Training in progress, step 274, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9f07b559833c664b940028fadff307d4f9c6c31b9d2495ca5517b3232ce314d
|
| 3 |
size 335922386
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b68477d58ee6163f80b6d10adb704491497cf5b858320688a4d6b9385c805dc9
|
| 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:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1ee28f2ad50f7d4d6db4a357fec6412e0c356277766a763cf3e27ea0e7ff718
|
| 3 |
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dc0fb8aa9466d382847ad5edc9f818f11724a349a169d2f60663f8307006330
|
| 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.
|
| 5 |
"eval_steps": 69,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1488,6 +1488,475 @@
|
|
| 1488 |
"eval_samples_per_second": 8.37,
|
| 1489 |
"eval_steps_per_second": 2.097,
|
| 1490 |
"step": 207
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1491 |
}
|
| 1492 |
],
|
| 1493 |
"logging_steps": 1,
|
|
@@ -1502,12 +1971,12 @@
|
|
| 1502 |
"should_evaluate": false,
|
| 1503 |
"should_log": false,
|
| 1504 |
"should_save": true,
|
| 1505 |
-
"should_training_stop":
|
| 1506 |
},
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
-
"total_flos":
|
| 1511 |
"train_batch_size": 2,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9977241693218024,
|
| 5 |
"eval_steps": 69,
|
| 6 |
+
"global_step": 274,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1488 |
"eval_samples_per_second": 8.37,
|
| 1489 |
"eval_steps_per_second": 2.097,
|
| 1490 |
"step": 207
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.757396449704142,
|
| 1494 |
+
"grad_norm": NaN,
|
| 1495 |
+
"learning_rate": 3.9868290870159405e-05,
|
| 1496 |
+
"loss": 0.0,
|
| 1497 |
+
"step": 208
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.761037778789258,
|
| 1501 |
+
"grad_norm": NaN,
|
| 1502 |
+
"learning_rate": 3.875363186960499e-05,
|
| 1503 |
+
"loss": 0.0,
|
| 1504 |
+
"step": 209
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.7646791078743741,
|
| 1508 |
+
"grad_norm": NaN,
|
| 1509 |
+
"learning_rate": 3.7651019814126654e-05,
|
| 1510 |
+
"loss": 0.0,
|
| 1511 |
+
"step": 210
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 0.7683204369594903,
|
| 1515 |
+
"grad_norm": NaN,
|
| 1516 |
+
"learning_rate": 3.6560671583635467e-05,
|
| 1517 |
+
"loss": 0.0,
|
| 1518 |
+
"step": 211
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 0.7719617660446063,
|
| 1522 |
+
"grad_norm": NaN,
|
| 1523 |
+
"learning_rate": 3.548280164579126e-05,
|
| 1524 |
+
"loss": 0.0,
|
| 1525 |
+
"step": 212
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.7756030951297224,
|
| 1529 |
+
"grad_norm": NaN,
|
| 1530 |
+
"learning_rate": 3.4417622013817595e-05,
|
| 1531 |
+
"loss": 0.0,
|
| 1532 |
+
"step": 213
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.7792444242148384,
|
| 1536 |
+
"grad_norm": NaN,
|
| 1537 |
+
"learning_rate": 3.336534220479961e-05,
|
| 1538 |
+
"loss": 0.0,
|
| 1539 |
+
"step": 214
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.7828857532999545,
|
| 1543 |
+
"grad_norm": NaN,
|
| 1544 |
+
"learning_rate": 3.2326169198472556e-05,
|
| 1545 |
+
"loss": 0.0,
|
