error577 commited on
Commit
a070e1d
·
verified ·
1 Parent(s): eaa370a

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 sha256:05f73c0efbb7e4c788519dc18f801061b41e9be30750e497d6fc14bea85f29f2
3
  size 503407240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d295fde1e2e1527ea3229b1addb681c14ed22ec09f1c14ff642b97cb129cae75
3
  size 503407240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4834c73e1693f4047f9d2198e24dc5334a6e649e63885ab50218954dd4c9dbf0
3
  size 256379860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74f459566ff70305e7962440f367dd7d859bd701c48991c72af29e68264f926
3
  size 256379860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e17268520031e76d27daced675e0408b4dec2dfc4a5f86fb136a6a2f348c4804
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684ab4c069816ce83df74605dd7bc98ab8887fe6aa1578150e9875021127b99c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3519da5d1a8fd21b6750678e739e53ded8ce396daf128a1b704ea180a416e138
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b756fb3a2c94d34f31f35fb7b3db5b1edafcc36018395c2aed67f86869b1a7
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.8699079751968384,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07167602436984828,
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": 3.192,
1090
  "eval_steps_per_second": 3.192,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1103,7 +1461,7 @@
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
- "early_stopping_patience_counter": 2
1107
  }
1108
  },
1109
  "TrainerControl": {
@@ -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": 7.90827261493248e+16,
1121
  "train_batch_size": 1,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 1.8699079751968384,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.09556803249313105,
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": 3.192,
1090
  "eval_steps_per_second": 3.192,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.07215386453231394,
1095
+ "grad_norm": 73.1042709350586,
1096
+ "learning_rate": 0.0002934200033124183,
1097
+ "loss": 35.5003,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.0726317046947796,
1102
+ "grad_norm": 67.41387176513672,
1103
+ "learning_rate": 0.0002933270397356629,
1104
+ "loss": 36.9316,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.07310954485724525,
1109
+ "grad_norm": 48.58037567138672,
1110
+ "learning_rate": 0.00029323343898911427,
1111
+ "loss": 29.3974,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.0735873850197109,
1116
+ "grad_norm": 40.163272857666016,
1117
+ "learning_rate": 0.0002931392014888805,
1118
+ "loss": 26.5929,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.07406522518217656,
1123
+ "grad_norm": 41.57120895385742,
1124
+ "learning_rate": 0.0002930443276539008,
1125
+ "loss": 27.1944,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.07454306534464222,
1130
+ "grad_norm": 46.67683029174805,
1131
+ "learning_rate": 0.00029294881790594297,
1132
+ "loss": 26.1255,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.07502090550710787,
1137
+ "grad_norm": 37.82615280151367,
1138
+ "learning_rate": 0.00029285267266960184,
1139
+ "loss": 25.7079,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.07549874566957353,
1144
+ "grad_norm": 36.55807113647461,
1145
+ "learning_rate": 0.0002927558923722975,
1146
+ "loss": 26.6228,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.07597658583203919,
1151
+ "grad_norm": 39.336666107177734,
1152
+ "learning_rate": 0.00029265847744427303,
1153
+ "loss": 26.4949,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.07645442599450483,
1158
+ "grad_norm": 44.27214050292969,
1159
+ "learning_rate": 0.0002925604283185929,
1160
+ "loss": 30.5683,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.07693226615697049,
1165
+ "grad_norm": 45.3945426940918,
1166
+ "learning_rate": 0.00029246174543114107,
1167
+ "loss": 27.7526,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.07741010631943615,
1172
+ "grad_norm": 41.8970832824707,
1173
+ "learning_rate": 0.0002923624292206187,
1174
+ "loss": 26.3692,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.07788794648190181,
1179
+ "grad_norm": 52.303524017333984,
1180
+ "learning_rate": 0.0002922624801285426,
1181
+ "loss": 32.3153,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.07836578664436746,
1186
+ "grad_norm": 62.98134231567383,
1187
+ "learning_rate": 0.00029216189859924307,
1188
+ "loss": 26.9408,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.07884362680683311,
1193
+ "grad_norm": 47.65409469604492,
1194
+ "learning_rate": 0.00029206068507986184,
1195
+ "loss": 26.4589,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.07932146696929877,
1200
+ "grad_norm": 53.36261749267578,
1201
+ "learning_rate": 0.0002919588400203503,
1202
+ "loss": 25.478,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.07979930713176442,
1207
+ "grad_norm": 62.68265914916992,
1208
+ "learning_rate": 0.0002918563638734674,
1209
+ "loss": 24.5028,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.08027714729423008,
1214
+ "grad_norm": 44.38447570800781,
1215
+ "learning_rate": 0.00029175325709477766,
1216
+ "loss": 25.8146,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.08075498745669574,
1221
+ "grad_norm": 60.98610305786133,
1222
+ "learning_rate": 0.00029164952014264884,
1223
+ "loss": 27.5951,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.0812328276191614,
1228
+ "grad_norm": 85.21952819824219,
1229
+ "learning_rate": 0.0002915451534782506,
1230
+ "loss": 24.431,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.08171066778162704,
1235
+ "grad_norm": 48.028133392333984,
1236
+ "learning_rate": 0.00029144015756555177,
1237
