prxy5605 commited on
Commit
0b0a764
·
verified ·
1 Parent(s): c71a003

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 sha256:16f0dc6e431f7b6b90f510918993168b5d4375476fd32863a49883b0971a02d8
3
  size 34456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0738ff673de621bcaa12ae872f2f336cb821bace482edfe5d0214f676af70be
3
  size 34456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c868a8450cb66f75df4e2345a41bd57abf7584e688e0350757894ed84bab76
3
  size 76154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7871adc6bc0d03f4881dd445392bef113a05d37e863924799536be2d4f9e8587
3
  size 76154
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:144921e75f42a1460d625a0de872fe0aecbbb880937260ed02766dacab7c2f59
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6d67f4b7e12eb5f2c92d804b66fe46cbe7464607443fe7b93ebafcbd0bc8bb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
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": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06737031214911296,
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": 153.122,
1090
  "eval_steps_per_second": 76.561,
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": 24319837470720.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.08982708286548394,
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": 153.122,
1090
  "eval_steps_per_second": 76.561,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.06781944756344038,
1095
+ "grad_norm": 0.0001438720792066306,
1096
+ "learning_rate": 1.7197048550474643e-05,
1097
+ "loss": 46.0,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.06826858297776779,
1102
+ "grad_norm": 7.472206925740466e-05,
1103
+ "learning_rate": 1.6543469682057106e-05,
1104
+ "loss": 46.0,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.06871771839209521,
1109
+ "grad_norm": 9.493398829363286e-05,
1110
+ "learning_rate": 1.5900081996875083e-05,
1111
+ "loss": 46.0,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.06916685380642264,
1116
+ "grad_norm": 5.300561315380037e-05,
1117
+ "learning_rate": 1.526708147705013e-05,
1118
+ "loss": 46.0,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.06961598922075006,
1123
+ "grad_norm": 6.254475738387555e-05,
1124
+ "learning_rate": 1.4644660940672627e-05,
1125
+ "loss": 46.0,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.07006512463507747,
1130
+ "grad_norm": 0.0001307373313466087,
1131
+ "learning_rate": 1.4033009983067452e-05,
1132
+ "loss": 46.0,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.07051426004940489,
1137
+ "grad_norm": 9.006000618683174e-05,
1138
+ "learning_rate": 1.3432314919041478e-05,
1139
+ "loss": 46.0,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.07096339546373231,
1144
+ "grad_norm": 8.949954644776881e-05,
1145
+ "learning_rate": 1.2842758726130283e-05,
1146
+ "loss": 46.0,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.07141253087805974,
1151
+ "grad_norm": 0.00011812666343757883,
1152
+ "learning_rate": 1.22645209888614e-05,
1153
+ "loss": 46.0,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.07186166629238716,
1158
+ "grad_norm": 0.00010641237895470113,
1159
+ "learning_rate": 1.1697777844051105e-05,
1160
+ "loss": 46.0,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.07231080170671457,
1165
+ "grad_norm": 5.68857321923133e-05,
1166
+ "learning_rate": 1.1142701927151456e-05,
1167
+ "loss": 46.0,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.07275993712104199,
1172
+ "grad_norm": 7.178529631346464e-05,
1173
+ "learning_rate": 1.0599462319663905e-05,
1174
+ "loss": 46.0,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.07320907253536942,
1179
+ "grad_norm": 6.591699639102444e-05,
1180
+ "learning_rate": 1.006822449763537e-05,
1181
+ "loss": 46.0,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.07365820794969684,
1186
+ "grad_norm": 7.649638428119943e-05,
1187
+ "learning_rate": 9.549150281252633e-06,
1188
+ "loss": 46.0,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.07410734336402425,
1193
+ "grad_norm": 0.0001560054370202124,
1194
+ "learning_rate": 9.042397785550405e-06,
1195
+ "loss": 46.0,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.07455647877835167,
1200
+ "grad_norm": 8.290179539471865e-05,
1201
+ "learning_rate": 8.548121372247918e-06,
1202
+ "loss": 46.0,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.0750056141926791,
1207
+ "grad_norm": 0.00012351403711363673,
1208
+ "learning_rate": 8.066471602728803e-06,
1209
+ "loss": 46.0,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.07545474960700652,
1214
+ "grad_norm": 7.974076288519427e-05,
1215
+ "learning_rate": 7.597595192178702e-06,
1216
+ "loss": 46.0,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.07590388502133394,
1221
+ "grad_norm": 5.896786387893371e-05,
1222
+ "learning_rate": 7.1416349648943894e-06,
1223
+ "loss": 46.0,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.07635302043566135,
1228
+ "grad_norm": 0.00010927852417808026,
1229
+ "learning_rate": 6.698729810778065e-06,
1230
+ "loss": 46.0,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.07680215584998877,
1235
+ "grad_norm": 7.081931835273281e-05,
1236
+ "learning_rate": 6.269014643030213e-06,
1237
+ "loss": 46.0,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.0772512912643162,
1242
+ "grad_norm": 0.00013235144433565438,
1243
+ "learning_rate": 5.852620357053651e-06,
1244
