Training in progress, step 240, 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 373077376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d5cb32555f036cc29e510981db920df70d9e90bc6775cbdddef9c9bc689ca68
|
| 3 |
size 373077376
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 422377867
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d96a6c94d5ea65063709fd1b3a2c97e499172bb263cf2e84c9c5a02acf2a0620
|
| 3 |
size 422377867
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1401
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37ec1b5270d425b99d0e1cc607e50e995f87916d2f0845b877477bb69e081603
|
| 3 |
size 1401
|
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": 0
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1422,6 +1422,286 @@
|
|
| 1422 |
"eval_samples_per_second": 13.356,
|
| 1423 |
"eval_steps_per_second": 0.835,
|
| 1424 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1425 |
}
|
| 1426 |
],
|
| 1427 |
"logging_steps": 1,
|
|
@@ -1436,12 +1716,12 @@
|
|
| 1436 |
"should_evaluate": false,
|
| 1437 |
"should_log": false,
|
| 1438 |
"should_save": true,
|
| 1439 |
-
"should_training_stop":
|
| 1440 |
},
|
| 1441 |
"attributes": {}
|
| 1442 |
}
|
| 1443 |
},
|
| 1444 |
-
"total_flos": 1.
|
| 1445 |
"train_batch_size": 16,
|
| 1446 |
"trial_name": null,
|
| 1447 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1422 |
"eval_samples_per_second": 13.356,
|
| 1423 |
"eval_steps_per_second": 0.835,
|
| 1424 |
"step": 200
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.8375,
|
| 1428 |
+
"grad_norm": 0.326171875,
|
| 1429 |
+
"learning_rate": 7.404029558083653e-05,
|
| 1430 |
+
"loss": 5.6536,
|
| 1431 |
+
"step": 201
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.8416666666666667,
|
| 1435 |
+
"grad_norm": 0.27734375,
|
| 1436 |
+
"learning_rate": 7.047302281505735e-05,
|
| 1437 |
+
"loss": 5.6053,
|
| 1438 |
+
"step": 202
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.8458333333333333,
|
| 1442 |
+
"grad_norm": 0.275390625,
|
| 1443 |
+
"learning_rate": 6.698729810778065e-05,
|
| 1444 |
+
"loss": 5.6449,
|
| 1445 |
+
"step": 203
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.85,
|
| 1449 |
+
"grad_norm": 0.29296875,
|
| 1450 |
+
"learning_rate": 6.358378324300929e-05,
|
| 1451 |
+
"loss": 5.6066,
|
| 1452 |
+
"step": 204
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.8541666666666666,
|
| 1456 |
+
"grad_norm": 0.26953125,
|
| 1457 |
+
"learning_rate": 6.026312439675552e-05,
|
| 1458 |
+
"loss": 5.6563,
|
| 1459 |
+
"step": 205
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.8583333333333333,
|
| 1463 |
+
"grad_norm": 0.234375,
|
| 1464 |
+
"learning_rate": 5.7025952014361004e-05,
|
| 1465 |
+
"loss": 5.6946,
|
| 1466 |
+
"step": 206
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.8625,
|
| 1470 |
+
"grad_norm": 0.259765625,
|
| 1471 |
+
"learning_rate": 5.387288069080298e-05,
|
| 1472 |
+
"loss": 5.6036,
|
| 1473 |
+
"step": 207
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.8666666666666667,
|
| 1477 |
+
"grad_norm": 0.2373046875,
|
| 1478 |
+
"learning_rate": 5.080450905401057e-05,
|
| 1479 |
+
"loss": 5.6453,
|
| 1480 |
+
"step": 208
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.8708333333333333,
|
| 1484 |
+
"grad_norm": 0.296875,
|
| 1485 |
+
"learning_rate": 4.7821419651211284e-05,
|
| 1486 |
+
"loss": 5.4334,
|
| 1487 |
+
"step": 209
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.875,
|
| 1491 |
+
