456	1
+457	1
+458	0
+459	1
+460	1
+461	1
+462	1
+463	1
+464	0
+465	0
+466	1
+467	1
+468	1
+469	1
+470	0
+471	1
+472	1
+473	1
+474	1
+475	1
+476	1
+477	1
+478	1
+479	0
+480	0
+481	1
+482	1
+483	1
+484	0
+485	1
+486	1
+487	1
+488	1
+489	1
+490	1
+491	0
+492	1
+493	1
+494	0
+495	1
+496	1
+497	1
+498	0
+499	1
+500	1
+501	1
+502	1
+503	0
+504	1
+505	1
+506	0
+507	1
+508	1
+509	0
+510	1
+511	1
+512	0
+513	1
+514	1
+515	1
+516	1
+517	1
+518	1
+519	1
+520	1
+521	1
+522	1
+523	1
+524	1
+525	1
+526	0
+527	1
+528	1
+529	1
+530	1
+531	1
+532	1
+533	0
+534	1
+535	1
+536	1
+537	1
+538	0
+539	1
+540	0
+541	1
+542	1
+543	1
+544	1
+545	1
+546	0
+547	0
+548	0
+549	0
+550	1
+551	1
+552	0
+553	1
+554	0
+555	1
+556	0
+557	1
+558	1
+559	1
+560	1
+561	0
+562	0
+563	0
+564	1
+565	1
+566	1
+567	1
+568	0
+569	0
+570	0
+571	1
+572	1
+573	1
+574	1
+575	0
+576	1
+577	1
+578	1
+579	1
+580	1
+581	1
+582	1
+583	1
+584	1
+585	1
+586	0
+587	1
+588	1
+589	1
+590	1
+591	1
+592	0
+593	0
+594	0
+595	1
+596	1
+597	0
+598	1
+599	1
+600	1
+601	1
+602	1
+603	1
+604	1
+605	1
+606	1
+607	0
+608	0
+609	1
+610	1
+611	1
+612	0
+613	1
+614	1
+615	1
+616	1
+617	0
+618	1
+619	1
+620	1
+621	0
+622	1
+623	0
+624	1
+625	0
+626	1
+627	1
+628	0
+629	1
+630	0
+631	0
+632	1
+633	0
+634	0
+635	1
+636	0
+637	1
+638	1
+639	1
+640	1
+641	1
+642	1
+643	1
+644	1
+645	1
+646	1
+647	1
+648	1
+649	0
+650	1
+651	0
+652	0
+653	1
+654	1
+655	1
+656	1
+657	1
+658	1
+659	1
+660	1
+661	1
+662	1
+663	1
+664	1
+665	0
+666	1
+667	0
+668	0
+669	0
+670	1
+671	1
+672	0
+673	1
+674	1
+675	0
+676	1
+677	1
+678	1
+679	1
+680	0
+681	1
+682	1
+683	1
+684	0
+685	1
+686	1
+687	0
+688	0
+689	1
+690	1
+691	0
+692	0
+693	1
+694	0
+695	0
+696	1
+697	1
+698	0
+699	1
+700	0
+701	1
+702	1
+703	0
+704	1
+705	0
+706	0
+707	0
+708	1
+709	1
+710	0
+711	0
+712	1
+713	1
+714	1
+715	1
+716	1
+717	1
+718	1
+719	1
+720	1
+721	1
+722	0
+723	0
+724	1
+725	1
+726	1
+727	1
+728	1
+729	0
+730	1
+731	1
+732	1
+733	0
+734	1
+735	1
+736	1
+737	1
+738	1
+739	1
+740	1
+741	1
+742	1
+743	1
+744	1
+745	0
+746	1
+747	0
+748	1
+749	0
+750	1
+751	1
+752	1
+753	0
+754	1
+755	1
+756	1
+757	1
+758	1
+759	1
+760	1
+761	1
+762	1
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	1
+770	1
+771	1
+772	1
+773	1
+774	1
+775	1
+776	1
+777	1
+778	0
+779	1
+780	0
+781	0
+782	1
+783	0
+784	1
+785	1
+786	1
+787	0
+788	1
+789	1
+790	1
+791	1
+792	1
+793	1
+794	1
+795	1
+796	0
+797	0
+798	1
+799	0
+800	0
+801	0
+802	1
+803	1
+804	0
+805	0
+806	1
+807	0
+808	1
+809	1
+810	1
+811	1
+812	0
+813	1
+814	0
+815	1
+816	0
+817	0
+818	0
+819	1
+820	0
+821	1
+822	1
+823	1
+824	1
+825	1
+826	1
+827	0
+828	0
+829	1
+830	1
+831	1
+832	1
+833	0
+834	1
+835	0
+836	1
+837	1
+838	1
+839	0
+840	0
+841	0
+842	1
+843	1
+844	0
+845	1
+846	1
+847	1
+848	0
+849	1
+850	1
+851	0
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	1
+861	1
+862	0
+863	1
+864	1
+865	1
+866	0
+867	1
+868	1
+869	1
+870	0
+871	1
+872	1
+873	1
+874	0
+875	0
+876	0
+877	0
+878	0
+879	0
+880	1
+881	1
+882	1
+883	1
+884	1
+885	1
+886	1
+887	1
+888	0
+889	1
+890	1
+891	1
+892	0
+893	0
+894	0
+895	0
+896	0
+897	1
+898	1
+899	1
+900	1
+901	1
