aleegis09 commited on
Commit
cb8e6b0
·
verified ·
1 Parent(s): 792b885

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 sha256:0c6d643f8126074a260cfd7e858ce670b6068cf9a0e9dd6f52e16b863f587478
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e553a81e3c65331a28560a69ce7395ca3c4a4955da8f4cc316a691f7cd743def
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b54f099c7feb6a0c1c7bdc2dc9e4441a0a4be831273f753fe05340a2dd7d3f
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d18583e857be71820ffc94fe968add322df441ef8026696c29bd89c389c0d41
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be1aac75f81331fdfd8ad7d3e40472a0482fb71a155973c5ad05c82bdc9a9e1f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c68eeefaacde1e92a940a4dadbbdc108300f4120afe51508c74bdd5c3b6b520
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": 0.6118667125701904,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.012709979452199885,
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": 19.15,
1090
  "eval_steps_per_second": 4.788,
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": 1.2067369021498982e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6110080480575562,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.01694663926959985,
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": 19.15,
1090
  "eval_steps_per_second": 4.788,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.012794712648547885,
1095
+ "grad_norm": 0.6554815173149109,
1096
+ "learning_rate": 1.553232954407171e-05,
1097
+ "loss": 4.4105,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.012879445844895884,
1102
+ "grad_norm": 2.143887758255005,
1103
+ "learning_rate": 1.4938160786375572e-05,
1104
+ "loss": 5.4198,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.012964179041243883,
1109
+ "grad_norm": 2.2846806049346924,
1110
+ "learning_rate": 1.435357758543015e-05,
1111
+ "loss": 4.6667,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.013048912237591883,
1116
+ "grad_norm": 0.7438145279884338,
1117
+ "learning_rate": 1.3778739760445552e-05,
1118
+ "loss": 2.034,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.013133645433939882,
1123
+ "grad_norm": 0.9079766869544983,
1124
+ "learning_rate": 1.3213804466343421e-05,
1125
+ "loss": 1.8094,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.01321837863028788,
1130
+ "grad_norm": 0.8040716052055359,
1131
+ "learning_rate": 1.2658926150792322e-05,
1132
+ "loss": 2.6914,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.01330311182663588,
1137
+ "grad_norm": 0.7632900476455688,
1138
+ "learning_rate": 1.2114256511983274e-05,
1139
+ "loss": 2.0123,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.01338784502298388,
1144
+ "grad_norm": 0.5317680835723877,
1145
+ "learning_rate": 1.157994445715706e-05,
1146
+ "loss": 1.6039,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.013472578219331878,
1151
+ "grad_norm": 0.8505305647850037,
1152
+ "learning_rate": 1.1056136061894384e-05,
1153
+ "loss": 1.976,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.013557311415679878,
1158
+ "grad_norm": 0.7244216203689575,
1159
+ "learning_rate": 1.0542974530180327e-05,
1160
+ "loss": 1.51,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.013642044612027877,
1165
+ "grad_norm": 1.1887725591659546,
1166
+ "learning_rate": 1.0040600155253765e-05,
1167
+ "loss": 1.6946,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.013726777808375876,
1172
+ "grad_norm": 0.7089770436286926,
1173
+ "learning_rate": 9.549150281252633e-06,
1174
+ "loss": 2.0679,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.013811511004723876,
1179
+ "grad_norm": 1.1469897031784058,
1180
+ "learning_rate": 9.068759265665384e-06,
1181
+ "loss": 2.4496,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.013896244201071875,
1186
+ "grad_norm": 0.8589446544647217,
1187
+ "learning_rate": 8.599558442598998e-06,
1188
+ "loss": 2.0527,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.013980977397419873,
1193
+ "grad_norm": 0.8439194560050964,
1194
+ "learning_rate": 8.141676086873572e-06,
1195
+ "loss": 1.7199,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.014065710593767874,
1200
+ "grad_norm": 0.6832525730133057,
1201
+ "learning_rate": 7.695237378953223e-06,
1202
+ "loss": 1.8389,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.014150443790115872,
1207
+ "grad_norm": 0.7510490417480469,
1208
+ "learning_rate": 7.260364370723044e-06,
1209
+ "loss": 1.4477,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.014235176986463871,
1214
+ "grad_norm": 0.6456084251403809,
1215
+ "learning_rate": 6.837175952121306e-06,
1216
+ "loss": 1.7282,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.014319910182811871,
1221
+ "grad_norm": 0.7840536832809448,
1222
+ "learning_rate": 6.425787818636131e-06,
1223
+ "loss": 1.6125,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.01440464337915987,
1228
+ "grad_norm": 0.9131442904472351,
1229
+ "learning_rate": 6.026312439675552e-06,
1230
+ "loss": 1.5309,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.014489376575507869,
1235
+ "grad_norm": 0.8122759461402893,
1236
+ "learning_rate": 5.6388590278194096e-06,
1237
+ "loss": 1.3547,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.01457410977185587,
1242
+ "grad_norm": 0.8226937651634216,
1243
+ "learning_rate": 5.263533508961827e-06,
1244
+ "loss": 1.9562,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.014658842968203868,
