ngwgsang commited on
Commit
c66e69d
·
verified ·
1 Parent(s): ff144b0

Training in progress, epoch 5, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22f1c25c7953d6a5108a4b6fc7080702552a6bb1f16f251f046e3390647a072f
3
  size 442668636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd963ef9d1066ee9c29fda8218d751e6a9fea1ff2912b0738cd9c19a32e6e461
3
  size 442668636
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7c6e390de6c1ae74b56d014d81fd84c5dad9c5f95f331df6e27c451ab06fdc1
3
  size 885457146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83593bc411734e7a401bbc347bc9627fa9eb55cf1edea083c4f55b2fe259b3c8
3
  size 885457146
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:477f91354fd8aea0f5c9e6fc8dd016c4da35fb6cfebf8934fb22ca7a1787fc34
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a5a167dc07ebab0b9cea53ada9b05e82574e778de7f66f0c0aebf45401b959
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebc45971367a1422b700ca22cac475fb887ee0026f043dc303ad59ac58e9b528
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71755248ab73d5a916224356091e133a775eece5af2a6db3870c836ddde78c53
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 4.082648913065593,
3
  "best_model_checkpoint": "./results/checkpoint-9444",
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 18888,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1371,6 +1371,342 @@
1371
  "eval_samples_per_second": 124.146,
1372
  "eval_steps_per_second": 3.882,
1373
  "step": 18888
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1374
  }
1375
  ],
1376
  "logging_steps": 100,
@@ -1385,12 +1721,12 @@
1385
  "should_evaluate": false,
1386
  "should_log": false,
1387
  "should_save": true,
1388
- "should_training_stop": false
1389
  },
1390
  "attributes": {}
1391
  }
1392
  },
1393
- "total_flos": 7.95044552080343e+16,
1394
  "train_batch_size": 32,
1395
  "trial_name": null,
1396
  "trial_params": null
 
1
  {
2
  "best_metric": 4.082648913065593,
3
  "best_model_checkpoint": "./results/checkpoint-9444",
4
+ "epoch": 5.0,
5
  "eval_steps": 500,
6
+ "global_step": 23610,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1371
  "eval_samples_per_second": 124.146,
1372
  "eval_steps_per_second": 3.882,
1373
  "step": 18888
1374
+ },
1375
+ {
1376
+ "epoch": 4.002541296060991,
1377
+ "grad_norm": 34.70132064819336,
1378
+ "learning_rate": 1.9949174078780177e-06,
1379
+ "loss": 3.8421,
1380
+ "step": 18900
1381
+ },
1382
+ {
1383
+ "epoch": 4.023718763235917,
1384
+ "grad_norm": 41.18425369262695,
1385
+ "learning_rate": 1.952562473528166e-06,
1386
+ "loss": 3.7346,
1387
+ "step": 19000
1388
+ },
1389
+ {
1390
+ "epoch": 4.044896230410843,
1391
+ "grad_norm": 49.83196258544922,
1392
+ "learning_rate": 1.9102075391783147e-06,
1393
+ "loss": 3.6407,
1394
+ "step": 19100
1395
+ },
1396
+ {
1397
+ "epoch": 4.066073697585769,
1398