+902	0
+903	1
+904	1
+905	1
+906	1
+907	1
+908	1
+909	1
+910	0
+911	1
+912	0
+913	0
+914	1
+915	1
+916	1
+917	1
+918	0
+919	1
+920	0
+921	1
+922	1
+923	1
+924	1
+925	1
+926	1
+927	0
+928	0
+929	1
+930	1
+931	0
+932	0
+933	0
+934	0
+935	1
+936	0
+937	0
+938	1
+939	1
+940	1
+941	1
+942	0
+943	0
+944	1
+945	1
+946	1
+947	1
+948	1
+949	1
+950	0
+951	1
+952	1
+953	1
+954	1
+955	1
+956	1
+957	1
+958	1
+959	1
+960	1
+961	1
+962	1
+963	0
+964	0
+965	1
+966	1
+967	1
+968	1
+969	1
+970	1
+971	0
+972	0
+973	1
+974	1
+975	1
+976	1
+977	1
+978	1
+979	1
+980	1
+981	1
+982	0
+983	1
+984	0
+985	1
+986	1
+987	1
+988	1
+989	1
+990	0
+991	1
+992	1
+993	1
+994	0
+995	0
+996	1
+997	0
+998	1
+999	1
+1000	0
+1001	1
+1002	0
+1003	0
+1004	1
+1005	0
+1006	1
+1007	0
+1008	1
+1009	0
+1010	1
+1011	0
+1012	1
+1013	1
+1014	1
+1015	1
+1016	1
+1017	1
+1018	1
+1019	1
+1020	1
+1021	1
+1022	1
+1023	0
+1024	1
+1025	0
+1026	0
+1027	1
+1028	0
+1029	1
+1030	0
+1031	1
+1032	1
+1033	0
+1034	1
+1035	0
+1036	1
+1037	1
+1038	1
+1039	0
+1040	0
+1041	1
+1042	0
+1043	0
+1044	1
+1045	1
+1046	0
+1047	1
+1048	1
+1049	1
+1050	1
+1051	1
+1052	1
+1053	1
+1054	0
+1055	1
+1056	1
+1057	1
+1058	1
+1059	1
+1060	1
+1061	1
+1062	1
+1063	1
+1064	1
+1065	1
+1066	1
+1067	1
+1068	0
+1069	1
+1070	1
+1071	1
+1072	1
+1073	1
+1074	1
+1075	1
+1076	1
+1077	1
+1078	1
+1079	1
+1080	0
+1081	0
+1082	1
+1083	1
+1084	1
+1085	1
+1086	1
+1087	0
+1088	1
+1089	1
+1090	1
+1091	0
+1092	1
+1093	1
+1094	1
+1095	1
+1096	1
+1097	1
+1098	1
+1099	0
+1100	1
+1101	1
+1102	0
+1103	1
+1104	1
+1105	0
+1106	1
+1107	0
+1108	1
+1109	1
+1110	0
+1111	1
+1112	0
+1113	0
+1114	1
+1115	1
+1116	0
+1117	1
+1118	1
+1119	1
+1120	0
+1121	0
+1122	1
+1123	1
+1124	0
+1125	1
+1126	0
+1127	0
+1128	1
+1129	1
+1130	1
+1131	1
+1132	0
+1133	1
+1134	0
+1135	1
+1136	0
+1137	1
+1138	0
+1139	0
+1140	1
+1141	1
+1142	1
+1143	1
+1144	0
+1145	1
+1146	1
+1147	1
+1148	1
+1149	1
+1150	0
+1151	1
+1152	1
+1153	0
+1154	0
+1155	1
+1156	0
+1157	1
+1158	0
+1159	1
+1160	0
+1161	0
+1162	1
+1163	1
+1164	1
+1165	0
+1166	0
+1167	1
+1168	1
+1169	1
+1170	0
+1171	1
+1172	1
+1173	1
+1174	1
+1175	0
+1176	1
+1177	1
+1178	1
+1179	1
+1180	1
+1181	0
+1182	1
+1183	1
+1184	1
+1185	1
+1186	0
+1187	1
+1188	1
+1189	0
+1190	1
+1191	0
+1192	1
+1193	1
+1194	1
+1195	1
+1196	0
+1197	1
+1198	0
+1199	1
+1200	1
+1201	1
+1202	0
+1203	1
+1204	0
+1205	1
+1206	0
+1207	0
+1208	1
+1209	1
+1210	1
+1211	1
+1212	1
+1213	1
+1214	1
+1215	1
+1216	1
+1217	1
+1218	1
+1219	1
+1220	1
+1221	0
+1222	1
+1223	1
+1224	0
+1225	1
+1226	0
+1227	1
+1228	1
+1229	1
+1230	1
+1231	0
+1232	1
+1233	1
+1234	1
+1235	1
+1236	1
+1237	1
+1238	1
+1239	1
+1240	1
+1241	0
+1242	1
+1243	1
+1244	1
+1245	1
+1246	0
+1247	1
+1248	1
+1249	1
+1250	1
+1251	1
+1252	1
+1253	1
+1254	1
+1255	1
+1256	1
+1257	1
+1258	0
+1259	0
+1260	0
+1261	1
+1262	1
+1263	1
+1264	1
+1265	1
+1266	1
+1267	1
+1268	1
+1269	1
+1270	1
+1271	1
+1272	0
+1273	0
+1274	0
+1275	1
+1276	0
+1277	1
+1278	1
+1279	0
+1280	1
+1281	0
+1282	0
+1283	0
+1284	1
+1285	1
+1286	1
+1287	1
+1288	1
+1289	1
+1290	1
+1291	1
+1292	0
+1293	1
+1294	0
+1295	1
+1296	1
+1297	1
+1298	1
+1299	1
+1300	0
+1301	1
+1302	1
+1303	1