| 1546 |
+
"step": 215
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.7865270823850705,
|
| 1550 |
+
"grad_norm": NaN,
|
| 1551 |
+
"learning_rate": 3.130030739650983e-05,
|
| 1552 |
+
"loss": 0.0,
|
| 1553 |
+
"step": 216
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.7901684114701866,
|
| 1557 |
+
"grad_norm": NaN,
|
| 1558 |
+
"learning_rate": 3.0287958582317676e-05,
|
| 1559 |
+
"loss": 0.0,
|
| 1560 |
+
"step": 217
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 0.7938097405553027,
|
| 1564 |
+
"grad_norm": NaN,
|
| 1565 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 1566 |
+
"loss": 0.0,
|
| 1567 |
+
"step": 218
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.7974510696404188,
|
| 1571 |
+
"grad_norm": NaN,
|
| 1572 |
+
"learning_rate": 2.8304593721917285e-05,
|
| 1573 |
+
"loss": 0.0,
|
| 1574 |
+
"step": 219
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.8010923987255348,
|
| 1578 |
+
"grad_norm": NaN,
|
| 1579 |
+
"learning_rate": 2.7333967796597315e-05,
|
| 1580 |
+
"loss": 0.0,
|
| 1581 |
+
"step": 220
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.8047337278106509,
|
| 1585 |
+
"grad_norm": NaN,
|
| 1586 |
+
"learning_rate": 2.6377635024089087e-05,
|
| 1587 |
+
"loss": 0.0,
|
| 1588 |
+
"step": 221
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 0.8083750568957669,
|
| 1592 |
+
"grad_norm": NaN,
|
| 1593 |
+
"learning_rate": 2.5435783511683443e-05,
|
| 1594 |
+
"loss": 0.0,
|
| 1595 |
+
"step": 222
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 0.812016385980883,
|
| 1599 |
+
"grad_norm": NaN,
|
| 1600 |
+
"learning_rate": 2.450859851825842e-05,
|
| 1601 |
+
"loss": 0.0,
|
| 1602 |
+
"step": 223
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.815657715065999,
|
| 1606 |
+
"grad_norm": NaN,
|
| 1607 |
+
"learning_rate": 2.3596262417839255e-05,
|
| 1608 |
+
"loss": 0.0,
|
| 1609 |
+
"step": 224
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.8192990441511152,
|
| 1613 |
+
"grad_norm": NaN,
|
| 1614 |
+
"learning_rate": 2.26989546637263e-05,
|
| 1615 |
+
"loss": 0.0,
|
| 1616 |
+
"step": 225
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.8229403732362313,
|
| 1620 |
+
"grad_norm": NaN,
|
| 1621 |
+
"learning_rate": 2.181685175319702e-05,
|
| 1622 |
+
"loss": 0.0,
|
| 1623 |
+
"step": 226
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.8265817023213473,
|
| 1627 |
+
"grad_norm": NaN,
|
| 1628 |
+
"learning_rate": 2.095012719278966e-05,
|
| 1629 |
+
"loss": 0.0,
|
| 1630 |
+
"step": 227
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 0.8302230314064634,
|
| 1634 |
+
"grad_norm": NaN,
|
| 1635 |
+
"learning_rate": 2.009895146417512e-05,
|
| 1636 |
+
"loss": 0.0,
|
| 1637 |
+
"step": 228
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.8338643604915794,
|
| 1641 |
+
"grad_norm": NaN,
|
| 1642 |
+
"learning_rate": 1.926349199062376e-05,
|
| 1643 |
+
"loss": 0.0,
|
| 1644 |
+
"step": 229
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.8375056895766955,
|
| 1648 |
+
"grad_norm": NaN,
|
| 1649 |
+
"learning_rate": 1.8443913104073983e-05,
|
| 1650 |
+
"loss": 0.0,
|
| 1651 |
+
"step": 230
