bbytxt commited on
Commit
1c0b555
·
verified ·
1 Parent(s): bb2db01

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:a6d08eae97045ebcb9387966899d06b919e9a5080064a9dc6d449581f31ce795
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3f39c191dbe2a07a1ff67b81c95562b5db7856632eac7de5cab1fe30525a69
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45417ee77471c8e4564776773972a4b6fd0f9c63916c72a29b942506a9e759ce
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce1bafccd5775d18e02a062b5c5d5fc5ffee9e43dd814bfc89e065450f6f65b
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d82a56c3cee5bac146bfbc8d9553a71fbc98a844c5fabe7a96ee64f6b87592
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b353c00c6226784cfb9340695c54a4084ecc5ba81967c5d4714fcd0eea20689
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
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": 4.1894659996032715,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.1195457262402869,
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": 43.005,
1090
  "eval_steps_per_second": 21.503,
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": 3708264067891200.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.183354377746582,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.15939430165371588,
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": 43.005,
1090
  "eval_steps_per_second": 21.503,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.1203426977485555,
1095
+ "grad_norm": 0.2653471529483795,
1096
+ "learning_rate": 1.9136088935510362e-05,
1097
+ "loss": 4.3249,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.12113966925682407,
1102
+ "grad_norm": 0.30772659182548523,
1103
+ "learning_rate": 1.8414449687337464e-05,
1104
+ "loss": 4.3166,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.12193664076509265,
1109
+ "grad_norm": 0.30526572465896606,
1110
+ "learning_rate": 1.7703596875660645e-05,
1111
+ "loss": 4.3137,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.12273361227336123,
1116
+ "grad_norm": 0.2967657744884491,
1117
+ "learning_rate": 1.700377325606388e-05,
1118
+ "loss": 4.4396,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.1235305837816298,
1123
+ "grad_norm": 0.3225037157535553,
1124
+ "learning_rate": 1.631521781767214e-05,
1125
+ "loss": 4.2345,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.12432755528989839,
1130
+ "grad_norm": 0.3195071816444397,
1131
+ "learning_rate": 1.5638165701536868e-05,
1132
+ "loss": 4.3621,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.12512452679816696,
1137
+ "grad_norm": 0.31256967782974243,
1138
+ "learning_rate": 1.4972848120335453e-05,
1139
+ "loss": 4.4553,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.12592149830643554,
1144
+ "grad_norm": 0.32809165120124817,
1145
+ "learning_rate": 1.4319492279412388e-05,
1146
+ "loss": 4.2234,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.12671846981470414,
1151
+ "grad_norm": 0.2773759365081787,
1152
+ "learning_rate": 1.3678321299188801e-05,
1153
+ "loss": 4.277,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.1275154413229727,
1158
+ "grad_norm": 0.2871479094028473,
1159
+ "learning_rate": 1.3049554138967051e-05,
1160
+ "loss": 4.1204,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.12831241283124128,
1165
+ "grad_norm": 0.29100486636161804,
1166
+ "learning_rate": 1.2433405522156332e-05,
1167
+ "loss": 4.2218,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.12910938433950986,
1172
+ "grad_norm": 0.2950289845466614,
1173
+ "learning_rate": 1.183008586294485e-05,
1174
+ "loss": 4.3895,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.12990635584777843,
1179
+ "grad_norm": 0.2688523530960083,
1180
+ "learning_rate": 1.1239801194443506e-05,
1181
+ "loss": 4.078,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.13070332735604703,
1186
+ "grad_norm": 0.26284605264663696,
1187
+ "learning_rate": 1.066275309832584e-05,
1188
+ "loss": 4.1274,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.1315002988643156,
1193
+ "grad_norm": 0.2650034725666046,
1194
+ "learning_rate": 1.0099138635988026e-05,
1195
+ "loss": 4.2154,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.13229727037258418,
1200
+ "grad_norm": 0.25614309310913086,
1201
+ "learning_rate": 9.549150281252633e-06,
1202
+ "loss": 4.3905,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.13309424188085275,
1207
+ "grad_norm": 0.23772862553596497,
1208
+ "learning_rate": 9.012975854638949e-06,
1209
+ "loss": 4.0156,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.13389121338912133,
1214
+ "grad_norm": 0.2594856023788452,
1215
+ "learning_rate": 8.490798459222476e-06,
1216
+ "loss": 4.1311,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.13468818489738993,
1221
+ "grad_norm": 0.2590104937553406,
1222
+ "learning_rate": 7.982796418105371e-06,
1223
+ "loss": 4.2615,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.1354851564056585,
1228
+ "grad_norm": 0.25985562801361084,
1229
+ "learning_rate": 7.489143213519301e-06,
1230
+ "loss": 4.0188,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.13628212791392708,
1235
+ "grad_norm": 0.2538761794567108,
1236
+ "learning_rate": 7.010007427581378e-06,
1237
+ "loss": 4.2036,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.13707909942219565,
1242
+ "grad_norm": 0.25580894947052,
1243
+ "learning_rate": 6.5455526847235825e-06,
1244