+1304	1
+1305	0
+1306	0
+1307	1
+1308	1
+1309	0
+1310	1
+1311	1
+1312	1
+1313	1
+1314	1
+1315	1
+1316	1
+1317	1
+1318	0
+1319	1
+1320	1
+1321	0
+1322	1
+1323	1
+1324	1
+1325	1
+1326	1
+1327	1
+1328	1
+1329	0
+1330	1
+1331	1
+1332	1
+1333	0
+1334	1
+1335	0
+1336	0
+1337	0
+1338	0
+1339	1
+1340	0
+1341	1
+1342	0
+1343	0
+1344	1
+1345	1
+1346	1
+1347	1
+1348	1
+1349	1
+1350	1
+1351	1
+1352	1
+1353	0
+1354	0
+1355	0
+1356	1
+1357	1
+1358	0
+1359	1
+1360	1
+1361	1
+1362	1
+1363	0
+1364	1
+1365	1
+1366	0
+1367	0
+1368	1
+1369	1
+1370	0
+1371	0
+1372	1
+1373	1
+1374	0
+1375	1
+1376	1
+1377	1
+1378	1
+1379	1
+1380	1
+1381	1
+1382	1
+1383	1
+1384	1
+1385	1
+1386	0
+1387	1
+1388	1
+1389	1
+1390	1
+1391	0
+1392	0
+1393	1
+1394	1
+1395	1
+1396	0
+1397	1
+1398	1
+1399	1
+1400	0
+1401	0
+1402	1
+1403	0
+1404	1
+1405	0
+1406	1
+1407	1
+1408	1
+1409	1
+1410	0
+1411	1
+1412	1
+1413	1
+1414	0
+1415	1
+1416	1
+1417	1
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	1
+1428	0
+1429	1
+1430	1
+1431	1
+1432	1
+1433	0
+1434	1
+1435	0
+1436	1
+1437	1
+1438	1
+1439	1
+1440	1
+1441	1
+1442	0
+1443	0
+1444	0
+1445	1
+1446	1
+1447	1
+1448	0
+1449	1
+1450	1
+1451	0
+1452	1
+1453	1
+1454	1
+1455	1
+1456	1
+1457	1
+1458	1
+1459	1
+1460	1
+1461	1
+1462	1
+1463	0
+1464	1
+1465	1
+1466	1
+1467	0
+1468	1
+1469	0
+1470	0
+1471	1
+1472	0
+1473	0
+1474	1
+1475	0
+1476	0
+1477	1
+1478	1
+1479	0
+1480	1
+1481	0
+1482	1
+1483	0
+1484	0
+1485	1
+1486	0
+1487	0
+1488	1
+1489	1
+1490	0
+1491	1
+1492	1
+1493	0
+1494	0
+1495	1
+1496	1
+1497	0
+1498	0
+1499	0
+1500	1
+1501	1
+1502	0
+1503	0
+1504	0
+1505	1
+1506	1
+1507	1
+1508	1
+1509	0
+1510	1
+1511	1
+1512	0
+1513	1
+1514	0
+1515	1
+1516	0
+1517	1
+1518	0
+1519	0
+1520	0
+1521	0
+1522	0
+1523	1
+1524	1
+1525	1
+1526	1
+1527	1
+1528	0
+1529	1
+1530	1
+1531	1
+1532	1
+1533	1
+1534	1
+1535	0
+1536	1
+1537	0
+1538	1
+1539	0
+1540	0
+1541	1
+1542	0
+1543	1
+1544	0
+1545	1
+1546	1
+1547	0
+1548	1
+1549	1
+1550	1
+1551	0
+1552	0
+1553	0
+1554	1
+1555	1
+1556	0
+1557	1
+1558	0
+1559	1
+1560	1
+1561	0
+1562	1
+1563	1
+1564	0
+1565	1
+1566	1
+1567	1
+1568	1
+1569	1
+1570	1
+1571	1
+1572	1
+1573	0
+1574	1
+1575	1
+1576	1
+1577	0
+1578	0
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	1
+1586	0
+1587	1
+1588	1
+1589	1
+1590	0
+1591	1
+1592	1
+1593	0
+1594	1
+1595	1
+1596	1
+1597	0
+1598	0
+1599	1
+1600	0
+1601	1
+1602	1
+1603	1
+1604	0
+1605	0
+1606	1
+1607	1
+1608	0
+1609	1
+1610	0
+1611	1
+1612	1
+1613	1
+1614	1
+1615	1
+1616	1
+1617	0
+1618	1
+1619	1
+1620	0
+1621	0
+1622	1
+1623	1
+1624	0
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	0
+1632	1
+1633	1
+1634	1
+1635	1
+1636	1
+1637	1
+1638	0
+1639	1
+1640	0
+1641	1
+1642	0
+1643	1
+1644	1
+1645	1
+1646	1
+1647	0
+1648	1
+1649	1
+1650	1
+1651	0
+1652	0
+1653	1
+1654	1
+1655	1
+1656	0
+1657	0
+1658	1
+1659	1
+1660	0
+1661	1
+1662	0
+1663	1
+1664	0
+1665	0
+1666	0
+1667	1
+1668	0
+1669	1
+1670	0
+1671	0
+1672	1
+1673	1
+1674	1
+1675	1
+1676	1
+1677	1
+1678	1
+1679	1
+1680	0
+1681	1
+1682	1
+1683	0
+1684	1
+1685	1
+1686	0
+1687	0
+1688	1
+1689	0
+1690	1
+1691	0
+1692	1
+1693	1
+1694	0
+1695	1
