jasong03 commited on
Commit
ea53439
·
verified ·
1 Parent(s): 88f58aa

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:e140581cf97c2ff49feded27279cbd08eace0495f5afd12562fa8c1906693ba4
3
  size 59021064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52dbb1c7c067e9ba27b2e7da3bb6053b059fd5387007401eacf762b479fae287
3
  size 59021064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba59ea4e8eba7f0640208573e688cfef98d93f03d724499b344550aa047c5607
3
  size 30290452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f428e99ccaf14806440dd3e432b84203b5b3c4c02ab9fd73c2c6c881dbb790
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:fe86356e82949734df1ffbf4ca1d6d4aad55d9e61b90271979f2d574e6a34d95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29da30c716a7b51d3364ebf232268bdcf561ec7f62aed00ffc0af7bb38312f0
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": 1.9985210378020464e-05,
1058
  "loss": 2.5719,
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": 1.9985210378020464e-05,
1058
  "loss": 2.5719,
1059
  "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 3.285126799177519,
1063
+ "grad_norm": 0.10682094097137451,
1064
+ "learning_rate": 1.9984400346486818e-05,
1065
+ "loss": 2.5789,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 3.307059629883482,
1070
+ "grad_norm": 0.07144833356142044,
1071
+ "learning_rate": 1.9983568736882576e-05,
1072
+ "loss": 2.6486,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 3.3289924605894448,
1077
+ "grad_norm": 0.0906018614768982,
1078
+ "learning_rate": 1.9982715551005004e-05,
1079
+ "loss": 2.5802,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 3.350925291295408,
1084
+ "grad_norm": 0.07979454845190048,
1085
+ "learning_rate": 1.998184079069798e-05,
1086
+ "loss": 2.6363,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 3.3728581220013707,
1091
+ "grad_norm": 0.07958266884088516,
1092
+ "learning_rate": 1.998094445785203e-05,
1093
+ "loss": 2.5702,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 3.394790952707334,
1098
+ "grad_norm": 0.09631014615297318,
1099
+ "learning_rate": 1.9980026554404273e-05,
1100
+ "loss": 2.4837,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 3.4167237834132966,
1105
+ "grad_norm": 0.07759011536836624,
1106
+ "learning_rate": 1.9979087082338475e-05,
1107
+ "loss": 2.5704,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 3.43865661411926,
1112
+ "grad_norm": 0.10578745603561401,
1113
+ "learning_rate": 1.9978126043684995e-05,
1114
+ "loss": 2.4912,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 3.4605894448252226,
1119
+ "grad_norm": 0.07946617901325226,
1120
+ "learning_rate": 1.9977143440520816e-05,
1121
+ "loss": 2.534,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 3.4825222755311858,
1126
+ "grad_norm": 0.11045356839895248,
1127
+ "learning_rate": 1.9976139274969507e-05,
1128
+ "loss": 2.4873,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 3.504455106237149,
1133
+ "grad_norm": 0.07916330546140671,
1134
+ "learning_rate": 1.9975113549201262e-05,
1135
+ "loss": 2.5131,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 3.5263879369431117,
1140
+ "grad_norm": 0.08077295124530792,
1141
+ "learning_rate": 1.997406626543285e-05,
1142
+ "loss": 2.503,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 3.5483207676490744,
1147
+ "grad_norm": 0.07065772265195847,
1148
+ "learning_rate": 1.9972997425927643e-05,
1149
+ "loss": 2.5109,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 3.5702535983550376,
1154
+ "grad_norm": 0.06934299319982529,
1155
+ "learning_rate": 1.997190703299559e-05,
1156
+ "loss": 2.5821,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 3.592186429061001,
1161
+ "grad_norm": 0.08165900409221649,
1162
+ "learning_rate": 1.9970795088993223e-05,
1163
+ "loss": 2.563,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 3.6141192597669636,
1168
+ "grad_norm": 0.227840855717659,
1169
+ "learning_rate": 1.9969661596323656e-05,
1170
+ "loss": 2.4826,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 3.6360520904729268,
1175
+ "grad_norm": 0.09745700657367706,
1176
+ "learning_rate": 1.9968506557436567e-05,
1177
+ "loss": 2.5694,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 3.6579849211788895,
1182
+ "grad_norm": 0.06451422721147537,
1183
+ "learning_rate": 1.99673299748282e-05,
1184
+ "loss": 2.5795,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 3.6799177518848527,
1189
+ "grad_norm": 0.37331581115722656,
1190
+ "learning_rate": 1.996613185104136e-05,
1191
+ "loss": 2.4005,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 3.701850582590816,
1196
+ "grad_norm": 0.10922300815582275,
1197
+ "learning_rate": 1.9964912188665407e-05,
1198
+ "loss": 2.6179,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 3.7237834132967786,
1203
+ "grad_norm": 0.0699249655008316,
1204
+ "learning_rate": 1.9963670990336253e-05,
1205
+ "loss": 2.5814,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 3.7457162440027414,
1210
+ "grad_norm": 0.10342008620500565,
1211
+ "learning_rate": 1.9962408258736343e-05,
1212
+ "loss": 2.6033,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 3.7676490747087046,
