Batch upload part 27

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/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": [
+    "output.dense",
+    "attention.output.dense",
+    "intermediate.dense",
+    "query_proj",
+    "key_proj",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/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": [
+    "output.dense",
+    "attention.output.dense",
+    "intermediate.dense",
+    "query_proj",
+    "key_proj",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/1dr0.15,mlr2e-04,clr2e-03,ep=30.0t=18d22h41m02/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcdd19e8394363f6c95f5e8945212598c8421cd08f2012465c1a7cef07f05b7
+size 7449859

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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": 0.5908,
+    "eval_samples": 408,
+    "eval_samples_per_second": 690.621,
+    "eval_steps_per_second": 1.693
+}

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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": 0.5908,
+    "eval_samples": 408,
+    "eval_samples_per_second": 690.621,
+    "eval_steps_per_second": 1.693
+}

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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": [
+    "attention.output.dense",
+    "query_proj",
+    "intermediate.dense",
+    "key_proj",
+    "output.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/ft/added_tokens.json

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

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/ft/spm.model

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

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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": [
+    "attention.output.dense",
+    "query_proj",
+    "intermediate.dense",
+    "key_proj",
+    "output.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcdd19e8394363f6c95f5e8945212598c8421cd08f2012465c1a7cef07f05b7
+size 7449859

nlu/glue_exp/mrpc/3dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 2400,
+  "best_metric": 0.9093137254901961,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.1,mlr2e-04,clr2e-03,ep=30.0t=18d22h26m32/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": 0.7374,
+      "eval_samples_per_second": 553.332,
+      "eval_steps_per_second": 1.356,
+      "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": 0.6419,
+      "eval_samples_per_second": 635.594,
+      "eval_steps_per_second": 1.558,
+      "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": 0.6484,
+      "eval_samples_per_second": 629.277,
+      "eval_steps_per_second": 1.542,
+      "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": 1.1062,
+      "eval_samples_per_second": 368.828,
+      "eval_steps_per_second": 0.904,
+      "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": 0.5936,
+      "eval_samples_per_second": 687.364,
+      "eval_steps_per_second": 1.685,
+      "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": 0.6425,
+      "eval_samples_per_second": 635.031,
+      "eval_steps_per_second": 1.556,
+      "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": 0.6489,
+      "eval_samples_per_second": 628.73,
+      "eval_steps_per_second": 1.541,
+      "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": 0.6464,
+      "eval_samples_per_second": 631.174,
+      "eval_steps_per_second": 1.547,
+      "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": 0.6437,
+      "eval_samples_per_second": 633.797,
+      "eval_steps_per_second": 1.553,
+      "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": 0.6465,
+      "eval_samples_per_second": 631.11,
+      "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": 0.6378,
+      "eval_samples_per_second": 639.665,
+      "eval_steps_per_second": 1.568,
+      "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": 0.6405,
+      "eval_samples_per_second": 636.968,
+      "eval_steps_per_second": 1.561,
+      "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": 0.6492,
+      "eval_samples_per_second": 628.429,
+      "eval_steps_per_second": 1.54,
+      "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": 0.636,
+      "eval_samples_per_second": 641.507,
+      "eval_steps_per_second": 1.572,
+      "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": 0.6377,
+      "eval_samples_per_second": 639.775,
+      "eval_steps_per_second": 1.568,
+      "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": 0.6405,
+      "eval_samples_per_second": 637.046,
+      "eval_steps_per_second": 1.561,
+      "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": 0.6449,
+      "eval_samples_per_second": 632.646,
+      "eval_steps_per_second": 1.551,
+      "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": 0.6502,
+      "eval_samples_per_second": 627.542,
+      "eval_steps_per_second": 1.538,
+      "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": 0.6449,
+      "eval_samples_per_second": 632.69,
+      "eval_steps_per_second": 1.551,
+      "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": 0.6444,
+      "eval_samples_per_second": 633.184,
+      "eval_steps_per_second": 1.552,
+      "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": 0.6408,
+      "eval_samples_per_second": 636.704,
+      "eval_steps_per_second": 1.561,
+      "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": 0.6425,
+      "eval_samples_per_second": 635.066,
+      "eval_steps_per_second": 1.557,
+      "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": 0.643,
+      "eval_samples_per_second": 634.57,
+      "eval_steps_per_second": 1.555,
+      "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": 0.6388,
+      "eval_samples_per_second": 638.67,
+      "eval_steps_per_second": 1.565,
+      "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": 0.6423,
+      "eval_samples_per_second": 635.222,
+      "eval_steps_per_second": 1.557,
+      "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": 0.6393,
+      "eval_samples_per_second": 638.166,
+      "eval_steps_per_second": 1.564,
+      "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": 0.6413,
+      "eval_samples_per_second": 636.196,
+      "eval_steps_per_second": 1.559,
+      "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": 0.6467,
+      "eval_samples_per_second": 630.906,
+      "eval_steps_per_second": 1.546,
+      "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": 0.5912,
+      "eval_samples_per_second": 690.116,
+      "eval_steps_per_second": 1.691,
+      "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": 0.6462,
+      "eval_samples_per_second": 631.358,
+      "eval_steps_per_second": 1.547,
+      "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": 638.106,
+      "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": 0.6378,
+      "eval_samples_per_second": 639.702,
+      "eval_steps_per_second": 1.568,
+      "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": 0.648,
+      "eval_samples_per_second": 629.653,
+      "eval_steps_per_second": 1.543,
+      "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": 0.6472,
+      "eval_samples_per_second": 630.419,
+      "eval_steps_per_second": 1.545,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.08607926879240119,
+      "train_runtime": 845.9298,
+      "train_samples_per_second": 130.082,
+      "train_steps_per_second": 4.078
+    }
+  ],
+  "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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	0
+4	0
+5	1
+6	0
+7	1
+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	0
+30	1
+31	0
+32	0
+33	0
+34	1
+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	1
+76	1
+77	0
+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	1
+92	1
+93	1
+94	1
+95	0
+96	1
+97	1
+98	0
+99	1
+100	1
+101	0
+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	1
+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	0
+172	1
+173	0
+174	0
+175	0
+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	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	1
+230	1
+231	1
+232	0
+233	1
+234	0
+235	1
+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	0
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	1
+261	0
+262	1
+263	1
+264	0
+265	1
+266	0
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	0
+276	1
+277	0
+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	1
+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	1
+330	0
+331	0
+332	1
+333	1
+334	1
+335	0
+336	1
+337	1
+338	0
+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	1
+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	1
+370	1
+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	0
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	1
+395	1
+396	1
+397	1
+398	0
+399	0
+400	1
+401	0
+402	1
+403	1
+404	1
+405	0
+406	0
+407	1
+408	1
+409	1
+410	1
+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	0
+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	0
+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	0
+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	0
+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	1
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	0
+578	1
+579	1
+580	1
+581	0
+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	0
+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	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	1
+650	1
+651	0
+652	0
+653	1
+654	0
+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	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	0
+742	1
+743	1
+744	1
+745	0
+746	1
+747	0
+748	1
+749	1
+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	0
+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	0
+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	0
+839	0
+840	0
+841	0
+842	1
+843	1
+844	1
+845	1
+846	1
+847	1
+848	0
+849	1
+850	1
+851	1
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	0
+861	1
+862	1
+863	1
+864	0
+865	1
+866	1
+867	1
+868	1
+869	1
+870	0
+871	1
+872	1
+873	1
+874	1
+875	0
+876	1
+877	0
+878	0
+879	0
+880	0
+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	1
+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	0
+946	1
+947	1
+948	0
+949	1
+950	0
+951	1
+952	0
+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	0
+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	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	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	0
+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	0
+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	0
+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	1
+1151	1
+1152	0
+1153	1
+1154	0
+1155	1
+1156	1
+1157	0
+1158	0
+1159	1
+1160	1
+1161	1
+1162	1
+1163	1
+1164	1
+1165	0
+1166	1
+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	0
+1181	0
+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	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	1
+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	0
+1248	1
+1249	1
+1250	1
+1251	1
+1252	1
+1253	1
+1254	1
+1255	1
+1256	1
+1257	1
+1258	1
+1259	0
+1260	1
+1261	1
+1262	1
+1263	1
+1264	1
+1265	1
+1266	0
+1267	1
+1268	1
+1269	1
+1270	1
+1271	1
+1272	0
+1273	0
+1274	0
+1275	1
+1276	0
+1277	1
+1278	0
+1279	0
+1280	1
+1281	1
+1282	0
+1283	0
+1284	1
+1285	1
+1286	1
+1287	1
+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	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	0
+1322	1
+1323	1
+1324	1
+1325	1
+1326	0
+1327	1
+1328	1
+1329	0
+1330	0
+1331	1
+1332	1
+1333	0
+1334	1
+1335	1
+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	0
+1358	0
+1359	1
+1360	1
+1361	1
+1362	1
+1363	0
+1364	1
+1365	0
+1366	0
+1367	0
+1368	1
+1369	0
+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	0
+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	1
+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	1
+1425	1
+1426	0
+1427	1
+1428	1
+1429	1
+1430	0
+1431	1
+1432	1
+1433	0
+1434	0
+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	1
+1468	1
+1469	0
+1470	1
+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	1
+1503	1
+1504	1
+1505	1
+1506	1
+1507	1
+1508	1
+1509	0
+1510	1
+1511	1
+1512	1
+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	1
+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	1
+1565	1
+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	1
+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	0
+1595	1
+1596	1
+1597	0
+1598	1
+1599	1
+1600	1
+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	0
+1623	1
+1624	1
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	1
+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	1
+1651	0
+1652	0
+1653	1
+1654	1
+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	0
+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	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	1
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	1
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9191176470588235,
+    "eval_combined_score": 0.9303552837064029,
+    "eval_f1": 0.9415929203539823,
+    "eval_loss": 0.43192246556282043,
+    "eval_runtime": 0.5887,
+    "eval_samples": 408,
+    "eval_samples_per_second": 693.086,
+    "eval_steps_per_second": 1.699
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9191176470588235,
+    "eval_combined_score": 0.9303552837064029,
+    "eval_f1": 0.9415929203539823,
+    "eval_loss": 0.43192246556282043,
+    "eval_runtime": 0.5887,
+    "eval_samples": 408,
+    "eval_samples_per_second": 693.086,
+    "eval_steps_per_second": 1.699
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.0,
+  "inference_mode": false,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "key_proj",
+    "output.dense",
+    "query_proj",
+    "attention.output.dense",
+    "intermediate.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/ft/added_tokens.json

