aleegis12 commited on
Commit
84ac592
·
verified ·
1 Parent(s): 42ed900

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 sha256:85c445597e6cd50064e4a1f26875f99a2c851bd09472470077911df8b9170961
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a4168c128ee8fb3505e6b5d31190664c2f99b50368f82d20983bb8fa255ce7
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2a7411f4bad5c411c52e889eb9ae3efc7df954665d540d5c3025bf311d5903a
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d0780342311289330adb0c372388d724c9561796e8cd992c59f576ac5c3007
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d0c0423edf0cca1f3d30671e858c8edaa66bd972ad3699dcc50fec9f5341f54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d3aa6c31bf9fc77abf2c0f2da93e8beab40c6a6364458602149e2a3c64ced6
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": 1.339070439338684,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 2.18978102189781,
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": 12.012,
1090
  "eval_steps_per_second": 3.003,
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": 1
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": 2.3265653613920256e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 1.339070439338684,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 2.9197080291970803,
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": 12.012,
1090
  "eval_steps_per_second": 3.003,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.204379562043796,
1095
+ "grad_norm": 0.46815821528434753,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 1.3282,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.218978102189781,
1102
+ "grad_norm": 0.6017105579376221,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 1.0545,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.2335766423357666,
1109
+ "grad_norm": 0.6463600397109985,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.8,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.2481751824817517,
1116
+ "grad_norm": 0.9423279166221619,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.7809,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.2627737226277373,
1123
+ "grad_norm": 0.25780820846557617,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 1.1084,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.2773722627737225,
1130
+ "grad_norm": 0.29834485054016113,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 1.2842,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.291970802919708,
1137
+ "grad_norm": 0.3100908100605011,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 1.2667,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.3065693430656933,
1144
+ "grad_norm": 0.3335644602775574,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.2981,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.321167883211679,
1151
+ "grad_norm": 0.3528653085231781,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.2278,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.335766423357664,
1158
+ "grad_norm": 0.3596493601799011,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.194,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.3503649635036497,
1165
+ "grad_norm": 0.3201064169406891,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.076,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.3649635036496353,
1172
+ "grad_norm": 0.34449872374534607,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 1.2571,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.3795620437956204,
1179
+ "grad_norm": 0.36741119623184204,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 1.4119,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.394160583941606,
1186
+ "grad_norm": 0.39679640531539917,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 1.1969,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.408759124087591,
1193
+ "grad_norm": 0.40736815333366394,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.2261,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.423357664233577,
1200
+ "grad_norm": 0.4197560250759125,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.3001,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.437956204379562,
1207
+ "grad_norm": 0.45832544565200806,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.1555,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.4525547445255476,
1214
+ "grad_norm": 0.5514608025550842,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.2566,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.4671532846715327,
1221
+ "grad_norm": 0.5834535956382751,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 1.09,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.4817518248175183,
1228
+ "grad_norm": 0.6819263100624084,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.761,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.4963503649635035,
1235
+ "grad_norm": 0.9520904421806335,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.6747,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.510948905109489,
1242
+ "grad_norm": 0.25262385606765747,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.1072,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.5255474452554747,
1249
+ "grad_norm": 0.22888913750648499,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.9735,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.54014598540146,
1256
+ "grad_norm": 0.27815407514572144,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 1.1549,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.554744525547445,
1263
+ "grad_norm": 0.2952488362789154,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 1.1367,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.5693430656934306,
1270
+ "grad_norm": 0.30662426352500916,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 1.1852,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.5839416058394162,
1277
+ "grad_norm": 0.3116922676563263,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 1.125,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.5985401459854014,
1284
+ "grad_norm": 0.3175325393676758,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 1.1855,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.613138686131387,
1291
+ "grad_norm": 0.34450942277908325,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.218,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.627737226277372,
1298
+ "grad_norm": 0.3555043041706085,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 1.4273,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.6423357664233578,
1305
+ "grad_norm": 0.3660329282283783,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 1.2961,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.656934306569343,
1312
+ "grad_norm": 0.38958269357681274,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.0501,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.6715328467153285,
1319
+ "grad_norm": 0.4110100567340851,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 1.1618,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.686131386861314,
1326
+ "grad_norm": 0.4916228652000427,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 1.1906,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.7007299270072993,
1333
+ "grad_norm": 0.5581548810005188,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 1.0481,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.7153284671532845,
1340
+ "grad_norm": 0.6251854300498962,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.8345,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.72992700729927,
1347
+ "grad_norm": 0.7108532786369324,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.7292,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.7445255474452557,
1354
+ "grad_norm": 0.9583161473274231,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.9962,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.759124087591241,
1361
+ "grad_norm": 0.22289897501468658,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.9235,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.7737226277372264,
1368
+ "grad_norm": 0.2782759368419647,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 1.2478,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.7883211678832116,
1375
+ "grad_norm": 0.29329487681388855,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 1.2171,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.802919708029197,
1382
+ "grad_norm": 0.3230476379394531,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 1.253,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.8175182481751824,
1389
+ "grad_norm": 0.31199565529823303,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 1.1981,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.832116788321168,
1396
+ "grad_norm": 0.3323785662651062,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 1.1482,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.846715328467153,
1403
+ "grad_norm": 0.3421997129917145,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 1.246,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.8613138686131387,
1410
+ "grad_norm": 0.3328395485877991,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 1.2957,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.875912408759124,
1417
+ "grad_norm": 0.36648160219192505,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 1.3804,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.8905109489051095,
1424
+ "grad_norm": 0.3710862100124359,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 1.2646,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 2.905109489051095,
1431
+ "grad_norm": 0.3807961642742157,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 1.2366,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 2.9197080291970803,
1438
+ "grad_norm": 0.40780678391456604,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 1.1805,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 2.9197080291970803,
1445
+ "eval_loss": 1.3487451076507568,
1446
+ "eval_runtime": 9.6553,
1447
+ "eval_samples_per_second": 12.014,
1448
+ "eval_steps_per_second": 3.004,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 2
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": 3.105049416617165e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null