Training in progress, step 503, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1049614696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a8012a7e4ebbcf674e7c053aab2984371f5b66d18160874ef76e47df13d7d10
|
| 3 |
size 1049614696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1372902609
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3767a23772d915d4f0d08aecbd8ba1007c2450b7f4264217c6dc062863bcbb62
|
| 3 |
size 1372902609
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abb0ed761d9206a280c8415a8884f5ff0e1548d6a1c2cc83a21b80bc00311e4e
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 76,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1462,6 +1462,365 @@
|
|
| 1462 |
"learning_rate": 4.4928312680573064e-05,
|
| 1463 |
"loss": 1.4603819847106934,
|
| 1464 |
"step": 404
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1465 |
}
|
| 1466 |
],
|
| 1467 |
"logging_steps": 2,
|
|
@@ -1476,12 +1835,12 @@
|
|
| 1476 |
"should_evaluate": false,
|
| 1477 |
"should_log": false,
|
| 1478 |
"should_save": true,
|
| 1479 |
-
"should_training_stop":
|
| 1480 |
},
|
| 1481 |
"attributes": {}
|
| 1482 |
}
|
| 1483 |
},
|
| 1484 |
-
"total_flos":
|
| 1485 |
"train_batch_size": 4,
|
| 1486 |
"trial_name": null,
|
| 1487 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.2512437810945274,
|
| 6 |
"eval_steps": 76,
|
| 7 |
+
"global_step": 503,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1462 |
"learning_rate": 4.4928312680573064e-05,
|
| 1463 |
"loss": 1.4603819847106934,
|
| 1464 |
"step": 404
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.0099502487562189,
|
| 1468 |
+
"grad_norm": 0.7265625,
|
| 1469 |
+
"learning_rate": 4.415111107797445e-05,
|
| 1470 |
+
"loss": 1.4816609621047974,
|
| 1471 |
+
"step": 406
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.0149253731343284,
|
| 1475 |
+
"grad_norm": 0.6640625,
|
| 1476 |
+
"learning_rate": 4.332629679574566e-05,
|
| 1477 |
+
"loss": 1.4633798599243164,
|
| 1478 |
+
"step": 408
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.0199004975124377,
|
| 1482 |
+
"grad_norm": 0.75390625,
|
| 1483 |
+
"learning_rate": 4.245592045215182e-05,
|
| 1484 |
+
"loss": 1.4657684564590454,
|
| 1485 |
+
"step": 410
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.0248756218905473,
|
| 1489 |
+
"grad_norm": 0.59765625,
|
| 1490 |
+
"learning_rate": 4.154214593992149e-05,
|
| 1491 |
+
"loss": 1.4662880897521973,
|
| 1492 |
+
"step": 412
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.0298507462686568,
|
| 1496 |
+
"grad_norm": 0.8125,
|
| 1497 |
+
"learning_rate": 4.058724504646834e-05,
|
| 1498 |
+
"loss": 1.4156984090805054,
|
| 1499 |
+
"step": 414
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.0348258706467661,
|
| 1503 |
+
"grad_norm": 0.73046875,
|
| 1504 |
+
"learning_rate": 3.959359180586975e-05,
|
| 1505 |
+
"loss": 1.4586745500564575,
|
| 1506 |
+
"step": 416
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.0398009950248757,
|
| 1510 |
+
"grad_norm": 0.58984375,
|
| 1511 |
+
"learning_rate": 3.856365659664399e-05,
|
| 1512 |
+
"loss": 1.4008747339248657,
|
| 1513 |
+
"step": 418
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.044776119402985,
|
| 1517 |
+
"grad_norm": 0.67578125,
|
| 1518 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1519 |
+
"loss": 1.5016967058181763,
|
| 1520 |
+
"step": 420
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.0497512437810945,
