fats-fme commited on
Commit
5250aa9
·
verified ·
1 Parent(s): bb14acc

Training in progress, step 220, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39806d510b9ab24c764ffd908298907c327f0384acbaeda1da48e73cbb9e8ff6
3
  size 70667778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae68e20f3bfeb812d98efcc8550348acc422a6dc71de7b7a07a53e110f18734
3
  size 70667778
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:257e290e23f3600edd1a568035aeb836a5aa20ce6d4cb3d5d8a1e69ff580b547
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66eaf898cd078a8e99514739c64d152aaa242acfc9f3b6673130c8d7fc10d78f
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d1e404665d992b110eddd34e0b6a2f6f7b0fb1ba998e4738f1e997e398233ee
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a260dfaa7dc8f9038439dd584616d48f6c6ef819c2d616c4a80c15e9bd863c8
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79db7aed3a9923aa682703f13ca01a142bd6b5bf7acc8d720a4162bff9c52329
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62f2a20ef1f2075cf61d8ea39db729041ad20a4a7796856e9fcdaba3cd70921
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.7474518686296716,
5
  "eval_steps": 55,
6
- "global_step": 165,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1194,6 +1194,399 @@
1194
  "eval_samples_per_second": 22.224,
1195
  "eval_steps_per_second": 5.556,
1196
  "step": 165
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1197
  }
1198
  ],
1199
  "logging_steps": 1,
@@ -1208,12 +1601,12 @@
1208
  "should_evaluate": false,
1209
  "should_log": false,
1210
  "should_save": true,
1211
- "should_training_stop": false
1212
  },
1213
  "attributes": {}
1214
  }
1215
  },
1216
- "total_flos": 2.37914919272448e+16,
1217
  "train_batch_size": 2,
1218
  "trial_name": null,
1219
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9966024915062288,
5
  "eval_steps": 55,
6
+ "global_step": 220,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1194
  "eval_samples_per_second": 22.224,
1195
  "eval_steps_per_second": 5.556,
1196
  "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.7519818799546999,
1200
+ "grad_norm": NaN,
1201
+ "learning_rate": 2.2897332176377528e-05,
1202
+ "loss": 0.0,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.7565118912797282,
1207
+ "grad_norm": NaN,
1208
+ "learning_rate": 2.2125528032855724e-05,
1209
+ "loss": 0.0,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.7610419026047565,
1214
+ "grad_norm": NaN,
1215
+ "learning_rate": 2.136324299597474e-05,
1216
+ "loss": 0.0,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.7655719139297849,
1221
+ "grad_norm": NaN,
1222
+ "learning_rate": 2.061073738537635e-05,
1223
+ "loss": 0.0,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.7701019252548131,
1228
+ "grad_norm": NaN,
1229
+ "learning_rate": 1.9868268181037185e-05,
1230
+ "loss": 0.0,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.7746319365798414,
1235
+ "grad_norm": NaN,
1236
+ "learning_rate": 1.9136088935510362e-05,
1237
+ "loss": 0.0,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.7791619479048698,
1242
+ "grad_norm": NaN,
1243
+ "learning_rate": 1.8414449687337464e-05,
1244
+ "loss": 0.0,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.7836919592298981,
1249
+ "grad_norm": NaN,
1250
+ "learning_rate": 1.7703596875660645e-05,
1251
+ "loss": 0.0,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.7882219705549264,
1256
+ "grad_norm": NaN,
1257
+ "learning_rate": 1.700377325606388e-05,
1258
+ "loss": 0.0,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.7927519818799547,
1263
+ "grad_norm": NaN,
1264
+ "learning_rate": 1.631521781767214e-05,
1265
+ "loss": 0.0,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.797281993204983,
1270
+ "grad_norm": NaN,
1271
+ "learning_rate": 1.5638165701536868e-05,
1272
+ "loss": 0.0,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.8018120045300113,
