adammandic87 commited on
Commit
3e2050a
·
verified ·
1 Parent(s): cd37ad3

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 sha256:96357fb0e78da9ddeb7d0598f32802b96afa2016adac01d085bf291b0c7ef24c
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0854de05ff06a1bb6bebc463437e23deac75cb2c91c516e856d79e5ce02f0d
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dd1c739c74a63dd88e6d988da0a91c90e23f03715aa8b6de63c6414165820fc
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf6db02e4e23668a02eda25306d34b08e2c20f7be9971b73b2f4cd1fc571fe0
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2fb8dc2a85d0cc09b3d729bf71a8da974bf095341dbe298d83978634de38d32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982eb43f0b685032f5d229850fc4c6116b1560071673bb981b13063a46a6b3e1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
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": 0.028351367953503757,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1089,6 +1089,364 @@
1089
  "eval_samples_per_second": 279.253,
1090
  "eval_steps_per_second": 139.626,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1103,12 +1461,12 @@
1103
  "should_evaluate": false,
1104
  "should_log": false,
1105
  "should_save": true,
1106
- "should_training_stop": false
1107
  },
1108
  "attributes": {}
1109
  }
1110
  },
1111
- "total_flos": 3879272448000.0,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.037801823938005005,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 279.253,
1090
  "eval_steps_per_second": 139.626,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.028540377073193783,
1095
+ "grad_norm": 0.06216558441519737,
1096
+ "learning_rate": 3.106465908814342e-05,
1097
+ "loss": 10.3635,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.028729386192883805,
1102
+ "grad_norm": 0.05615238845348358,
1103
+ "learning_rate": 2.9876321572751144e-05,
1104
+ "loss": 10.3545,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.02891839531257383,
1109
+ "grad_norm": 0.057838547974824905,
1110
+ "learning_rate": 2.87071551708603e-05,
1111
+ "loss": 10.3583,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.029107404432263857,
1116
+ "grad_norm": 0.052986498922109604,
1117
+ "learning_rate": 2.7557479520891104e-05,
1118
+ "loss": 10.3552,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.029296413551953882,
1123
+ "grad_norm": 0.055312514305114746,
1124
+ "learning_rate": 2.6427608932686843e-05,
1125
+ "loss": 10.356,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.029485422671643908,
1130
+ "grad_norm": 0.05807175859808922,
1131
+ "learning_rate": 2.5317852301584643e-05,
1132
+ "loss": 10.3565,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.029674431791333934,
1137
+ "grad_norm": 0.06103501841425896,
1138
+ "learning_rate": 2.422851302396655e-05,
1139
+ "loss": 10.3547,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.029863440911023956,
1144
+ "grad_norm": 0.05311097204685211,
1145
+ "learning_rate": 2.315988891431412e-05,
1146
+ "loss": 10.355,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.03005245003071398,
1151
+ "grad_norm": 0.05598808079957962,
1152
+ "learning_rate": 2.2112272123788768e-05,
1153
+ "loss": 10.3571,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.030241459150404007,
1158
+ "grad_norm": 0.05674521625041962,
1159
+ "learning_rate": 2.1085949060360654e-05,
1160
+ "loss": 10.3537,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.030430468270094033,
1165
+ "grad_norm": 0.05536748096346855,
1166
+ "learning_rate": 2.008120031050753e-05,
1167
+ "loss": 10.3545,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.03061947738978406,
1172
+ "grad_norm": 0.051667895168066025,
1173
+ "learning_rate": 1.9098300562505266e-05,
1174
+ "loss": 10.3562,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.03080848650947408,
1179
+ "grad_norm": 0.05974581092596054,
1180
+ "learning_rate": 1.8137518531330767e-05,
1181
+ "loss": 10.3538,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.030997495629164106,
1186
+ "grad_norm": 0.05384739860892296,
1187
+ "learning_rate": 1.7199116885197995e-05,
1188
+ "loss": 10.3574,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.031186504748854132,
1193
+ "grad_norm": 0.06221851706504822,
1194
+ "learning_rate": 1.6283352173747145e-05,
1195
+ "loss": 10.3545,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.031375513868544154,
1200
+ "grad_norm": 0.05726971849799156,
1201
+ "learning_rate": 1.5390474757906446e-05,
1202
+ "loss": 10.3546,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.03156452298823418,
1207
+ "grad_norm": 0.061142805963754654,
1208
+ "learning_rate": 1.4520728741446089e-05,
1209
+ "loss": 10.3572,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.031753532107924205,
1214
+ "grad_norm": 0.055892013013362885,
1215
+ "learning_rate": 1.3674351904242611e-05,
1216
+ "loss": 10.3557,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.03194254122761423,
1221
+ "grad_norm": 0.04323485121130943,
1222
+ "learning_rate": 1.2851575637272262e-05,
1223
+ "loss": 10.3557,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.03213155034730426,
1228
+ "grad_norm": 0.060065269470214844,
1229
+ "learning_rate": 1.2052624879351104e-05,
1230
+ "loss": 10.358,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.03232055946699428,
1235
+ "grad_norm": 0.05526785925030708,
1236
+ "learning_rate": 1.1277718055638819e-05,
1237
+ "loss": 10.3573,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.03250956858668431,
1242
+ "grad_norm": 0.05861446261405945,
1243
+ "learning_rate": 1.0527067017923654e-05,
1244
+ "loss": 10.3558,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.032698577706374334,