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/ft/spm.model

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.0,
+  "inference_mode": true,
+  "layers_to_transform": null,
+  "modules_to_save": [
+    "classifier",
+    "pooler"
+  ],
+  "num_rotations": 1,
+  "peft_type": "ROTATION",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "key_proj",
+    "output.dense",
+    "query_proj",
+    "attention.output.dense",
+    "intermediate.dense",
+    "value_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8745c7b476e73f1c87b67d5afdac5acce7282fe9eca17ab68d40f16b9eb2e5ca
+size 7449859

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.9191176470588235,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h32m05,r=4,s43/checkpoint-1500",
+  "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": 1.5893659591674805,
+      "learning_rate": 0.00198,
+      "loss": 0.5836,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.7426470588235294,
+      "eval_combined_score": 0.7916573685619923,
+      "eval_f1": 0.8406676783004552,
+      "eval_loss": 0.7225454449653625,
+      "eval_runtime": 0.6841,
+      "eval_samples_per_second": 596.379,
+      "eval_steps_per_second": 1.462,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 1.7734744548797607,
+      "learning_rate": 0.0019956152348614225,
+      "loss": 0.3627,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.9019544564813877,
+      "eval_f1": 0.919104991394148,
+      "eval_loss": 0.29524144530296326,
+      "eval_runtime": 0.5761,
+      "eval_samples_per_second": 708.244,
+      "eval_steps_per_second": 1.736,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.618133068084717,
+      "learning_rate": 0.0019823226955326743,
+      "loss": 0.2857,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9029914085775652,
+      "eval_f1": 0.9187279151943463,
+      "eval_loss": 0.33274513483047485,
+      "eval_runtime": 0.5751,
+      "eval_samples_per_second": 709.477,
+      "eval_steps_per_second": 1.739,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 1.351619839668274,
+      "learning_rate": 0.0019602408686963785,
+      "loss": 0.225,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9160153571918278,
+      "eval_f1": 0.9300699300699301,
+      "eval_loss": 0.28772440552711487,
+      "eval_runtime": 0.5909,
+      "eval_samples_per_second": 690.416,
+      "eval_steps_per_second": 1.692,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 3.242846965789795,
+      "learning_rate": 0.0019295673304908422,
+      "loss": 0.1716,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8700980392156863,
+      "eval_combined_score": 0.8903609926263929,
+      "eval_f1": 0.9106239460370995,
+      "eval_loss": 0.42163893580436707,
+      "eval_runtime": 0.5909,
+      "eval_samples_per_second": 690.434,
+      "eval_steps_per_second": 1.692,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 7.72324275970459,
+      "learning_rate": 0.001890576530999922,
+      "loss": 0.1191,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9162581699346406,
+      "eval_f1": 0.9305555555555556,
+      "eval_loss": 0.6345019340515137,
+      "eval_runtime": 0.5872,
+      "eval_samples_per_second": 694.841,
+      "eval_steps_per_second": 1.703,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 11.79227352142334,
+      "learning_rate": 0.0018436173386234143,
+      "loss": 0.1218,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8651960784313726,
+      "eval_combined_score": 0.8863795518207283,
+      "eval_f1": 0.907563025210084,
+      "eval_loss": 0.6440550088882446,
+      "eval_runtime": 0.592,
+      "eval_samples_per_second": 689.203,
+      "eval_steps_per_second": 1.689,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 6.427208423614502,
+      "learning_rate": 0.001789109918592965,
+      "loss": 0.0815,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.8774509803921569,
+      "eval_combined_score": 0.8959172710179962,
+      "eval_f1": 0.9143835616438356,
+      "eval_loss": 0.5999459028244019,
+      "eval_runtime": 0.5867,
+      "eval_samples_per_second": 695.377,
+      "eval_steps_per_second": 1.704,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 4.7944841384887695,
+      "learning_rate": 0.001727541973562826,
+      "loss": 0.0735,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8823529411764706,
+      "eval_combined_score": 0.9004985044865403,
+      "eval_f1": 0.9186440677966101,
+      "eval_loss": 0.5001353025436401,
+      "eval_runtime": 0.5871,
+      "eval_samples_per_second": 694.956,
+      "eval_steps_per_second": 1.703,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.232080340385437,
+      "learning_rate": 0.001659464379912601,
+      "loss": 0.0396,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.903972278566599,
+      "eval_f1": 0.9206896551724137,
+      "eval_loss": 0.6272836327552795,
+      "eval_runtime": 0.5868,
+      "eval_samples_per_second": 695.335,
+      "eval_steps_per_second": 1.704,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 0.12160742282867432,
+      "learning_rate": 0.0015854862588059726,
+      "loss": 0.0454,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.917196905692259,
+      "eval_f1": 0.9299820466786356,
+      "eval_loss": 0.5900373458862305,
+      "eval_runtime": 0.5853,
+      "eval_samples_per_second": 697.098,
+      "eval_steps_per_second": 1.709,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 3.2582204341888428,
+      "learning_rate": 0.0015062695261068735,
+      "loss": 0.0505,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9080161476355249,
+      "eval_f1": 0.9238754325259516,
+      "eval_loss": 0.7707640528678894,
+      "eval_runtime": 0.5885,
+      "eval_samples_per_second": 693.277,
+      "eval_steps_per_second": 1.699,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 0.03892024978995323,
+      "learning_rate": 0.0014225229699174897,
+      "loss": 0.0276,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9180552693932214,
+      "eval_f1": 0.9316987740805605,
+      "eval_loss": 0.7422796487808228,
+      "eval_runtime": 0.5862,
+      "eval_samples_per_second": 696.003,
+      "eval_steps_per_second": 1.706,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 0.02271677926182747,
+      "learning_rate": 0.0013349959087290495,
+      "loss": 0.0306,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.9260243617873437,
+      "eval_f1": 0.9378330373001776,
+      "eval_loss": 0.5293979048728943,
+      "eval_runtime": 0.5891,
+      "eval_samples_per_second": 692.594,
+      "eval_steps_per_second": 1.698,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 1.8397374153137207,
+      "learning_rate": 0.001244471486928804,
+      "loss": 0.0282,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.9191176470588235,
+      "eval_combined_score": 0.9303552837064029,
+      "eval_f1": 0.9415929203539823,
+      "eval_loss": 0.43192246556282043,
+      "eval_runtime": 0.5874,
+      "eval_samples_per_second": 694.633,
+      "eval_steps_per_second": 1.703,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 0.9747097492218018,
+      "learning_rate": 0.0011517596676513472,
+      "loss": 0.0207,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.917692608016658,
+      "eval_f1": 0.9309734513274336,
+      "eval_loss": 0.4927181899547577,
+      "eval_runtime": 0.5912,
+      "eval_samples_per_second": 690.121,
+      "eval_steps_per_second": 1.691,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 0.00376587244682014,
+      "learning_rate": 0.001057689985670419,
+      "loss": 0.0153,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9179352320893208,
+      "eval_f1": 0.9314586994727593,
+      "eval_loss": 0.8056793808937073,
+      "eval_runtime": 0.5879,
+      "eval_samples_per_second": 694.04,
+      "eval_steps_per_second": 1.701,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 7.063637733459473,
+      "learning_rate": 0.0009631041251743559,
+      "loss": 0.014,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9142263057736093,
+      "eval_f1": 0.92894280762565,
+      "eval_loss": 0.6877063512802124,
+      "eval_runtime": 0.5883,
+      "eval_samples_per_second": 693.581,
+      "eval_steps_per_second": 1.7,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.005422030575573444,
+      "learning_rate": 0.0008688483888352111,
+      "loss": 0.0127,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.9044117647058824,
+      "eval_combined_score": 0.9179352320893208,
+      "eval_f1": 0.9314586994727593,
+      "eval_loss": 0.8292607069015503,
+      "eval_runtime": 0.5877,
+      "eval_samples_per_second": 694.209,
+      "eval_steps_per_second": 1.701,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.0020996863022446632,
+      "learning_rate": 0.000775766125554205,
+      "loss": 0.0143,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9200980392156863,
+      "eval_f1": 0.9333333333333333,
+      "eval_loss": 0.7557045221328735,
+      "eval_runtime": 0.5871,
+      "eval_samples_per_second": 694.999,
+      "eval_steps_per_second": 1.703,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.01305614784359932,
+      "learning_rate": 0.0006846901846358999,
+      "loss": 0.0146,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9161371865819499,
+      "eval_f1": 0.9303135888501742,
+      "eval_loss": 0.6693629622459412,
+      "eval_runtime": 0.5871,
+      "eval_samples_per_second": 694.989,
+      "eval_steps_per_second": 1.703,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 0.2836249768733978,
+      "learning_rate": 0.0005964354639070397,
+      "loss": 0.0071,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.9262436456063907,
+      "eval_f1": 0.9382716049382716,
+      "eval_loss": 0.6643729209899902,
+      "eval_runtime": 0.5924,
+      "eval_samples_per_second": 688.697,
+      "eval_steps_per_second": 1.688,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0006859056884422898,
+      "learning_rate": 0.0005117916184554203,
+      "loss": 0.004,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9202145893322364,
+      "eval_f1": 0.9335664335664335,
+      "eval_loss": 0.8549216985702515,
+      "eval_runtime": 0.5862,
+      "eval_samples_per_second": 695.967,
+      "eval_steps_per_second": 1.706,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 0.00031100164051167667,
+      "learning_rate": 0.0004315159952270119,
