jasong03 commited on
Commit
9b1158f
·
verified ·
1 Parent(s): b050610

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d677ee422d7d952d82e155501d8cedf29701adb2bc408cddedcd4a2effc7a9b
3
  size 59021064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b098f5be97368564400daa33e61e01649d6898d5f945ead65c7699fe89f22c2
3
  size 59021064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44a7c8de71650802e9962c5585657526f55438d992b89e4f9c1d9b9076e1490e
3
  size 30290452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e21724620d938204f90c9851c1ae3b89f43daf4cec5db4c95ee7cd30653c2b4c
3
  size 30290452
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8abf2c3a2d675d09f86f31a4bbaac529a18147ee9c2568ece2b0294dff92a441
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f619428f22a65bad4c67283dd32446722a932445baa6cbcfa5dc672cec70838
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f35320c42144c7251b9b46e1825ad1d96489c18d4a0a4f57d23b19abb29d8223
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861460d28a40118010decbc24a8a35b7c62b696146d598c3f8218a79b43aff1e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.2631939684715556,
5
  "eval_steps": 500,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1057,6 +1057,356 @@
1057
  "learning_rate": 1.5943133835480536e-05,
1058
  "loss": 2.5524,
1059
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1060
  }
1061
  ],
1062
  "logging_steps": 1,
@@ -1076,7 +1426,7 @@
1076
  "attributes": {}
1077
  }
1078
  },
1079
- "total_flos": 3.2639143951466496e+17,
1080
  "train_batch_size": 1,
1081
  "trial_name": null,
1082
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.3509252912954075,
5
  "eval_steps": 500,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1057
  "learning_rate": 1.5943133835480536e-05,
1058
  "loss": 2.5524,
1059
  "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 3.285126799177519,
1063
+ "grad_norm": 0.07187870889902115,
1064
+ "learning_rate": 1.588380316067307e-05,
1065
+ "loss": 2.5522,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 3.307059629883482,
1070
+ "grad_norm": 0.06179989129304886,
1071
+ "learning_rate": 1.582415399266036e-05,
1072
+ "loss": 2.6259,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 3.3289924605894448,
1077
+ "grad_norm": 0.0755513459444046,
1078
+ "learning_rate": 1.5764189560281677e-05,
1079
+ "loss": 2.5568,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 3.350925291295408,
1084
+ "grad_norm": 0.08130097389221191,
1085
+ "learning_rate": 1.5703913109441715e-05,
1086
+ "loss": 2.6148,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 3.3728581220013707,
1091
+ "grad_norm": 0.07435321062803268,
1092
+ "learning_rate": 1.564332790293487e-05,
1093
+ "loss": 2.5511,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 3.394790952707334,
1098
+ "grad_norm": 0.05641249567270279,
1099
+ "learning_rate": 1.5582437220268648e-05,
1100
+ "loss": 2.4647,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 3.4167237834132966,
1105
+ "grad_norm": 0.05596217140555382,
1106
+ "learning_rate": 1.5521244357486132e-05,
1107
+ "loss": 2.5502,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 3.43865661411926,
1112
+ "grad_norm": 0.06887087225914001,
1113
+ "learning_rate": 1.5459752626987563e-05,
1114
+ "loss": 2.4662,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 3.4605894448252226,
1119
+ "grad_norm": 0.06323248893022537,
1120
+ "learning_rate": 1.5397965357351035e-05,
1121
+ "loss": 2.5123,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 3.4825222755311858,
1126
+ "grad_norm": 0.09084805101156235,
1127
+ "learning_rate": 1.5335885893152335e-05,
1128
+ "loss": 2.4644,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 3.504455106237149,
1133
+ "grad_norm": 0.07094909995794296,
1134
+ "learning_rate": 1.5273517594783878e-05,
1135
+ "loss": 2.493,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 3.5263879369431117,
1140
+ "grad_norm": 0.04841725155711174,
1141
+ "learning_rate": 1.521086383827282e-05,
1142
+ "loss": 2.4868,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 3.5483207676490744,
1147
+ "grad_norm": 0.062218405306339264,
1148
+ "learning_rate": 1.5147928015098309e-05,
1149
+ "loss": 2.4924,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 3.5702535983550376,
1154
+ "grad_norm": 0.06784085184335709,
1155
+ "learning_rate": 1.5084713532007906e-05,
1156
+ "loss": 2.5649,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 3.592186429061001,
1161
+ "grad_norm": 0.07132422924041748,
1162
+ "learning_rate": 1.5021223810833165e-05,
1163
+ "loss": 2.5442,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 3.6141192597669636,
1168
+ "grad_norm": 0.05512155964970589,
1169
+ "learning_rate": 1.4957462288304421e-05,
1170
+ "loss": 2.4669,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 3.6360520904729268,
1175
+ "grad_norm": 0.060434065759181976,
1176
+ "learning_rate": 1.489343241586475e-05,
1177
+ "loss": 2.549,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 3.6579849211788895,
1182
+ "grad_norm": 0.05476135015487671,
1183
+ "learning_rate": 1.4829137659483144e-05,
1184
+ "loss": 2.5643,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 3.6799177518848527,
1189
+ "grad_norm": 0.06881222128868103,
1190
+ "learning_rate": 1.4764581499466895e-05,
1191
+ "loss": 2.3814,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 3.701850582590816,
1196
+ "grad_norm": 0.08369456231594086,
1197
+ "learning_rate": 1.4699767430273202e-05,
1198
+ "loss": 2.5987,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 3.7237834132967786,
1203
+ "grad_norm": 0.05814111605286598,
1204