+1696	1
+1697	0
+1698	0
+1699	1
+1700	1
+1701	1
+1702	0
+1703	1
+1704	1
+1705	1
+1706	0
+1707	0
+1708	1
+1709	1
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	0
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9068627450980392,
+    "eval_combined_score": 0.9199806683236675,
+    "eval_f1": 0.9330985915492958,
+    "eval_loss": 0.5321406126022339,
+    "eval_runtime": 0.6788,
+    "eval_samples": 408,
+    "eval_samples_per_second": 601.071,
+    "eval_steps_per_second": 1.473
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9068627450980392,
+    "eval_combined_score": 0.9199806683236675,
+    "eval_f1": 0.9330985915492958,
+    "eval_loss": 0.5321406126022339,
+    "eval_runtime": 0.6788,
+    "eval_samples": 408,
+    "eval_samples_per_second": 601.071,
+    "eval_steps_per_second": 1.473
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": false,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "intermediate.dense",
+    "query_proj",
+    "attention.output.dense",
+    "value_proj",
+    "output.dense",
+    "key_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.15,
+  "inference_mode": true,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "intermediate.dense",
+    "query_proj",
+    "attention.output.dense",
+    "value_proj",
+    "output.dense",
+    "key_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a47b3bfa05b7b955006b777121342941176b2c31da8ac869ba0e7f22c62063
+size 7449859

nlu/glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 1300,
+  "best_metric": 0.9068627450980392,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.15,mlr1e-04,clr2e-03,ep=30.0t=18d23h46m48/checkpoint-1300",
+  "epoch": 30.0,
+  "eval_steps": 100,
+  "global_step": 3450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.9800822734832764,
+      "learning_rate": 0.00198,
+      "loss": 0.631,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_combined_score": 0.7657565626547795,
+      "eval_f1": 0.8231797919762258,
+      "eval_loss": 0.5315466523170471,
+      "eval_runtime": 0.7483,
+      "eval_samples_per_second": 545.226,
+      "eval_steps_per_second": 1.336,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 3.5322961807250977,
+      "learning_rate": 0.0019956152348614225,
+      "loss": 0.455,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8284313725490197,
+      "eval_combined_score": 0.8546918767507004,
+      "eval_f1": 0.8809523809523809,
+      "eval_loss": 0.347840815782547,
+      "eval_runtime": 0.6888,
+      "eval_samples_per_second": 592.342,
+      "eval_steps_per_second": 1.452,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 4.208593368530273,
+      "learning_rate": 0.0019823226955326743,
+      "loss": 0.3668,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9116873065015481,
+      "eval_f1": 0.9263157894736842,
+      "eval_loss": 0.2938854694366455,
+      "eval_runtime": 0.6794,
+      "eval_samples_per_second": 600.537,
+      "eval_steps_per_second": 1.472,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 2.5013794898986816,
+      "learning_rate": 0.0019602408686963785,