+      "loss": 0.0034,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.9261343918098213,
+      "eval_f1": 0.9380530973451328,
+      "eval_loss": 0.8290520310401917,
+      "eval_runtime": 0.5881,
+      "eval_samples_per_second": 693.711,
+      "eval_steps_per_second": 1.7,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.0001474908203817904,
+      "learning_rate": 0.0003563268566987077,
+      "loss": 0.0026,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.9117647058823529,
+      "eval_combined_score": 0.924192212096106,
+      "eval_f1": 0.9366197183098591,
+      "eval_loss": 0.8578133583068848,
+      "eval_runtime": 0.5843,
+      "eval_samples_per_second": 698.319,
+      "eval_steps_per_second": 1.712,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.0011402611853554845,
+      "learning_rate": 0.0002868969542575783,
+      "loss": 0.005,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.9261343918098213,
+      "eval_f1": 0.9380530973451328,
+      "eval_loss": 0.8785954117774963,
+      "eval_runtime": 0.5886,
+      "eval_samples_per_second": 693.167,
+      "eval_steps_per_second": 1.699,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 9.641557699069381e-05,
+      "learning_rate": 0.00022384750878852333,
+      "loss": 0.0015,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.9191176470588235,
+      "eval_combined_score": 0.9304582944288826,
+      "eval_f1": 0.9417989417989417,
+      "eval_loss": 0.9162914752960205,
+      "eval_runtime": 0.6263,
+      "eval_samples_per_second": 651.461,
+      "eval_steps_per_second": 1.597,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.000294726574793458,
+      "learning_rate": 0.00016774265232874353,
+      "loss": 0.006,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.926352131362211,
+      "eval_f1": 0.9384885764499121,
+      "eval_loss": 0.858831524848938,
+      "eval_runtime": 0.5747,
+      "eval_samples_per_second": 709.941,
+      "eval_steps_per_second": 1.74,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.0001405712537234649,
+      "learning_rate": 0.00011908438052207082,
+      "loss": 0.0024,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9202145893322364,
+      "eval_f1": 0.9335664335664335,
+      "eval_loss": 0.8538783192634583,
+      "eval_runtime": 0.5853,
+      "eval_samples_per_second": 697.132,
+      "eval_steps_per_second": 1.709,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.0005564729799516499,
+      "learning_rate": 7.830806103584498e-05,
+      "loss": 0.0025,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9202145893322364,
+      "eval_f1": 0.9335664335664335,
+      "eval_loss": 0.866047203540802,
+      "eval_runtime": 0.5862,
+      "eval_samples_per_second": 695.983,
+      "eval_steps_per_second": 1.706,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 8.019042434170842e-05,
+      "learning_rate": 4.577853812857102e-05,
+      "loss": 0.0016,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9202145893322364,
+      "eval_f1": 0.9335664335664335,
+      "eval_loss": 0.8777211308479309,
+      "eval_runtime": 0.5876,
+      "eval_samples_per_second": 694.315,
+      "eval_steps_per_second": 1.702,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.003190132789313793,
+      "learning_rate": 2.178686822255904e-05,
+      "loss": 0.0021,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.926352131362211,
+      "eval_f1": 0.9384885764499121,
+      "eval_loss": 0.8823443651199341,
+      "eval_runtime": 0.5835,
+      "eval_samples_per_second": 699.276,
+      "eval_steps_per_second": 1.714,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.00853230245411396,
+      "learning_rate": 6.547715689861789e-06,
+      "loss": 0.0026,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.926352131362211,
+      "eval_f1": 0.9384885764499121,
+      "eval_loss": 0.8846958875656128,
+      "eval_runtime": 0.5855,
+      "eval_samples_per_second": 696.884,
+      "eval_steps_per_second": 1.708,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.00021078009740449488,
+      "learning_rate": 1.97432152599486e-07,
+      "loss": 0.0022,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.926352131362211,
+      "eval_f1": 0.9384885764499121,
+      "eval_loss": 0.8843898177146912,
+      "eval_runtime": 0.5846,
+      "eval_samples_per_second": 697.894,
+      "eval_steps_per_second": 1.711,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.0690272841764533,
+      "train_runtime": 676.117,
+      "train_samples_per_second": 162.753,
+      "train_steps_per_second": 5.103
+    }
+  ],
+  "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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/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	1
+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	1
+85	0
+86	1
+87	1
+88	0
+89	1
+90	0
+91	1
+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	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	1
+159	1
+160	1
+161	1
+162	1
+163	0
+164	0
+165	1
+166	1
+167	0
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	0
+175	0
+176	0
+177	0
+178	1
+179	1
+180	0
+181	0
+182	0
+183	1
+184	1
+185	1
+186	0
+187	1
+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	0
+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	0
+228	0
+229	1
+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	1
+243	1
+244	0
+245	1
+246	1
+247	0
+248	1
+249	1
+250	1
+251	1
+252	1
+253	0
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	1
+261	1
+262	1
+263	1
+264	1
+265	1
+266	0
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	0
+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	0
+296	0
+297	0
+298	1
+299	1
+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	0
+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	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	1
+347	0
+348	0
+349	0
+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	0
+363	1
+364	0
+365	1
+366	0
+367	0
+368	1
+369	1
+370	1
+371	1
+372	1
+373	1
+374	1
+375	0
+376	0
+377	1
+378	0
+379	0
+380	1
+381	1
+382	1
+383	1
+384	1
+385	0
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	1
+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	1
+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	1
+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	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	0
+480	1
+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	1
+504	1
+505	1
+506	0
+507	1
+508	0
+509	0
+510	1
+511	1
+512	1
+513	1
+514	1
+515	1
+516	1
+517	0
+518	1
+519	1
+520	1
+521	1
+522	0
+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	1
+542	1
+543	1
+544	1
+545	1
+546	1
+547	0
+548	0
+549	0
+550	0
+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	1
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	0
+578	1
+579	0
+580	1
+581	0
+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	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	1
+629	1
+630	1
+631	1
+632	1
+633	0
+634	0
+635	1
+636	1
+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	1
+686	1
+687	0
+688	1
+689	1
+690	1
+691	0
+692	0
+693	1
+694	1
+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	0
+719	1
+720	1
+721	1
+722	0
+723	0
+724	1
+725	0
+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	0
+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	0
+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	0
+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	0
+817	0
+818	0
+819	1
+820	1
+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	0
+851	0
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	0
+861	1
+862	1
+863	1
+864	1
+865	1
+866	0
+867	1
+868	1
+869	1
+870	0
+871	1
+872	1
+873	1
+874	1
+875	0
+876	1
+877	0
+878	0
+879	1
+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	1
+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	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	0
+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	1
+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	1
+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	0
+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	0
+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	0
+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	1
+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	0
+1141	1
+1142	1
+1143	1
+1144	1
+1145	1
+1146	1
+1147	0
+1148	1
+1149	1
+1150	1
+1151	1
+1152	1
+1153	1
+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	0
+1170	1
+1171	1
+1172	1
+1173	1
+1174	1
+1175	0
+1176	0
+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	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	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	0
+1277	1
+1278	0
+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	0
+1294	0
+1295	1
+1296	1
+1297	1
+1298	1
+1299	1
+1300	1
+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	1
+1322	1
+1323	1
+1324	1
+1325	1
+1326	1
+1327	1
+1328	1
+1329	0
+1330	0
+1331	1
+1332	1
+1333	0
+1334	1
+1335	0
+1336	1
+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	1
+1384	1
+1385	1
+1386	0
+1387	0
+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	0
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	1
+1428	1
+1429	1
+1430	0
+1431	1
+1432	1
+1433	1
+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	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	1
+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	1
+1509	0
+1510	1
+1511	1
+1512	1
+1513	1
+1514	0
+1515	1
+1516	0
+1517	0
+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	1
+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	1
+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	0
+1571	1
+1572	0
+1573	1
+1574	1
+1575	1
+1576	1
+1577	0
+1578	1
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	1
+1586	0
+1587	1
+1588	1
+1589	0
+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	0
+1617	0
+1618	1
+1619	1
+1620	0
+1621	0
+1622	0
+1623	1
+1624	0
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	1
+1632	1
+1633	1
+1634	1
+1635	1
+1636	1
+1637	1
+1638	0
+1639	0
+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	0
+1660	0
+1661	1
+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	0
+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	1
+1690	1
+1691	0
+1692	1
+1693	1
+1694	1
+1695	1
+1696	1
+1697	0
+1698	0
+1699	1
+1700	0
+1701	1
+1702	0
+1703	1
+1704	1
+1705	1
+1706	1
+1707	0
+1708	1
+1709	1
+1710	1
+1711	1
+1712	1
+1713	0
+1714	1
+1715	1
+1716	1
+1717	1
+1718	1
+1719	1
+1720	0
+1721	0
+1722	0
+1723	1
+1724	1