|
| 1524 |
+
"grad_norm": 0.6875,
|
| 1525 |
+
"learning_rate": 3.6405266433829075e-05,
|
| 1526 |
+
"loss": 1.420767903327942,
|
| 1527 |
+
"step": 422
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.054726368159204,
|
| 1531 |
+
"grad_norm": 0.796875,
|
| 1532 |
+
"learning_rate": 3.5282177578265296e-05,
|
| 1533 |
+
"loss": 1.4615557193756104,
|
| 1534 |
+
"step": 424
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 1.0597014925373134,
|
| 1538 |
+
"grad_norm": 0.6875,
|
| 1539 |
+
"learning_rate": 3.413352560915988e-05,
|
| 1540 |
+
"loss": 1.426128625869751,
|
| 1541 |
+
"step": 426
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.064676616915423,
|
| 1545 |
+
"grad_norm": 0.84765625,
|
| 1546 |
+
"learning_rate": 3.2962166256292113e-05,
|
| 1547 |
+
"loss": 1.4995248317718506,
|
| 1548 |
+
"step": 428
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.0696517412935322,
|
| 1552 |
+
"grad_norm": 0.73046875,
|
| 1553 |
+
"learning_rate": 3.177101170357513e-05,
|
| 1554 |
+
"loss": 1.544938325881958,
|
| 1555 |
+
"step": 430
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.0746268656716418,
|
| 1559 |
+
"grad_norm": 0.68359375,
|
| 1560 |
+
"learning_rate": 3.056302334890786e-05,
|
| 1561 |
+
"loss": 1.5545825958251953,
|
| 1562 |
+
"step": 432
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.0796019900497513,
|
| 1566 |
+
"grad_norm": 0.6875,
|
| 1567 |
+
"learning_rate": 2.9341204441673266e-05,
|
| 1568 |
+
"loss": 1.4614660739898682,
|
| 1569 |
+
"step": 434
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.0845771144278606,
|
| 1573 |
+
"grad_norm": 0.765625,
|
| 1574 |
+
"learning_rate": 2.8108592616187133e-05,
|
| 1575 |
+
"loss": 1.4706202745437622,
|
| 1576 |
+
"step": 436
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 1.0895522388059702,
|
| 1580 |
+
"grad_norm": 0.66796875,
|
| 1581 |
+
"learning_rate": 2.686825233966061e-05,
|
| 1582 |
+
"loss": 1.4637281894683838,
|
| 1583 |
+
"step": 438
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.0945273631840795,
|
| 1587 |
+
"grad_norm": 0.84375,
|
| 1588 |
+
"learning_rate": 2.5623267293451826e-05,
|
| 1589 |
+
"loss": 1.4879995584487915,
|
| 1590 |
+
"step": 440
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.099502487562189,
|
| 1594 |
+
"grad_norm": 0.75390625,
|
| 1595 |
+
"learning_rate": 2.4376732706548183e-05,
|
| 1596 |
+
"loss": 1.5506470203399658,
|
| 1597 |
+
"step": 442
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.1044776119402986,
|
| 1601 |
+
"grad_norm": 0.73828125,
|
| 1602 |
+
"learning_rate": 2.3131747660339394e-05,
|
| 1603 |
+
"loss": 1.5075286626815796,
|
| 1604 |
+
"step": 444
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 1.109452736318408,
|
| 1608 |
+
"grad_norm": 0.9453125,
|
| 1609 |
+
"learning_rate": 2.189140738381288e-05,
|
| 1610 |
+
"loss": 1.4878989458084106,
|
| 1611 |
+
"step": 446
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.1144278606965174,
|
| 1615 |
+
"grad_norm": 0.7421875,
|
| 1616 |
+
"learning_rate": 2.0658795558326743e-05,
|
| 1617 |
+
"loss": 1.4383412599563599,
|
| 1618 |
+
"step": 448
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.1194029850746268,
|
| 1622 |
+
"grad_norm": 0.7265625,
|
| 1623 |
+
"learning_rate": 1.9436976651092144e-05,
|
| 1624 |
+
"loss": 1.5081899166107178,
|
| 1625 |
+
"step": 450
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.1243781094527363,