1249
+ "grad_norm": 0.7177022099494934,
1250
+ "learning_rate": 4.900438493352055e-06,
1251
+ "loss": 1.7206,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.014743576164551866,
1256
+ "grad_norm": 0.7838985323905945,
1257
+ "learning_rate": 4.549673247541875e-06,
1258
+ "loss": 2.0408,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.014828309360899867,
1263
+ "grad_norm": 0.7556291222572327,
1264
+ "learning_rate": 4.2113336672471245e-06,
1265
+ "loss": 3.3785,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.014913042557247866,
1270
+ "grad_norm": 0.8151933550834656,
1271
+ "learning_rate": 3.885512251130763e-06,
1272
+ "loss": 2.5495,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.014997775753595864,
1277
+ "grad_norm": 0.7658029198646545,
1278
+ "learning_rate": 3.5722980755146517e-06,
1279
+ "loss": 1.9918,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.015082508949943865,
1284
+ "grad_norm": 0.9327448606491089,
1285
+ "learning_rate": 3.271776770026963e-06,
1286
+ "loss": 2.5801,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.015167242146291863,
1291
+ "grad_norm": 1.0551213026046753,
1292
+ "learning_rate": 2.9840304941919415e-06,
1293
+ "loss": 1.4426,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.015251975342639862,
1298
+ "grad_norm": 0.978588879108429,
1299
+ "learning_rate": 2.7091379149682685e-06,
1300
+ "loss": 2.3184,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.015336708538987862,
1305
+ "grad_norm": 1.5680279731750488,
1306
+ "learning_rate": 2.4471741852423237e-06,
1307
+ "loss": 2.0095,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.015421441735335861,
1312
+ "grad_norm": 0.8339734673500061,
1313
+ "learning_rate": 2.1982109232821178e-06,
1314
+ "loss": 1.5813,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.015506174931683861,
1319
+ "grad_norm": 1.009131908416748,
1320
+ "learning_rate": 1.962316193157593e-06,
1321
+ "loss": 2.4437,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.01559090812803186,
1326
+ "grad_norm": 0.9678205847740173,
1327
+ "learning_rate": 1.7395544861325718e-06,
1328
+ "loss": 2.8736,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.01567564132437986,
1333
+ "grad_norm": 1.3465261459350586,
1334
+ "learning_rate": 1.5299867030334814e-06,
1335
+ "loss": 2.5842,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.015760374520727857,
1340
+ "grad_norm": 1.254457950592041,
1341
+ "learning_rate": 1.333670137599713e-06,
1342
+ "loss": 3.2385,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.015845107717075858,
1347
+ "grad_norm": 1.3965961933135986,
1348
+ "learning_rate": 1.1506584608200367e-06,
1349
+ "loss": 2.9635,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.015929840913423858,
1354
+ "grad_norm": 1.1905745267868042,
1355
+ "learning_rate": 9.810017062595322e-07,
1356
+ "loss": 3.6272,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.016014574109771855,
1361
+ "grad_norm": 1.2281651496887207,
1362
+ "learning_rate": 8.247462563808817e-07,
1363
+ "loss": 3.3412,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.016099307306119855,
1368
+ "grad_norm": 0.9285405874252319,
1369
+ "learning_rate": 6.819348298638839e-07,
1370
+ "loss": 3.6246,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.016184040502467856,
1375
+ "grad_norm": 1.4655163288116455,
1376
+ "learning_rate": 5.526064699265753e-07,
1377
+ "loss": 4.2569,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.016268773698815853,
1382
+ "grad_norm": 1.1888004541397095,
1383
+ "learning_rate": 4.367965336512403e-07,
1384
+ "loss": 3.1601,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.016353506895163853,
1389
+ "grad_norm": 1.584453821182251,
1390
+ "learning_rate": 3.3453668231809286e-07,
1391
+ "loss": 4.1065,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.016438240091511853,
1396
+ "grad_norm": 1.3552757501602173,
1397
+ "learning_rate": 2.458548727494292e-07,
1398
+ "loss": 3.6222,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.01652297328785985,
1403
+ "grad_norm": 1.4499890804290771,
1404
+ "learning_rate": 1.7077534966650766e-07,
1405
+ "loss": 3.6696,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.01660770648420785,
1410
+ "grad_norm": 1.3624193668365479,
1411
+ "learning_rate": 1.0931863906127327e-07,
1412
+ "loss": 3.3733,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.01669243968055585,
1417
+ "grad_norm": 1.3254767656326294,
1418
+ "learning_rate": 6.150154258476315e-08,
1419
+ "loss": 3.6421,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.016777172876903848,
1424
+ "grad_norm": 1.2194263935089111,
1425
+ "learning_rate": 2.7337132953697554e-08,
1426
+ "loss": 2.5926,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.01686190607325185,
1431
+ "grad_norm": 1.3185057640075684,
1432
+ "learning_rate": 6.834750376549792e-09,
1433
+ "loss": 2.4015,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.01694663926959985,
1438
+ "grad_norm": 2.024052619934082,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 2.7907,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.01694663926959985,
1445
+ "eval_loss": 0.6110080480575562,
1446
+ "eval_runtime": 1037.4354,
1447
+ "eval_samples_per_second": 19.16,
1448
+ "eval_steps_per_second": 4.791,
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": 1.605205581889536e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null