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9166666666666666,
+    "eval_combined_score": 0.9282979976442873,
+    "eval_f1": 0.9399293286219081,
+    "eval_loss": 0.4379878342151642,
+    "eval_runtime": 0.59,
+    "eval_samples": 408,
+    "eval_samples_per_second": 691.558,
+    "eval_steps_per_second": 1.695
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9166666666666666,
+    "eval_combined_score": 0.9282979976442873,
+    "eval_f1": 0.9399293286219081,
+    "eval_loss": 0.4379878342151642,
+    "eval_runtime": 0.59,
+    "eval_samples": 408,
+    "eval_samples_per_second": 691.558,
+    "eval_steps_per_second": 1.695
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.0,
+  "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",
+    "intermediate.dense",
+    "output.dense",
+    "query_proj",
+    "key_proj",
+    "attention.output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/ft/added_tokens.json

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/ft/spm.model

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/ft2/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.0,
+  "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",
+    "intermediate.dense",
+    "output.dense",
+    "query_proj",
+    "key_proj",
+    "attention.output.dense"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659c1db1180853a7b1ca2995cf400ac5c4a565e09751b0a064bcbc98d55a42c0
+size 7449859

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.9166666666666666,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h43m47,r=4,s44/checkpoint-800",
+  "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": 1.8360604047775269,
+      "learning_rate": 0.00198,
+      "loss": 0.5914,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.7818627450980392,
+      "eval_combined_score": 0.8212913099512105,
+      "eval_f1": 0.8607198748043818,
+      "eval_loss": 0.49459952116012573,
+      "eval_runtime": 0.6854,
+      "eval_samples_per_second": 595.272,
+      "eval_steps_per_second": 1.459,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 2.4401156902313232,
+      "learning_rate": 0.0019956152348614225,
+      "loss": 0.4002,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8431372549019608,
+      "eval_combined_score": 0.868937048503612,
+      "eval_f1": 0.8947368421052632,
+      "eval_loss": 0.48239845037460327,
+      "eval_runtime": 0.5905,
+      "eval_samples_per_second": 690.894,
+      "eval_steps_per_second": 1.693,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.450094223022461,
+      "learning_rate": 0.0019823226955326743,
+      "loss": 0.2987,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8799019607843137,
+      "eval_combined_score": 0.8980706385118149,
+      "eval_f1": 0.9162393162393162,
+      "eval_loss": 0.31535765528678894,
+      "eval_runtime": 0.5903,
+      "eval_samples_per_second": 691.194,
+      "eval_steps_per_second": 1.694,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 2.1748127937316895,
+      "learning_rate": 0.0019602408686963785,
+      "loss": 0.2165,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9038350634371395,
+      "eval_f1": 0.9204152249134948,
+      "eval_loss": 0.35315826535224915,
+      "eval_runtime": 0.5883,
+      "eval_samples_per_second": 693.519,
+      "eval_steps_per_second": 1.7,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 1.631756067276001,
+      "learning_rate": 0.0019295673304908422,
+      "loss": 0.1806,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8651960784313726,
+      "eval_combined_score": 0.8865343876243965,
+      "eval_f1": 0.9078726968174204,
+      "eval_loss": 0.433360755443573,
+      "eval_runtime": 0.5864,
+      "eval_samples_per_second": 695.779,
+      "eval_steps_per_second": 1.705,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 3.0931460857391357,
+      "learning_rate": 0.001890576530999922,
+      "loss": 0.1185,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9112953692115144,
+      "eval_f1": 0.925531914893617,
+      "eval_loss": 0.5076855421066284,
+      "eval_runtime": 0.5875,
+      "eval_samples_per_second": 694.515,
+      "eval_steps_per_second": 1.702,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 7.7334113121032715,
+      "learning_rate": 0.0018436173386234143,
+      "loss": 0.1018,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8455882352941176,
+      "eval_combined_score": 0.8710699797160244,
+      "eval_f1": 0.896551724137931,
+      "eval_loss": 0.7612046599388123,
+      "eval_runtime": 0.5881,
+      "eval_samples_per_second": 693.813,
+      "eval_steps_per_second": 1.701,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 7.458433628082275,
+      "learning_rate": 0.001789109918592965,
+      "loss": 0.0663,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.9166666666666666,
+      "eval_combined_score": 0.9282979976442873,
+      "eval_f1": 0.9399293286219081,
+      "eval_loss": 0.4379878342151642,
+      "eval_runtime": 0.5904,
+      "eval_samples_per_second": 691.039,
+      "eval_steps_per_second": 1.694,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 0.46179747581481934,
+      "learning_rate": 0.001727541973562826,
+      "loss": 0.0584,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9061266072694137,
+      "eval_f1": 0.9225473321858864,
+      "eval_loss": 0.6456283926963806,
+      "eval_runtime": 0.5878,
+      "eval_samples_per_second": 694.099,
+      "eval_steps_per_second": 1.701,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.026321955025196075,
+      "learning_rate": 0.001659464379912601,
+      "loss": 0.0478,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9029914085775652,
+      "eval_f1": 0.9187279151943463,
+      "eval_loss": 0.6597155332565308,
+      "eval_runtime": 0.591,
+      "eval_samples_per_second": 690.371,
+      "eval_steps_per_second": 1.692,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 1.8554913997650146,
+      "learning_rate": 0.0015854862588059726,
+      "loss": 0.0457,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.91500916913528,
+      "eval_f1": 0.9280575539568345,
+      "eval_loss": 0.5039987564086914,
+      "eval_runtime": 0.5869,
+      "eval_samples_per_second": 695.126,
+      "eval_steps_per_second": 1.704,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 1.1184793710708618,
+      "learning_rate": 0.0015062695261068735,
+      "loss": 0.0326,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9152661064425771,
+      "eval_f1": 0.9285714285714286,
+      "eval_loss": 0.6569485664367676,
+      "eval_runtime": 0.5902,
+      "eval_samples_per_second": 691.244,
+      "eval_steps_per_second": 1.694,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 5.948911666870117,
+      "learning_rate": 0.0014225229699174897,
+      "loss": 0.0397,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9136669593210418,
+      "eval_f1": 0.9253731343283582,
+      "eval_loss": 0.6822256445884705,
+      "eval_runtime": 0.5855,
+      "eval_samples_per_second": 696.804,
+      "eval_steps_per_second": 1.708,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 0.024277156218886375,
+      "learning_rate": 0.0013349959087290495,
+      "loss": 0.0297,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.661496102809906,
+      "eval_runtime": 0.5892,
+      "eval_samples_per_second": 692.509,
+      "eval_steps_per_second": 1.697,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 0.0037559494376182556,
+      "learning_rate": 0.001244471486928804,
+      "loss": 0.0262,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9153932035447632,
+      "eval_f1": 0.9288256227758007,
+      "eval_loss": 0.6715577840805054,
+      "eval_runtime": 0.5906,
+      "eval_samples_per_second": 690.767,
+      "eval_steps_per_second": 1.693,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 1.3978617191314697,
+      "learning_rate": 0.0011517596676513472,