+      "loss": 0.3204,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.90965068163868,
+      "eval_f1": 0.9246935201401051,
+      "eval_loss": 0.2600504755973816,
+      "eval_runtime": 0.683,
+      "eval_samples_per_second": 597.333,
+      "eval_steps_per_second": 1.464,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 3.019318103790283,
+      "learning_rate": 0.0019295673304908422,
+      "loss": 0.2921,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9099126172208014,
+      "eval_f1": 0.9252173913043479,
+      "eval_loss": 0.26120612025260925,
+      "eval_runtime": 0.683,
+      "eval_samples_per_second": 597.365,
+      "eval_steps_per_second": 1.464,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 3.8250582218170166,
+      "learning_rate": 0.001890576530999922,
+      "loss": 0.2527,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9084071984958367,
+      "eval_f1": 0.9246575342465754,
+      "eval_loss": 0.2798168659210205,
+      "eval_runtime": 1.0999,
+      "eval_samples_per_second": 370.951,
+      "eval_steps_per_second": 0.909,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 4.765564441680908,
+      "learning_rate": 0.0018436173386234143,
+      "loss": 0.2206,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8700980392156863,
+      "eval_combined_score": 0.8908086189400635,
+      "eval_f1": 0.9115191986644408,
+      "eval_loss": 0.48960059881210327,
+      "eval_runtime": 0.685,
+      "eval_samples_per_second": 595.61,
+      "eval_steps_per_second": 1.46,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 5.843444347381592,
+      "learning_rate": 0.001789109918592965,
+      "loss": 0.2071,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9170707472178061,
+      "eval_f1": 0.9297297297297298,
+      "eval_loss": 0.26192545890808105,
+      "eval_runtime": 0.6783,
+      "eval_samples_per_second": 601.512,
+      "eval_steps_per_second": 1.474,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 4.098570823669434,
+      "learning_rate": 0.001727541973562826,
+      "loss": 0.1792,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.2987627387046814,
+      "eval_runtime": 0.6696,
+      "eval_samples_per_second": 609.289,
+      "eval_steps_per_second": 1.493,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.7064694762229919,
+      "learning_rate": 0.001659464379912601,
+      "loss": 0.1473,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.28019386529922485,
+      "eval_runtime": 0.6785,
+      "eval_samples_per_second": 601.359,
+      "eval_steps_per_second": 1.474,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 3.233572006225586,
+      "learning_rate": 0.0015854862588059726,
+      "loss": 0.1591,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9010348583877996,
+      "eval_f1": 0.9148148148148149,
+      "eval_loss": 0.3983463943004608,
+      "eval_runtime": 0.6634,
+      "eval_samples_per_second": 615.057,
+      "eval_steps_per_second": 1.507,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 6.187975883483887,
+      "learning_rate": 0.0015062695261068735,
