Training in progress, step 250, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323014168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b81c89bf5a89dea220e294a4652d890349bf12553800a49024591d26ca2757a4
|
| 3 |
size 323014168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 164464564
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4536e6d49005fda0a95151faebf86801ba2e3b8da30b27d77d184347ee694363
|
| 3 |
size 164464564
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:356dcfdc03c399d2e663c95cf1133f32813c707adc33ad61bc750dcc5222213f
|
| 3 |
size 14244
|
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 sha256:517cde929c0b918b0e53e0ffd764ecc43637194fb41b83640993bbae7c21d100
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1447,6 +1447,364 @@
|
|
| 1447 |
"eval_samples_per_second": 2.941,
|
| 1448 |
"eval_steps_per_second": 2.941,
|
| 1449 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
@@ -1475,7 +1833,7 @@
|
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
-
"total_flos": 1.
|
| 1479 |
"train_batch_size": 1,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.39342138171195984,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 0.42435815828559303,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1447 |
"eval_samples_per_second": 2.941,
|
| 1448 |
"eval_steps_per_second": 2.941,
|
| 1449 |
"step": 200
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.3411839592616168,
|
| 1453 |
+
"grad_norm": 0.5887985825538635,
|
| 1454 |
+
"learning_rate": 0.0002732809457224292,
|
| 1455 |
+
"loss": 0.9434,
|
| 1456 |
+
"step": 201
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.3428813918947592,
|
| 1460 |
+
"grad_norm": 0.38302966952323914,
|
| 1461 |
+
"learning_rate": 0.00027300916279262866,
|
| 1462 |
+
"loss": 1.0988,
|
| 1463 |
+
"step": 202
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.34457882452790156,
|
| 1467 |
+
"grad_norm": 0.2614414095878601,
|
| 1468 |
+
"learning_rate": 0.0002727361411619245,
|
| 1469 |
+
"loss": 0.6772,
|
| 1470 |
+
"step": 203
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.34627625716104393,
|
| 1474 |
+
"grad_norm": 0.3063081204891205,
|
| 1475 |
+
"learning_rate": 0.0002724618835796414,
|
| 1476 |
+
"loss": 0.7314,
|
| 1477 |
+
"step": 204
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.3479736897941863,
|
| 1481 |
+
"grad_norm": 0.18658895790576935,
|
| 1482 |
+
"learning_rate": 0.0002721863928075503,
|
| 1483 |
+
"loss": 0.514,
|
| 1484 |
+
"step": 205
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.3496711224273287,
|
| 1488 |
+
"grad_norm": 0.282010018825531,
|
| 1489 |
+
"learning_rate": 0.0002719096716198402,
|
| 1490 |
+
"loss": 0.892,
|
| 1491 |
+
"step": 206
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.35136855506047104,
|
| 1495 |
+
"grad_norm": 0.17541489005088806,
|
| 1496 |
+
"learning_rate": 0.00027163172280309026,
|
| 1497 |
+
"loss": 0.5047,
|
| 1498 |
+
"step": 207
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.3530659876936134,
|
| 1502 |
+
"grad_norm": 0.21916832029819489,
|
| 1503 |
+
"learning_rate": 0.0002713525491562421,
|
| 1504 |
+
"loss": 0.7146,
|
| 1505 |
+
"step": 208
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.3547634203267558,
|
| 1509 |
+
"grad_norm": 0.20561501383781433,
|
| 1510 |
+