+ "grad_norm": 36.5186653137207,
1399
+ "learning_rate": 1.8678526048284626e-06,
1400
+ "loss": 3.688,
1401
+ "step": 19200
1402
+ },
1403
+ {
1404
+ "epoch": 4.087251164760695,
1405
+ "grad_norm": 48.14241027832031,
1406
+ "learning_rate": 1.8254976704786108e-06,
1407
+ "loss": 3.7296,
1408
+ "step": 19300
1409
+ },
1410
+ {
1411
+ "epoch": 4.10842863193562,
1412
+ "grad_norm": 56.28713607788086,
1413
+ "learning_rate": 1.7831427361287593e-06,
1414
+ "loss": 3.628,
1415
+ "step": 19400
1416
+ },
1417
+ {
1418
+ "epoch": 4.129606099110546,
1419
+ "grad_norm": 39.89173889160156,
1420
+ "learning_rate": 1.7407878017789074e-06,
1421
+ "loss": 3.6782,
1422
+ "step": 19500
1423
+ },
1424
+ {
1425
+ "epoch": 4.150783566285472,
1426
+ "grad_norm": 43.402748107910156,
1427
+ "learning_rate": 1.6984328674290557e-06,
1428
+ "loss": 3.7261,
1429
+ "step": 19600
1430
+ },
1431
+ {
1432
+ "epoch": 4.1719610334603985,
1433
+ "grad_norm": 39.53237533569336,
1434
+ "learning_rate": 1.6560779330792037e-06,
1435
+ "loss": 3.6417,
1436
+ "step": 19700
1437
+ },
1438
+ {
1439
+ "epoch": 4.193138500635324,
1440
+ "grad_norm": 30.591480255126953,
1441
+ "learning_rate": 1.613722998729352e-06,
1442
+ "loss": 3.6738,
1443
+ "step": 19800
1444
+ },
1445
+ {
1446
+ "epoch": 4.21431596781025,
1447
+ "grad_norm": 36.14173126220703,
1448
+ "learning_rate": 1.5713680643795005e-06,
1449
+ "loss": 3.6229,
1450
+ "step": 19900
1451
+ },
1452
+ {
1453
+ "epoch": 4.235493434985176,
1454
+ "grad_norm": 39.41557312011719,
1455
+ "learning_rate": 1.5290131300296486e-06,
1456
+ "loss": 3.636,
1457
+ "step": 20000
1458
+ },
1459
+ {
1460
+ "epoch": 4.256670902160102,
1461
+ "grad_norm": 40.32093048095703,
1462
+ "learning_rate": 1.4866581956797968e-06,
1463
+ "loss": 3.7148,
1464
+ "step": 20100
1465
+ },
1466
+ {
1467
+ "epoch": 4.277848369335027,
1468
+ "grad_norm": 44.603755950927734,
1469
+ "learning_rate": 1.4443032613299451e-06,
1470
+ "loss": 3.6529,
1471
+ "step": 20200
1472
+ },
1473
+ {
1474
+ "epoch": 4.299025836509953,
1475
+ "grad_norm": 38.85076904296875,
1476
+ "learning_rate": 1.4019483269800932e-06,
1477
+ "loss": 3.6765,
1478
+ "step": 20300
1479
+ },
1480
+ {
1481
+ "epoch": 4.320203303684879,
1482
+ "grad_norm": 34.17532730102539,
1483
+ "learning_rate": 1.3595933926302415e-06,
1484
+ "loss": 3.7936,
1485
+ "step": 20400
1486
+ },
1487
+ {
1488
+ "epoch": 4.341380770859805,
1489
+ "grad_norm": 35.63409423828125,
1490
+ "learning_rate": 1.31723845828039e-06,
1491
+ "loss": 3.5933,
1492
+ "step": 20500
1493
+ },
1494
+ {
1495
+ "epoch": 4.362558238034731,
1496
+ "grad_norm": 38.114383697509766,
1497
+ "learning_rate": 1.274883523930538e-06,
1498
+ "loss": 3.6522,
1499
+ "step": 20600
1500
+ },
1501
+ {
1502
+ "epoch": 4.383735705209657,
1503
+ "grad_norm": 33.56945037841797,
1504
+ "learning_rate": 1.2325285895806863e-06,
1505
+ "loss": 3.6351,
