0x1202 commited on
Commit
b06b441
·
verified ·
1 Parent(s): 8d85088

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 sha256:7647ae0627a7b725e322f0e4d5e33cd169586fc185828a0e8f595005b45fa3df
3
  size 2269195160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6e8289afbb5b7a6c01b2e2cfb6109769e332fba99d585b5a6d31019acc682e
3
  size 2269195160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9f4f0d2f5d6b2ead9512276ab4388b03851af6e42e5e40a1fdb4e34188d3049
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdc5361dc010fed4b9e2c108e3ffd12a71982725995fff96bfbc2a3dbd54194
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c36b216c590f6eca2a00a39d4b3b2093147d8c280798056ecb0b21597d90051e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5432f7d821ce4350169c76b75dea6eadce5659f64df6eb2118f93374d0ed33da
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": 1.169845700263977,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.29708485486166986,
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": 6.292,
1114
  "eval_steps_per_second": 6.292,
1115
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1116
  }
1117
  ],
1118
  "logging_steps": 1,
@@ -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": 2.364766999805952e+17,
1145
  "train_batch_size": 1,
1146
  "trial_name": null,
1147
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1278622150421143,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.39611313981555984,
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": 6.292,
1114
  "eval_steps_per_second": 6.292,
1115
  "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.29906542056074764,
1119
+ "grad_norm": 0.5212217569351196,
1120
+ "learning_rate": 4.659698863221513e-05,
1121
+ "loss": 0.9336,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.3010459862598255,
1126
+ "grad_norm": 0.5553271770477295,
1127
+ "learning_rate": 4.481448235912671e-05,
1128
+ "loss": 0.9745,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.30302655195890327,
1133
+ "grad_norm": 0.6053627133369446,
1134
+ "learning_rate": 4.306073275629044e-05,
1135
+ "loss": 0.953,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.30500711765798105,
1140
+ "grad_norm": 0.5293852686882019,
1141
+ "learning_rate": 4.133621928133665e-05,
1142
+ "loss": 0.8579,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.30698768335705884,
1147
+ "grad_norm": 0.5316524505615234,
1148
+ "learning_rate": 3.964141339903026e-05,
1149
+ "loss": 0.8284,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.3089682490561367,
1154
+ "grad_norm": 0.5538764595985413,
1155
+ "learning_rate": 3.797677845237696e-05,
1156
+ "loss": 0.8725,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.31094881475521446,
1161
+ "grad_norm": 0.5353713631629944,
1162
+ "learning_rate": 3.634276953594982e-05,
1163
+ "loss": 0.8798,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 0.31292938045429225,
1168
+ "grad_norm": 0.45507702231407166,
1169
+ "learning_rate": 3.473983337147118e-05,
1170
+ "loss": 0.7345,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 0.31490994615337004,
1175
+ "grad_norm": 0.5768627524375916,
1176
+ "learning_rate": 3.316840818568315e-05,
1177
+ "loss": 0.9696,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 0.3168905118524479,
1182
+ "grad_norm": 0.4070928394794464,
1183
+ "learning_rate": 3.162892359054098e-05,
1184
+ "loss": 0.8171,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 0.31887107755152566,
1189
+ "grad_norm": 0.28896093368530273,
1190
+ "learning_rate": 3.0121800465761293e-05,
1191
+ "loss": 0.6783,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 0.32085164325060345,
1196
+ "grad_norm": 0.292948842048645,
1197
+ "learning_rate": 2.8647450843757897e-05,
1198
+ "loss": 0.8252,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 0.32283220894968123,
1203
+ "grad_norm": 0.373655766248703,
1204
+ "learning_rate": 2.7206277796996144e-05,
1205
+ "loss": 0.8913,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 0.3248127746487591,
1210
+ "grad_norm": 0.2723099887371063,
1211
+ "learning_rate": 2.5798675327796993e-05,
1212
+ "loss": 0.7866,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 0.32679334034783686,
1217
+ "grad_norm": 0.31054458022117615,
1218
+ "learning_rate": 2.4425028260620715e-05,
1219
+ "loss": 0.7626,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 0.32877390604691464,
1224
+ "grad_norm": 0.31001657247543335,
1225
+ "learning_rate": 2.3085712136859668e-05,
1226
+ "loss": 0.837,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 0.33075447174599243,
1231
+ "grad_norm": 0.3545086085796356,
1232
+ "learning_rate": 2.178109311216913e-05,
1233
+ "loss": 1.0232,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 0.33273503744507027,
1238
+ "grad_norm": 0.3655906915664673,
1239
+ "learning_rate": 2.0511527856363912e-05,
1240
+ "loss": 0.9356,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 0.33471560314414806,
1245
+ "grad_norm": 0.42094361782073975,
1246
+ "learning_rate": 1.927736345590839e-05,
1247
+ "loss": 1.122,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 0.33669616884322584,
1252
+ "grad_norm": 0.4121546745300293,
1253
+ "learning_rate": 1.8078937319026654e-05,
1254
+ "loss": 1.1692,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 0.3386767345423036,
1259
+ "grad_norm": 0.43121325969696045,
1260
+ "learning_rate": 1.6916577083458228e-05,
1261
+ "loss": 1.1433,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 0.34065730024138147,
1266
+ "grad_norm": 0.44818028807640076,
1267
+ "learning_rate": 1.579060052688548e-05,
1268
+ "loss": 1.1544,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 0.34263786594045925,
1273
+ "grad_norm": 0.46644723415374756,