1277
+ "grad_norm": NaN,
1278
+ "learning_rate": 1.4972848120335453e-05,
1279
+ "loss": 0.0,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.8063420158550396,
1284
+ "grad_norm": NaN,
1285
+ "learning_rate": 1.4319492279412388e-05,
1286
+ "loss": 0.0,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.8108720271800679,
1291
+ "grad_norm": NaN,
1292
+ "learning_rate": 1.3678321299188801e-05,
1293
+ "loss": 0.0,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.8154020385050963,
1298
+ "grad_norm": NaN,
1299
+ "learning_rate": 1.3049554138967051e-05,
1300
+ "loss": 0.0,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.8199320498301246,
1305
+ "grad_norm": NaN,
1306
+ "learning_rate": 1.2433405522156332e-05,
1307
+ "loss": 0.0,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.8244620611551529,
1312
+ "grad_norm": NaN,
1313
+ "learning_rate": 1.183008586294485e-05,
1314
+ "loss": 0.0,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.8289920724801813,
1319
+ "grad_norm": NaN,
1320
+ "learning_rate": 1.1239801194443506e-05,
1321
+ "loss": 0.0,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.8335220838052095,
1326
+ "grad_norm": NaN,
1327
+ "learning_rate": 1.066275309832584e-05,
1328
+ "loss": 0.0,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.8380520951302378,
1333
+ "grad_norm": NaN,
1334
+ "learning_rate": 1.0099138635988026e-05,
1335
+ "loss": 0.0,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.8425821064552661,
1340
+ "grad_norm": NaN,
1341
+ "learning_rate": 9.549150281252633e-06,
1342
+ "loss": 0.0,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.8471121177802945,
1347
+ "grad_norm": NaN,
1348
+ "learning_rate": 9.012975854638949e-06,
1349
+ "loss": 0.0,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.8516421291053228,
1354
+ "grad_norm": NaN,
1355
+ "learning_rate": 8.490798459222476e-06,
1356
+ "loss": 0.0,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.8561721404303511,
1361
+ "grad_norm": NaN,
1362
+ "learning_rate": 7.982796418105371e-06,
1363
+ "loss": 0.0,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8607021517553793,
1368
+ "grad_norm": NaN,
1369
+ "learning_rate": 7.489143213519301e-06,
1370
+ "loss": 0.0,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8652321630804077,
1375
+ "grad_norm": NaN,
1376
+ "learning_rate": 7.010007427581378e-06,
1377
+ "loss": 0.0,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.869762174405436,
1382
+ "grad_norm": NaN,
1383
+ "learning_rate": 6.5455526847235825e-06,
1384
+ "loss": 0.0,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8742921857304643,
1389
+ "grad_norm": NaN,
1390
+ "learning_rate": 6.0959375958151045e-06,
1391
+ "loss": 0.0,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.8788221970554927,
1396
+ "grad_norm": NaN,
1397
+ "learning_rate": 5.6613157039969055e-06,
1398
+ "loss": 0.0,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.883352208380521,
1403
+ "grad_norm": NaN,
1404
+ "learning_rate": 5.241835432246889e-06,
1405
+ "loss": 0.0,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.8878822197055493,
1410
+ "grad_norm": NaN,
1411
+ "learning_rate": 4.837640032693558e-06,
1412
+ "loss": 0.0,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.8924122310305775,
1417
+ "grad_norm": NaN,
1418
+ "learning_rate": 4.448867537695578e-06,
1419
+ "loss": 0.0,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.8969422423556059,
1424
+ "grad_norm": NaN,
1425
+ "learning_rate": 4.075650712703849e-06,
1426
+ "loss": 0.0,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.9014722536806342,
1431
+ "grad_norm": NaN,
1432
+ "learning_rate": 3.71811701092219e-06,
1433
+ "loss": 0.0,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.9060022650056625,
1438
+ "grad_norm": NaN,
1439
+ "learning_rate": 3.376388529782215e-06,
1440