"grad_norm": 0.283203125,
|
| 1492 |
+
"learning_rate": 4.492417883833155e-05,
|
| 1493 |
+
"loss": 5.5169,
|
| 1494 |
+
"step": 210
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.8791666666666667,
|
| 1498 |
+
"grad_norm": 0.30078125,
|
| 1499 |
+
"learning_rate": 4.211333667247125e-05,
|
| 1500 |
+
"loss": 5.4803,
|
| 1501 |
+
"step": 211
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.8833333333333333,
|
| 1505 |
+
"grad_norm": 0.279296875,
|
| 1506 |
+
"learning_rate": 3.938942680747176e-05,
|
| 1507 |
+
"loss": 5.5033,
|
| 1508 |
+
"step": 212
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.8875,
|
| 1512 |
+
"grad_norm": 0.23828125,
|
| 1513 |
+
"learning_rate": 3.675296639259912e-05,
|
| 1514 |
+
"loss": 5.7133,
|
| 1515 |
+
"step": 213
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.8916666666666667,
|
| 1519 |
+
"grad_norm": 0.232421875,
|
| 1520 |
+
"learning_rate": 3.420445597436056e-05,
|
| 1521 |
+
"loss": 5.5607,
|
| 1522 |
+
"step": 214
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.8958333333333334,
|
| 1526 |
+
"grad_norm": 0.26171875,
|
| 1527 |
+
"learning_rate": 3.174437940147268e-05,
|
| 1528 |
+
"loss": 5.4607,
|
| 1529 |
+
"step": 215
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.9,
|
| 1533 |
+
"grad_norm": 0.28125,
|
| 1534 |
+
"learning_rate": 2.9373203733000232e-05,
|
| 1535 |
+
"loss": 5.4973,
|
| 1536 |
+
"step": 216
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9041666666666667,
|
| 1540 |
+
"grad_norm": 0.25390625,
|
| 1541 |
+
"learning_rate": 2.709137914968268e-05,
|
| 1542 |
+
"loss": 5.5641,
|
| 1543 |
+
"step": 217
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.9083333333333333,
|
| 1547 |
+
"grad_norm": 0.2294921875,
|
| 1548 |
+
"learning_rate": 2.4899338868464407e-05,
|
| 1549 |
+
"loss": 5.6054,
|
| 1550 |
+
"step": 218
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.9125,
|
| 1554 |
+
"grad_norm": 0.251953125,
|
| 1555 |
+
"learning_rate": 2.2797499060246252e-05,
|
| 1556 |
+
"loss": 5.4569,
|
| 1557 |
+
"step": 219
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.9166666666666666,
|
| 1561 |
+
"grad_norm": 0.279296875,
|
| 1562 |
+
"learning_rate": 2.0786258770873646e-05,
|
| 1563 |
+
"loss": 5.5549,
|
| 1564 |
+
"step": 220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.9208333333333333,
|
| 1568 |
+
"grad_norm": 0.306640625,
|
| 1569 |
+
"learning_rate": 1.886599984537479e-05,
|
| 1570 |
+
"loss": 5.5161,
|
| 1571 |
+
"step": 221
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.925,
|
| 1575 |
+
"grad_norm": 0.259765625,
|
| 1576 |
+
"learning_rate": 1.70370868554659e-05,
|
| 1577 |
+
"loss": 5.509,
|
| 1578 |
+
"step": 222
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.9291666666666667,
|
| 1582 |
+
"grad_norm": 0.31640625,
|
| 1583 |
+
"learning_rate": 1.5299867030334813e-05,
|
| 1584 |
+
"loss": 5.3626,
|
| 1585 |
+
"step": 223
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.9333333333333333,
|
| 1589 |
+
"grad_norm": 0.265625,
|
| 1590 |
+
"learning_rate": 1.3654670190718033e-05,
|
| 1591 |
+
"loss": 5.6124,
|
| 1592 |
+
"step": 224
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.9375,
|
| 1596 |
+
"grad_norm": 0.29296875,
|
| 1597 |
+
"learning_rate": 1.210180868628219e-05,
|
| 1598 |
+
"loss": 5.5415,
|
| 1599 |
+
"step": 225
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.9416666666666667,
|
| 1603 |
+
"grad_norm": 0.271484375,
|
| 1604 |
+
"learning_rate": 1.064157733632276e-05,
