prxy5608 commited on
Commit
c0227e5
·
verified ·
1 Parent(s): 3e64ee1

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 sha256:5d490b306231ba6f490f9f1cb2b4fdc9b062b5d04e5933af38bce20d470950c9
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed2c66f3672692a1823e21b3270b2715fcccf1d3229ea59e9f67d93a36bd6c8
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d23bc811e2cc9ce957162eb0ff2e83679cdd51ba0db138a0d16ac04706db845f
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65371d27274beb37ece7c7642cf499ff2ce640794801355cb9a6fc8f3bef46b
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a7aa262f490b58e038a6eb5a21c8e6014c8364d4b7c5a6669d70dbd66e53011
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f0fc4c2ec99ba0d00b37378d8f70486ef532a34e132f69d1f3605927febfee
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": 0.9026663899421692,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.3442340791738382,
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": 21.731,
1090
  "eval_steps_per_second": 5.448,
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": 9.244615391576064e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8940922021865845,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.4589787722317843,
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": 21.731,
1090
  "eval_steps_per_second": 5.448,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.34652897303499713,
1095
+ "grad_norm": 1.6480083465576172,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.0325,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.3488238668961561,
1102
+ "grad_norm": 1.9100923538208008,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.0681,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.35111876075731496,
1109
+ "grad_norm": 1.7827497720718384,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 1.0215,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.3534136546184739,
1116
+ "grad_norm": 1.951094388961792,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 1.0411,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.3557085484796328,
1123
+ "grad_norm": 1.4764305353164673,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.739,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.35800344234079173,
1130
+ "grad_norm": 1.7889875173568726,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.9965,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.3602983362019507,
1137
+ "grad_norm": 1.9953656196594238,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.9345,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.36259323006310956,
1144
+ "grad_norm": 1.4267107248306274,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.9785,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.3648881239242685,
1151
+ "grad_norm": 1.3861805200576782,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.9489,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.36718301778542745,
1158
+ "grad_norm": 1.3143510818481445,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.07,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.36947791164658633,
1165
+ "grad_norm": 1.434395432472229,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.8829,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.3717728055077453,
1172
+ "grad_norm": 1.4105231761932373,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.9945,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.37406769936890416,
1179
+ "grad_norm": 1.4786529541015625,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.957,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.3763625932300631,
1186
+ "grad_norm": 1.5985033512115479,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.911,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.37865748709122204,
1193
+ "grad_norm": 1.1807379722595215,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.801,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.38095238095238093,
1200
+ "grad_norm": 1.3797551393508911,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.8695,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.3832472748135399,
1207
+ "grad_norm": 1.369858741760254,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.9341,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.3855421686746988,
1214
+ "grad_norm": 1.5000876188278198,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.8159,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.3878370625358577,
1221
+ "grad_norm": 1.2416213750839233,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.8057,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.39013195639701664,
1228
+ "grad_norm": 1.524393916130066,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.051,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.3924268502581756,
1235
+ "grad_norm": 1.3561407327651978,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.9033,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.3947217441193345,
1242
+ "grad_norm": 1.625829815864563,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.9101,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.3970166379804934,
1249
+ "grad_norm": 1.4260931015014648,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.8852,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.3993115318416523,
1256
+ "grad_norm": 1.825695514678955,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.1489,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.40160642570281124,
1263
+ "grad_norm": 1.5194275379180908,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.0181,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.4039013195639702,
1270
+ "grad_norm": 1.459893822669983,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.108,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.40619621342512907,
1277
+ "grad_norm": 1.2587231397628784,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.9476,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.408491107286288,
1284
+ "grad_norm": 1.0984941720962524,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.7951,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.41078600114744696,
1291
+ "grad_norm": 1.4001713991165161,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.0232,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.41308089500860584,
1298
+ "grad_norm": 1.2408440113067627,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.6772,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.4153757888697648,
1305
+ "grad_norm": 1.281936526298523,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.887,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.41767068273092367,
1312
+ "grad_norm": 1.2071911096572876,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.7811,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.4199655765920826,
1319
+ "grad_norm": 1.2717124223709106,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.9339,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.42226047045324155,
1326
+ "grad_norm": 1.3442198038101196,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.9263,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.42455536431440044,
1333
+ "grad_norm": 1.3797053098678589,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.6704,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.4268502581755594,
1340
+ "grad_norm": 1.7550997734069824,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.9233,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.4291451520367183,
1347
+ "grad_norm": 1.3640536069869995,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.7387,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.4314400458978772,
1354
+ "grad_norm": 1.20999014377594,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.7567,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.43373493975903615,
1361
+ "grad_norm": 1.2680433988571167,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.7227,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.43602983362019504,
1368
+ "grad_norm": 1.28988778591156,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.96,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.438324727481354,
1375
+ "grad_norm": 1.3224800825119019,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.8058,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.4406196213425129,
1382
+ "grad_norm": 1.329875111579895,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.8736,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.4429145152036718,
1389
+ "grad_norm": 1.364579439163208,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.9289,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.44520940906483075,
1396
+ "grad_norm": 1.319206953048706,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.9776,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.4475043029259897,
1403
+ "grad_norm": 1.4133667945861816,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.7376,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.4497991967871486,
1410
+ "grad_norm": 1.420677661895752,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.9188,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.4520940906483075,
1417
+ "grad_norm": 1.6266146898269653,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.8498,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.45438898450946646,
1424
+ "grad_norm": 1.701554775238037,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.7882,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.45668387837062535,
1431
+ "grad_norm": 2.07875919342041,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.9874,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.4589787722317843,
1438
+ "grad_norm": 1.7471427917480469,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.8814,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.4589787722317843,
1445
+ "eval_loss": 0.8940922021865845,
1446
+ "eval_runtime": 33.4647,
1447
+ "eval_samples_per_second": 21.934,
1448
+ "eval_steps_per_second": 5.498,
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": 1.2311821118393549e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null