+      "loss": 0.0191,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9058581404832297,
+      "eval_f1": 0.9220103986135182,
+      "eval_loss": 0.6576076745986938,
+      "eval_runtime": 0.5782,
+      "eval_samples_per_second": 705.656,
+      "eval_steps_per_second": 1.73,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 0.014365606009960175,
+      "learning_rate": 0.001057689985670419,
+      "loss": 0.0234,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9092508242234947,
+      "eval_f1": 0.9238938053097345,
+      "eval_loss": 0.641814649105072,
+      "eval_runtime": 0.5743,
+      "eval_samples_per_second": 710.406,
+      "eval_steps_per_second": 1.741,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 0.007329825311899185,
+      "learning_rate": 0.0009631041251743559,
+      "loss": 0.0233,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9219134999132397,
+      "eval_f1": 0.9345132743362832,
+      "eval_loss": 0.5932002067565918,
+      "eval_runtime": 0.5875,
+      "eval_samples_per_second": 694.434,
+      "eval_steps_per_second": 1.702,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 3.096741199493408,
+      "learning_rate": 0.0008688483888352111,
+      "loss": 0.0101,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9114269382664727,
+      "eval_f1": 0.9257950530035336,
+      "eval_loss": 0.7496433854103088,
+      "eval_runtime": 0.5893,
+      "eval_samples_per_second": 692.33,
+      "eval_steps_per_second": 1.697,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 3.4940972328186035,
+      "learning_rate": 0.000775766125554205,
+      "loss": 0.0154,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9143490297673473,
+      "eval_f1": 0.9291882556131261,
+      "eval_loss": 0.7340260148048401,
+      "eval_runtime": 0.5876,
+      "eval_samples_per_second": 694.4,
+      "eval_steps_per_second": 1.702,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.021862367168068886,
+      "learning_rate": 0.0006846901846358999,
+      "loss": 0.0077,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9158926728586172,
+      "eval_f1": 0.9298245614035088,
+      "eval_loss": 0.7796983122825623,
+      "eval_runtime": 0.5951,
+      "eval_samples_per_second": 685.546,
+      "eval_steps_per_second": 1.68,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 0.4798244833946228,
+      "learning_rate": 0.0005964354639070397,
+      "loss": 0.0131,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.9166666666666666,
+      "eval_combined_score": 0.9280842230130486,
+      "eval_f1": 0.9395017793594306,
+      "eval_loss": 0.616762638092041,
+      "eval_runtime": 0.5925,
+      "eval_samples_per_second": 688.63,
+      "eval_steps_per_second": 1.688,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0014620067086070776,
+      "learning_rate": 0.0005117916184554203,
+      "loss": 0.0056,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9200980392156863,
+      "eval_f1": 0.9333333333333333,
+      "eval_loss": 0.8317950367927551,
+      "eval_runtime": 0.5854,
+      "eval_samples_per_second": 697.003,
+      "eval_steps_per_second": 1.708,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 0.03271247446537018,
+      "learning_rate": 0.0004315159952270119,
+      "loss": 0.0035,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9155193992490613,
+      "eval_f1": 0.9290780141843972,
+      "eval_loss": 0.877530038356781,
+      "eval_runtime": 0.5888,
+      "eval_samples_per_second": 692.978,
+      "eval_steps_per_second": 1.698,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.0165140051394701,
+      "learning_rate": 0.0003563268566987077,
+      "loss": 0.0038,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9223706498306128,
+      "eval_f1": 0.9354275741710296,
+      "eval_loss": 0.827203631401062,
+      "eval_runtime": 0.5885,
+      "eval_samples_per_second": 693.274,
+      "eval_steps_per_second": 1.699,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.0022780098952353,
+      "learning_rate": 0.0002868969542575783,
+      "loss": 0.0042,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9200980392156863,
+      "eval_f1": 0.9333333333333333,
+      "eval_loss": 0.8698594570159912,
+      "eval_runtime": 0.6076,
+      "eval_samples_per_second": 671.512,
+      "eval_steps_per_second": 1.646,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 0.007629064377397299,
+      "learning_rate": 0.00022384750878852333,
+      "loss": 0.0031,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9160153571918278,
+      "eval_f1": 0.9300699300699301,
+      "eval_loss": 0.9649954438209534,
+      "eval_runtime": 0.5903,
+      "eval_samples_per_second": 691.22,
+      "eval_steps_per_second": 1.694,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.16465626657009125,
+      "learning_rate": 0.00016774265232874353,
+      "loss": 0.003,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9204452614379085,
+      "eval_f1": 0.9340277777777778,
+      "eval_loss": 1.0196751356124878,
+      "eval_runtime": 0.5876,
+      "eval_samples_per_second": 694.325,
+      "eval_steps_per_second": 1.702,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.000333487696480006,
+      "learning_rate": 0.00011908438052207082,
+      "loss": 0.0054,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9221436817257659,
+      "eval_f1": 0.9349736379613357,
+      "eval_loss": 0.971728503704071,
+      "eval_runtime": 0.5913,
+      "eval_samples_per_second": 690.03,
+      "eval_steps_per_second": 1.691,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.0011938128154724836,
+      "learning_rate": 7.830806103584498e-05,
+      "loss": 0.0025,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9221436817257659,
+      "eval_f1": 0.9349736379613357,
+      "eval_loss": 0.9873009324073792,
+      "eval_runtime": 0.5881,
+      "eval_samples_per_second": 693.708,
+      "eval_steps_per_second": 1.7,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 0.004215817432850599,
+      "learning_rate": 4.577853812857102e-05,
+      "loss": 0.0015,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9222575632704921,
+      "eval_f1": 0.9352014010507881,
+      "eval_loss": 1.000651240348816,
+      "eval_runtime": 0.5964,
+      "eval_samples_per_second": 684.119,
+      "eval_steps_per_second": 1.677,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.022620199248194695,
+      "learning_rate": 2.178686822255904e-05,
+      "loss": 0.0015,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9222575632704921,
+      "eval_f1": 0.9352014010507881,
+      "eval_loss": 1.0103635787963867,
+      "eval_runtime": 0.5893,
+      "eval_samples_per_second": 692.364,
+      "eval_steps_per_second": 1.697,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.0005388130084611475,
+      "learning_rate": 6.547715689861789e-06,
+      "loss": 0.0006,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9222575632704921,
+      "eval_f1": 0.9352014010507881,
+      "eval_loss": 1.0093270540237427,
+      "eval_runtime": 0.5869,
+      "eval_samples_per_second": 695.149,
+      "eval_steps_per_second": 1.704,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.004557831212878227,
+      "learning_rate": 1.97432152599486e-07,
+      "loss": 0.0013,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.9093137254901961,
+      "eval_combined_score": 0.9222575632704921,
+      "eval_f1": 0.9352014010507881,
+      "eval_loss": 1.0097448825836182,
+      "eval_runtime": 0.5963,
+      "eval_samples_per_second": 684.233,
+      "eval_steps_per_second": 1.677,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.06965703106876733,
+      "train_runtime": 684.2534,
+      "train_samples_per_second": 160.818,
+      "train_steps_per_second": 5.042
+    }
+  ],
+  "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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/MRPC.tsv