|
| 1605 |
+
"loss": 5.7405,
|
| 1606 |
+
"step": 226
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.9458333333333333,
|
| 1610 |
+
"grad_norm": 0.2451171875,
|
| 1611 |
+
"learning_rate": 9.274253373791064e-06,
|
| 1612 |
+
"loss": 5.6103,
|
| 1613 |
+
"step": 227
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.95,
|
| 1617 |
+
"grad_norm": 0.294921875,
|
| 1618 |
+
"learning_rate": 8.000096392660028e-06,
|
| 1619 |
+
"loss": 5.5475,
|
| 1620 |
+
"step": 228
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.9541666666666667,
|
| 1624 |
+
"grad_norm": 0.29296875,
|
| 1625 |
+
"learning_rate": 6.819348298638839e-06,
|
| 1626 |
+
"loss": 5.493,
|
| 1627 |
+
"step": 229
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.9583333333333334,
|
| 1631 |
+
"grad_norm": 0.2890625,
|
| 1632 |
+
"learning_rate": 5.732233263245845e-06,
|
| 1633 |
+
"loss": 5.5532,
|
| 1634 |
+
"step": 230
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.9625,
|
| 1638 |
+
"grad_norm": 0.27734375,
|
| 1639 |
+
"learning_rate": 4.738957681248379e-06,
|
| 1640 |
+
"loss": 5.495,
|
| 1641 |
+
"step": 231
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.9666666666666667,
|
| 1645 |
+
"grad_norm": 0.298828125,
|
| 1646 |
+
"learning_rate": 3.839710131477492e-06,
|
| 1647 |
+
"loss": 5.4654,
|
| 1648 |
+
"step": 232
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.9708333333333333,
|
| 1652 |
+
"grad_norm": 0.26171875,
|
| 1653 |
+
"learning_rate": 3.034661341025258e-06,
|
| 1654 |
+
"loss": 5.3983,
|
| 1655 |
+
"step": 233
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.975,
|
| 1659 |
+
"grad_norm": 0.26171875,
|
| 1660 |
+
"learning_rate": 2.323964152831426e-06,
|
| 1661 |
+
"loss": 5.5638,
|
| 1662 |
+
"step": 234
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.9791666666666666,
|
| 1666 |
+
"grad_norm": 0.2216796875,
|
| 1667 |
+
"learning_rate": 1.7077534966650766e-06,
|
| 1668 |
+
"loss": 5.6353,
|
| 1669 |
+
"step": 235
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.9833333333333333,
|
| 1673 |
+
"grad_norm": 0.322265625,
|
| 1674 |
+
"learning_rate": 1.1861463635077786e-06,
|
| 1675 |
+
"loss": 5.513,
|
| 1676 |
+
"step": 236
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.9875,
|
| 1680 |
+
"grad_norm": 0.25,
|
| 1681 |
+
"learning_rate": 7.592417833419129e-07,
|
| 1682 |
+
"loss": 5.5575,
|
| 1683 |
+
"step": 237
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.9916666666666667,
|
| 1687 |
+
"grad_norm": 0.265625,
|
| 1688 |
+
"learning_rate": 4.2712080634949023e-07,
|
| 1689 |
+
"loss": 5.5291,
|
| 1690 |
+
"step": 238
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.9958333333333333,
|
| 1694 |
+
"grad_norm": 0.25390625,
|
| 1695 |
+
"learning_rate": 1.8984648752429223e-07,
|
| 1696 |
+
"loss": 5.6134,
|
| 1697 |
+
"step": 239
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.0,
|
| 1701 |
+
"grad_norm": 0.271484375,
|
| 1702 |
+
"learning_rate": 4.746387470044855e-08,
|
| 1703 |
+
"loss": 5.5174,
|
| 1704 |
+
"step": 240
|
| 1705 |
}
|
| 1706 |
],
|
| 1707 |
"logging_steps": 1,
|
|
|
|
| 1716 |
"should_evaluate": false,
|
| 1717 |
"should_log": false,
|
| 1718 |
"should_save": true,
|
| 1719 |
+
"should_training_stop": true
|
| 1720 |
},
|
| 1721 |
"attributes": {}
|
| 1722 |
}
|
| 1723 |
},
|
| 1724 |
+
"total_flos": 1.2226734657110016e+17,
|
| 1725 |
"train_batch_size": 16,
|
| 1726 |
"trial_name": null,
|
| 1727 |
"trial_params": null
|