+ "loss": 4.2554,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.13787607093046422,
1249
+ "grad_norm": 0.24640843272209167,
1250
+ "learning_rate": 6.0959375958151045e-06,
1251
+ "loss": 3.9291,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.13867304243873282,
1256
+ "grad_norm": 0.2420421540737152,
1257
+ "learning_rate": 5.6613157039969055e-06,
1258
+ "loss": 4.2622,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.1394700139470014,
1263
+ "grad_norm": 0.2577573359012604,
1264
+ "learning_rate": 5.241835432246889e-06,
1265
+ "loss": 3.9891,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.14026698545526997,
1270
+ "grad_norm": 0.2526918649673462,
1271
+ "learning_rate": 4.837640032693558e-06,
1272
+ "loss": 4.04,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.14106395696353854,
1277
+ "grad_norm": 0.2588857412338257,
1278
+ "learning_rate": 4.448867537695578e-06,
1279
+ "loss": 4.1807,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.14186092847180715,
1284
+ "grad_norm": 0.24917973577976227,
1285
+ "learning_rate": 4.075650712703849e-06,
1286
+ "loss": 4.2169,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.14265789998007572,
1291
+ "grad_norm": 0.25603026151657104,
1292
+ "learning_rate": 3.71811701092219e-06,
1293
+ "loss": 3.9137,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.1434548714883443,
1298
+ "grad_norm": 0.26696962118148804,
1299
+ "learning_rate": 3.376388529782215e-06,
1300
+ "loss": 4.2429,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.14425184299661287,
1305
+ "grad_norm": 0.2555984556674957,
1306
+ "learning_rate": 3.0505819692471792e-06,
1307
+ "loss": 4.2023,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.14504881450488144,
1312
+ "grad_norm": 0.27253782749176025,
1313
+ "learning_rate": 2.7408085919590264e-06,
1314
+ "loss": 4.0074,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.14584578601315004,
1319
+ "grad_norm": 0.27349719405174255,
1320
+ "learning_rate": 2.4471741852423237e-06,
1321
+ "loss": 4.274,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.14664275752141862,
1326
+ "grad_norm": 0.31064373254776,
1327
+ "learning_rate": 2.1697790249779636e-06,
1328
+ "loss": 4.4011,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.1474397290296872,
1333
+ "grad_norm": 0.2815253436565399,
1334
+ "learning_rate": 1.908717841359048e-06,
1335
+ "loss": 4.1062,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.14823670053795576,
1340
+ "grad_norm": 0.27812743186950684,
1341
+ "learning_rate": 1.6640797865406288e-06,
1342
+ "loss": 4.0384,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.14903367204622434,
1347
+ "grad_norm": 0.2721196711063385,
1348
+ "learning_rate": 1.4359484041943038e-06,
1349
+ "loss": 4.0728,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.14983064355449294,
1354
+ "grad_norm": 0.31800466775894165,
1355
+ "learning_rate": 1.2244016009781701e-06,
1356
+ "loss": 4.102,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.1506276150627615,
1361
+ "grad_norm": 0.3215753734111786,
1362
+ "learning_rate": 1.0295116199317057e-06,
1363
+ "loss": 4.1268,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.15142458657103008,
1368
+ "grad_norm": 0.29382383823394775,
1369
+ "learning_rate": 8.513450158049108e-07,
1370
+ "loss": 4.0609,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.15222155807929866,
1375
+ "grad_norm": 0.2936742305755615,
1376
+ "learning_rate": 6.899626323298713e-07,
1377
+ "loss": 4.2683,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.15301852958756723,
1382
+ "grad_norm": 0.2987104058265686,
1383
+ "learning_rate": 5.454195814427021e-07,
1384
+ "loss": 4.0856,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.15381550109583583,
1389
+ "grad_norm": 0.31946101784706116,
1390
+ "learning_rate": 4.177652244628627e-07,
1391
+ "loss": 4.1578,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.1546124726041044,
1396
+ "grad_norm": 0.2962910532951355,
1397
+ "learning_rate": 3.0704315523631953e-07,
1398
+ "loss": 4.0711,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.15540944411237298,
1403
+ "grad_norm": 0.3355628550052643,
1404
+ "learning_rate": 2.1329118524827662e-07,
1405
+ "loss": 4.1497,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.15620641562064155,
1410
+ "grad_norm": 0.3637641966342926,
1411
+ "learning_rate": 1.3654133071059893e-07,
1412
+ "loss": 4.1806,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.15700338712891015,
1417
+ "grad_norm": 0.35605573654174805,
1418
+ "learning_rate": 7.681980162830282e-08,
1419
+ "loss": 3.9998,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.15780035863717873,
1424
+ "grad_norm": 0.4277958869934082,
1425
+ "learning_rate": 3.4146992848854695e-08,
1426
+ "loss": 4.1548,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.1585973301454473,
1431
+ "grad_norm": 0.5168968439102173,
1432
+ "learning_rate": 8.537477097364522e-09,
1433
+ "loss": 4.1243,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.15939430165371588,
1438
+ "grad_norm": 0.9556027054786682,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 4.2316,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.15939430165371588,
1445
+ "eval_loss": 4.183354377746582,
1446
+ "eval_runtime": 49.1904,
1447
+ "eval_samples_per_second": 42.976,
1448
+ "eval_steps_per_second": 21.488,
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": 4944352090521600.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null