+      "loss": 0.1312,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.39305704832077026,
+      "eval_runtime": 0.6877,
+      "eval_samples_per_second": 593.316,
+      "eval_steps_per_second": 1.454,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 4.355435848236084,
+      "learning_rate": 0.0014225229699174897,
+      "loss": 0.098,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9199806683236675,
+      "eval_f1": 0.9330985915492958,
+      "eval_loss": 0.5321406126022339,
+      "eval_runtime": 0.6779,
+      "eval_samples_per_second": 601.878,
+      "eval_steps_per_second": 1.475,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 1.263325572013855,
+      "learning_rate": 0.0013349959087290495,
+      "loss": 0.0941,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9085357692565081,
+      "eval_f1": 0.9249146757679181,
+      "eval_loss": 0.47166481614112854,
+      "eval_runtime": 0.6614,
+      "eval_samples_per_second": 616.884,
+      "eval_steps_per_second": 1.512,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 4.007717132568359,
+      "learning_rate": 0.001244471486928804,
+      "loss": 0.096,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9138529755159507,
+      "eval_f1": 0.9281961471103327,
+      "eval_loss": 0.389970600605011,
+      "eval_runtime": 1.1089,
+      "eval_samples_per_second": 367.916,
+      "eval_steps_per_second": 0.902,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 2.6422905921936035,
+      "learning_rate": 0.0011517596676513472,
+      "loss": 0.0701,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9153932035447632,
+      "eval_f1": 0.9288256227758007,
+      "eval_loss": 0.506246030330658,
+      "eval_runtime": 0.6855,
+      "eval_samples_per_second": 595.198,
+      "eval_steps_per_second": 1.459,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 6.49318265914917,
+      "learning_rate": 0.001057689985670419,
+      "loss": 0.0704,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9130822722648988,
+      "eval_f1": 0.9266547406082289,
+      "eval_loss": 0.4763994514942169,
+      "eval_runtime": 0.6755,
+      "eval_samples_per_second": 604.01,
+      "eval_steps_per_second": 1.48,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 9.077567100524902,
+      "learning_rate": 0.0009631041251743559,
+      "loss": 0.0528,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9155193992490613,
+      "eval_f1": 0.9290780141843972,
+      "eval_loss": 0.5805758833885193,
+      "eval_runtime": 0.6729,
+      "eval_samples_per_second": 606.371,
+      "eval_steps_per_second": 1.486,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.12327190488576889,
+      "learning_rate": 0.0008688483888352111,
+      "loss": 0.0657,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9174465240641712,
+      "eval_f1": 0.93048128342246,
+      "eval_loss": 0.5554280877113342,
+      "eval_runtime": 0.674,
+      "eval_samples_per_second": 605.339,
+      "eval_steps_per_second": 1.484,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.08613881468772888,
+      "learning_rate": 0.000775766125554205,