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.8411470186618115,
|
| 1655 |
+
"grad_norm": NaN,
|
| 1656 |
+
"learning_rate": 1.7640376012808536e-05,
|
| 1657 |
+
"loss": 0.0,
|
| 1658 |
+
"step": 231
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.8447883477469277,
|
| 1662 |
+
"grad_norm": NaN,
|
| 1663 |
+
"learning_rate": 1.6853038769745467e-05,
|
| 1664 |
+
"loss": 0.0,
|
| 1665 |
+
"step": 232
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.8484296768320437,
|
| 1669 |
+
"grad_norm": NaN,
|
| 1670 |
+
"learning_rate": 1.6082056241349786e-05,
|
| 1671 |
+
"loss": 0.0,
|
| 1672 |
+
"step": 233
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 0.8520710059171598,
|
| 1676 |
+
"grad_norm": NaN,
|
| 1677 |
+
"learning_rate": 1.5327580077171587e-05,
|
| 1678 |
+
"loss": 0.0,
|
| 1679 |
+
"step": 234
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.8557123350022758,
|
| 1683 |
+
"grad_norm": NaN,
|
| 1684 |
+
"learning_rate": 1.4589758680017263e-05,
|
| 1685 |
+
"loss": 0.0,
|
| 1686 |
+
"step": 235
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.8593536640873919,
|
| 1690 |
+
"grad_norm": NaN,
|
| 1691 |
+
"learning_rate": 1.3868737176759106e-05,
|
| 1692 |
+
"loss": 0.0,
|
| 1693 |
+
"step": 236
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.8629949931725079,
|
| 1697 |
+
"grad_norm": NaN,
|
| 1698 |
+
"learning_rate": 1.3164657389789458e-05,
|
| 1699 |
+
"loss": 0.0,
|
| 1700 |
+
"step": 237
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.866636322257624,
|
| 1704 |
+
"grad_norm": NaN,
|
| 1705 |
+
"learning_rate": 1.2477657809124631e-05,
|
| 1706 |
+
"loss": 0.0,
|
| 1707 |
+
"step": 238
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.8702776513427402,
|
| 1711 |
+
"grad_norm": NaN,
|
| 1712 |
+
"learning_rate": 1.1807873565164506e-05,
|
| 1713 |
+
"loss": 0.0,
|
| 1714 |
+
"step": 239
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.8739189804278562,
|
| 1718 |
+
"grad_norm": NaN,
|
| 1719 |
+
"learning_rate": 1.1155436402112785e-05,
|
| 1720 |
+
"loss": 0.0,
|
| 1721 |
+
"step": 240
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.8775603095129723,
|
| 1725 |
+
"grad_norm": NaN,
|
| 1726 |
+
"learning_rate": 1.0520474652063394e-05,
|
| 1727 |
+
"loss": 0.0,
|
| 1728 |
+
"step": 241
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.8812016385980883,
|
| 1732 |
+
"grad_norm": NaN,
|
| 1733 |
+
"learning_rate": 9.903113209758096e-06,
|
| 1734 |
+
"loss": 0.0,
|
| 1735 |
+
"step": 242
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.8848429676832044,
|
| 1739 |
+
"grad_norm": NaN,
|
| 1740 |
+
"learning_rate": 9.303473508019944e-06,
|
| 1741 |
+
"loss": 0.0,
|
| 1742 |
+
"step": 243
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.8884842967683204,
|
| 1746 |
+
"grad_norm": NaN,
|
| 1747 |
+
"learning_rate": 8.72167349386811e-06,
|
| 1748 |
+
"loss": 0.0,
|
| 1749 |
+
"step": 244
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.8921256258534365,
|
| 1753 |
+
"grad_norm": NaN,
|
| 1754 |
+
"learning_rate": 8.157827605317892e-06,
|
| 1755 |
+
"loss": 0.0,
|
| 1756 |
+
"step": 245
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.8957669549385525,
|
| 1760 |
+
