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 156926880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0220fc1d90ea8fc616a75a349e3a3de3f88c807fd95fbaeb193fce07d25ce28e
|
| 3 |
size 156926880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 79968772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf8aa25bcfa9e3a2765287904893589e75a733b33907eb0862824d2de06ddf0b
|
| 3 |
size 79968772
|
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 sha256:2cda862f419774a7c8b4ce1fb67a9fbe630bd62f435694c988f3646fa0602c1e
|
| 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 sha256:7e60969e1684cc952ca893a4a3214ee3106c2aedea456babc2aab138cf120dc6
|
| 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":
|
| 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": 28.342,
|
| 1448 |
"eval_steps_per_second": 7.12,
|
| 1449 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
@@ -1475,7 +1833,7 @@
|
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
-
"total_flos":
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4097523093223572,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 2.078838174273859,
|
| 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": 28.342,
|
| 1448 |
"eval_steps_per_second": 7.12,
|
| 1449 |
"step": 200
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.6701244813278007,
|
| 1453 |
+
"grad_norm": 7.207304954528809,
|
| 1454 |
+
"learning_rate": 4.308566424176336e-05,
|
| 1455 |
+
"loss": 0.5757,
|
| 1456 |
+
"step": 201
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.6784232365145229,
|
| 1460 |
+
"grad_norm": 8.592957496643066,
|
| 1461 |
+
"learning_rate": 4.264272645841419e-05,
|
| 1462 |
+
"loss": 0.487,
|
| 1463 |
+
"step": 202
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.6867219917012448,
|
| 1467 |
+
"grad_norm": 4.523548603057861,
|
| 1468 |
+
"learning_rate": 4.2200378060659116e-05,
|
| 1469 |
+
"loss": 0.1985,
|
| 1470 |
+
"step": 203
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.6950207468879668,
|
| 1474 |
+
"grad_norm": 3.577657699584961,
|
| 1475 |
+
"learning_rate": 4.1758654484692186e-05,
|
| 1476 |
+
"loss": 0.217,
|
| 1477 |
+
"step": 204
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.703319502074689,
|
| 1481 |
+
"grad_norm": 5.221662998199463,
|
| 1482 |
+
"learning_rate": 4.131759111665349e-05,
|
| 1483 |
+
"loss": 0.3242,
|
| 1484 |
+
"step": 205
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.711618257261411,
|
| 1488 |
+
"grad_norm": 4.403975009918213,
|
| 1489 |
+
"learning_rate": 4.087722328979438e-05,
|
| 1490 |
+
"loss": 0.2363,
|
| 1491 |
+
"step": 206
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.7199170124481329,
|
| 1495 |
+
"grad_norm": 4.955993175506592,
|
| 1496 |
+
"learning_rate": 4.043758628164688e-05,
|
| 1497 |
+
"loss": 0.4589,
|
| 1498 |
+
"step": 207
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.7282157676348548,
|
| 1502 |
+
"grad_norm": 5.290609836578369,
|
| 1503 |
+
"learning_rate": 3.9998715311197785e-05,
|
| 1504 |
+
"loss": 0.304,
|
| 1505 |
+
"step": 208
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.7365145228215768,
|
| 1509 |
+
"grad_norm": 4.659958362579346,
|
| 1510 |
+
"learning_rate": 3.956064553606708e-05,
|
| 1511 |
+
"loss": 0.1433,
|
| 1512 |
+
"step": 209
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.7448132780082988,
|
| 1516 |
+
"grad_norm": 6.113132953643799,
|
| 1517 |
+
"learning_rate": 3.912341204969164e-05,
|
| 1518 |
+
"loss": 0.2607,
|
| 1519 |
+
"step": 210
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.7531120331950207,
|
| 1523 |
+
"grad_norm": 7.161942005157471,
|
| 1524 |
+
"learning_rate": 3.86870498785139e-05,
|
| 1525 |
+
"loss": 0.5274,
|
| 1526 |
+
"step": 211
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.7614107883817427,
|
| 1530 |
+