+      "loss": 0.0444,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9118161250514192,
+      "eval_f1": 0.9265734265734266,
+      "eval_loss": 0.5723967552185059,
+      "eval_runtime": 0.6843,
+      "eval_samples_per_second": 596.221,
+      "eval_steps_per_second": 1.461,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 1.079032301902771,
+      "learning_rate": 0.0006846901846358999,
+      "loss": 0.0494,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.917692608016658,
+      "eval_f1": 0.9309734513274336,
+      "eval_loss": 0.5196344256401062,
+      "eval_runtime": 0.6825,
+      "eval_samples_per_second": 597.79,
+      "eval_steps_per_second": 1.465,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 7.605502128601074,
+      "learning_rate": 0.0005964354639070397,
+      "loss": 0.0574,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9173221614227086,
+      "eval_f1": 0.9302325581395349,
+      "eval_loss": 0.5725175142288208,
+      "eval_runtime": 0.6629,
+      "eval_samples_per_second": 615.468,
+      "eval_steps_per_second": 1.509,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.016635773703455925,
+      "learning_rate": 0.0005117916184554203,
+      "loss": 0.0474,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9092508242234947,
+      "eval_f1": 0.9238938053097345,
+      "eval_loss": 0.5967176556587219,
+      "eval_runtime": 0.6861,
+      "eval_samples_per_second": 594.699,
+      "eval_steps_per_second": 1.458,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 13.558172225952148,
+      "learning_rate": 0.0004315159952270119,
+      "loss": 0.0219,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9108950031625553,
+      "eval_f1": 0.9247311827956989,
+      "eval_loss": 0.6834716200828552,
+      "eval_runtime": 1.0972,
+      "eval_samples_per_second": 371.848,
+      "eval_steps_per_second": 0.911,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 3.322960138320923,
+      "learning_rate": 0.0003563268566987077,
+      "loss": 0.0302,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9118161250514192,
+      "eval_f1": 0.9265734265734266,
+      "eval_loss": 0.661984920501709,
+      "eval_runtime": 0.6634,
+      "eval_samples_per_second": 614.998,
+      "eval_steps_per_second": 1.507,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.02534395456314087,
+      "learning_rate": 0.0002868969542575783,
+      "loss": 0.0326,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9088423831070891,
+      "eval_f1": 0.9230769230769231,
+      "eval_loss": 0.687604546546936,
+      "eval_runtime": 0.6814,
+      "eval_samples_per_second": 598.8,
+      "eval_steps_per_second": 1.468,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 0.030124587938189507,
+      "learning_rate": 0.00022384750878852333,
+      "loss": 0.0361,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9046024939492792,
+      "eval_f1": 0.9194991055456172,
+      "eval_loss": 0.6979523301124573,
+      "eval_runtime": 0.6831,
+      "eval_samples_per_second": 597.263,