"grad_norm": NaN,
|
| 1761 |
+
"learning_rate": 7.612046748871327e-06,
|
| 1762 |
+
"loss": 0.0,
|
| 1763 |
+
"step": 246
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.8994082840236687,
|
| 1767 |
+
"grad_norm": NaN,
|
| 1768 |
+
"learning_rate": 7.084438277702188e-06,
|
| 1769 |
+
"loss": 0.0,
|
| 1770 |
+
"step": 247
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.9030496131087847,
|
| 1774 |
+
"grad_norm": NaN,
|
| 1775 |
+
"learning_rate": 6.5751059705400295e-06,
|
| 1776 |
+
"loss": 0.0,
|
| 1777 |
+
"step": 248
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 0.9066909421939008,
|
| 1781 |
+
"grad_norm": NaN,
|
| 1782 |
+
"learning_rate": 6.084150011257239e-06,
|
| 1783 |
+
"loss": 0.0,
|
| 1784 |
+
"step": 249
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 0.9103322712790168,
|
| 1788 |
+
"grad_norm": NaN,
|
| 1789 |
+
"learning_rate": 5.611666969163243e-06,
|
| 1790 |
+
"loss": 0.0,
|
| 1791 |
+
"step": 250
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.9139736003641329,
|
| 1795 |
+
"grad_norm": NaN,
|
| 1796 |
+
"learning_rate": 5.157749780009735e-06,
|
| 1797 |
+
"loss": 0.0,
|
| 1798 |
+
"step": 251
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 0.9176149294492489,
|
| 1802 |
+
"grad_norm": NaN,
|
| 1803 |
+
"learning_rate": 4.722487727710368e-06,
|
| 1804 |
+
"loss": 0.0,
|
| 1805 |
+
"step": 252
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 0.921256258534365,
|
| 1809 |
+
"grad_norm": NaN,
|
| 1810 |
+
"learning_rate": 4.305966426779118e-06,
|
| 1811 |
+
"loss": 0.0,
|
| 1812 |
+
"step": 253
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 0.9248975876194812,
|
| 1816 |
+
"grad_norm": NaN,
|
| 1817 |
+
"learning_rate": 3.908267805490051e-06,
|
| 1818 |
+
"loss": 0.0,
|
| 1819 |
+
"step": 254
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.9285389167045972,
|
| 1823 |
+
"grad_norm": NaN,
|
| 1824 |
+
"learning_rate": 3.529470089762421e-06,
|
| 1825 |
+
"loss": 0.0,
|
| 1826 |
+
"step": 255
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.9321802457897133,
|
| 1830 |
+
"grad_norm": NaN,
|
| 1831 |
+
"learning_rate": 3.169647787773866e-06,
|
| 1832 |
+
"loss": 0.0,
|
| 1833 |
+
"step": 256
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.9358215748748293,
|
| 1837 |
+
"grad_norm": NaN,
|
| 1838 |
+
"learning_rate": 2.8288716753049005e-06,
|
| 1839 |
+
"loss": 0.0,
|
| 1840 |
+
"step": 257
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.9394629039599454,
|
| 1844 |
+
"grad_norm": NaN,
|
| 1845 |
+
"learning_rate": 2.5072087818176382e-06,
|
| 1846 |
+
"loss": 0.0,
|
| 1847 |
+
"step": 258
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.9431042330450614,
|
| 1851 |
+
"grad_norm": NaN,
|
| 1852 |
+
"learning_rate": 2.20472237727124e-06,
|
| 1853 |
+
"loss": 0.0,
|
| 1854 |
+
"step": 259
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.9467455621301775,
|
| 1858 |
+
"grad_norm": NaN,
|
| 1859 |
+
"learning_rate": 1.921471959676957e-06,
|
| 1860 |
+
"loss": 0.0,
|
| 1861 |
+
"step": 260
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.9503868912152936,
|
| 1865 |
+
"grad_norm": NaN,
|
| 1866 |
+
"learning_rate": 1.657513243395159e-06,