1249
+ "grad_norm": 0.04735025390982628,
1250
+ "learning_rate": 9.80087698670411e-06,
1251
+ "loss": 10.36,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.03288758682606436,
1256
+ "grad_norm": 0.05781494081020355,
1257
+ "learning_rate": 9.09934649508375e-06,
1258
+ "loss": 10.3573,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.033076595945754385,
1263
+ "grad_norm": 0.050222914665937424,
1264
+ "learning_rate": 8.422667334494249e-06,
1265
+ "loss": 10.3582,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.03326560506544441,
1270
+ "grad_norm": 0.048023052513599396,
1271
+ "learning_rate": 7.771024502261526e-06,
1272
+ "loss": 10.3555,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.033454614185134436,
1277
+ "grad_norm": 0.05381546914577484,
1278
+ "learning_rate": 7.144596151029303e-06,
1279
+ "loss": 10.3539,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.033643623304824455,
1284
+ "grad_norm": 0.047901567071676254,
1285
+ "learning_rate": 6.543553540053926e-06,
1286
+ "loss": 10.3579,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.03383263242451448,
1291
+ "grad_norm": 0.06044565513730049,
1292
+ "learning_rate": 5.968060988383883e-06,
1293
+ "loss": 10.3576,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.034021641544204506,
1298
+ "grad_norm": 0.046510256826877594,
1299
+ "learning_rate": 5.418275829936537e-06,
1300
+ "loss": 10.3577,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.03421065066389453,
1305
+ "grad_norm": 0.06163431704044342,
1306
+ "learning_rate": 4.8943483704846475e-06,
1307
+ "loss": 10.3548,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.03439965978358456,
1312
+ "grad_norm": 0.04503452777862549,
1313
+ "learning_rate": 4.3964218465642355e-06,
1314
+ "loss": 10.3549,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.03458866890327458,
1319
+ "grad_norm": 0.06345223635435104,
1320
+ "learning_rate": 3.924632386315186e-06,
1321
+ "loss": 10.3554,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.03477767802296461,
1326
+ "grad_norm": 0.06070295348763466,
1327
+ "learning_rate": 3.4791089722651436e-06,
1328
+ "loss": 10.3572,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.034966687142654634,
1333
+ "grad_norm": 0.056091003119945526,
1334
+ "learning_rate": 3.059973406066963e-06,
1335
+ "loss": 10.3572,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.03515569626234466,
1340
+ "grad_norm": 0.06234334036707878,
1341
+ "learning_rate": 2.667340275199426e-06,
1342
+ "loss": 10.3522,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.035344705382034686,
1347
+ "grad_norm": 0.060099318623542786,
1348
+ "learning_rate": 2.3013169216400733e-06,
1349
+ "loss": 10.3557,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.03553371450172471,
1354
+ "grad_norm": 0.04145883023738861,
1355
+ "learning_rate": 1.9620034125190644e-06,
1356
+ "loss": 10.3583,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.03572272362141473,
1361
+ "grad_norm": 0.06402470171451569,
1362
+ "learning_rate": 1.6494925127617634e-06,
1363
+ "loss": 10.3515,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.035911732741104756,
1368
+ "grad_norm": 0.054933883249759674,
1369
+ "learning_rate": 1.3638696597277679e-06,
1370
+ "loss": 10.3598,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.03610074186079478,
1375
+ "grad_norm": 0.058887969702482224,
1376
+ "learning_rate": 1.1052129398531507e-06,
1377
+ "loss": 10.3567,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.03628975098048481,
1382
+ "grad_norm": 0.057484857738018036,
1383
+ "learning_rate": 8.735930673024806e-07,
1384
+ "loss": 10.3565,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.03647876010017483,
1389
+ "grad_norm": 0.057735905051231384,
1390
+ "learning_rate": 6.690733646361857e-07,
1391
+ "loss": 10.357,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.03666776921986486,
1396
+ "grad_norm": 0.05184992402791977,
1397
+ "learning_rate": 4.917097454988584e-07,
1398
+ "loss": 10.3594,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.036856778339554884,
1403
+ "grad_norm": 0.061963826417922974,
1404
+ "learning_rate": 3.415506993330153e-07,
1405
+ "loss": 10.3577,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.03704578745924491,
1410
+ "grad_norm": 0.06438171863555908,
1411
+ "learning_rate": 2.1863727812254653e-07,
1412
+ "loss": 10.3575,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.037234796578934935,
1417
+ "grad_norm": 0.05486460402607918,
1418
+ "learning_rate": 1.230030851695263e-07,
1419
+ "loss": 10.3526,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.03742380569862496,
1424
+ "grad_norm": 0.05459611490368843,
1425
+ "learning_rate": 5.467426590739511e-08,
1426
+ "loss": 10.3542,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.03761281481831499,
1431
+ "grad_norm": 0.05004322901368141,
1432
+ "learning_rate": 1.3669500753099585e-08,
1433
+ "loss": 10.3573,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.037801823938005005,
1438
+ "grad_norm": 0.06536795943975449,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 10.3544,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.037801823938005005,
1445
+ "eval_loss": 10.35628604888916,
1446
+ "eval_runtime": 7.8439,
1447
+ "eval_samples_per_second": 284.041,
1448
+ "eval_steps_per_second": 142.021,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "should_evaluate": false,
1462
  "should_log": false,
1463
  "should_save": true,
1464
+ "should_training_stop": true
1465
  },
1466
  "attributes": {}
1467
  }
1468
  },
1469
+ "total_flos": 5172363264000.0,
1470
  "train_batch_size": 2,
1471
  "trial_name": null,
1472
  "trial_params": null