"grad_norm": 7.1513671875,
|
| 1531 |
+
"learning_rate": 3.825159397917589e-05,
|
| 1532 |
+
"loss": 0.4634,
|
| 1533 |
+
"step": 212
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.7697095435684647,
|
| 1537 |
+
"grad_norm": 5.32570219039917,
|
| 1538 |
+
"learning_rate": 3.781707923571891e-05,
|
| 1539 |
+
"loss": 0.1875,
|
| 1540 |
+
"step": 213
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 1.7780082987551866,
|
| 1544 |
+
"grad_norm": 4.187331199645996,
|
| 1545 |
+
"learning_rate": 3.738354045678891e-05,
|
| 1546 |
+
"loss": 0.1516,
|
| 1547 |
+
"step": 214
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.7863070539419086,
|
| 1551 |
+
"grad_norm": 7.296047687530518,
|
| 1552 |
+
"learning_rate": 3.695101237284815e-05,
|
| 1553 |
+
"loss": 0.3847,
|
| 1554 |
+
"step": 215
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.7946058091286305,
|
| 1558 |
+
"grad_norm": 5.951739311218262,
|
| 1559 |
+
"learning_rate": 3.651952963339282e-05,
|
| 1560 |
+
"loss": 0.2656,
|
| 1561 |
+
"step": 216
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.8029045643153527,
|
| 1565 |
+
"grad_norm": 6.873353958129883,
|
| 1566 |
+
"learning_rate": 3.608912680417737e-05,
|
| 1567 |
+
"loss": 0.165,
|
| 1568 |
+
"step": 217
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.8112033195020747,
|
| 1572 |
+
"grad_norm": 6.497419834136963,
|
| 1573 |
+
"learning_rate": 3.5659838364445505e-05,
|
| 1574 |
+
"loss": 0.2504,
|
| 1575 |
+
"step": 218
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 1.8195020746887967,
|
| 1579 |
+
"grad_norm": 7.605969429016113,
|
| 1580 |
+
"learning_rate": 3.523169870416795e-05,
|
| 1581 |
+
"loss": 0.3794,
|
| 1582 |
+
"step": 219
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 1.8278008298755186,
|
| 1586 |
+
"grad_norm": 7.117875576019287,
|
| 1587 |
+
"learning_rate": 3.480474212128766e-05,
|
| 1588 |
+
"loss": 0.3687,
|
| 1589 |
+
"step": 220
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 1.8360995850622408,
|
| 1593 |
+
"grad_norm": 4.442015647888184,
|
| 1594 |
+
"learning_rate": 3.4379002818972124e-05,
|
| 1595 |
+
"loss": 0.2042,
|
| 1596 |
+
"step": 221
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 1.8443983402489628,
|
| 1600 |
+
"grad_norm": 8.238639831542969,
|
| 1601 |
+
"learning_rate": 3.3954514902873425e-05,
|
| 1602 |
+
"loss": 0.5648,
|
| 1603 |
+
"step": 222
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 1.8526970954356847,
|
| 1607 |
+
"grad_norm": 7.620614051818848,
|
| 1608 |
+
"learning_rate": 3.3531312378396026e-05,
|
| 1609 |
+
"loss": 0.3973,
|
| 1610 |
+
"step": 223
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.8609958506224067,
|
| 1614 |
+
"grad_norm": 5.214080333709717,
|
| 1615 |
+
"learning_rate": 3.310942914797265e-05,
|
| 1616 |
+
"loss": 0.2133,
|
| 1617 |
+
"step": 224
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.8692946058091287,
|
| 1621 |
+
"grad_norm": 5.911538600921631,
|
| 1622 |
+
"learning_rate": 3.2688899008348386e-05,
|
| 1623 |
+
"loss": 0.219,
|
| 1624 |
+
"step": 225
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 1.8775933609958506,
|
| 1628 |
+
"grad_norm": 10.658268928527832,
|
| 1629 |
+
"learning_rate": 3.226975564787322e-05,
|
| 1630 |
+
"loss": 0.338,
|
| 1631 |
+
"step": 226
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 1.8858921161825726,
|
| 1635 |
+
"grad_norm": 6.180187702178955,
|
| 1636 |
+
"learning_rate": 3.185203264380338e-05,
|
| 1637 |
+
"loss": 0.2234,
|
| 1638 |
+
"step": 227
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 1.8941908713692945,
|
| 1642 |
+
"grad_norm": 5.702350616455078,
|
| 1643 |
+
"learning_rate": 3.143576345961132e-05,
|
| 1644 |
+
"loss": 0.2215,
|
| 1645 |
+
"step": 228
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 1.9024896265560165,
|
| 1649 |
