prxy5608 commited on
Commit
027801c
·
verified ·
1 Parent(s): 0c4ac1c

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:b0fb8c3d1b017333efd5baf10b994276e684363b0afaccfe8fe6c0b0a9f8cd49
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3883f37237301f5f00925f2bdd8dd19b926f2820300266d6e9781d312595bc2c
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d362b5ff11e00d34385d893abd4a3d6d90cc6636839ff18cbc7623eff3bb5a1
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3242846e9b620de80ba5aea2fca70ce0913022b648bb5163d0409b77509bd974
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dbdd0dd72f22d9408b06bc00d30c241adb65267239598a3daf252ceb9581833
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb68da360966a87c3a7696cdab0b5723f2ac69e0043ddb6b16e3e0e620db86d
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": 2.5873875617980957,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.102880658436214,
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": 88.728,
1090
  "eval_steps_per_second": 22.182,
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": 1.11768269488128e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5416412353515625,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.13717421124828533,
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": 88.728,
1090
  "eval_steps_per_second": 22.182,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.10356652949245541,
1095
+ "grad_norm": 70.4255599975586,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 10.7022,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.10425240054869685,
1102
+ "grad_norm": 72.38617706298828,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 10.7702,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.10493827160493827,
1109
+ "grad_norm": 69.93809509277344,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 10.4283,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.1056241426611797,
1116
+ "grad_norm": 77.07926177978516,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 10.2906,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.10631001371742113,
1123
+ "grad_norm": 70.95220184326172,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 10.3806,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.10699588477366255,
1130
+ "grad_norm": 65.11528015136719,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 10.3674,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.10768175582990398,
1137
+ "grad_norm": 67.45489501953125,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 10.4724,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.1083676268861454,
1144
+ "grad_norm": 67.21087646484375,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 10.1885,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.10905349794238683,
1151
+ "grad_norm": 71.32520294189453,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 10.1943,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.10973936899862825,
1158
+ "grad_norm": 70.40990447998047,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 10.1976,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.11042524005486969,
1165
+ "grad_norm": 68.82344818115234,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 9.78,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.1111111111111111,
1172
+ "grad_norm": 66.81336975097656,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 9.8149,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.11179698216735254,
1179
+ "grad_norm": 69.47315979003906,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 10.1638,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.11248285322359397,
1186
+ "grad_norm": 68.41928100585938,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 10.8401,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.11316872427983539,
1193
+ "grad_norm": 68.94377136230469,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 10.735,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.11385459533607682,
1200
+ "grad_norm": 64.20032501220703,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 10.3732,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.11454046639231824,
1207
+ "grad_norm": 78.93729400634766,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 10.5986,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.11522633744855967,
1214
+ "grad_norm": 69.44711303710938,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 10.57,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.11591220850480109,
1221
+ "grad_norm": 84.74750518798828,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 10.4673,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.11659807956104253,
1228
+ "grad_norm": 63.21523666381836,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 9.6459,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.11728395061728394,
1235
+ "grad_norm": 63.81535720825195,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 10.5836,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.11796982167352538,
1242
+ "grad_norm": 74.9435806274414,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 10.21,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.11865569272976681,
1249
+ "grad_norm": 80.28829193115234,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 9.9517,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.11934156378600823,
1256
+ "grad_norm": 56.12078857421875,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 10.2741,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.12002743484224966,
1263
+ "grad_norm": 60.06998062133789,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 9.9261,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.12071330589849108,
1270
+ "grad_norm": 68.69584655761719,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 10.1702,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.12139917695473251,
1277
+ "grad_norm": 83.58258819580078,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 10.7339,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.12208504801097393,
1284
+ "grad_norm": 67.84488677978516,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 10.5149,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.12277091906721536,
1291
+ "grad_norm": 73.4597396850586,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 9.5782,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.12345679012345678,
1298
+ "grad_norm": 79.10492706298828,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 10.292,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.12414266117969822,
1305
+ "grad_norm": 73.77743530273438,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 11.2363,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.12482853223593965,
1312
+ "grad_norm": 59.835994720458984,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 10.7522,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.12551440329218108,
1319
+ "grad_norm": 68.94219207763672,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 10.9599,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.1262002743484225,
1326
+ "grad_norm": 68.62545776367188,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 9.8215,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.12688614540466392,
1333
+ "grad_norm": 71.54290771484375,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.4858,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.12757201646090535,
1340
+ "grad_norm": 73.2717514038086,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.229,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.12825788751714678,
1347
+ "grad_norm": 83.46717834472656,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 10.071,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.1289437585733882,
1354
+ "grad_norm": 61.62462615966797,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 9.9997,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.12962962962962962,
1361
+ "grad_norm": 65.07300567626953,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 9.7776,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.13031550068587106,
1368
+ "grad_norm": 70.35834503173828,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 9.5993,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.1310013717421125,
1375
+ "grad_norm": 68.59699249267578,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 10.057,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.13168724279835392,
1382
+ "grad_norm": 84.115966796875,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 9.7622,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.13237311385459533,
1389
+ "grad_norm": 72.11085510253906,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 9.7314,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.13305898491083676,
1396
+ "grad_norm": 55.28156661987305,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 9.8484,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.1337448559670782,
1403
+ "grad_norm": 70.85758972167969,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 9.7574,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.13443072702331962,
1410
+ "grad_norm": 66.05179595947266,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 9.0654,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.13511659807956103,
1417
+ "grad_norm": 60.33279037475586,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 10.2341,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.13580246913580246,
1424
+ "grad_norm": 70.23603820800781,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 9.7082,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.1364883401920439,
1431
+ "grad_norm": 60.87910842895508,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 10.2319,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.13717421124828533,
1438
+ "grad_norm": 88.05852508544922,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 14.9627,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.13717421124828533,
1445
+ "eval_loss": 2.5416412353515625,
1446
+ "eval_runtime": 27.7018,
1447
+ "eval_samples_per_second": 88.659,
1448
+ "eval_steps_per_second": 22.165,
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": 1.49024359317504e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null