|
| 1629 |
+
"grad_norm": 0.8203125,
|
| 1630 |
+
"learning_rate": 1.8228988296424877e-05,
|
| 1631 |
+
"loss": 1.497464656829834,
|
| 1632 |
+
"step": 452
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 1.1293532338308458,
|
| 1636 |
+
"grad_norm": 0.80078125,
|
| 1637 |
+
"learning_rate": 1.7037833743707892e-05,
|
| 1638 |
+
"loss": 1.4927465915679932,
|
| 1639 |
+
"step": 454
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.1343283582089552,
|
| 1643 |
+
"grad_norm": 0.7109375,
|
| 1644 |
+
"learning_rate": 1.5866474390840125e-05,
|
| 1645 |
+
"loss": 1.4225599765777588,
|
| 1646 |
+
"step": 456
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 1.1343283582089552,
|
| 1650 |
+
"eval_loss": 1.460990071296692,
|
| 1651 |
+
"eval_runtime": 1.4591,
|
| 1652 |
+
"eval_samples_per_second": 89.097,
|
| 1653 |
+
"eval_steps_per_second": 11.651,
|
| 1654 |
+
"step": 456
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.1393034825870647,
|
| 1658 |
+
"grad_norm": 0.7109375,
|
| 1659 |
+
"learning_rate": 1.4717822421734718e-05,
|
| 1660 |
+
"loss": 1.3992186784744263,
|
| 1661 |
+
"step": 458
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.144278606965174,
|
| 1665 |
+
"grad_norm": 0.703125,
|
| 1666 |
+
"learning_rate": 1.3594733566170926e-05,
|
| 1667 |
+
"loss": 1.5498771667480469,
|
| 1668 |
+
"step": 460
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.1492537313432836,
|
| 1672 |
+
"grad_norm": 0.64453125,
|
| 1673 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 1674 |
+
"loss": 1.4473354816436768,
|
| 1675 |
+
"step": 462
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.154228855721393,
|
| 1679 |
+
"grad_norm": 0.7578125,
|
| 1680 |
+
"learning_rate": 1.1436343403356017e-05,
|
| 1681 |
+
"loss": 1.4893980026245117,
|
| 1682 |
+
"step": 464
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.1592039800995024,
|
| 1686 |
+
"grad_norm": 0.75390625,
|
| 1687 |
+
"learning_rate": 1.0406408194130259e-05,
|
| 1688 |
+
"loss": 1.4563506841659546,
|
| 1689 |
+
"step": 466
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.164179104477612,
|
| 1693 |
+
"grad_norm": 0.70703125,
|
| 1694 |
+
"learning_rate": 9.412754953531663e-06,
|
| 1695 |
+
"loss": 1.4524166584014893,
|
| 1696 |
+
"step": 468
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.1691542288557213,
|
| 1700 |
+
"grad_norm": 0.7265625,
|
| 1701 |
+
"learning_rate": 8.45785406007852e-06,
|
| 1702 |
+
"loss": 1.4781806468963623,
|
| 1703 |
+
"step": 470
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.1741293532338308,
|
| 1707 |
+
"grad_norm": 0.69140625,
|
| 1708 |
+
"learning_rate": 7.5440795478481815e-06,
|
| 1709 |
+
"loss": 1.5440560579299927,
|
| 1710 |
+
"step": 472
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.1791044776119404,
|
| 1714 |
+
"grad_norm": 0.83203125,
|
| 1715 |
+
"learning_rate": 6.673703204254347e-06,
|
| 1716 |
+
"loss": 1.4499876499176025,
|
| 1717 |
+
"step": 474
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.1840796019900497,
|
| 1721 |
+
"grad_norm": 0.69140625,
|
| 1722 |
+
"learning_rate": 5.848888922025553e-06,
|
| 1723 |
+
"loss": 1.5100181102752686,
|
| 1724 |
+
"step": 476
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.1890547263681592,
|
| 1728 |
+
"grad_norm": 0.765625,
|
| 1729 |
+
"learning_rate": 5.071687319426946e-06,
|
| 1730 |
+
"loss": 1.4939875602722168,
|
| 1731 |
+
"step": 478