1506
+ "step": 20700
1507
+ },
1508
+ {
1509
+ "epoch": 4.404913172384583,
1510
+ "grad_norm": 31.772396087646484,
1511
+ "learning_rate": 1.1901736552308346e-06,
1512
+ "loss": 3.6894,
1513
+ "step": 20800
1514
+ },
1515
+ {
1516
+ "epoch": 4.426090639559509,
1517
+ "grad_norm": 37.5047492980957,
1518
+ "learning_rate": 1.1478187208809826e-06,
1519
+ "loss": 3.6985,
1520
+ "step": 20900
1521
+ },
1522
+ {
1523
+ "epoch": 4.447268106734435,
1524
+ "grad_norm": 39.2713737487793,
1525
+ "learning_rate": 1.105463786531131e-06,
1526
+ "loss": 3.6066,
1527
+ "step": 21000
1528
+ },
1529
+ {
1530
+ "epoch": 4.46844557390936,
1531
+ "grad_norm": 44.23392868041992,
1532
+ "learning_rate": 1.0631088521812792e-06,
1533
+ "loss": 3.7353,
1534
+ "step": 21100
1535
+ },
1536
+ {
1537
+ "epoch": 4.489623041084286,
1538
+ "grad_norm": 36.74165725708008,
1539
+ "learning_rate": 1.0207539178314275e-06,
1540
+ "loss": 3.6744,
1541
+ "step": 21200
1542
+ },
1543
+ {
1544
+ "epoch": 4.510800508259212,
1545
+ "grad_norm": 40.30073547363281,
1546
+ "learning_rate": 9.783989834815758e-07,
1547
+ "loss": 3.6351,
1548
+ "step": 21300
1549
+ },
1550
+ {
1551
+ "epoch": 4.531977975434138,
1552
+ "grad_norm": 43.76948547363281,
1553
+ "learning_rate": 9.360440491317239e-07,
1554
+ "loss": 3.6974,
1555
+ "step": 21400
1556
+ },
1557
+ {
1558
+ "epoch": 4.553155442609064,
1559
+ "grad_norm": 40.2607421875,
1560
+ "learning_rate": 8.936891147818721e-07,
1561
+ "loss": 3.7225,
1562
+ "step": 21500
1563
+ },
1564
+ {
1565
+ "epoch": 4.5743329097839895,
1566
+ "grad_norm": 40.06145477294922,
1567
+ "learning_rate": 8.513341804320204e-07,
1568
+ "loss": 3.6033,
1569
+ "step": 21600
1570
+ },
1571
+ {
1572
+ "epoch": 4.595510376958916,
1573
+ "grad_norm": 37.53938674926758,
1574
+ "learning_rate": 8.089792460821687e-07,
1575
+ "loss": 3.6537,
1576
+ "step": 21700
1577
+ },
1578
+ {
1579
+ "epoch": 4.616687844133842,
1580
+ "grad_norm": 30.05097007751465,
1581
+ "learning_rate": 7.666243117323169e-07,
1582
+ "loss": 3.67,
1583
+ "step": 21800
1584
+ },
1585
+ {
1586
+ "epoch": 4.637865311308768,
1587
+ "grad_norm": 58.58922576904297,
1588
+ "learning_rate": 7.242693773824651e-07,
1589
+ "loss": 3.6375,
1590
+ "step": 21900
1591
+ },
1592
+ {
1593
+ "epoch": 4.659042778483693,
1594
+ "grad_norm": 42.74998474121094,
1595
+ "learning_rate": 6.819144430326134e-07,
1596
+ "loss": 3.6113,
1597
+ "step": 22000
1598
+ },
1599
+ {
1600
+ "epoch": 4.680220245658619,
1601
+ "grad_norm": 37.71262741088867,
1602
+ "learning_rate": 6.395595086827617e-07,
1603
+ "loss": 3.6832,
1604
+ "step": 22100
1605
+ },
1606
+ {
1607
+ "epoch": 4.701397712833545,
1608
+ "grad_norm": 42.499698638916016,
1609
+ "learning_rate": 5.972045743329098e-07,
1610
+ "loss": 3.6732,
1611
+ "step": 22200
1612
+ },
1613
+ {
1614
+ "epoch": 4.722575180008471,
1615