1217
+ "grad_norm": 0.0686383843421936,
1218
+ "learning_rate": 1.9961123996594667e-05,
1219
+ "loss": 2.5201,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 3.7895819054146678,
1224
+ "grad_norm": 0.07538346201181412,
1225
+ "learning_rate": 1.9959818206686746e-05,
1226
+ "loss": 2.5111,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 3.8115147361206305,
1231
+ "grad_norm": 0.09987260401248932,
1232
+ "learning_rate": 1.9958490891834622e-05,
1233
+ "loss": 2.4405,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 3.8334475668265937,
1238
+ "grad_norm": 0.0893922969698906,
1239
+ "learning_rate": 1.9957142054906865e-05,
1240
+ "loss": 2.5832,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 3.8553803975325565,
1245
+ "grad_norm": 0.15604530274868011,
1246
+ "learning_rate": 1.9955771698818546e-05,
1247
+ "loss": 2.5808,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 3.8773132282385196,
1252
+ "grad_norm": 0.06112189590930939,
1253
+ "learning_rate": 1.9954379826531252e-05,
1254
+ "loss": 2.557,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 3.8992460589444824,
1259
+ "grad_norm": 0.06319453567266464,
1260
+ "learning_rate": 1.9952966441053068e-05,
1261
+ "loss": 2.5131,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 3.9211788896504456,
1266
+ "grad_norm": 0.0734332725405693,
1267
+ "learning_rate": 1.995153154543857e-05,
1268
+ "loss": 2.5174,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 3.9431117203564083,
1273
+ "grad_norm": 0.10146480053663254,
1274
+ "learning_rate": 1.9950075142788825e-05,
1275
+ "loss": 2.5421,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 3.9650445510623715,
1280
+ "grad_norm": 0.07505933940410614,
1281
+ "learning_rate": 1.9948597236251383e-05,
1282
+ "loss": 2.5325,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 3.9869773817683347,
1287
+ "grad_norm": 0.062325164675712585,
1288
+ "learning_rate": 1.9947097829020252e-05,
1289
+ "loss": 2.4771,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 4.0,
1294
+ "grad_norm": 0.07560485601425171,
1295
+ "learning_rate": 1.994557692433593e-05,
1296
+ "loss": 2.7176,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 4.021932830705963,
1301
+ "grad_norm": 0.07008741050958633,
1302
+ "learning_rate": 1.994403452548536e-05,
1303
+ "loss": 2.5798,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 4.043865661411926,
1308
+ "grad_norm": 0.048197850584983826,
1309
+ "learning_rate": 1.9942470635801936e-05,
1310
+ "loss": 2.497,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 4.065798492117889,
1315
+ "grad_norm": 0.0692463144659996,
1316
+ "learning_rate": 1.994088525866551e-05,
1317
+ "loss": 2.603,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 4.087731322823852,
1322
+ "grad_norm": 0.05762163922190666,
1323
+ "learning_rate": 1.993927839750236e-05,
1324
+ "loss": 2.5735,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 4.109664153529815,
1329
+ "grad_norm": 0.052715737372636795,
1330
+ "learning_rate": 1.9937650055785204e-05,
1331
+ "loss": 2.4437,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 4.131596984235778,
1336
+ "grad_norm": 0.06728165596723557,
1337
+ "learning_rate": 1.9936000237033175e-05,
1338
+ "loss": 2.5553,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 4.153529814941741,
1343
+ "grad_norm": 0.06328797340393066,
1344
+ "learning_rate": 1.993432894481183e-05,
1345
+ "loss": 2.5226,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 4.175462645647704,
1350
+ "grad_norm": 0.05177456885576248,
1351
+ "learning_rate": 1.9932636182733126e-05,
1352
+ "loss": 2.4486,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 4.197395476353667,
1357
+ "grad_norm": 0.04876350983977318,
1358
+ "learning_rate": 1.993092195445542e-05,
1359
+ "loss": 2.5473,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 4.21932830705963,
1364
+ "grad_norm": 0.07933732122182846,
1365
+ "learning_rate": 1.9929186263683475e-05,
1366
+ "loss": 2.6092,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 4.241261137765592,
1371
+ "grad_norm": 0.049367763102054596,
1372
+ "learning_rate": 1.992742911416842e-05,
1373
+ "loss": 2.5666,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 4.263193968471556,
1378
+ "grad_norm": 0.06599163264036179,
1379
+ "learning_rate": 1.9925650509707776e-05,
1380
+ "loss": 2.5365,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 4.285126799177519,
1385
+ "grad_norm": 0.06409162282943726,
1386
+ "learning_rate": 1.9923850454145416e-05,
1387
+ "loss": 2.6515,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 4.307059629883482,
1392
+ "grad_norm": 0.05242309346795082,
1393
+ "learning_rate": 1.992202895137159e-05,
1394
+ "loss": 2.5379,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 4.328992460589445,
1399
+ "grad_norm": 0.052728235721588135,
1400
+ "learning_rate": 1.9920186005322885e-05,
1401
+ "loss": 2.5069,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 4.3509252912954075,
1406
+ "grad_norm": 0.05289866030216217,
1407
+ "learning_rate": 1.9918321619982238e-05,
1408
+ "loss": 2.5229,
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