Training in progress, epoch 6
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +288 -3
- pytorch_model.bin +1 -1
- runs/Feb20_18-27-58_ubuntu-2004/events.out.tfevents.1676885321.ubuntu-2004.886785.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 236470789
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27f3648a6badaba6668f8c6d4db4c2b9896ababb988525769298b2731863da37
|
| 3 |
size 236470789
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118243218
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3d71c32019041a99199225d8bb52225cec92c140618e167aad1e1ccb4d0d934
|
| 3 |
size 118243218
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce5c3856f1342734c9ff443026f78f9d74949332f5c5b796847ea499dbf0c080
|
| 3 |
size 15597
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b278cd6e09360f31a3d837f80dee4c2ce4d9c9d186a939ecf157e1a0deb793f3
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1f64a9b985406894ef65cdb08cec8746d6a7f750e0466984f5ddbc1f0df99b9
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1425,11 +1425,296 @@
|
|
| 1425 |
"eval_samples_per_second": 496.191,
|
| 1426 |
"eval_steps_per_second": 31.012,
|
| 1427 |
"step": 114700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1428 |
}
|
| 1429 |
],
|
| 1430 |
"max_steps": 321160,
|
| 1431 |
"num_train_epochs": 14,
|
| 1432 |
-
"total_flos":
|
| 1433 |
"trial_name": null,
|
| 1434 |
"trial_params": null
|
| 1435 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 137640,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1425 |
"eval_samples_per_second": 496.191,
|
| 1426 |
"eval_steps_per_second": 31.012,
|
| 1427 |
"step": 114700
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 5.01,
|
| 1431 |
+
"learning_rate": 6.485651741794256e-05,
|
| 1432 |
+
"loss": 1.9898,
|
| 1433 |
+
"step": 115000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 5.03,
|
| 1437 |
+
"learning_rate": 6.469957351516601e-05,
|
| 1438 |
+
"loss": 1.988,
|
| 1439 |
+
"step": 115500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 5.06,
|
| 1443 |
+
"learning_rate": 6.454231509555022e-05,
|
| 1444 |
+
"loss": 1.9881,
|
| 1445 |
+
"step": 116000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 5.08,
|
| 1449 |
+
"learning_rate": 6.438505667593443e-05,
|
| 1450 |
+
"loss": 1.9849,
|
| 1451 |
+
"step": 116500
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 5.1,
|
| 1455 |
+
"learning_rate": 6.422779825631865e-05,
|
| 1456 |
+
"loss": 1.9872,
|
| 1457 |
+
"step": 117000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 5.12,
|
| 1461 |
+
"learning_rate": 6.407085435354208e-05,
|
| 1462 |
+
"loss": 1.9834,
|
| 1463 |
+
"step": 117500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 5.14,
|
| 1467 |
+
"learning_rate": 6.391359593392631e-05,
|
| 1468 |
+
"loss": 1.9814,
|
| 1469 |
+
"step": 118000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 5.17,
|
| 1473 |
+
"learning_rate": 6.375633751431052e-05,
|
| 1474 |
+
"loss": 1.978,
|
| 1475 |
+
"step": 118500
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 5.19,
|
| 1479 |
+
"learning_rate": 6.359907909469474e-05,
|
| 1480 |
+
"loss": 1.9857,
|
| 1481 |
+
"step": 119000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 5.21,
|
| 1485 |
+
"learning_rate": 6.344213519191819e-05,
|
| 1486 |
+
"loss": 1.9816,
|
| 1487 |
+
"step": 119500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 5.23,
|
| 1491 |
+
"learning_rate": 6.32848767723024e-05,
|
| 1492 |
+
"loss": 1.9817,