+ "grad_norm": 44.75648498535156,
1616
+ "learning_rate": 5.548496399830581e-07,
1617
+ "loss": 3.61,
1618
+ "step": 22300
1619
+ },
1620
+ {
1621
+ "epoch": 4.743752647183397,
1622
+ "grad_norm": 41.20449447631836,
1623
+ "learning_rate": 5.124947056332063e-07,
1624
+ "loss": 3.6846,
1625
+ "step": 22400
1626
+ },
1627
+ {
1628
+ "epoch": 4.7649301143583225,
1629
+ "grad_norm": 36.351951599121094,
1630
+ "learning_rate": 4.7013977128335456e-07,
1631
+ "loss": 3.6024,
1632
+ "step": 22500
1633
+ },
1634
+ {
1635
+ "epoch": 4.786107581533249,
1636
+ "grad_norm": 41.274478912353516,
1637
+ "learning_rate": 4.2778483693350273e-07,
1638
+ "loss": 3.5914,
1639
+ "step": 22600
1640
+ },
1641
+ {
1642
+ "epoch": 4.807285048708175,
1643
+ "grad_norm": 36.048309326171875,
1644
+ "learning_rate": 3.85429902583651e-07,
1645
+ "loss": 3.6893,
1646
+ "step": 22700
1647
+ },
1648
+ {
1649
+ "epoch": 4.828462515883101,
1650
+ "grad_norm": 36.90802764892578,
1651
+ "learning_rate": 3.430749682337993e-07,
1652
+ "loss": 3.6362,
1653
+ "step": 22800
1654
+ },
1655
+ {
1656
+ "epoch": 4.849639983058026,
1657
+ "grad_norm": 42.20147705078125,
1658
+ "learning_rate": 3.007200338839475e-07,
1659
+ "loss": 3.5946,
1660
+ "step": 22900
1661
+ },
1662
+ {
1663
+ "epoch": 4.870817450232952,
1664
+ "grad_norm": 45.40840148925781,
1665
+ "learning_rate": 2.5836509953409574e-07,
1666
+ "loss": 3.6693,
1667
+ "step": 23000
1668
+ },
1669
+ {
1670
+ "epoch": 4.891994917407878,
1671
+ "grad_norm": 40.9852180480957,
1672
+ "learning_rate": 2.16010165184244e-07,
1673
+ "loss": 3.6719,
1674
+ "step": 23100
1675
+ },
1676
+ {
1677
+ "epoch": 4.913172384582804,
1678
+ "grad_norm": 33.30469512939453,
1679
+ "learning_rate": 1.7365523083439224e-07,
1680
+ "loss": 3.6519,
1681
+ "step": 23200
1682
+ },
1683
+ {
1684
+ "epoch": 4.93434985175773,
1685
+ "grad_norm": 33.49442672729492,
1686
+ "learning_rate": 1.3130029648454047e-07,
1687
+ "loss": 3.6324,
1688
+ "step": 23300
1689
+ },
1690
+ {
1691
+ "epoch": 4.955527318932655,
1692
+ "grad_norm": 35.012969970703125,
1693
+ "learning_rate": 8.89453621346887e-08,
1694
+ "loss": 3.6501,
1695
+ "step": 23400
1696
+ },
1697
+ {
1698
+ "epoch": 4.9767047861075815,
1699
+ "grad_norm": 35.98733901977539,
1700
+ "learning_rate": 4.659042778483694e-08,
1701
+ "loss": 3.6817,
1702
+ "step": 23500
1703
+ },
1704
+ {
1705
+ "epoch": 4.997882253282508,
1706
+ "grad_norm": 34.76976776123047,
1707
+ "learning_rate": 4.235493434985176e-09,
1708
+ "loss": 3.6526,
1709
+ "step": 23600
1710
  }
1711
  ],
1712
  "logging_steps": 100,
 
1721
  "should_evaluate": false,
1722
  "should_log": false,
1723
  "should_save": true,
1724
+ "should_training_stop": true
1725
  },
1726
  "attributes": {}
1727
  }
1728
  },
1729
+ "total_flos": 9.938056901004288e+16,
1730
  "train_batch_size": 32,
1731
  "trial_name": null,
1732
  "trial_params": null