|
| 1867 |
+
"loss": 0.0,
|
| 1868 |
+
"step": 261
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.9540282203004097,
|
| 1872 |
+
"grad_norm": NaN,
|
| 1873 |
+
"learning_rate": 1.4128981481764115e-06,
|
| 1874 |
+
"loss": 0.0,
|
| 1875 |
+
"step": 262
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.9576695493855257,
|
| 1879 |
+
"grad_norm": NaN,
|
| 1880 |
+
"learning_rate": 1.1876747889491223e-06,
|
| 1881 |
+
"loss": 0.0,
|
| 1882 |
+
"step": 263
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.9613108784706418,
|
| 1886 |
+
"grad_norm": NaN,
|
| 1887 |
+
"learning_rate": 9.818874663554357e-07,
|
| 1888 |
+
"loss": 0.0,
|
| 1889 |
+
"step": 264
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.9649522075557578,
|
| 1893 |
+
"grad_norm": NaN,
|
| 1894 |
+
"learning_rate": 7.955766580375335e-07,
|
| 1895 |
+
"loss": 0.0,
|
| 1896 |
+
"step": 265
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.9685935366408739,
|
| 1900 |
+
"grad_norm": NaN,
|
| 1901 |
+
"learning_rate": 6.287790106757396e-07,
|
| 1902 |
+
"loss": 0.0,
|
| 1903 |
+
"step": 266
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 0.9722348657259899,
|
| 1907 |
+
"grad_norm": NaN,
|
| 1908 |
+
"learning_rate": 4.815273327803182e-07,
|
| 1909 |
+
"loss": 0.0,
|
| 1910 |
+
"step": 267
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 0.9758761948111061,
|
| 1914 |
+
"grad_norm": NaN,
|
| 1915 |
+
"learning_rate": 3.5385058823809156e-07,
|
| 1916 |
+
"loss": 0.0,
|
| 1917 |
+
"step": 268
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 0.9795175238962222,
|
| 1921 |
+
"grad_norm": NaN,
|
| 1922 |
+
"learning_rate": 2.457738906153972e-07,
|
| 1923 |
+
"loss": 0.0,
|
| 1924 |
+
"step": 269
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 0.9831588529813382,
|
| 1928 |
+
"grad_norm": NaN,
|
| 1929 |
+
"learning_rate": 1.5731849821833954e-07,
|
| 1930 |
+
"loss": 0.0,
|
| 1931 |
+
"step": 270
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 0.9868001820664543,
|
| 1935 |
+
"grad_norm": NaN,
|
| 1936 |
+
"learning_rate": 8.850180991131219e-08,
|
| 1937 |
+
"loss": 0.0,
|
| 1938 |
+
"step": 271
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.9904415111515703,
|
| 1942 |
+
"grad_norm": NaN,
|
| 1943 |
+
"learning_rate": 3.933736169471347e-08,
|
| 1944 |
+
"loss": 0.0,
|
| 1945 |
+
"step": 272
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.9940828402366864,
|
| 1949 |
+
"grad_norm": NaN,
|
| 1950 |
+
"learning_rate": 9.834824042498358e-09,
|
| 1951 |
+
"loss": 0.0,
|
| 1952 |
+
"step": 273
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 0.9977241693218024,
|
| 1956 |
+
"grad_norm": NaN,
|
| 1957 |
+
"learning_rate": 0.0,
|
| 1958 |
+
"loss": 0.0,
|
| 1959 |
+
"step": 274
|
| 1960 |
}
|
| 1961 |
],
|
| 1962 |
"logging_steps": 1,
|
|
|
|
| 1971 |
"should_evaluate": false,
|
| 1972 |
"should_log": false,
|
| 1973 |
"should_save": true,
|
| 1974 |
+
"should_training_stop": true
|
| 1975 |
},
|
| 1976 |
"attributes": {}
|
| 1977 |
}
|
| 1978 |
},
|
| 1979 |
+
"total_flos": 7.706308131705324e+17,
|
| 1980 |
"train_batch_size": 2,
|
| 1981 |
"trial_name": null,
|
| 1982 |
"trial_params": null
|