bbytxt commited on
Commit
011ba99
·
verified ·
1 Parent(s): 909f085

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:e3c9faf1def9960b2f9aca1e7d133ad1037762fb92a52f7a82cd746febc9fd3f
3
  size 26008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f266738e617dfdb92ff0555a94a3adb2e3e79fa3e282793ef69075d2f405bf0
3
  size 26008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0de3a484f719053f672cc924c249d7a917da92155779707d1233cdc3548ca084
3
  size 68874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06be7e3069e4208797e0f76925f30ba742cad1bd2f97fdc63c6e7f38df9daac8
3
  size 68874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02cecdf2e6a32300a7e5d4017b0bed35eae6027556dcc31245ce6c23aa2017f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8260a1e862944e32ed6a06c3def23f785af121d836c1470c9830d9997e80b05
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.908464431762695,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.01855459690138232,
5
  "eval_steps": 25,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1113,6 +1113,372 @@
1113
  "eval_samples_per_second": 189.851,
1114
  "eval_steps_per_second": 26.579,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -1127,7 +1493,7 @@
1127
  "early_stopping_threshold": 0.0
1128
  },
1129
  "attributes": {
1130
- "early_stopping_patience_counter": 0
1131
  }
1132
  },
1133
  "TrainerControl": {
@@ -1136,12 +1502,12 @@
1136
  "should_evaluate": false,
1137
  "should_log": false,
1138
  "should_save": true,
1139
- "should_training_stop": false
1140
  },
1141
  "attributes": {}
1142
  }
1143
  },
1144
- "total_flos": 238893465600.0,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
  "best_metric": 11.908464431762695,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.024739462535176424,
5
  "eval_steps": 25,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1113
  "eval_samples_per_second": 189.851,
1114
  "eval_steps_per_second": 26.579,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.0186782942140582,
1119
+ "grad_norm": 0.038416147232055664,
1120
+ "learning_rate": 4.659698863221513e-05,
1121
+ "loss": 11.9251,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.01880199152673408,
1126
+ "grad_norm": 0.03391510993242264,
1127
+ "learning_rate": 4.481448235912671e-05,
1128
+ "loss": 11.9185,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.018925688839409965,
1133
+ "grad_norm": 0.03237089142203331,
1134
+ "learning_rate": 4.306073275629044e-05,
1135
+ "loss": 11.9204,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.019049386152085845,
1140
+ "grad_norm": 0.023452546447515488,
1141
+ "learning_rate": 4.133621928133665e-05,
1142
+ "loss": 11.9194,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.01917308346476173,
1147
+ "grad_norm": 0.030487986281514168,
1148
+ "learning_rate": 3.964141339903026e-05,
1149
+ "loss": 11.916,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.01929678077743761,
1154
+ "grad_norm": 0.055698998272418976,
1155
+ "learning_rate": 3.797677845237696e-05,
1156
+ "loss": 11.9158,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.01942047809011349,
1161
+ "grad_norm": 0.03359595313668251,
1162
+ "learning_rate": 3.634276953594982e-05,
1163
+ "loss": 11.9154,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.019544175402789375,
1168
+ "grad_norm": 0.026363002136349678,
1169
+ "learning_rate": 3.473983337147118e-05,
1170
+ "loss": 11.9137,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.019667872715465256,
1175
+ "grad_norm": 0.023208264261484146,
1176
+ "learning_rate": 3.316840818568315e-05,
1177
+ "loss": 11.9112,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.01979157002814114,
1182
+ "grad_norm": 0.05028776079416275,
1183
+ "learning_rate": 3.162892359054098e-05,
1184
+ "loss": 11.9199,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.01991526734081702,
1189
+ "grad_norm": 0.04316272214055061,
1190
+ "learning_rate": 3.0121800465761293e-05,
1191
+ "loss": 11.9127,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.0200389646534929,
1196
