aleegis10 commited on
Commit
02087f6
·
verified ·
1 Parent(s): c11017d

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 sha256:98cc3b4bb335fcb15bae8c27856f6eaa0a3565c2fc72c7b455b91bc49528fdb3
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3b63223dee44a26f842965d3b7e7553179322982a31ab6facce9d914682e69
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5acc6678f7036e4f3f80845020587364071fda23796dc80bdb2a07db9eaf1af7
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446e533cca73ab08fbb49c0a0a03fe355c9bd5b9ce17d6009fd25d7219c69e03
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad8c757e6ef8b19dc628f26a8a609c46a78c2fc4a5158213365d6269c5153660
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0873a8300660888ba188d3cff6cd044193c8ae5ebe9ba16ed951943ba2b1875
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": 10.309906959533691,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.06796556411418214,
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": 432.403,
1090
  "eval_steps_per_second": 108.188,
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": 17262464729088.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.30843448638916,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.09062075215224287,
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": 432.403,
1090
  "eval_steps_per_second": 108.188,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.06841866787494336,
1095
+ "grad_norm": 0.08348909765481949,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 10.3128,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.06887177163570457,
1102
+ "grad_norm": 0.09379616379737854,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 10.3159,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.06932487539646578,
1109
+ "grad_norm": 0.0836254358291626,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 10.3124,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.069777979157227,
1116
+ "grad_norm": 0.09745253622531891,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 10.3097,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.07023108291798821,
1123
+ "grad_norm": 0.08137994259595871,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 10.3102,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.07068418667874943,
1130
+ "grad_norm": 0.12498476356267929,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 10.3071,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.07113729043951064,
1137
+ "grad_norm": 0.1092490404844284,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 10.3114,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.07159039420027186,
1144
+ "grad_norm": 0.09169293940067291,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 10.309,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.07204349796103307,
1151
+ "grad_norm": 0.11189093440771103,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 10.3033,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.07249660172179428,
1158
+ "grad_norm": 0.08791095018386841,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 10.3112,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.0729497054825555,
1165
+ "grad_norm": 0.08543276786804199,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 10.31,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.07340280924331671,
1172
+ "grad_norm": 0.08431566506624222,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 10.3044,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.07385591300407793,
1179
+ "grad_norm": 0.07814370840787888,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 10.3143,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.07430901676483914,
1186
+ "grad_norm": 0.09191855788230896,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 10.3017,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.07476212052560036,
1193
+ "grad_norm": 0.09807488322257996,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 10.3141,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.07521522428636157,
1200
+ "grad_norm": 0.07995956391096115,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 10.314,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.07566832804712278,
1207
+ "grad_norm": 0.07811577618122101,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 10.3099,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.076121431807884,
1214
+ "grad_norm": 0.08100374788045883,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 10.3058,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.07657453556864521,
1221
+ "grad_norm": 0.07173501700162888,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 10.3133,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.07702763932940643,
1228
+ "grad_norm": 0.09132947772741318,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 10.3105,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.07748074309016764,
1235
+ "grad_norm": 0.07854383438825607,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 10.3081,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.07793384685092886,
1242
+ "grad_norm": 0.0775444358587265,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 10.3118,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.07838695061169007,
1249
+ "grad_norm": 0.08046716451644897,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 10.3063,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.07884005437245128,
1256
+ "grad_norm": 0.0875779464840889,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 10.316,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.0792931581332125,
1263
+ "grad_norm": 0.07684172689914703,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 10.3075,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.07974626189397371,
1270
+ "grad_norm": 0.08233340829610825,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 10.3063,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.08019936565473493,
1277
+ "grad_norm": 0.08705272525548935,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 10.3084,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.08065246941549614,
1284
+ "grad_norm": 0.08085699379444122,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 10.3118,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.08110557317625736,
1291
+ "grad_norm": 0.08175158500671387,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 10.3074,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.08155867693701857,
1298
+ "grad_norm": 0.0819338709115982,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 10.3111,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.08201178069777978,
1305
+ "grad_norm": 0.08131764829158783,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 10.3073,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.082464884458541,
1312
+ "grad_norm": 0.09145107865333557,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 10.3095,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.08291798821930221,
1319
+ "grad_norm": 0.10062360763549805,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 10.3068,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.08337109198006344,
1326
+ "grad_norm": 0.0973200649023056,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 10.3095,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.08382419574082466,
1333
+ "grad_norm": 0.08843878656625748,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 10.3099,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.08427729950158587,
1340
+ "grad_norm": 0.08757731318473816,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 10.3083,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.08473040326234708,
1347
+ "grad_norm": 0.07891438901424408,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 10.3117,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.0851835070231083,
1354
+ "grad_norm": 0.08320674300193787,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 10.3063,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.08563661078386951,
1361
+ "grad_norm": 0.09015924483537674,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 10.3128,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.08608971454463073,
1368
+ "grad_norm": 0.09279254823923111,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 10.3092,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.08654281830539194,
1375
+ "grad_norm": 0.09104158729314804,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 10.3095,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.08699592206615316,
1382
+ "grad_norm": 0.09526855498552322,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 10.3143,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.08744902582691437,
1389
+ "grad_norm": 0.08919867873191833,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 10.312,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.08790212958767558,
1396
+ "grad_norm": 0.08875775337219238,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 10.3029,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.0883552333484368,
1403
+ "grad_norm": 0.07775101065635681,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 10.3073,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.08880833710919801,
1410
+ "grad_norm": 0.07984912395477295,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 10.3121,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.08926144086995923,
1417
+ "grad_norm": 0.08644933253526688,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 10.3098,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.08971454463072044,
1424
+ "grad_norm": 0.07364819943904877,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 10.3072,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.09016764839148166,
1431
+ "grad_norm": 0.08544598519802094,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 10.3105,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.09062075215224287,
1438
+ "grad_norm": 0.10996384173631668,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 10.3074,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.09062075215224287,
1445
+ "eval_loss": 10.30843448638916,
1446
+ "eval_runtime": 8.601,
1447
+ "eval_samples_per_second": 432.157,
1448
+ "eval_steps_per_second": 108.127,
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": 23035211415552.0,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null