+ "loss": 46.0,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.07770042667864362,
1249
+ "grad_norm": 7.40899340598844e-05,
1250
+ "learning_rate": 5.449673790581611e-06,
1251
+ "loss": 46.0,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.07814956209297103,
1256
+ "grad_norm": 7.721033762209117e-05,
1257
+ "learning_rate": 5.060297685041659e-06,
1258
+ "loss": 46.0,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.07859869750729845,
1263
+ "grad_norm": 0.00010103748354595155,
1264
+ "learning_rate": 4.684610648167503e-06,
1265
+ "loss": 46.0,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.07904783292162587,
1270
+ "grad_norm": 5.865566708962433e-05,
1271
+ "learning_rate": 4.322727117869951e-06,
1272
+ "loss": 46.0,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.0794969683359533,
1277
+ "grad_norm": 0.0001235765084857121,
1278
+ "learning_rate": 3.974757327377981e-06,
1279
+ "loss": 46.0,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.0799461037502807,
1284
+ "grad_norm": 9.430928184883669e-05,
1285
+ "learning_rate": 3.6408072716606346e-06,
1286
+ "loss": 46.0,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.08039523916460813,
1291
+ "grad_norm": 8.264468488050625e-05,
1292
+ "learning_rate": 3.3209786751399187e-06,
1293
+ "loss": 46.0,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.08084437457893555,
1298
+ "grad_norm": 5.9367048379499465e-05,
1299
+ "learning_rate": 3.0153689607045845e-06,
1300
+ "loss": 46.0,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.08129350999326297,
1305
+ "grad_norm": 0.00012005270400550216,
1306
+ "learning_rate": 2.724071220034158e-06,
1307
+ "loss": 46.0,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.0817426454075904,
1312
+ "grad_norm": 6.05574095970951e-05,
1313
+ "learning_rate": 2.4471741852423237e-06,
1314
+ "loss": 46.0,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.0821917808219178,
1319
+ "grad_norm": 0.00014828034909442067,
1320
+ "learning_rate": 2.1847622018482283e-06,
1321
+ "loss": 46.0,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.08264091623624523,
1326
+ "grad_norm": 0.0001592932385392487,
1327
+ "learning_rate": 1.9369152030840556e-06,
1328
+ "loss": 46.0,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.08309005165057265,
1333
+ "grad_norm": 0.0001511089358245954,
1334
+ "learning_rate": 1.70370868554659e-06,
1335
+ "loss": 46.0,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.08353918706490007,
1340
+ "grad_norm": 0.00013895431766286492,
1341
+ "learning_rate": 1.4852136862001764e-06,
1342
+ "loss": 46.0,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.08398832247922748,
1347
+ "grad_norm": 5.225280256127007e-05,
1348
+ "learning_rate": 1.2814967607382432e-06,
1349
+ "loss": 46.0,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.0844374578935549,
1354
+ "grad_norm": 0.0001045409808284603,
1355
+ "learning_rate": 1.0926199633097157e-06,
1356
+ "loss": 46.0,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.08488659330788233,
1361
+ "grad_norm": 0.00014955301594454795,
1362
+ "learning_rate": 9.186408276168013e-07,
1363
+ "loss": 46.0,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.08533572872220975,
1368
+ "grad_norm": 0.00010593217302812263,
1369
+ "learning_rate": 7.596123493895991e-07,
1370
+ "loss": 46.0,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.08578486413653717,
1375
+ "grad_norm": 7.444553921232e-05,
1376
+ "learning_rate": 6.15582970243117e-07,
1377
+ "loss": 46.0,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.08623399955086458,
1382
+ "grad_norm": 4.052293297718279e-05,
1383
+ "learning_rate": 4.865965629214819e-07,
1384
+ "loss": 46.0,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.086683134965192,
1389
+ "grad_norm": 0.00012066525232512504,
1390
+ "learning_rate": 3.7269241793390085e-07,
1391
+ "loss": 46.0,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.08713227037951943,
1396
+ "grad_norm": 8.483009150950238e-05,
1397
+ "learning_rate": 2.7390523158633554e-07,
1398
+ "loss": 46.0,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.08758140579384685,
1403
+ "grad_norm": 9.945972851710394e-05,
1404
+ "learning_rate": 1.9026509541272275e-07,
1405
+ "loss": 46.0,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.08803054120817426,
1410
+ "grad_norm": 9.102479816647246e-05,
1411
+ "learning_rate": 1.2179748700879012e-07,
1412
+ "loss": 46.0,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.08847967662250168,
1417
+ "grad_norm": 0.0001648725738050416,
1418
+ "learning_rate": 6.852326227130834e-08,
1419
+ "loss": 46.0,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.0889288120368291,
1424
+ "grad_norm": 0.00018249057757202536,
1425
+ "learning_rate": 3.04586490452119e-08,
1426
+ "loss": 46.0,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.08937794745115653,
1431
+ "grad_norm": 8.922704728320241e-05,
1432
+ "learning_rate": 7.615242180436522e-09,
1433
+ "loss": 46.0,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.08982708286548394,
1438
+ "grad_norm": 0.0001207529567182064,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 46.0,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.08982708286548394,
1445
+ "eval_loss": 11.5,
1446
+ "eval_runtime": 24.3109,
1447
+ "eval_samples_per_second": 154.252,
1448
+ "eval_steps_per_second": 77.126,
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": 32399651241984.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null