"learning_rate": 0.0002710721534905712,
|
| 1511 |
+
"loss": 0.6104,
|
| 1512 |
+
"step": 209
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.35646085295989816,
|
| 1516 |
+
"grad_norm": 0.1947142332792282,
|
| 1517 |
+
"learning_rate": 0.00027079053862965875,
|
| 1518 |
+
"loss": 0.4924,
|
| 1519 |
+
"step": 210
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.3581582855930405,
|
| 1523 |
+
"grad_norm": 0.23798146843910217,
|
| 1524 |
+
"learning_rate": 0.00027050770740936336,
|
| 1525 |
+
"loss": 0.6153,
|
| 1526 |
+
"step": 211
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.3598557182261829,
|
| 1530 |
+
"grad_norm": 0.21775560081005096,
|
| 1531 |
+
"learning_rate": 0.00027022366267779224,
|
| 1532 |
+
"loss": 0.4658,
|
| 1533 |
+
"step": 212
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.36155315085932527,
|
| 1537 |
+
"grad_norm": 0.24994409084320068,
|
| 1538 |
+
"learning_rate": 0.0002699384072952727,
|
| 1539 |
+
"loss": 0.5979,
|
| 1540 |
+
"step": 213
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.36325058349246764,
|
| 1544 |
+
"grad_norm": 0.28469640016555786,
|
| 1545 |
+
"learning_rate": 0.0002696519441343233,
|
| 1546 |
+
"loss": 0.8796,
|
| 1547 |
+
"step": 214
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.36494801612561,
|
| 1551 |
+
"grad_norm": 0.2747570276260376,
|
| 1552 |
+
"learning_rate": 0.0002693642760796248,
|
| 1553 |
+
"loss": 0.8625,
|
| 1554 |
+
"step": 215
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.3666454487587524,
|
| 1558 |
+
"grad_norm": 0.2469591647386551,
|
| 1559 |
+
"learning_rate": 0.00026907540602799136,
|
| 1560 |
+
"loss": 0.6991,
|
| 1561 |
+
"step": 216
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.36834288139189475,
|
| 1565 |
+
"grad_norm": 0.20425763726234436,
|
| 1566 |
+
"learning_rate": 0.00026878533688834123,
|
| 1567 |
+
"loss": 0.5774,
|
| 1568 |
+
"step": 217
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.3700403140250371,
|
| 1572 |
+
"grad_norm": 0.2737872898578644,
|
| 1573 |
+
"learning_rate": 0.0002684940715816674,
|
| 1574 |
+
"loss": 0.9062,
|
| 1575 |
+
"step": 218
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.3717377466581795,
|
| 1579 |
+
"grad_norm": 0.2064121514558792,
|
| 1580 |
+
"learning_rate": 0.00026820161304100823,
|
| 1581 |
+
"loss": 0.5054,
|
| 1582 |
+
"step": 219
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.37343517929132186,
|
| 1586 |
+
"grad_norm": 0.14863868057727814,
|
| 1587 |
+
"learning_rate": 0.00026790796421141813,
|
| 1588 |
+
"loss": 0.285,
|
| 1589 |
+
"step": 220
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.37513261192446423,
|
| 1593 |
+
"grad_norm": 0.12498918920755386,
|
| 1594 |
+
"learning_rate": 0.00026761312804993734,
|
| 1595 |
+
"loss": 0.1999,
|
| 1596 |
+
"step": 221
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.3768300445576066,
|
| 1600 |
+
"grad_norm": 0.1726280152797699,
|
| 1601 |
+
"learning_rate": 0.0002673171075255629,
|
| 1602 |
+
"loss": 0.2852,
|
| 1603 |
+
"step": 222
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.378527477190749,
|
| 1607 |
+
"grad_norm": 0.1533537358045578,
|
| 1608 |
+
"learning_rate": 0.0002670199056192181,
|
| 1609 |
+
"loss": 0.3106,
|
| 1610 |
+
"step": 223
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.38022490982389134,