@@ -0,0 +1,1726 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	0
+5	1
+6	0
+7	1
+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	1
+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	1
+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	1
+79	0
+80	1
+81	0
+82	1
+83	0
+84	0
+85	0
+86	1
+87	1
+88	0
+89	1
+90	0
+91	1
+92	1
+93	1
+94	1
+95	0
+96	1
+97	1
+98	0
+99	1
+100	1
+101	0
+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	1
+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	1
+159	1
+160	1
+161	1
+162	1
+163	0
+164	0
+165	1
+166	1
+167	0
+168	1
+169	1
+170	1
+171	1
+172	1
+173	0
+174	1
+175	0
+176	1
+177	0
+178	1
+179	1
+180	0
+181	0
+182	0
+183	1
+184	1
+185	1
+186	0
+187	1
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	0
+195	0
+196	1
+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	0
+212	0
+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	1
+230	1
+231	1
+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	1
+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	1
+261	1
+262	1
+263	1
+264	1
+265	1
+266	1
+267	0
+268	1
+269	1
+270	1
+271	0
+272	1
+273	0
+274	0
+275	0
+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	0
+291	1
+292	1
+293	1
+294	1
+295	0
+296	0
+297	0
+298	1
+299	1
+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	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	1
+347	0
+348	1
+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	1
+369	0
+370	1
+371	1
+372	1
+373	1
+374	1
+375	0
+376	0
+377	1
+378	0
+379	0
+380	1
+381	1
+382	1
+383	1
+384	1
+385	0
+386	1
+387	0
+388	1
+389	1
+390	1
+391	0
+392	0
+393	1
+394	1
+395	1
+396	1
+397	1
+398	0
+399	1
+400	1
+401	0
+402	0
+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	0
+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	0
+522	1
+523	1
+524	1
+525	1
+526	0
+527	1
+528	1
+529	0
+530	1
+531	1
+532	1
+533	0
+534	1
+535	1
+536	1
+537	0
+538	0
+539	1
+540	0
+541	1
+542	1
+543	1
+544	1
+545	1
+546	1
+547	0
+548	0
+549	0
+550	1
+551	1
+552	1
+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	1
+571	1
+572	1
+573	1
+574	1
+575	1
+576	1
+577	0
+578	1
+579	1
+580	1
+581	0
+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	0
+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	0
+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	1
+683	1
+684	1
+685	1
+686	1
+687	0
+688	1
+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	0
+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	0
+758	1
+759	1
+760	1
+761	1
+762	1
+763	1
+764	1
+765	1
+766	1
+767	1
+768	1
+769	0
+770	1
+771	1
+772	1
+773	1
+774	1
+775	1
+776	0
+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	0
+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	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	0
+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	1
+852	1
+853	0
+854	1
+855	0
+856	1
+857	1
+858	0
+859	1
+860	0
+861	1
+862	1
+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	0
+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	1
+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	1
+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	0
+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	0
+988	1
+989	0
+990	1
+991	1
+992	1
+993	1
+994	0
+995	0
+996	1
+997	1
+998	1
+999	1
+1000	0
+1001	1
+1002	0
+1003	0
+1004	1
+1005	1
+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	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	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	0
+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	0
+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	0
+1158	0
+1159	1
+1160	0
+1161	0
+1162	1
+1163	1
+1164	1
+1165	0
+1166	0
+1167	1
+1168	1
+1169	0
+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	1
+1191	0
+1192	1
+1193	1
+1194	1
+1195	1
+1196	0
+1197	1
+1198	1
+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	1
+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	0
+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	0
+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	0
+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	0
+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	0
+1418	1
+1419	1
+1420	1
+1421	1
+1422	0
+1423	0
+1424	0
+1425	1
+1426	0
+1427	1
+1428	0
+1429	0
+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	1
+1468	1
+1469	0
+1470	1
+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	1
+1494	1
+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	1
+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	1
+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	1
+1566	1
+1567	1
+1568	1
+1569	1
+1570	1
+1571	1
+1572	0
+1573	0
+1574	1
+1575	1
+1576	1
+1577	0
+1578	1
+1579	1
+1580	1
+1581	1
+1582	1
+1583	1
+1584	0
+1585	0
+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	1
+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	1
+1625	0
+1626	1
+1627	1
+1628	1
+1629	0
+1630	0
+1631	1
+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	1
+1648	1
+1649	1
+1650	0
+1651	0
+1652	0
+1653	1
+1654	1
+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	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	1
+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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9142156862745098,
+    "eval_combined_score": 0.92656683092085,
+    "eval_f1": 0.9389179755671903,
+    "eval_loss": 0.673913836479187,
+    "eval_runtime": 0.5729,
+    "eval_samples": 408,
+    "eval_samples_per_second": 712.173,
+    "eval_steps_per_second": 1.746
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.9142156862745098,
+    "eval_combined_score": 0.92656683092085,
+    "eval_f1": 0.9389179755671903,
+    "eval_loss": 0.673913836479187,
+    "eval_runtime": 0.5729,
+    "eval_samples": 408,
+    "eval_samples_per_second": 712.173,
+    "eval_steps_per_second": 1.746
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/ft/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "T": 1.0,
+  "base_model_name_or_path": "microsoft/deberta-v3-base",
+  "bias": "none",
+  "drop_out": 0.0,
+  "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",
+    "output.dense",
+    "value_proj",
+    "attention.output.dense",
+    "query_proj",
+    "key_proj"
+  ],
+  "target_modules_to_skip": null,
+  "task_type": "SEQ_CLS"
+}