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.1940298507462686,
|
| 1735 |
+
"grad_norm": 0.6640625,
|
| 1736 |
+
"learning_rate": 4.344030642100133e-06,
|
| 1737 |
+
"loss": 1.5198827981948853,
|
| 1738 |
+
"step": 480
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.199004975124378,
|
| 1742 |
+
"grad_norm": 0.66015625,
|
| 1743 |
+
"learning_rate": 3.66772795919611e-06,
|
| 1744 |
+
"loss": 1.490272879600525,
|
| 1745 |
+
"step": 482
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.2039800995024876,
|
| 1749 |
+
"grad_norm": 0.765625,
|
| 1750 |
+
"learning_rate": 3.044460665744284e-06,
|
| 1751 |
+
"loss": 1.5192978382110596,
|
| 1752 |
+
"step": 484
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.208955223880597,
|
| 1756 |
+
"grad_norm": 0.73046875,
|
| 1757 |
+
"learning_rate": 2.475778302439524e-06,
|
| 1758 |
+
"loss": 1.4486744403839111,
|
| 1759 |
+
"step": 486
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.2139303482587065,
|
| 1763 |
+
"grad_norm": 0.6796875,
|
| 1764 |
+
"learning_rate": 1.9630947032398067e-06,
|
| 1765 |
+
"loss": 1.4685592651367188,
|
| 1766 |
+
"step": 488
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.2189054726368158,
|
| 1770 |
+
"grad_norm": 0.71875,
|
| 1771 |
+
"learning_rate": 1.5076844803522922e-06,
|
| 1772 |
+
"loss": 1.3960230350494385,
|
| 1773 |
+
"step": 490
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.2238805970149254,
|
| 1777 |
+
"grad_norm": 0.5859375,
|
| 1778 |
+
"learning_rate": 1.1106798553464804e-06,
|
| 1779 |
+
"loss": 1.4277310371398926,
|
| 1780 |
+
"step": 492
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.228855721393035,
|
| 1784 |
+
"grad_norm": 0.66015625,
|
| 1785 |
+
"learning_rate": 7.730678442730538e-07,
|
| 1786 |
+
"loss": 1.5258288383483887,
|
| 1787 |
+
"step": 494
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.2338308457711442,
|
| 1791 |
+
"grad_norm": 0.80859375,
|
| 1792 |
+
"learning_rate": 4.956878037864043e-07,
|
| 1793 |
+
"loss": 1.5295201539993286,
|
| 1794 |
+
"step": 496
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.2388059701492538,
|
| 1798 |
+
"grad_norm": 0.7734375,
|
| 1799 |
+
"learning_rate": 2.7922934437178695e-07,
|
| 1800 |
+
"loss": 1.461329698562622,
|
| 1801 |
+
"step": 498
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.243781094527363,
|
| 1805 |
+
"grad_norm": 0.72265625,
|
| 1806 |
+
"learning_rate": 1.2423061586496477e-07,
|
| 1807 |
+
"loss": 1.4992496967315674,
|
| 1808 |
+
"step": 500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.2487562189054726,
|
| 1812 |
+
"grad_norm": 0.78515625,
|
| 1813 |
+
"learning_rate": 3.107696952694139e-08,
|
| 1814 |
+
"loss": 1.4631916284561157,
|
| 1815 |
+
"step": 502
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.2512437810945274,
|
| 1819 |
+
"eval_loss": 1.4604582786560059,
|
| 1820 |
+
"eval_runtime": 1.4388,
|
| 1821 |
+
"eval_samples_per_second": 90.352,
|
| 1822 |
+
"eval_steps_per_second": 11.815,
|
| 1823 |
+
"step": 503
|
| 1824 |
}
|
| 1825 |
],
|
| 1826 |
"logging_steps": 2,
|
|
|
|
| 1835 |
"should_evaluate": false,
|
| 1836 |
"should_log": false,
|
| 1837 |
"should_save": true,
|
| 1838 |
+
"should_training_stop": true
|
| 1839 |
},
|
| 1840 |
"attributes": {}
|
| 1841 |
}
|
| 1842 |
},
|
| 1843 |
+
"total_flos": 1.1908427380948992e+16,
|
| 1844 |
"train_batch_size": 4,
|
| 1845 |
"trial_name": null,
|
| 1846 |
"trial_params": null
|