+ "loss": 25.095,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.0821885079440927,
1242
+ "grad_norm": 73.59846496582031,
1243
+ "learning_rate": 0.00029133453287131855,
1244
+ "loss": 28.3034,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.08266634810655836,
1249
+ "grad_norm": 45.977203369140625,
1250
+ "learning_rate": 0.0002912282798651125,
1251
+ "loss": 27.0948,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.083144188269024,
1256
+ "grad_norm": 53.401058197021484,
1257
+ "learning_rate": 0.00029112139901928835,
1258
+ "loss": 29.868,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.08362202843148966,
1263
+ "grad_norm": 58.298431396484375,
1264
+ "learning_rate": 0.00029101389080899196,
1265
+ "loss": 32.2812,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.08409986859395532,
1270
+ "grad_norm": 53.36587905883789,
1271
+ "learning_rate": 0.0002909057557121581,
1272
+ "loss": 24.3247,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.08457770875642098,
1277
+ "grad_norm": 46.0224494934082,
1278
+ "learning_rate": 0.00029079699420950857,
1279
+ "loss": 25.1548,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.08505554891888663,
1284
+ "grad_norm": 56.60353088378906,
1285
+ "learning_rate": 0.00029068760678454967,
1286
+ "loss": 26.9328,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.08553338908135229,
1291
+ "grad_norm": 58.66796112060547,
1292
+ "learning_rate": 0.00029057759392357046,
1293
+ "loss": 29.9578,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.08601122924381795,
1298
+ "grad_norm": 48.172393798828125,
1299
+ "learning_rate": 0.00029046695611564035,
1300
+ "loss": 27.7044,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.08648906940628359,
1305
+ "grad_norm": 44.48200607299805,
1306
+ "learning_rate": 0.00029035569385260705,
1307
+ "loss": 27.6591,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.08696690956874925,
1312
+ "grad_norm": 52.23008728027344,
1313
+ "learning_rate": 0.00029024380762909417,
1314
+ "loss": 26.7203,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.08744474973121491,
1319
+ "grad_norm": 43.81805419921875,
1320
+ "learning_rate": 0.0002901312979424994,
1321
+ "loss": 23.8,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.08792258989368057,
1326
+ "grad_norm": 55.3267936706543,
1327
+ "learning_rate": 0.0002900181652929919,
1328
+ "loss": 27.4224,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.08840043005614621,
1333
+ "grad_norm": 58.86140441894531,
1334
+ "learning_rate": 0.00028990441018351027,
1335
+ "loss": 35.963,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.08887827021861187,
1340
+ "grad_norm": 51.00541687011719,
1341
+ "learning_rate": 0.0002897900331197604,
1342
+ "loss": 30.9547,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.08935611038107753,
1347
+ "grad_norm": 52.07486343383789,
1348
+ "learning_rate": 0.00028967503461021306,
1349
+ "loss": 31.6428,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.08983395054354318,
1354
+ "grad_norm": 52.02641677856445,
1355
+ "learning_rate": 0.0002895594151661017,
1356
+ "loss": 28.4133,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.09031179070600884,
1361
+ "grad_norm": 48.312191009521484,
1362
+ "learning_rate": 0.00028944317530142015,
1363
+ "loss": 27.4251,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.0907896308684745,
1368
+ "grad_norm": 49.348209381103516,
1369
+ "learning_rate": 0.0002893263155329204,
1370
+ "loss": 32.0529,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.09126747103094016,
1375
+ "grad_norm": 67.97216796875,
1376
+ "learning_rate": 0.00028920883638011024,
1377
+ "loss": 31.9651,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.0917453111934058,
1382
+ "grad_norm": 56.64366912841797,
1383
+ "learning_rate": 0.000289090738365251,
1384
+ "loss": 30.6982,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.09222315135587146,
1389
+ "grad_norm": 44.88423538208008,
1390
+ "learning_rate": 0.0002889720220133551,
1391
+ "loss": 28.7906,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.09270099151833712,
1396
+ "grad_norm": 47.730342864990234,
1397
+ "learning_rate": 0.00028885268785218394,
1398
+ "loss": 33.0764,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.09317883168080277,
1403
+ "grad_norm": 73.9120864868164,
1404
+ "learning_rate": 0.00028873273641224546,
1405
+ "loss": 23.5101,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.09365667184326842,
1410
+ "grad_norm": 52.90140914916992,
1411
+ "learning_rate": 0.00028861216822679165,
1412
+ "loss": 26.4448,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.09413451200573408,
1417
+ "grad_norm": 52.82747268676758,
1418
+ "learning_rate": 0.0002884909838318163,
1419
+ "loss": 28.8465,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.09461235216819974,
1424
+ "grad_norm": 49.55004119873047,
1425
+ "learning_rate": 0.0002883691837660526,
1426
+ "loss": 27.031,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.09509019233066539,
1431
+ "grad_norm": 70.98810577392578,
1432
+ "learning_rate": 0.0002882467685709708,
1433
+ "loss": 29.6785,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.09556803249313105,
1438
+ "grad_norm": 73.06131744384766,
1439
+ "learning_rate": 0.0002881237387907757,
1440
+ "loss": 33.2941,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.09556803249313105,
1445
+ "eval_loss": 1.9855343103408813,
1446
+ "eval_runtime": 214.0224,
1447
+ "eval_samples_per_second": 3.196,
1448
+ "eval_steps_per_second": 3.196,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 3
1465
  }
1466
  },
1467
  "TrainerControl": {
 
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": 1.054436348657664e+17,
1479
  "train_batch_size": 1,
1480
  "trial_name": null,
1481
  "trial_params": null