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/ft/added_tokens.json

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/ft/spm.model

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

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/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/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/ft2/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7ac523189d4f334737eb019e5e9b4341211dcd9610d889def582abdbc973d2
+size 7449859

nlu/glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/trainer_state.json

@@ -0,0 +1,655 @@
+{
+  "best_global_step": 1800,
+  "best_metric": 0.9142156862745098,
+  "best_model_checkpoint": "./glue_exp/mrpc/dr0.0,mlr5e-04,clr2e-03,ep=30.0t=24d16h55m38,r=4,s45/checkpoint-1800",
+  "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": 4.347602367401123,
+      "learning_rate": 0.00198,
+      "loss": 0.5803,
+      "step": 100
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8822478991596638,
+      "eval_f1": 0.9042016806722689,
+      "eval_loss": 0.45600226521492004,
+      "eval_runtime": 0.6867,
+      "eval_samples_per_second": 594.12,
+      "eval_steps_per_second": 1.456,
+      "step": 100
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 1.9366239309310913,
+      "learning_rate": 0.0019956152348614225,
+      "loss": 0.3704,
+      "step": 200
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_accuracy": 0.8480392156862745,
+      "eval_combined_score": 0.872864492331586,
+      "eval_f1": 0.8976897689768977,
+      "eval_loss": 0.3966831862926483,
+      "eval_runtime": 0.5852,
+      "eval_samples_per_second": 697.138,
+      "eval_steps_per_second": 1.709,
+      "step": 200
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 3.378814458847046,
+      "learning_rate": 0.0019823226955326743,
+      "loss": 0.3041,
+      "step": 300
+    },
+    {
+      "epoch": 2.608695652173913,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9097821065599014,
+      "eval_f1": 0.924956369982548,
+      "eval_loss": 0.31703782081604004,
+      "eval_runtime": 0.5834,
+      "eval_samples_per_second": 699.371,
+      "eval_steps_per_second": 1.714,
+      "step": 300
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 2.2696948051452637,
+      "learning_rate": 0.0019602408686963785,
+      "loss": 0.2206,
+      "step": 400
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9041085506367494,
+      "eval_f1": 0.9209621993127147,
+      "eval_loss": 0.4423012435436249,
+      "eval_runtime": 0.5798,
+      "eval_samples_per_second": 703.712,
+      "eval_steps_per_second": 1.725,
+      "step": 400
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 5.197021484375,
+      "learning_rate": 0.0019295673304908422,
+      "loss": 0.191,
+      "step": 500
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9106770050439257,
+      "eval_f1": 0.9267461669505963,
+      "eval_loss": 0.3691416084766388,
+      "eval_runtime": 0.5749,
+      "eval_samples_per_second": 709.637,
+      "eval_steps_per_second": 1.739,
+      "step": 500
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 5.0261335372924805,
+      "learning_rate": 0.001890576530999922,
+      "loss": 0.1352,
+      "step": 600
+    },
+    {
+      "epoch": 5.217391304347826,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9070713391739675,
+      "eval_f1": 0.9219858156028369,
+      "eval_loss": 0.473999559879303,
+      "eval_runtime": 0.5737,
+      "eval_samples_per_second": 711.204,
+      "eval_steps_per_second": 1.743,
+      "step": 600
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 1.5393813848495483,
+      "learning_rate": 0.0018436173386234143,
+      "loss": 0.1133,
+      "step": 700
+    },
+    {
+      "epoch": 6.086956521739131,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9035577645692423,
+      "eval_f1": 0.9198606271777003,
+      "eval_loss": 0.5273416638374329,
+      "eval_runtime": 0.5734,
+      "eval_samples_per_second": 711.6,
+      "eval_steps_per_second": 1.744,
+      "step": 700
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 7.234371662139893,
+      "learning_rate": 0.001789109918592965,
+      "loss": 0.0789,
+      "step": 800
+    },
+    {
+      "epoch": 6.956521739130435,
+      "eval_accuracy": 0.8921568627450981,
+      "eval_combined_score": 0.9060784313725491,
+      "eval_f1": 0.92,
+      "eval_loss": 0.4842986762523651,
+      "eval_runtime": 0.5746,
+      "eval_samples_per_second": 709.998,
+      "eval_steps_per_second": 1.74,
+      "step": 800
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 2.4622912406921387,
+      "learning_rate": 0.001727541973562826,
+      "loss": 0.0699,
+      "step": 900
+    },
+    {
+      "epoch": 7.826086956521739,
+      "eval_accuracy": 0.8725490196078431,
+      "eval_combined_score": 0.8912918108419838,
+      "eval_f1": 0.9100346020761245,
+      "eval_loss": 0.5077530145645142,
+      "eval_runtime": 0.574,
+      "eval_samples_per_second": 710.746,
+      "eval_steps_per_second": 1.742,
+      "step": 900
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.014082511886954308,
+      "learning_rate": 0.001659464379912601,
+      "loss": 0.0523,
+      "step": 1000
+    },
+    {
+      "epoch": 8.695652173913043,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.9008090404303314,
+      "eval_f1": 0.9168141592920354,
+      "eval_loss": 0.5472626686096191,
+      "eval_runtime": 0.5723,
+      "eval_samples_per_second": 712.973,
+      "eval_steps_per_second": 1.747,
+      "step": 1000
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 0.1075880229473114,
+      "learning_rate": 0.0015854862588059726,
+      "loss": 0.063,
+      "step": 1100
+    },
+    {
+      "epoch": 9.565217391304348,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9035577645692423,
+      "eval_f1": 0.9198606271777003,
+      "eval_loss": 0.5933418869972229,
+      "eval_runtime": 0.5735,
+      "eval_samples_per_second": 711.449,
+      "eval_steps_per_second": 1.744,
+      "step": 1100
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 0.10556649416685104,
+      "learning_rate": 0.0015062695261068735,
+      "loss": 0.0312,
+      "step": 1200
+    },
+    {
+      "epoch": 10.434782608695652,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9044579681064526,
+      "eval_f1": 0.9192100538599641,
+      "eval_loss": 0.5497579574584961,
+      "eval_runtime": 0.574,
+      "eval_samples_per_second": 710.848,
+      "eval_steps_per_second": 1.742,
+      "step": 1200
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 0.3477442264556885,
+      "learning_rate": 0.0014225229699174897,
+      "loss": 0.0367,
+      "step": 1300
+    },
+    {
+      "epoch": 11.304347826086957,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9015029088558499,
+      "eval_f1": 0.9157509157509157,
+      "eval_loss": 0.7066847085952759,
+      "eval_runtime": 0.574,
+      "eval_samples_per_second": 710.823,
+      "eval_steps_per_second": 1.742,
+      "step": 1300
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 0.02786153554916382,
+      "learning_rate": 0.0013349959087290495,
+      "loss": 0.0323,
+      "step": 1400
+    },
+    {
+      "epoch": 12.173913043478262,
+      "eval_accuracy": 0.8848039215686274,
+      "eval_combined_score": 0.9003626047914693,
+      "eval_f1": 0.9159212880143113,
+      "eval_loss": 0.7087417244911194,
+      "eval_runtime": 0.5749,
+      "eval_samples_per_second": 709.65,
+      "eval_steps_per_second": 1.739,
+      "step": 1400
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 0.6905132532119751,
+      "learning_rate": 0.001244471486928804,
+      "loss": 0.0301,
+      "step": 1500
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_accuracy": 0.9068627450980392,
+      "eval_combined_score": 0.9195028011204482,
+      "eval_f1": 0.9321428571428572,
+      "eval_loss": 0.5149193406105042,
+      "eval_runtime": 0.5739,
+      "eval_samples_per_second": 710.867,
+      "eval_steps_per_second": 1.742,
+      "step": 1500
+    },
+    {
+      "epoch": 13.91304347826087,
+      "grad_norm": 1.0678400993347168,
+      "learning_rate": 0.0011517596676513472,
+      "loss": 0.0224,
+      "step": 1600
+    },
+    {
+      "epoch": 13.91304347826087,
+      "eval_accuracy": 0.8897058823529411,
+      "eval_combined_score": 0.9054483877614092,
+      "eval_f1": 0.9211908931698775,
+      "eval_loss": 0.6445961594581604,
+      "eval_runtime": 0.5759,
+      "eval_samples_per_second": 708.4,
+      "eval_steps_per_second": 1.736,
+      "step": 1600
+    },
+    {
+      "epoch": 14.782608695652174,
+      "grad_norm": 0.01732761226594448,
+      "learning_rate": 0.001057689985670419,
+      "loss": 0.0213,
+      "step": 1700
+    },
+    {
+      "epoch": 14.782608695652174,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9095183328164307,