|
| 1614 |
+
"grad_norm": 0.125217467546463,
|
| 1615 |
+
"learning_rate": 0.00026672152532372287,
|
| 1616 |
+
"loss": 0.1804,
|
| 1617 |
+
"step": 224
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.3819223424570337,
|
| 1621 |
+
"grad_norm": 0.05522383376955986,
|
| 1622 |
+
"learning_rate": 0.0002664219696437635,
|
| 1623 |
+
"loss": 0.0442,
|
| 1624 |
+
"step": 225
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.3836197750901761,
|
| 1628 |
+
"grad_norm": 0.04138198867440224,
|
| 1629 |
+
"learning_rate": 0.00026612124159586237,
|
| 1630 |
+
"loss": 0.023,
|
| 1631 |
+
"step": 226
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.38531720772331846,
|
| 1635 |
+
"grad_norm": 0.05575822666287422,
|
| 1636 |
+
"learning_rate": 0.0002658193442083475,
|
| 1637 |
+
"loss": 0.0024,
|
| 1638 |
+
"step": 227
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.3870146403564608,
|
| 1642 |
+
"grad_norm": 0.12629126012325287,
|
| 1643 |
+
"learning_rate": 0.0002655162805213223,
|
| 1644 |
+
"loss": 0.1524,
|
| 1645 |
+
"step": 228
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.38871207298960325,
|
| 1649 |
+
"grad_norm": 0.02942221239209175,
|
| 1650 |
+
"learning_rate": 0.00026521205358663477,
|
| 1651 |
+
"loss": 0.0096,
|
| 1652 |
+
"step": 229
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.3904095056227456,
|
| 1656 |
+
"grad_norm": 0.0953650251030922,
|
| 1657 |
+
"learning_rate": 0.00026490666646784665,
|
| 1658 |
+
"loss": 0.0043,
|
| 1659 |
+
"step": 230
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.392106938255888,
|
| 1663 |
+
"grad_norm": 0.005734459031373262,
|
| 1664 |
+
"learning_rate": 0.00026460012224020297,
|
| 1665 |
+
"loss": 0.0003,
|
| 1666 |
+
"step": 231
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.39380437088903036,
|
| 1670 |
+
"grad_norm": 0.010758363641798496,
|
| 1671 |
+
"learning_rate": 0.0002642924239906006,
|
| 1672 |
+
"loss": 0.0003,
|
| 1673 |
+
"step": 232
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.39550180352217273,
|
| 1677 |
+
"grad_norm": 0.01772010512650013,
|
| 1678 |
+
"learning_rate": 0.0002639835748175575,
|
| 1679 |
+
"loss": 0.0007,
|
| 1680 |
+
"step": 233
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.3971992361553151,
|
| 1684 |
+
"grad_norm": 0.005056055262684822,
|
| 1685 |
+
"learning_rate": 0.0002636735778311815,
|
| 1686 |
+
"loss": 0.0002,
|
| 1687 |
+
"step": 234
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.3988966687884575,
|
| 1691 |
+
"grad_norm": 0.24263891577720642,
|
| 1692 |
+
"learning_rate": 0.00026336243615313873,
|
| 1693 |
+
"loss": 0.0008,
|
| 1694 |
+
"step": 235
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.40059410142159985,
|
| 1698 |
+
"grad_norm": 0.0014849180588498712,
|
| 1699 |
+
"learning_rate": 0.0002630501529166224,
|
| 1700 |
+
"loss": 0.0001,
|
| 1701 |
+
"step": 236
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.4022915340547422,
|
| 1705 |
+
"grad_norm": 0.0037826071493327618,
|
| 1706 |
+
"learning_rate": 0.00026273673126632133,
|
| 1707 |
+
"loss": 0.0002,
|
| 1708 |
+
"step": 237
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.4039889666878846,
|
| 1712 |
+
"grad_norm": 0.08331254124641418,
|
| 1713 |
+
"learning_rate": 0.0002624221743583881,
|
| 1714 |
+