+ "learning_rate": 1.4634698960320018e-05,
1205
+ "loss": 2.5668,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 3.7457162440027414,
1210
+ "grad_norm": 0.05372776836156845,
1211
+ "learning_rate": 1.4569379611796137e-05,
1212
+ "loss": 2.5888,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 3.7676490747087046,
1217
+ "grad_norm": 0.060161709785461426,
1218
+ "learning_rate": 1.4503812920470535e-05,
1219
+ "loss": 2.5052,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 3.7895819054146678,
1224
+ "grad_norm": 0.06631386280059814,
1225
+ "learning_rate": 1.443800243550098e-05,
1226
+ "loss": 2.4963,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 3.8115147361206305,
1231
+ "grad_norm": 0.06452737748622894,
1232
+ "learning_rate": 1.4371951719241906e-05,
1233
+ "loss": 2.4251,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 3.8334475668265937,
1238
+ "grad_norm": 0.09428981691598892,
1239
+ "learning_rate": 1.4305664347051586e-05,
1240
+ "loss": 2.5676,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 3.8553803975325565,
1245
+ "grad_norm": 0.050980083644390106,
1246
+ "learning_rate": 1.423914390709861e-05,
1247
+ "loss": 2.5683,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 3.8773132282385196,
1252
+ "grad_norm": 0.05442551150918007,
1253
+ "learning_rate": 1.4172394000167625e-05,
1254
+ "loss": 2.5449,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 3.8992460589444824,
1259
+ "grad_norm": 0.04739952087402344,
1260
+ "learning_rate": 1.4105418239464452e-05,
1261
+ "loss": 2.5018,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 3.9211788896504456,
1266
+ "grad_norm": 0.06977739185094833,
1267
+ "learning_rate": 1.4038220250420487e-05,
1268
+ "loss": 2.5065,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 3.9431117203564083,
1273
+ "grad_norm": 0.09621317684650421,
1274
+ "learning_rate": 1.3970803670496453e-05,
1275
+ "loss": 2.5293,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 3.9650445510623715,
1280
+ "grad_norm": 0.07425831258296967,
1281
+ "learning_rate": 1.390317214898551e-05,
1282
+ "loss": 2.5197,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 3.9869773817683347,
1287
+ "grad_norm": 0.05756077170372009,
1288
+ "learning_rate": 1.3835329346815716e-05,
1289
+ "loss": 2.4661,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 4.0,
1294
+ "grad_norm": 0.07039082795381546,
1295
+ "learning_rate": 1.3767278936351853e-05,
1296
+ "loss": 2.7058,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 4.021932830705963,
1301
+ "grad_norm": 0.06809078902006149,
1302
+ "learning_rate": 1.3699024601196641e-05,
1303
+ "loss": 2.5684,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 4.043865661411926,
1308
+ "grad_norm": 0.044164013117551804,
1309
+ "learning_rate": 1.3630570035991352e-05,
1310
+ "loss": 2.4878,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 4.065798492117889,
1315
+ "grad_norm": 0.07478977739810944,
1316
+ "learning_rate": 1.3561918946215807e-05,
1317
+ "loss": 2.5928,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 4.087731322823852,
1322
+ "grad_norm": 0.053608592599630356,
1323
+ "learning_rate": 1.34930750479878e-05,
1324
+ "loss": 2.5654,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 4.109664153529815,
1329
+ "grad_norm": 0.049672599881887436,
1330
+ "learning_rate": 1.3424042067861944e-05,
1331
+ "loss": 2.4353,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 4.131596984235778,
1336
+ "grad_norm": 0.07206689566373825,
1337
+ "learning_rate": 1.335482374262795e-05,
1338
+ "loss": 2.5453,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 4.153529814941741,
1343
+ "grad_norm": 0.059480294585227966,
1344
+ "learning_rate": 1.3285423819108349e-05,
1345
+ "loss": 2.5138,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 4.175462645647704,
1350
+ "grad_norm": 0.05027122050523758,
1351
+ "learning_rate": 1.3215846053955683e-05,
1352
+ "loss": 2.441,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 4.197395476353667,
1357
+ "grad_norm": 0.04946836456656456,
1358
+ "learning_rate": 1.3146094213449148e-05,
1359
+ "loss": 2.5398,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 4.21932830705963,
1364
+ "grad_norm": 0.073307566344738,
1365
+ "learning_rate": 1.3076172073290726e-05,
1366
+ "loss": 2.5996,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 4.241261137765592,
1371
+ "grad_norm": 0.04758650064468384,
1372
+ "learning_rate": 1.3006083418400799e-05,
1373
+ "loss": 2.5598,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 4.263193968471556,
1378
+ "grad_norm": 0.0642954632639885,
1379
+ "learning_rate": 1.2935832042713288e-05,
1380
+ "loss": 2.53,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 4.285126799177519,
1385
+ "grad_norm": 0.06495189666748047,
1386
+ "learning_rate": 1.2865421748970257e-05,
1387
+ "loss": 2.6442,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 4.307059629883482,
1392
+ "grad_norm": 0.05023903772234917,
1393
+ "learning_rate": 1.2794856348516095e-05,
1394
+ "loss": 2.5318,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 4.328992460589445,
1399
+ "grad_norm": 0.04791835695505142,
1400
+ "learning_rate": 1.2724139661091188e-05,
1401
+ "loss": 2.5011,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 4.3509252912954075,
1406
+ "grad_norm": 0.0522720031440258,
1407
+ "learning_rate": 1.2653275514625165e-05,
1408
+ "loss": 2.5169,
1409
+ "step": 200
1410
  }
1411
  ],
1412
  "logging_steps": 1,
 
1426
  "attributes": {}
1427
  }
1428
  },
1429
+ "total_flos": 4.351885860195533e+17,
1430
  "train_batch_size": 1,
1431
  "trial_name": null,
1432
  "trial_params": null