+ "grad_norm": 0.04402907192707062,
1197
+ "learning_rate": 2.8647450843757897e-05,
1198
+ "loss": 11.9105,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.020162661966168786,
1203
+ "grad_norm": 0.027768168598413467,
1204
+ "learning_rate": 2.7206277796996144e-05,
1205
+ "loss": 11.9161,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.020286359278844666,
1210
+ "grad_norm": 0.040380846709012985,
1211
+ "learning_rate": 2.5798675327796993e-05,
1212
+ "loss": 11.9126,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.02041005659152055,
1217
+ "grad_norm": 0.033700235188007355,
1218
+ "learning_rate": 2.4425028260620715e-05,
1219
+ "loss": 11.9119,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.02053375390419643,
1224
+ "grad_norm": 0.03703916445374489,
1225
+ "learning_rate": 2.3085712136859668e-05,
1226
+ "loss": 11.9096,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.020657451216872312,
1231
+ "grad_norm": 0.02751343883574009,
1232
+ "learning_rate": 2.178109311216913e-05,
1233
+ "loss": 11.9118,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.020781148529548196,
1238
+ "grad_norm": 0.037701401859521866,
1239
+ "learning_rate": 2.0511527856363912e-05,
1240
+ "loss": 11.9093,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.020904845842224077,
1245
+ "grad_norm": 0.03141371160745621,
1246
+ "learning_rate": 1.927736345590839e-05,
1247
+ "loss": 11.9119,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.02102854315489996,
1252
+ "grad_norm": 0.02860465832054615,
1253
+ "learning_rate": 1.8078937319026654e-05,
1254
+ "loss": 11.9096,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.021152240467575842,
1259
+ "grad_norm": 0.030303940176963806,
1260
+ "learning_rate": 1.6916577083458228e-05,
1261
+ "loss": 11.9084,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.021275937780251723,
1266
+ "grad_norm": 0.036338724195957184,
1267
+ "learning_rate": 1.579060052688548e-05,
1268
+ "loss": 11.9069,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.021399635092927607,
1273
+ "grad_norm": 0.04576665908098221,
1274
+ "learning_rate": 1.4701315480056164e-05,
1275
+ "loss": 11.9076,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.021523332405603487,
1280
+ "grad_norm": 0.02855774015188217,
1281
+ "learning_rate": 1.3649019742625623e-05,
1282
+ "loss": 11.9078,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.02164702971827937,
1287
+ "grad_norm": 0.04007178544998169,
1288
+ "learning_rate": 1.2634001001741373e-05,
1289
+ "loss": 11.9067,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.02164702971827937,
1294
+ "eval_loss": 11.908154487609863,
1295
+ "eval_runtime": 0.2644,
1296
+ "eval_samples_per_second": 189.073,
1297
+ "eval_steps_per_second": 26.47,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.021770727030955252,
1302
+ "grad_norm": 0.03717833757400513,
1303
+ "learning_rate": 1.1656536753392287e-05,
1304
+ "loss": 11.9075,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.021894424343631133,
1309
+ "grad_norm": 0.04426046460866928,
1310
+ "learning_rate": 1.0716894226543953e-05,
1311
+ "loss": 11.9041,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.022018121656307017,
1316
+ "grad_norm": 0.048932015895843506,
1317
+ "learning_rate": 9.815330310080887e-06,
1318
+ "loss": 11.9051,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.022141818968982898,
1323
+ "grad_norm": 0.03865474462509155,
1324
+ "learning_rate": 8.952091482575824e-06,
1325
+ "loss": 11.9107,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.022265516281658782,
1330
+ "grad_norm": 0.052123475819826126,
1331
+ "learning_rate": 8.127413744904804e-06,
1332
+ "loss": 11.9026,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.022389213594334663,
1337
+ "grad_norm": 0.04693127050995827,
1338
+ "learning_rate": 7.34152255572697e-06,
1339
+ "loss": 11.9022,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.022512910907010544,
1344
+ "grad_norm": 0.03584551811218262,
1345
+ "learning_rate": 6.594632769846353e-06,
1346