+      "eval_f1": 0.9244288224956063,
+      "eval_loss": 0.524046003818512,
+      "eval_runtime": 0.5737,
+      "eval_samples_per_second": 711.122,
+      "eval_steps_per_second": 1.743,
+      "step": 1700
+    },
+    {
+      "epoch": 15.652173913043478,
+      "grad_norm": 0.05506271496415138,
+      "learning_rate": 0.0009631041251743559,
+      "loss": 0.0132,
+      "step": 1800
+    },
+    {
+      "epoch": 15.652173913043478,
+      "eval_accuracy": 0.9142156862745098,
+      "eval_combined_score": 0.92656683092085,
+      "eval_f1": 0.9389179755671903,
+      "eval_loss": 0.673913836479187,
+      "eval_runtime": 0.5748,
+      "eval_samples_per_second": 709.792,
+      "eval_steps_per_second": 1.74,
+      "step": 1800
+    },
+    {
+      "epoch": 16.52173913043478,
+      "grad_norm": 0.014215093106031418,
+      "learning_rate": 0.0008688483888352111,
+      "loss": 0.0134,
+      "step": 1900
+    },
+    {
+      "epoch": 16.52173913043478,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9126843775484877,
+      "eval_f1": 0.9258589511754068,
+      "eval_loss": 0.625953197479248,
+      "eval_runtime": 0.5727,
+      "eval_samples_per_second": 712.434,
+      "eval_steps_per_second": 1.746,
+      "step": 1900
+    },
+    {
+      "epoch": 17.391304347826086,
+      "grad_norm": 0.03137849271297455,
+      "learning_rate": 0.000775766125554205,
+      "loss": 0.0122,
+      "step": 2000
+    },
+    {
+      "epoch": 17.391304347826086,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9038350634371395,
+      "eval_f1": 0.9204152249134948,
+      "eval_loss": 0.6894273161888123,
+      "eval_runtime": 0.5759,
+      "eval_samples_per_second": 708.407,
+      "eval_steps_per_second": 1.736,
+      "step": 2000
+    },
+    {
+      "epoch": 18.26086956521739,
+      "grad_norm": 0.2494587004184723,
+      "learning_rate": 0.0006846901846358999,
+      "loss": 0.0164,
+      "step": 2100
+    },
+    {
+      "epoch": 18.26086956521739,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9118161250514192,
+      "eval_f1": 0.9265734265734266,
+      "eval_loss": 0.6536701917648315,
+      "eval_runtime": 0.5739,
+      "eval_samples_per_second": 710.931,
+      "eval_steps_per_second": 1.742,
+      "step": 2100
+    },
+    {
+      "epoch": 19.130434782608695,
+      "grad_norm": 1.4710524082183838,
+      "learning_rate": 0.0005964354639070397,
+      "loss": 0.0111,
+      "step": 2200
+    },
+    {
+      "epoch": 19.130434782608695,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.911029411764706,
+      "eval_f1": 0.925,
+      "eval_loss": 0.6434887051582336,
+      "eval_runtime": 0.5745,
+      "eval_samples_per_second": 710.204,
+      "eval_steps_per_second": 1.741,
+      "step": 2200
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0021493160165846348,
+      "learning_rate": 0.0005117916184554203,
+      "loss": 0.0116,
+      "step": 2300
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9092508242234947,
+      "eval_f1": 0.9238938053097345,
+      "eval_loss": 0.7062434554100037,
+      "eval_runtime": 0.573,
+      "eval_samples_per_second": 712.091,
+      "eval_steps_per_second": 1.745,
+      "step": 2300
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 0.08960673213005066,
+      "learning_rate": 0.0004315159952270119,
+      "loss": 0.0065,
+      "step": 2400
+    },
+    {
+      "epoch": 20.869565217391305,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9128179650238474,
+      "eval_f1": 0.9261261261261261,
+      "eval_loss": 0.7081242203712463,
+      "eval_runtime": 0.578,
+      "eval_samples_per_second": 705.838,
+      "eval_steps_per_second": 1.73,
+      "step": 2400
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 0.012382442131638527,
+      "learning_rate": 0.0003563268566987077,
+      "loss": 0.0061,
+      "step": 2500
+    },
+    {
+      "epoch": 21.73913043478261,
+      "eval_accuracy": 0.8946078431372549,
+      "eval_combined_score": 0.9092508242234947,
+      "eval_f1": 0.9238938053097345,
+      "eval_loss": 0.7085114121437073,
+      "eval_runtime": 0.573,
+      "eval_samples_per_second": 712.01,
+      "eval_steps_per_second": 1.745,
+      "step": 2500
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 0.0018653898732736707,
+      "learning_rate": 0.0002868969542575783,
+      "loss": 0.0078,
+      "step": 2600
+    },
+    {
+      "epoch": 22.608695652173914,
+      "eval_accuracy": 0.8872549019607843,
+      "eval_combined_score": 0.9031344932339133,
+      "eval_f1": 0.9190140845070423,
+      "eval_loss": 0.7475114464759827,
+      "eval_runtime": 0.5754,
+      "eval_samples_per_second": 709.044,
+      "eval_steps_per_second": 1.738,
+      "step": 2600
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 0.0017870579613372684,
+      "learning_rate": 0.00022384750878852333,
+      "loss": 0.0038,
+      "step": 2700
+    },
+    {
+      "epoch": 23.47826086956522,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9116873065015481,
+      "eval_f1": 0.9263157894736842,
+      "eval_loss": 0.7797441482543945,
+      "eval_runtime": 0.5734,
+      "eval_samples_per_second": 711.491,
+      "eval_steps_per_second": 1.744,
+      "step": 2700
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 0.001991760218515992,
+      "learning_rate": 0.00016774265232874353,
+      "loss": 0.0059,
+      "step": 2800
+    },
+    {
+      "epoch": 24.347826086956523,
+      "eval_accuracy": 0.9019607843137255,
+      "eval_combined_score": 0.9155193992490613,
+      "eval_f1": 0.9290780141843972,
+      "eval_loss": 0.7348427772521973,
+      "eval_runtime": 0.5751,
+      "eval_samples_per_second": 709.446,
+      "eval_steps_per_second": 1.739,
+      "step": 2800
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 0.000965337676461786,
+      "learning_rate": 0.00011908438052207082,
+      "loss": 0.0029,
+      "step": 2900
+    },
+    {
+      "epoch": 25.217391304347824,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.7361888289451599,
+      "eval_runtime": 0.5744,
+      "eval_samples_per_second": 710.324,
+      "eval_steps_per_second": 1.741,
+      "step": 2900
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 0.0016472822753712535,
+      "learning_rate": 7.830806103584498e-05,
+      "loss": 0.0044,
+      "step": 3000
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_accuracy": 0.8970588235294118,
+      "eval_combined_score": 0.9116873065015481,
+      "eval_f1": 0.9263157894736842,
+      "eval_loss": 0.7820258140563965,
+      "eval_runtime": 0.5737,
+      "eval_samples_per_second": 711.172,
+      "eval_steps_per_second": 1.743,
+      "step": 3000
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 0.001823047990910709,
+      "learning_rate": 4.577853812857102e-05,
+      "loss": 0.0036,
+      "step": 3100
+    },
+    {
+      "epoch": 26.956521739130434,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.7820542454719543,
+      "eval_runtime": 0.5754,
+      "eval_samples_per_second": 709.051,
+      "eval_steps_per_second": 1.738,
+      "step": 3100
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 0.009837474673986435,
+      "learning_rate": 2.178686822255904e-05,
+      "loss": 0.0013,
+      "step": 3200
+    },
+    {
+      "epoch": 27.82608695652174,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.793246328830719,
+      "eval_runtime": 0.5725,
+      "eval_samples_per_second": 712.603,
+      "eval_steps_per_second": 1.747,
+      "step": 3200
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 0.02098868414759636,
+      "learning_rate": 6.547715689861789e-06,
+      "loss": 0.001,
+      "step": 3300
+    },
+    {
+      "epoch": 28.695652173913043,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.7973781824111938,
+      "eval_runtime": 0.5737,
+      "eval_samples_per_second": 711.127,
+      "eval_steps_per_second": 1.743,
+      "step": 3300
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 0.00035156868398189545,
+      "learning_rate": 1.97432152599486e-07,
+      "loss": 0.0017,
+      "step": 3400
+    },
+    {
+      "epoch": 29.565217391304348,
+      "eval_accuracy": 0.8995098039215687,
+      "eval_combined_score": 0.9135996991389148,
+      "eval_f1": 0.927689594356261,
+      "eval_loss": 0.7983468770980835,
+      "eval_runtime": 0.5733,
+      "eval_samples_per_second": 711.635,
+      "eval_steps_per_second": 1.744,
+      "step": 3400
+    },
+    {
+      "epoch": 30.0,
+      "step": 3450,
+      "total_flos": 1.83610838283264e+16,
+      "train_loss": 0.07176048623262972,
+      "train_runtime": 655.6937,
+      "train_samples_per_second": 167.822,
+      "train_steps_per_second": 5.262
+    }
+  ],
+  "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
+}