1274
+ "learning_rate": 1.4701315480056164e-05,
1275
+ "loss": 1.1511,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 0.34461843163953704,
1280
+ "grad_norm": 0.5559659004211426,
1281
+ "learning_rate": 1.3649019742625623e-05,
1282
+ "loss": 1.1325,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 0.3465989973386148,
1287
+ "grad_norm": 0.486060231924057,
1288
+ "learning_rate": 1.2634001001741373e-05,
1289
+ "loss": 1.0881,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 0.3465989973386148,
1294
+ "eval_loss": 1.13009774684906,
1295
+ "eval_runtime": 7.9539,
1296
+ "eval_samples_per_second": 6.286,
1297
+ "eval_steps_per_second": 6.286,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 0.34857956303769266,
1302
+ "grad_norm": 0.4915584921836853,
1303
+ "learning_rate": 1.1656536753392287e-05,
1304
+ "loss": 1.1702,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 0.35056012873677045,
1309
+ "grad_norm": 0.5216694474220276,
1310
+ "learning_rate": 1.0716894226543953e-05,
1311
+ "loss": 1.2237,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 0.35254069443584823,
1316
+ "grad_norm": 0.4730156660079956,
1317
+ "learning_rate": 9.815330310080887e-06,
1318
+ "loss": 1.1725,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 0.354521260134926,
1323
+ "grad_norm": 0.5110475420951843,
1324
+ "learning_rate": 8.952091482575824e-06,
1325
+ "loss": 1.2701,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 0.35650182583400386,
1330
+ "grad_norm": 0.5410056114196777,
1331
+ "learning_rate": 8.127413744904804e-06,
1332
+ "loss": 1.125,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 0.35848239153308165,
1337
+ "grad_norm": 0.4916069209575653,
1338
+ "learning_rate": 7.34152255572697e-06,
1339
+ "loss": 1.063,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 0.36046295723215943,
1344
+ "grad_norm": 0.5280264019966125,
1345
+ "learning_rate": 6.594632769846353e-06,
1346
+ "loss": 1.022,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 0.3624435229312372,
1351
+ "grad_norm": 0.4919007420539856,
1352
+ "learning_rate": 5.886948579472778e-06,
1353
+ "loss": 1.0365,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 0.36442408863031506,
1358
+ "grad_norm": 0.5240092873573303,
1359
+ "learning_rate": 5.218663458397715e-06,
1360
+ "loss": 1.1609,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 0.36640465432939284,
1365
+ "grad_norm": 0.6551080942153931,
1366
+ "learning_rate": 4.589960109100444e-06,
1367
+ "loss": 0.8449,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 0.36838522002847063,
1372
+ "grad_norm": 0.5417661666870117,
1373
+ "learning_rate": 4.001010412799138e-06,
1374
+ "loss": 1.0913,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 0.3703657857275484,
1379
+ "grad_norm": 0.5707260370254517,
1380
+ "learning_rate": 3.451975382460109e-06,
1381
+ "loss": 0.8799,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 0.37234635142662625,
1386
+ "grad_norm": 0.5540571808815002,
1387
+ "learning_rate": 2.9430051187785962e-06,
1388
+ "loss": 0.9926,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 0.37432691712570404,
1393
+ "grad_norm": 0.5678872466087341,
1394
+ "learning_rate": 2.4742387691426445e-06,
1395
+ "loss": 0.9895,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 0.3763074828247818,
1400
+ "grad_norm": 0.6278743743896484,
1401
+ "learning_rate": 2.0458044895916513e-06,
1402
+ "loss": 0.9935,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 0.3782880485238596,
1407
+ "grad_norm": 0.6568822860717773,
1408
+ "learning_rate": 1.6578194097797258e-06,
1409
+ "loss": 0.8738,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 0.38026861422293745,
1414
+ "grad_norm": 0.6540056467056274,
1415
+ "learning_rate": 1.3103896009537207e-06,
1416
+ "loss": 1.1838,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 0.38224917992201524,
1421
+ "grad_norm": 0.7000465393066406,
1422
+ "learning_rate": 1.0036100469542786e-06,
1423
+ "loss": 1.0445,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 0.384229745621093,
1428
+ "grad_norm": 0.5517255663871765,
1429
+ "learning_rate": 7.375646182482875e-07,
1430
+ "loss": 0.6349,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 0.3862103113201708,
1435
+ "grad_norm": 0.837535560131073,
1436
+ "learning_rate": 5.123260489995229e-07,
1437
+ "loss": 0.7306,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 0.38819087701924865,
1442
+ "grad_norm": 0.7388361096382141,
1443
+ "learning_rate": 3.2795591718381975e-07,
1444
+ "loss": 0.9283,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 0.39017144271832643,
1449
+ "grad_norm": 1.2435849905014038,
1450
+ "learning_rate": 1.8450462775428942e-07,
1451
+ "loss": 1.205,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 0.3921520084174042,
1456
+ "grad_norm": 1.1012904644012451,
1457
+ "learning_rate": 8.201139886109264e-08,
1458
+ "loss": 1.2314,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 0.394132574116482,
1463
+ "grad_norm": 1.3080377578735352,
1464
+ "learning_rate": 2.0504251129649374e-08,
1465
+ "loss": 0.7755,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 0.39611313981555984,
1470
+ "grad_norm": 1.854987621307373,
1471
+ "learning_rate": 0.0,
1472
+ "loss": 0.8858,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 0.39611313981555984,
1477
+ "eval_loss": 1.1278622150421143,
1478
+ "eval_runtime": 7.959,
1479
+ "eval_samples_per_second": 6.282,
1480
+ "eval_steps_per_second": 6.282,
1481
+ "step": 200
1482
  }
1483
  ],
1484
  "logging_steps": 1,
 
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": 3.153022666407936e+17,
1511
  "train_batch_size": 1,
1512
  "trial_name": null,
1513
  "trial_params": null