prxy5606 commited on
Commit
a26516f
·
verified ·
1 Parent(s): 8e0929c

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 sha256:95be0d19157edc8f15c0bd8cf35ad27b3bc5e9c0e25521a169a7e8e835389578
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125f0667759393e8b31c82ddeb654b89f1e279d1c75cb93b275ef82203f1c58d
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08a8a218dd326b1107cff46263d88cadf68a4d82e7ddf91ff357f4c57c1a54e8
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65505a64e957cf3699db3093f6aed4a1c2e98d82bb850093a98e7b1c9ea975f1
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fc8373d93ddeb51d80809b23724c056f0f9376cba8673cc52b33c10488dde5a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e350c4ea83a6c4f0e421c99dc7d650c8268593e4783417f80f54648cb45e5eb7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.153057336807251,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.09302325581395349,
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": 26.547,
1090
  "eval_steps_per_second": 6.637,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1112,12 +1470,12 @@
1112
  "should_evaluate": false,
1113
  "should_log": false,
1114
  "should_save": true,
1115
- "should_training_stop": false
1116
  },
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 6.700806212419584e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1455647945404053,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.12403100775193798,
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": 26.547,
1090
  "eval_steps_per_second": 6.637,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.09364341085271317,
1095
+ "grad_norm": 0.10860100388526917,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.6042,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.09426356589147286,
1102
+ "grad_norm": 0.14194871485233307,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.4467,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.09488372093023256,
1109
+ "grad_norm": 0.11349450051784515,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.3209,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.09550387596899225,
1116
+ "grad_norm": 0.12873560190200806,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 1.3321,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.09612403100775194,
1123
+ "grad_norm": 0.11935944110155106,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 1.3027,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.09674418604651162,
1130
+ "grad_norm": 0.11928416788578033,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 1.3033,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.09736434108527131,
1137
+ "grad_norm": 0.11890328675508499,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 1.3474,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.09798449612403101,
1144
+ "grad_norm": 0.11656662821769714,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.2582,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.0986046511627907,
1151
+ "grad_norm": 0.1079067811369896,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.2472,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.09922480620155039,
1158
+ "grad_norm": 0.11712710559368134,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.3365,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.09984496124031007,
1165
+ "grad_norm": 0.11288685351610184,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.3426,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.10046511627906977,
1172
+ "grad_norm": 0.1056363582611084,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 1.3034,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.10108527131782946,
1179
+ "grad_norm": 0.1013500913977623,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 1.2612,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.10170542635658915,
1186
+ "grad_norm": 0.10476074367761612,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 1.337,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.10232558139534884,
1193
+ "grad_norm": 0.09871833026409149,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.306,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.10294573643410852,
1200
+ "grad_norm": 0.09859535843133926,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.2699,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.10356589147286822,
1207
+ "grad_norm": 0.09351277351379395,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.3122,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.10418604651162791,
1214
+ "grad_norm": 0.1069040596485138,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.2367,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.1048062015503876,
1221
+ "grad_norm": 0.11953876167535782,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 1.1204,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.10542635658914729,
1228
+ "grad_norm": 0.11346074193716049,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.2051,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.10604651162790697,
1235
+ "grad_norm": 0.09117977321147919,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 1.2328,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.10666666666666667,
1242
+ "grad_norm": 0.09915192425251007,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.205,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.10728682170542636,
1249
+ "grad_norm": 0.09774057567119598,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 1.2009,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.10790697674418605,
1256
+ "grad_norm": 0.10364478826522827,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.2175,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.10852713178294573,
1263
+ "grad_norm": 0.10799111425876617,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.2195,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.10914728682170542,
1270
+ "grad_norm": 0.11679966747760773,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.2075,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.10976744186046512,
1277
+ "grad_norm": 0.115420401096344,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 1.2249,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.11038759689922481,
1284
+ "grad_norm": 0.12822076678276062,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 1.2099,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.1110077519379845,
1291
+ "grad_norm": 0.12438376247882843,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.1975,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.11162790697674418,
1298
+ "grad_norm": 0.1283199042081833,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 1.1447,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.11224806201550387,
1305
+ "grad_norm": 0.12820540368556976,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 1.1846,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.11286821705426357,
1312
+ "grad_norm": 0.13904087245464325,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.1244,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.11348837209302326,
1319
+ "grad_norm": 0.14931564033031464,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 1.1839,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.11410852713178295,
1326
+ "grad_norm": 0.1478007733821869,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 1.166,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.11472868217054263,
1333
+ "grad_norm": 0.15556959807872772,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 1.039,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.11534883720930232,
1340
+ "grad_norm": 0.1660860776901245,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.9418,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.11596899224806202,
1347
+ "grad_norm": 0.15761886537075043,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 1.1031,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.11658914728682171,
1354
+ "grad_norm": 0.17165237665176392,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.9677,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.1172093023255814,
1361
+ "grad_norm": 0.16813836991786957,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.9772,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.11782945736434108,
1368
+ "grad_norm": 0.18344461917877197,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.8545,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.11844961240310077,
1375
+ "grad_norm": 0.19450584053993225,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.8741,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.11906976744186047,
1382
+ "grad_norm": 0.18070702254772186,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.9445,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.11968992248062016,
1389
+ "grad_norm": 0.1926768273115158,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.9059,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.12031007751937985,
1396
+ "grad_norm": 0.19076108932495117,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.9797,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.12093023255813953,
1403
+ "grad_norm": 0.195748433470726,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.9198,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.12155038759689922,
1410
+ "grad_norm": 0.20470620691776276,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.8694,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.12217054263565892,
1417
+ "grad_norm": 0.20787949860095978,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.8156,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.12279069767441861,
1424
+ "grad_norm": 0.2252711057662964,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.8061,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.1234108527131783,
1431
+ "grad_norm": 0.2498621642589569,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.7947,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.12403100775193798,
1438
+ "grad_norm": 0.28271934390068054,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.6973,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.12403100775193798,
1445
+ "eval_loss": 1.1455647945404053,
1446
+ "eval_runtime": 102.4074,
1447
+ "eval_samples_per_second": 26.522,
1448
+ "eval_steps_per_second": 6.63,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1470
  "should_evaluate": false,
1471
  "should_log": false,
1472
  "should_save": true,
1473
+ "should_training_stop": true
1474
  },
1475
  "attributes": {}
1476
  }
1477
  },
1478
+ "total_flos": 8.926135682963866e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null