abaddon182 commited on
Commit
2ae0827
·
verified ·
1 Parent(s): d1866d8

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 sha256:1ecf4dbc1255bbd04e0ec71b9ec2144f9f5f5167a2a08c031be550e7477c7b36
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd6fc4c18172aa23c1ba612de3c3fbb39a359330f7be0dbb4c6fe5df4d07391
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bcd0be5d2068ff2b65dcb91cd7972e94f9879c41464997a119bddce9a8f4850
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22528871ccb57b659905d7837f403d4d08749d2d40adbbbbbb379aa59391f3d5
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d5a1a6230db7d6af7c9d0a0591d9593cb0fd1c360905819e6471801d9e5d61
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ad49c27edeca2f4ed1aa8c2d31b767a11b8bb3e317062407e70e466b34fdb
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": 0.36657968163490295,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.00628509176233973,
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": 58.026,
1090
  "eval_steps_per_second": 14.506,
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": 1.1612044853772288e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3646468222141266,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.008380122349786306,
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": 58.026,
1090
  "eval_steps_per_second": 14.506,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.006326992374088662,
1095
+ "grad_norm": 0.3790470063686371,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 0.3643,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.006368892985837593,
1102
+ "grad_norm": 0.4393303692340851,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 0.3707,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.006410793597586525,
1109
+ "grad_norm": 0.3993956446647644,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 0.3618,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.006452694209335456,
1116
+ "grad_norm": 0.3912157118320465,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 0.3621,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.006494594821084388,
1123
+ "grad_norm": 0.40146297216415405,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 0.3607,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.006536495432833319,
1130
+ "grad_norm": 0.3602310121059418,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 0.3631,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.006578396044582251,
1137
+ "grad_norm": 0.35525843501091003,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 0.3577,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.0066202966563311825,
1144
+ "grad_norm": 0.518125057220459,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 0.3728,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.006662197268080114,
1151
+ "grad_norm": 0.38681668043136597,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 0.3642,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.0067040978798290456,
1158
+ "grad_norm": 0.7894763946533203,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 0.3822,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.006745998491577977,
1165
+ "grad_norm": 0.4261036515235901,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 0.3767,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.006787899103326909,
1172
+ "grad_norm": 0.37567344307899475,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 0.3727,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.00682979971507584,
1179
+ "grad_norm": 0.37848037481307983,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 0.3578,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.006871700326824772,
1186
+ "grad_norm": 0.3375943601131439,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 0.3659,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.006913600938573703,
1193
+ "grad_norm": 0.3530254364013672,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 0.3587,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.006955501550322635,
1200
+ "grad_norm": 0.3661386966705322,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 0.3707,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.006997402162071566,
1207
+ "grad_norm": 0.3463679254055023,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 0.3644,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.007039302773820498,
1214
+ "grad_norm": 0.3842766582965851,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 0.3617,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.007081203385569429,
1221
+ "grad_norm": 0.44086405634880066,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 0.3583,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.007123103997318361,
1228
+ "grad_norm": 0.5864846110343933,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 0.3706,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.007165004609067292,
1235
+ "grad_norm": 0.3484610319137573,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 0.3537,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.007206905220816224,
1242
+ "grad_norm": 0.34717440605163574,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 0.3597,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.007248805832565155,
1249
+ "grad_norm": 0.4218187630176544,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 0.3615,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.007290706444314087,
1256
+ "grad_norm": 0.36104816198349,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 0.3697,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.0073326070560630185,
1263
+ "grad_norm": 0.36783576011657715,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 0.3634,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.0073745076678119505,
1270
+ "grad_norm": 0.3596624433994293,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 0.3654,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.007416408279560882,
1277
+ "grad_norm": 0.3116663098335266,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 0.3628,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.007458308891309813,
1284
+ "grad_norm": 0.3371797204017639,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 0.3681,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.007500209503058745,
1291
+ "grad_norm": 0.374452143907547,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 0.3543,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.007542110114807676,
1298
+ "grad_norm": 0.3471692204475403,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 0.3588,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.007584010726556608,
1305
+ "grad_norm": 0.37220466136932373,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 0.3689,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.007625911338305539,
1312
+ "grad_norm": 0.39862167835235596,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 0.367,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.007667811950054471,
1319
+ "grad_norm": 0.37802115082740784,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 0.3578,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.007709712561803402,
1326
+ "grad_norm": 0.3749293386936188,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 0.3645,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.007751613173552334,
1333
+ "grad_norm": 0.3764847218990326,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 0.3627,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.007793513785301265,
1340
+ "grad_norm": 0.39325788617134094,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 0.3637,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.007835414397050197,
1347
+ "grad_norm": 0.41122153401374817,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 0.3675,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.00787731500879913,
1354
+ "grad_norm": 0.4208770990371704,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 0.3705,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.00791921562054806,
1361
+ "grad_norm": 0.3626030683517456,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 0.3595,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.007961116232296991,
1368
+ "grad_norm": 0.36591896414756775,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 0.3608,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.008003016844045923,
1375
+ "grad_norm": 0.365206241607666,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 0.3729,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.008044917455794855,
1382
+ "grad_norm": 0.394902765750885,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 0.3681,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.008086818067543786,
1389
+ "grad_norm": 0.4147816300392151,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 0.3744,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.008128718679292718,
1396
+ "grad_norm": 0.4281652569770813,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 0.3683,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.00817061929104165,
1403
+ "grad_norm": 0.4012470841407776,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 0.3723,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.008212519902790582,
1410
+ "grad_norm": 0.3961266279220581,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 0.3677,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.008254420514539512,
1417
+ "grad_norm": 0.4153655767440796,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 0.3827,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.008296321126288444,
1424
+ "grad_norm": 0.4204557240009308,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 0.3799,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.008338221738037376,
1431
+ "grad_norm": 0.43716534972190857,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 0.3762,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.008380122349786306,
1438
+ "grad_norm": 0.5038236975669861,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.3883,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.008380122349786306,
1445
+ "eval_loss": 0.3646468222141266,
1446
+ "eval_runtime": 694.3148,
1447
+ "eval_samples_per_second": 57.893,
1448
+ "eval_steps_per_second": 14.473,
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": 1.5476286069669888e+16,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null