+ "loss": 0.0,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.9105322763306908,
1445
+ "grad_norm": NaN,
1446
+ "learning_rate": 3.0505819692471792e-06,
1447
+ "loss": 0.0,
1448
+ "step": 201
1449
+ },
1450
+ {
1451
+ "epoch": 0.9150622876557192,
1452
+ "grad_norm": NaN,
1453
+ "learning_rate": 2.7408085919590264e-06,
1454
+ "loss": 0.0,
1455
+ "step": 202
1456
+ },
1457
+ {
1458
+ "epoch": 0.9195922989807475,
1459
+ "grad_norm": NaN,
1460
+ "learning_rate": 2.4471741852423237e-06,
1461
+ "loss": 0.0,
1462
+ "step": 203
1463
+ },
1464
+ {
1465
+ "epoch": 0.9241223103057757,
1466
+ "grad_norm": NaN,
1467
+ "learning_rate": 2.1697790249779636e-06,
1468
+ "loss": 0.0,
1469
+ "step": 204
1470
+ },
1471
+ {
1472
+ "epoch": 0.928652321630804,
1473
+ "grad_norm": NaN,
1474
+ "learning_rate": 1.908717841359048e-06,
1475
+ "loss": 0.0,
1476
+ "step": 205
1477
+ },
1478
+ {
1479
+ "epoch": 0.9331823329558324,
1480
+ "grad_norm": NaN,
1481
+ "learning_rate": 1.6640797865406288e-06,
1482
+ "loss": 0.0,
1483
+ "step": 206
1484
+ },
1485
+ {
1486
+ "epoch": 0.9377123442808607,
1487
+ "grad_norm": NaN,
1488
+ "learning_rate": 1.4359484041943038e-06,
1489
+ "loss": 0.0,
1490
+ "step": 207
1491
+ },
1492
+ {
1493
+ "epoch": 0.942242355605889,
1494
+ "grad_norm": NaN,
1495
+ "learning_rate": 1.2244016009781701e-06,
1496
+ "loss": 0.0,
1497
+ "step": 208
1498
+ },
1499
+ {
1500
+ "epoch": 0.9467723669309174,
1501
+ "grad_norm": NaN,
1502
+ "learning_rate": 1.0295116199317057e-06,
1503
+ "loss": 0.0,
1504
+ "step": 209
1505
+ },
1506
+ {
1507
+ "epoch": 0.9513023782559457,
1508
+ "grad_norm": NaN,
1509
+ "learning_rate": 8.513450158049108e-07,
1510
+ "loss": 0.0,
1511
+ "step": 210
1512
+ },
1513
+ {
1514
+ "epoch": 0.9558323895809739,
1515
+ "grad_norm": NaN,
1516
+ "learning_rate": 6.899626323298713e-07,
1517
+ "loss": 0.0,
1518
+ "step": 211
1519
+ },
1520
+ {
1521
+ "epoch": 0.9603624009060022,
1522
+ "grad_norm": NaN,
1523
+ "learning_rate": 5.454195814427021e-07,
1524
+ "loss": 0.0,
1525
+ "step": 212
1526
+ },
1527
+ {
1528
+ "epoch": 0.9648924122310306,
1529
+ "grad_norm": NaN,
1530
+ "learning_rate": 4.177652244628627e-07,
1531
+ "loss": 0.0,
1532
+ "step": 213
1533
+ },
1534
+ {
1535
+ "epoch": 0.9694224235560589,
1536
+ "grad_norm": NaN,
1537
+ "learning_rate": 3.0704315523631953e-07,
1538
+ "loss": 0.0,
1539
+ "step": 214
1540
+ },
1541
+ {
1542
+ "epoch": 0.9739524348810872,
1543
+ "grad_norm": NaN,
1544
+ "learning_rate": 2.1329118524827662e-07,
1545
+ "loss": 0.0,
1546
+ "step": 215
1547
+ },
1548
+ {
1549
+ "epoch": 0.9784824462061155,
1550
+ "grad_norm": NaN,
1551
+ "learning_rate": 1.3654133071059893e-07,
1552
+ "loss": 0.0,
1553
+ "step": 216
1554
+ },
1555
+ {
1556
+ "epoch": 0.9830124575311439,
1557
+ "grad_norm": NaN,
1558
+ "learning_rate": 7.681980162830282e-08,
1559
+ "loss": 0.0,
1560
+ "step": 217
1561
+ },
1562
+ {
1563
+ "epoch": 0.9875424688561721,
1564
+ "grad_norm": NaN,
1565
+ "learning_rate": 3.4146992848854695e-08,
1566
+ "loss": 0.0,
1567
+ "step": 218
1568
+ },
1569
+ {
1570
+ "epoch": 0.9920724801812004,
1571
+ "grad_norm": NaN,
1572
+ "learning_rate": 8.537477097364522e-09,
1573
+ "loss": 0.0,
1574
+ "step": 219
1575
+ },
1576
+ {
1577
+ "epoch": 0.9966024915062288,
1578
+ "grad_norm": NaN,
1579
+ "learning_rate": 0.0,
1580
+ "loss": 0.0,
1581
+ "step": 220
1582
+ },
1583
+ {
1584
+ "epoch": 0.9966024915062288,
1585
+ "eval_loss": NaN,
1586
+ "eval_runtime": 16.7651,
1587
+ "eval_samples_per_second": 22.189,
1588
+ "eval_steps_per_second": 5.547,
1589
+ "step": 220
1590
  }
1591
  ],
1592
  "logging_steps": 1,
 
1601
  "should_evaluate": false,
1602
  "should_log": false,
1603
  "should_save": true,
1604
+ "should_training_stop": true
1605
  },
1606
  "attributes": {}
1607
  }
1608
  },
1609
+ "total_flos": 3.17219892363264e+16,
1610
  "train_batch_size": 2,
1611
  "trial_name": null,
1612
  "trial_params": null