+ "loss": 11.905,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.022636608219686428,
1351
+ "grad_norm": 0.028417017310857773,
1352
+ "learning_rate": 5.886948579472778e-06,
1353
+ "loss": 11.907,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.02276030553236231,
1358
+ "grad_norm": 0.058878276497125626,
1359
+ "learning_rate": 5.218663458397715e-06,
1360
+ "loss": 11.9049,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.022884002845038193,
1365
+ "grad_norm": 0.04289981350302696,
1366
+ "learning_rate": 4.589960109100444e-06,
1367
+ "loss": 11.9034,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.023007700157714073,
1372
+ "grad_norm": 0.03270270675420761,
1373
+ "learning_rate": 4.001010412799138e-06,
1374
+ "loss": 11.9037,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.023131397470389954,
1379
+ "grad_norm": 0.047297991812229156,
1380
+ "learning_rate": 3.451975382460109e-06,
1381
+ "loss": 11.9048,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.02325509478306584,
1386
+ "grad_norm": 0.04329264536499977,
1387
+ "learning_rate": 2.9430051187785962e-06,
1388
+ "loss": 11.9019,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.02337879209574172,
1393
+ "grad_norm": 0.0510840006172657,
1394
+ "learning_rate": 2.4742387691426445e-06,
1395
+ "loss": 11.9074,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.023502489408417603,
1400
+ "grad_norm": 0.04246576875448227,
1401
+ "learning_rate": 2.0458044895916513e-06,
1402
+ "loss": 11.9031,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 0.023626186721093484,
1407
+ "grad_norm": 0.05678914487361908,
1408
+ "learning_rate": 1.6578194097797258e-06,
1409
+ "loss": 11.9003,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 0.023749884033769365,
1414
+ "grad_norm": 0.05008501559495926,
1415
+ "learning_rate": 1.3103896009537207e-06,
1416
+ "loss": 11.8984,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 0.02387358134644525,
1421
+ "grad_norm": 0.0424390472471714,
1422
+ "learning_rate": 1.0036100469542786e-06,
1423
+ "loss": 11.9011,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 0.02399727865912113,
1428
+ "grad_norm": 0.0445965901017189,
1429
+ "learning_rate": 7.375646182482875e-07,
1430
+ "loss": 11.8971,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 0.024120975971797014,
1435
+ "grad_norm": 0.05231767147779465,
1436
+ "learning_rate": 5.123260489995229e-07,
1437
+ "loss": 11.8981,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 0.024244673284472894,
1442
+ "grad_norm": 0.06141066178679466,
1443
+ "learning_rate": 3.2795591718381975e-07,
1444
+ "loss": 11.8995,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 0.02436837059714878,
1449
+ "grad_norm": 0.0452197827398777,
1450
+ "learning_rate": 1.8450462775428942e-07,
1451
+ "loss": 11.8955,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 0.02449206790982466,
1456
+ "grad_norm": 0.06387006491422653,
1457
+ "learning_rate": 8.201139886109264e-08,
1458
+ "loss": 11.8958,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 0.02461576522250054,
1463
+ "grad_norm": 0.05863620713353157,
1464
+ "learning_rate": 2.0504251129649374e-08,
1465
+ "loss": 11.8991,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 0.024739462535176424,
1470
+ "grad_norm": 0.08195962011814117,
1471
+ "learning_rate": 0.0,
1472
+ "loss": 11.8975,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 0.024739462535176424,
1477
+ "eval_loss": 11.909034729003906,
1478
+ "eval_runtime": 0.2632,
1479
+ "eval_samples_per_second": 189.962,
1480
+ "eval_steps_per_second": 26.595,
1481
+ "step": 200
1482
  }
1483
  ],
1484
  "logging_steps": 1,
 
1493
  "early_stopping_threshold": 0.0
1494
  },
1495
  "attributes": {
1496
+ "early_stopping_patience_counter": 1
1497
  }
1498
  },
1499
  "TrainerControl": {
 
1502
  "should_evaluate": false,
1503
  "should_log": false,
1504
  "should_save": true,
1505
+ "should_training_stop": true
1506
  },
1507
  "attributes": {}
1508
  }
1509
  },
1510
+ "total_flos": 318524620800.0,
1511
  "train_batch_size": 8,
1512
  "trial_name": null,
1513
  "trial_params": null