"loss": 0.0016,
|
| 1715 |
+
"step": 238
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.40568639932102696,
|
| 1719 |
+
"grad_norm": 0.002364553976804018,
|
| 1720 |
+
"learning_rate": 0.0002621064853604071,
|
| 1721 |
+
"loss": 0.0001,
|
| 1722 |
+
"step": 239
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.40738383195416933,
|
| 1726 |
+
"grad_norm": 0.014542756602168083,
|
| 1727 |
+
"learning_rate": 0.0002617896674513632,
|
| 1728 |
+
"loss": 0.0002,
|
| 1729 |
+
"step": 240
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.4090812645873117,
|
| 1733 |
+
"grad_norm": 0.0031418628059327602,
|
| 1734 |
+
"learning_rate": 0.00026147172382160914,
|
| 1735 |
+
"loss": 0.0001,
|
| 1736 |
+
"step": 241
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.41077869722045407,
|
| 1740 |
+
"grad_norm": 0.11094752699136734,
|
| 1741 |
+
"learning_rate": 0.00026115265767283374,
|
| 1742 |
+
"loss": 0.0031,
|
| 1743 |
+
"step": 242
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.41247612985359644,
|
| 1747 |
+
"grad_norm": 0.012769564054906368,
|
| 1748 |
+
"learning_rate": 0.0002608324722180296,
|
| 1749 |
+
"loss": 0.0005,
|
| 1750 |
+
"step": 243
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.4141735624867388,
|
| 1754 |
+
"grad_norm": 0.055052801966667175,
|
| 1755 |
+
"learning_rate": 0.0002605111706814607,
|
| 1756 |
+
"loss": 0.0023,
|
| 1757 |
+
"step": 244
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.4158709951198812,
|
| 1761 |
+
"grad_norm": 0.003668338293209672,
|
| 1762 |
+
"learning_rate": 0.00026018875629862996,
|
| 1763 |
+
"loss": 0.0002,
|
| 1764 |
+
"step": 245
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.41756842775302355,
|
| 1768 |
+
"grad_norm": 0.009973675012588501,
|
| 1769 |
+
"learning_rate": 0.0002598652323162466,
|
| 1770 |
+
"loss": 0.0003,
|
| 1771 |
+
"step": 246
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.4192658603861659,
|
| 1775 |
+
"grad_norm": 0.02005830593407154,
|
| 1776 |
+
"learning_rate": 0.0002595406019921936,
|
| 1777 |
+
"loss": 0.0008,
|
| 1778 |
+
"step": 247
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.4209632930193083,
|
| 1782 |
+
"grad_norm": 0.02860446274280548,
|
| 1783 |
+
"learning_rate": 0.0002592148685954946,
|
| 1784 |
+
"loss": 0.0024,
|
| 1785 |
+
"step": 248
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.42266072565245066,
|
| 1789 |
+
"grad_norm": 0.03582284599542618,
|
| 1790 |
+
"learning_rate": 0.0002588880354062814,
|
| 1791 |
+
"loss": 0.0014,
|
| 1792 |
+
"step": 249
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.42435815828559303,
|
| 1796 |
+
"grad_norm": 0.03657930716872215,
|
| 1797 |
+
"learning_rate": 0.0002585601057157605,
|
| 1798 |
+
"loss": 0.0023,
|
| 1799 |
+
"step": 250
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 0.42435815828559303,
|
| 1803 |
+
"eval_loss": 0.39342138171195984,
|
| 1804 |
+
"eval_runtime": 65.6277,
|
| 1805 |
+
"eval_samples_per_second": 2.941,
|
| 1806 |
+
"eval_steps_per_second": 2.941,
|
| 1807 |
+
"step": 250
|
| 1808 |
}
|
| 1809 |
],
|
| 1810 |
"logging_steps": 1,
|
|
|
|
| 1833 |
"attributes": {}
|
| 1834 |
}
|
| 1835 |
},
|
| 1836 |
+
"total_flos": 1.6186741772569805e+17,
|
| 1837 |
"train_batch_size": 1,
|
| 1838 |
"trial_name": null,
|
| 1839 |
"trial_params": null
|