aleegis09 commited on
Commit
c68466f
·
verified ·
1 Parent(s): 2c7c01a

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:a626e342c6fcc8699463f12185a6b765c8dacc4ff303388d5978149b9bdac422
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1d7509be74ba781c68a7668c5486c7171dcbd9581be129b9b6ef17e4563b0b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7a8ffb38d87758e5e0c6613f18453d5e591042be922685462d1a0b06bd911d8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41df67aeea2c94c22064b45f5a22b029f282312f26b804c4949b396f393bca83
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987d8dabb393fd2ae80a4e7d0c082d54b7eb9edd6ebf13e25fd3e50f36b01c96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626ba5035e06685cea8a52a6fd80497dbae889583ebaa94bd30c801660d975e5
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": 0.0014206551713868976,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.016515276630883566,
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": 12.108,
1090
  "eval_steps_per_second": 3.028,
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": 0
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": 2.3947653062590464e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.0014206551713868976,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02202036884117809,
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": 12.108,
1090
  "eval_steps_per_second": 3.028,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.016625378475089457,
1095
+ "grad_norm": 0.09660545736551285,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.0064,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.016735480319295348,
1102
+ "grad_norm": 0.025750622153282166,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.001,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.016845582163501238,
1109
+ "grad_norm": 0.008917738683521748,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.0002,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.01695568400770713,
1116
+ "grad_norm": 0.05178796499967575,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.0003,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.01706578585191302,
1123
+ "grad_norm": 0.027266381308436394,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.002,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.01717588769611891,
1130
+ "grad_norm": 0.01055882964283228,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.0002,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.0172859895403248,
1137
+ "grad_norm": 0.03038918972015381,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.0003,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.01739609138453069,
1144
+ "grad_norm": 0.05853760614991188,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.0021,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.01750619322873658,
1151
+ "grad_norm": 0.023376965895295143,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.0005,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.017616295072942472,
1158
+ "grad_norm": 0.005594929680228233,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.0001,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.017726396917148363,
1165
+ "grad_norm": 0.02659245766699314,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.001,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.017836498761354253,
1172
+ "grad_norm": 0.004689844325184822,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.0001,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.017946600605560144,
1179
+ "grad_norm": 0.022979892790317535,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.0002,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.018056702449766034,
1186
+ "grad_norm": 0.02723834291100502,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.0004,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.018166804293971925,
1193
+ "grad_norm": 0.03148455172777176,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.0017,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.018276906138177815,
1200
+ "grad_norm": 0.09429357945919037,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.0028,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.018387007982383706,
1207
+ "grad_norm": 0.04778239130973816,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.0006,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.018497109826589597,
1214
+ "grad_norm": 0.040221914649009705,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.001,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.018607211670795487,
1221
+ "grad_norm": 0.010748670436441898,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.0002,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.018717313515001378,
1228
+ "grad_norm": 0.05414541810750961,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.0008,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.018827415359207268,
1235
+ "grad_norm": 0.016328755766153336,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.0003,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.01893751720341316,
1242
+ "grad_norm": 0.03930515795946121,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.0015,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.01904761904761905,
1249
+ "grad_norm": 0.007215072400867939,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.0002,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.019157720891824936,
1256
+ "grad_norm": 0.003403697395697236,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.0002,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.019267822736030827,
1263
+ "grad_norm": 0.029215769842267036,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.0003,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.019377924580236718,
1270
+ "grad_norm": 0.012023699469864368,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.0001,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.019488026424442608,
1277
+ "grad_norm": 0.01875670626759529,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.0012,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.0195981282686485,
1284
+ "grad_norm": 0.008806823752820492,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.0002,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.01970823011285439,
1291
+ "grad_norm": 0.022227568551898003,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.0008,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.01981833195706028,
1298
+ "grad_norm": 0.051266446709632874,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.0026,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.01992843380126617,
1305
+ "grad_norm": 0.039944980293512344,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.0033,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.02003853564547206,
1312
+ "grad_norm": 0.05004933476448059,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.0049,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.02014863748967795,
1319
+ "grad_norm": 0.020467787981033325,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.0003,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.020258739333883842,
1326
+ "grad_norm": 0.0031345949973911047,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.0002,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.020368841178089733,
1333
+ "grad_norm": 0.04058748111128807,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.0044,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.020478943022295623,
1340
+ "grad_norm": 0.034639887511730194,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.001,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.020589044866501514,
1347
+ "grad_norm": 0.015364250168204308,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.0003,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.020699146710707404,
1354
+ "grad_norm": 0.02289467863738537,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.0007,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.020809248554913295,
1361
+ "grad_norm": 0.004905928857624531,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.0002,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.020919350399119185,
1368
+ "grad_norm": 0.15956906974315643,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.0064,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.021029452243325076,
1375
+ "grad_norm": 0.07649794965982437,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.0036,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.021139554087530966,
1382
+ "grad_norm": 0.032520826905965805,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.0006,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.021249655931736857,
1389
+ "grad_norm": 0.049935244023799896,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.0032,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.021359757775942748,
1396
+ "grad_norm": 0.042919401079416275,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.0003,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.021469859620148638,
1403
+ "grad_norm": 0.00869014859199524,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.0002,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.02157996146435453,
1410
+ "grad_norm": 0.032568126916885376,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.0005,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.02169006330856042,
1417
+ "grad_norm": 0.19234830141067505,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.0041,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.02180016515276631,
1424
+ "grad_norm": 0.16615378856658936,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.0118,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.0219102669969722,
1431
+ "grad_norm": 0.10315118730068207,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.001,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.02202036884117809,
1438
+ "grad_norm": 0.018361156806349754,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.0004,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.02202036884117809,
1445
+ "eval_loss": 0.0016941390931606293,
1446
+ "eval_runtime": 1261.3007,
1447
+ "eval_samples_per_second": 12.128,
1448
+ "eval_steps_per_second": 3.033,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "early_stopping_threshold": 0.0
1462
  },
1463
  "attributes": {
1464
+ "early_stopping_patience_counter": 1
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": 3.1905062190474854e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null