blood34 commited on
Commit
07fe7bb
·
verified ·
1 Parent(s): 0162507

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 sha256:31b57550b47cc9d73fcc7ca66146bd09ac1e43cf9ccfae41857f1fe83e9a5a0b
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f12639f2852006a43af3e0eb7efed4cf3f62f63d87ee92aa9de5d2a4c5fe727
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:112ebc82b8e1247ef1ea3c4c4593b099423f327759c1546d92c31df9cc3ba497
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519c0853b8bb8f09456f404c6b25824146d202ed0aec94053182e6f89a04bdb3
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4776e4129026d723dbb2dec02762a964eefeb64b432d57ef6895c00b49d12146
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce6a8bd5905b16bd1208531fdde2a52ac0973096d2c89f4c17bd1ea0432ce0f
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": 2.26181960105896,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.03849855630413859,
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": 8.887,
1090
  "eval_steps_per_second": 2.222,
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": 2.0466119856881664e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.252807140350342,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.05133140840551813,
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": 8.887,
1090
  "eval_steps_per_second": 2.222,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.03875521334616618,
1095
+ "grad_norm": 0.3422974646091461,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 2.2933,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.03901187038819377,
1102
+ "grad_norm": 0.4707757830619812,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 2.3283,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.03926852743022137,
1109
+ "grad_norm": 0.4521164894104004,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 2.3406,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.03952518447224896,
1116
+ "grad_norm": 0.44188806414604187,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 2.2193,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.03978184151427655,
1123
+ "grad_norm": 0.502597451210022,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 2.3505,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.04003849855630414,
1130
+ "grad_norm": 0.450508713722229,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 2.3172,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.04029515559833173,
1137
+ "grad_norm": 0.3949015736579895,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 2.3929,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.04055181264035932,
1144
+ "grad_norm": 0.3617224097251892,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 2.3032,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.04080846968238691,
1151
+ "grad_norm": 0.36014440655708313,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 2.2744,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.0410651267244145,
1158
+ "grad_norm": 0.3576134443283081,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 2.3233,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.04132178376644209,
1165
+ "grad_norm": 0.31801852583885193,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 2.2295,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.04157844080846968,
1172
+ "grad_norm": 0.3260203003883362,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 2.3959,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.04183509785049727,
1179
+ "grad_norm": 0.31979161500930786,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 2.1995,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.04209175489252486,
1186
+ "grad_norm": 0.3350762128829956,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 2.3218,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.04234841193455245,
1193
+ "grad_norm": 0.33540862798690796,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 2.3084,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.04260506897658004,
1200
+ "grad_norm": 0.33332133293151855,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 2.2475,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.04286172601860763,
1207
+ "grad_norm": 0.33638399839401245,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 2.275,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.04311838306063523,
1214
+ "grad_norm": 0.38856881856918335,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 2.2398,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.04337504010266282,
1221
+ "grad_norm": 0.3757133185863495,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 2.3224,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.04363169714469041,
1228
+ "grad_norm": 0.4081624448299408,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 2.3078,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.043888354186718,
1235
+ "grad_norm": 0.3590552806854248,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 2.2531,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.04414501122874559,
1242
+ "grad_norm": 0.38641491532325745,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 2.268,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.04440166827077318,
1249
+ "grad_norm": 0.396953821182251,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 2.2258,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.04465832531280077,
1256
+ "grad_norm": 0.400569349527359,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 2.2044,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.04491498235482836,
1263
+ "grad_norm": 0.394077330827713,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 2.2371,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.04517163939685595,
1270
+ "grad_norm": 0.38696473836898804,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 2.1553,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.04542829643888354,
1277
+ "grad_norm": 0.4218221604824066,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 2.3042,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.04568495348091113,
1284
+ "grad_norm": 0.4155186414718628,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 2.2698,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.04594161052293872,
1291
+ "grad_norm": 0.4689392149448395,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 2.2759,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.04619826756496631,
1298
+ "grad_norm": 0.4387744963169098,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 2.2866,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.0464549246069939,
1305
+ "grad_norm": 0.45942121744155884,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 2.2913,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.0467115816490215,
1312
+ "grad_norm": 0.4631074368953705,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 2.2984,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.04696823869104909,
1319
+ "grad_norm": 0.47069424390792847,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.1726,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.04722489573307668,
1326
+ "grad_norm": 0.49852561950683594,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 2.2916,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.04748155277510427,
1333
+ "grad_norm": 0.5104568004608154,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 2.2821,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.04773820981713186,
1340
+ "grad_norm": 0.47923555970191956,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 2.2352,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.04799486685915945,
1347
+ "grad_norm": 0.5244100093841553,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 2.1826,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.04825152390118704,
1354
+ "grad_norm": 0.5392053127288818,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 2.3235,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.04850818094321463,
1361
+ "grad_norm": 0.5164491534233093,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 2.2133,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.04876483798524222,
1368
+ "grad_norm": 0.5362449884414673,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 2.247,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.04902149502726981,
1375
+ "grad_norm": 0.5653479695320129,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 2.2328,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.0492781520692974,
1382
+ "grad_norm": 0.572383463382721,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 2.243,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.04953480911132499,
1389
+ "grad_norm": 0.6023736000061035,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 2.2308,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.04979146615335258,
1396
+ "grad_norm": 0.606105387210846,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 2.2906,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.05004812319538017,
1403
+ "grad_norm": 0.6184576749801636,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 2.3062,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.05030478023740776,
1410
+ "grad_norm": 0.6309393048286438,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 2.255,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.05056143727943536,
1417
+ "grad_norm": 0.6904622316360474,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 2.2363,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.05081809432146295,
1424
+ "grad_norm": 0.7422359585762024,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 2.2325,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.05107475136349054,
1431
+ "grad_norm": 0.7413392066955566,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 2.2729,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.05133140840551813,
1438
+ "grad_norm": 0.8726180195808411,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 2.0746,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.05133140840551813,
1445
+ "eval_loss": 2.252807140350342,
1446
+ "eval_runtime": 736.7405,
1447
+ "eval_samples_per_second": 8.908,
1448
+ "eval_steps_per_second": 2.227,
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": 2.7344078169440256e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null