+      "eval_steps_per_second": 1.464,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.02060295082628727,
+      "learning_rate": 0.00016774265232874353,
+      "loss": 0.0202,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9112953692115144,
+      "eval_f1": 0.925531914893617,
+      "eval_loss": 0.7171363234519958,
+      "eval_runtime": 0.6874,
+      "eval_samples_per_second": 593.526,
+      "eval_steps_per_second": 1.455,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.017371950671076775,
+      "learning_rate": 0.00011908438052207082,
+      "loss": 0.0198,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9089795008912656,
+      "eval_f1": 0.9233511586452763,
+      "eval_loss": 0.7544679641723633,
+      "eval_runtime": 0.6825,
+      "eval_samples_per_second": 597.839,
+      "eval_steps_per_second": 1.465,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.02417536824941635,
+      "learning_rate": 7.830806103584498e-05,
+      "loss": 0.0215,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9091156444815938,
+      "eval_f1": 0.9236234458259325,
+      "eval_loss": 0.7522897124290466,
+      "eval_runtime": 0.6756,
+      "eval_samples_per_second": 603.923,
+      "eval_steps_per_second": 1.48,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 31.321632385253906,
+      "learning_rate": 4.577853812857102e-05,
+      "loss": 0.0283,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9070713391739675,
+      "eval_f1": 0.9219858156028369,
+      "eval_loss": 0.7426566481590271,
+      "eval_runtime": 0.6885,
+      "eval_samples_per_second": 592.607,
+      "eval_steps_per_second": 1.452,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.062251750379800797,
+      "learning_rate": 2.178686822255904e-05,
+      "loss": 0.0188,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9074819401444789,
+      "eval_f1": 0.9228070175438596,
+      "eval_loss": 0.7423697113990784,
+      "eval_runtime": 0.6812,
+      "eval_samples_per_second": 598.9,
+      "eval_steps_per_second": 1.468,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.028158038854599,
+      "learning_rate": 6.547715689861789e-06,
+      "loss": 0.0169,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9051704014939308,
+      "eval_f1": 0.9206349206349206,
+      "eval_loss": 0.7425649762153625,
+      "eval_runtime": 1.1272,
+      "eval_samples_per_second": 361.956,
+      "eval_steps_per_second": 0.887,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 4.675174713134766,
+      "learning_rate": 1.97432152599486e-07,
+      "loss": 0.016,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9050299323269131,
+      "eval_f1": 0.9203539823008849,
+      "eval_loss": 0.7419539093971252,
+      "eval_runtime": 0.6884,
+      "eval_samples_per_second": 592.676,
+      "eval_steps_per_second": 1.453,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.12697370169819266,
+      "train_runtime": 1307.0637,
+      "train_samples_per_second": 84.189,
+      "train_steps_per_second": 2.64
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.83610838283264e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}