|
| 1493 |
+
"step": 120000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 5.25,
|
| 1497 |
+
"learning_rate": 6.312761835268661e-05,
|
| 1498 |
+
"loss": 1.9815,
|
| 1499 |
+
"step": 120500
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 5.27,
|
| 1503 |
+
"learning_rate": 6.297035993307082e-05,
|
| 1504 |
+
"loss": 1.9796,
|
| 1505 |
+
"step": 121000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 5.3,
|
| 1509 |
+
"learning_rate": 6.281341603029426e-05,
|
| 1510 |
+
"loss": 1.9842,
|
| 1511 |
+
"step": 121500
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 5.32,
|
| 1515 |
+
"learning_rate": 6.265615761067847e-05,
|
| 1516 |
+
"loss": 1.9816,
|
| 1517 |
+
"step": 122000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 5.34,
|
| 1521 |
+
"learning_rate": 6.249889919106268e-05,
|
| 1522 |
+
"loss": 1.976,
|
| 1523 |
+
"step": 122500
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 5.36,
|
| 1527 |
+
"learning_rate": 6.234164077144691e-05,
|
| 1528 |
+
"loss": 1.9798,
|
| 1529 |
+
"step": 123000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 5.38,
|
| 1533 |
+
"learning_rate": 6.218469686867035e-05,
|
| 1534 |
+
"loss": 1.9768,
|
| 1535 |
+
"step": 123500
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 5.41,
|
| 1539 |
+
"learning_rate": 6.202743844905456e-05,
|
| 1540 |
+
"loss": 1.9786,
|
| 1541 |
+
"step": 124000
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 5.43,
|
| 1545 |
+
"learning_rate": 6.187018002943879e-05,
|
| 1546 |
+
"loss": 1.9753,
|
| 1547 |
+
"step": 124500
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 5.45,
|
| 1551 |
+
"learning_rate": 6.1712921609823e-05,
|
| 1552 |
+
"loss": 1.9755,
|
| 1553 |
+
"step": 125000
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 5.47,
|
| 1557 |
+
"learning_rate": 6.155597770704644e-05,
|
| 1558 |
+
"loss": 1.9771,
|
| 1559 |
+
"step": 125500
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 5.49,
|
| 1563 |
+
"learning_rate": 6.139871928743065e-05,
|
| 1564 |
+
"loss": 1.9736,
|
| 1565 |
+
"step": 126000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 5.51,
|
| 1569 |
+
"learning_rate": 6.124146086781488e-05,
|
| 1570 |
+
"loss": 1.9729,
|
| 1571 |
+
"step": 126500
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 5.54,
|
| 1575 |
+
"learning_rate": 6.108420244819907e-05,
|
| 1576 |
+
"loss": 1.9692,
|
| 1577 |
+
"step": 127000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 5.56,
|
| 1581 |
+
"learning_rate": 6.0927258545422526e-05,
|
| 1582 |
+
"loss": 1.9702,
|
| 1583 |
+
"step": 127500
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 5.58,
|
| 1587 |
+
"learning_rate": 6.077000012580674e-05,
|
| 1588 |
+
"loss": 1.9709,
|
| 1589 |
+
"step": 128000
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 5.6,
|
| 1593 |
+
"learning_rate": 6.0612741706190954e-05,
|
| 1594 |
+
"loss": 1.9712,
|
| 1595 |
+
"step": 128500
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 5.62,
|
| 1599 |
+
"learning_rate": 6.0455483286575164e-05,
|
| 1600 |
+
"loss": 1.9714,
|
| 1601 |
+
"step": 129000
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 5.65,
|
| 1605 |
+
"learning_rate": 6.0298539383798616e-05,
|
| 1606 |
+
"loss": 1.9736,
|
| 1607 |
+
"step": 129500
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 5.67,
|
| 1611 |
+
"learning_rate": 6.014128096418282e-05,
|
| 1612 |
+
"loss": 1.9677,
|
| 1613 |
+
"step": 130000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 5.69,
