ancient41 commited on
Commit
7e12741
·
verified ·
1 Parent(s): f85e506

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:b615d32f9f351f38e44012428ffea3785b144dabd6a3d810d8246b4c4e667b6f
3
  size 226530600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd94671614fe11a8509432d43abc71a77a8ed3333e90c83ed41d81761bc9b69c
3
  size 226530600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b91e75aad5b64644a8f0cb52e449f5febf6d683e812121cd16962c250aa42186
3
  size 115354708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2bb1d888f0bc4987f6ee83531438a84ac59d7ec6e785bdd52fb00116699dc4
3
  size 115354708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b707ac600c72f72bf2ba8371bc20dfb0118abe1707e3f39b494d43329dfc34c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a973b704dd3d1e6923a5487fafa562cd9fea2677dcb831393560a73cdeccb9d8
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": 0.555241584777832,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 2.255639097744361,
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": 33.057,
1090
  "eval_steps_per_second": 8.264,
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": 4.15319576323031e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.555241584777832,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 3.007518796992481,
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": 33.057,
1090
  "eval_steps_per_second": 8.264,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.2706766917293235,
1095
+ "grad_norm": 0.162590891122818,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.6461,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.2857142857142856,
1102
+ "grad_norm": 0.17810818552970886,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.5882,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.300751879699248,
1109
+ "grad_norm": 0.1994241625070572,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.5266,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.3157894736842106,
1116
+ "grad_norm": 0.20960594713687897,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.5328,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.3308270676691727,
1123
+ "grad_norm": 0.23722250759601593,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.4816,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.345864661654135,
1130
+ "grad_norm": 0.2501429319381714,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.4603,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.3609022556390977,
1137
+ "grad_norm": 0.2598116397857666,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.4422,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.3759398496240602,
1144
+ "grad_norm": 0.26544246077537537,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.4352,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.3909774436090228,
1151
+ "grad_norm": 0.28918272256851196,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.4043,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.406015037593985,
1158
+ "grad_norm": 0.2864091694355011,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.3689,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.4210526315789473,
1165
+ "grad_norm": 0.3314032256603241,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.3901,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.43609022556391,
1172
+ "grad_norm": 0.2950114905834198,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.2565,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.451127819548872,
1179
+ "grad_norm": 0.36117634177207947,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.3079,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.4661654135338344,
1186
+ "grad_norm": 0.40990445017814636,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.3051,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.481203007518797,
1193
+ "grad_norm": 0.435947984457016,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.1591,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.4962406015037595,
1200
+ "grad_norm": 0.15773995220661163,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.6107,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.511278195488722,
1207
+ "grad_norm": 0.18130731582641602,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.6521,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.526315789473684,
1214
+ "grad_norm": 0.1928928941488266,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.584,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.5413533834586466,
1221
+ "grad_norm": 0.22154775261878967,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.536,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.556390977443609,
1228
+ "grad_norm": 0.24150554835796356,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.5197,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.571428571428571,
1235
+ "grad_norm": 0.2482544332742691,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.4437,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.5864661654135337,
1242
+ "grad_norm": 0.2693168818950653,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.4924,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.601503759398496,
1249
+ "grad_norm": 0.26239049434661865,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.3955,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.6165413533834587,
1256
+ "grad_norm": 0.28949567675590515,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.4173,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.6315789473684212,
1263
+ "grad_norm": 0.2859938144683838,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.388,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.6466165413533833,
1270
+ "grad_norm": 0.2940588891506195,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.3952,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 2.661654135338346,
1277
+ "grad_norm": 0.32735714316368103,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.3912,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.6766917293233083,
1284
+ "grad_norm": 0.32457244396209717,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.318,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.6917293233082704,
1291
+ "grad_norm": 0.3507591485977173,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.3252,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.706766917293233,
1298
+ "grad_norm": 0.41136404871940613,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.3047,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.7218045112781954,
1305
+ "grad_norm": 0.4661613702774048,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.1978,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 2.736842105263158,
1312
+ "grad_norm": 0.14506597816944122,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.5766,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 2.7518796992481205,
1319
+ "grad_norm": 0.1723233461380005,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.612,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 2.7669172932330826,
1326
+ "grad_norm": 0.18912146985530853,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.55,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 2.781954887218045,
1333
+ "grad_norm": 0.2082255482673645,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.6049,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 2.7969924812030076,
1340
+ "grad_norm": 0.21885396540164948,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.5299,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 2.8120300751879697,
1347
+ "grad_norm": 0.23263628780841827,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.5243,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 2.827067669172932,
1354
+ "grad_norm": 0.24706439673900604,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.4521,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 2.8421052631578947,
1361
+ "grad_norm": 0.26898086071014404,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.4638,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 2.857142857142857,
1368
+ "grad_norm": 0.277619332075119,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.4816,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 2.8721804511278197,
1375
+ "grad_norm": 0.28311529755592346,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.4499,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 2.887218045112782,
1382
+ "grad_norm": 0.2803266644477844,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.3319,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 2.9022556390977443,
1389
+ "grad_norm": 0.32511386275291443,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.4078,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.917293233082707,
1396
+ "grad_norm": 0.35642704367637634,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.3913,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.932330827067669,
1403
+ "grad_norm": 0.3581446707248688,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.3243,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.9473684210526314,
1410
+ "grad_norm": 0.4329220950603485,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.277,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.962406015037594,
1417
+ "grad_norm": 0.45859774947166443,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.1649,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.9774436090225564,
1424
+ "grad_norm": 0.19787120819091797,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.5944,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 2.992481203007519,
1431
+ "grad_norm": 0.2929736077785492,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.3918,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 3.007518796992481,
1438
+ "grad_norm": 0.6807894706726074,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.4638,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 3.007518796992481,
1445
+ "eval_loss": 0.5553240776062012,
1446
+ "eval_runtime": 3.3823,
1447
+ "eval_samples_per_second": 33.113,
1448
+ "eval_steps_per_second": 8.278,
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": 5.542925435928576e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null