|
| 1617 |
+
"learning_rate": 5.9984022544567044e-05,
|
| 1618 |
+
"loss": 1.9626,
|
| 1619 |
+
"step": 130500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 5.71,
|
| 1623 |
+
"learning_rate": 5.9826764124951254e-05,
|
| 1624 |
+
"loss": 1.966,
|
| 1625 |
+
"step": 131000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 5.73,
|
| 1629 |
+
"learning_rate": 5.96698202221747e-05,
|
| 1630 |
+
"loss": 1.9626,
|
| 1631 |
+
"step": 131500
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 5.75,
|
| 1635 |
+
"learning_rate": 5.951256180255891e-05,
|
| 1636 |
+
"loss": 1.9652,
|
| 1637 |
+
"step": 132000
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 5.78,
|
| 1641 |
+
"learning_rate": 5.935530338294313e-05,
|
| 1642 |
+
"loss": 1.9652,
|
| 1643 |
+
"step": 132500
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 5.8,
|
| 1647 |
+
"learning_rate": 5.919804496332734e-05,
|
| 1648 |
+
"loss": 1.9638,
|
| 1649 |
+
"step": 133000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 5.82,
|
| 1653 |
+
"learning_rate": 5.9040786543711554e-05,
|
| 1654 |
+
"loss": 1.9591,
|
| 1655 |
+
"step": 133500
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 5.84,
|
| 1659 |
+
"learning_rate": 5.888384264093499e-05,
|
| 1660 |
+
"loss": 1.9648,
|
| 1661 |
+
"step": 134000
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 5.86,
|
| 1665 |
+
"learning_rate": 5.872658422131922e-05,
|
| 1666 |
+
"loss": 1.9617,
|
| 1667 |
+
"step": 134500
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 5.88,
|
| 1671 |
+
"learning_rate": 5.856932580170342e-05,
|
| 1672 |
+
"loss": 1.9626,
|
| 1673 |
+
"step": 135000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 5.91,
|
| 1677 |
+
"learning_rate": 5.8412067382087644e-05,
|
| 1678 |
+
"loss": 1.9597,
|
| 1679 |
+
"step": 135500
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 5.93,
|
| 1683 |
+
"learning_rate": 5.825512347931108e-05,
|
| 1684 |
+
"loss": 1.9597,
|
| 1685 |
+
"step": 136000
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 5.95,
|
| 1689 |
+
"learning_rate": 5.80978650596953e-05,
|
| 1690 |
+
"loss": 1.962,
|
| 1691 |
+
"step": 136500
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 5.97,
|
| 1695 |
+
"learning_rate": 5.794060664007951e-05,
|
| 1696 |
+
"loss": 1.9557,
|
| 1697 |
+
"step": 137000
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 5.99,
|
| 1701 |
+
"learning_rate": 5.778334822046373e-05,
|
| 1702 |
+
"loss": 1.9576,
|
| 1703 |
+
"step": 137500
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 6.0,
|
| 1707 |
+
"eval_accuracy": 0.6267606171222161,
|
| 1708 |
+
"eval_loss": 1.8356587886810303,
|
| 1709 |
+
"eval_runtime": 358.323,
|
| 1710 |
+
"eval_samples_per_second": 496.625,
|
| 1711 |
+
"eval_steps_per_second": 31.039,
|
| 1712 |
+
"step": 137640
|
| 1713 |
}
|
| 1714 |
],
|
| 1715 |
"max_steps": 321160,
|
| 1716 |
"num_train_epochs": 14,
|
| 1717 |
+
"total_flos": 1.041429725631959e+18,
|
| 1718 |
"trial_name": null,
|
| 1719 |
"trial_params": null
|
| 1720 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118243218
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3d71c32019041a99199225d8bb52225cec92c140618e167aad1e1ccb4d0d934
|
| 3 |
size 118243218
|
runs/Feb20_18-27-58_ubuntu-2004/events.out.tfevents.1676885321.ubuntu-2004.886785.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:421928b94b23f10aa10b0c399afa84e783ed1e8b949a4822fbce947b89041721
|
| 3 |
+
size 49630
|