+
"grad_norm": 2.7787413597106934,
|
| 1650 |
+
"learning_rate": 3.1020981442305184e-05,
|
| 1651 |
+
"loss": 0.0856,
|
| 1652 |
+
"step": 229
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.9107883817427385,
|
| 1656 |
+
"grad_norm": 5.721746921539307,
|
| 1657 |
+
"learning_rate": 3.060771981975726e-05,
|
| 1658 |
+
"loss": 0.3339,
|
| 1659 |
+
"step": 230
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.9190871369294604,
|
| 1663 |
+
"grad_norm": 6.0323567390441895,
|
| 1664 |
+
"learning_rate": 3.019601169804216e-05,
|
| 1665 |
+
"loss": 0.1757,
|
| 1666 |
+
"step": 231
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.9273858921161826,
|
| 1670 |
+
"grad_norm": 8.973467826843262,
|
| 1671 |
+
"learning_rate": 2.978589005878476e-05,
|
| 1672 |
+
"loss": 0.262,
|
| 1673 |
+
"step": 232
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.9356846473029046,
|
| 1677 |
+
"grad_norm": 3.4507062435150146,
|
| 1678 |
+
"learning_rate": 2.9377387756517982e-05,
|
| 1679 |
+
"loss": 0.1235,
|
| 1680 |
+
"step": 233
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.9439834024896265,
|
| 1684 |
+
"grad_norm": 5.919799327850342,
|
| 1685 |
+
"learning_rate": 2.897053751605093e-05,
|
| 1686 |
+
"loss": 0.2862,
|
| 1687 |
+
"step": 234
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 1.9522821576763485,
|
| 1691 |
+
"grad_norm": 4.9692487716674805,
|
| 1692 |
+
"learning_rate": 2.8565371929847284e-05,
|
| 1693 |
+
"loss": 0.1764,
|
| 1694 |
+
"step": 235
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.9605809128630707,
|
| 1698 |
+
"grad_norm": 5.740837574005127,
|
| 1699 |
+
"learning_rate": 2.8161923455414367e-05,
|
| 1700 |
+
"loss": 0.1705,
|
| 1701 |
+
"step": 236
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.9688796680497926,
|
| 1705 |
+
"grad_norm": 5.595933437347412,
|
| 1706 |
+
"learning_rate": 2.776022441270295e-05,
|
| 1707 |
+
"loss": 0.2613,
|
| 1708 |
+
"step": 237
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.9771784232365146,
|
| 1712 |
+
"grad_norm": 4.591209888458252,
|
| 1713 |
+
"learning_rate": 2.7360306981518146e-05,
|
| 1714 |
+
"loss": 0.1906,
|
| 1715 |
+
"step": 238
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.9854771784232366,
|
| 1719 |
+
"grad_norm": 7.699284553527832,
|
| 1720 |
+
"learning_rate": 2.6962203198941587e-05,
|
| 1721 |
+
"loss": 0.4312,
|
| 1722 |
+
"step": 239
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.9937759336099585,
|
| 1726 |
+
"grad_norm": 6.995236873626709,
|
| 1727 |
+
"learning_rate": 2.656594495676482e-05,
|
| 1728 |
+
"loss": 0.3351,
|
| 1729 |
+
"step": 240
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.004149377593361,
|
| 1733 |
+
"grad_norm": 6.956718921661377,
|
| 1734 |
+
"learning_rate": 2.6171563998934605e-05,
|
| 1735 |
+
"loss": 0.2213,
|
| 1736 |
+
"step": 241
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.012448132780083,
|
| 1740 |
+
"grad_norm": 3.839200258255005,
|
| 1741 |
+
"learning_rate": 2.5779091919009877e-05,
|
| 1742 |
+
"loss": 0.2139,
|
| 1743 |
+
"step": 242
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 2.020746887966805,
|
| 1747 |
+
"grad_norm": 1.65491783618927,
|
| 1748 |
+
"learning_rate": 2.5388560157630765e-05,
|
| 1749 |
+
"loss": 0.0616,
|
| 1750 |
+
"step": 243
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 2.029045643153527,
|
| 1754 |
+
"grad_norm": 3.041247606277466,
|
| 1755 |
+
"learning_rate": 2.500000000000001e-05,
|
| 1756 |
+
"loss": 0.0922,
|
| 1757 |
+
"step": 244
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 2.037344398340249,
|
| 1761 |
+
"grad_norm": 1.837149739265442,
|
| 1762 |
+
"learning_rate": 2.461344257337662e-05,
|
| 1763 |
+
"loss": 0.0552,
|
| 1764 |
+
"step": 245
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 2.045643153526971,
|
| 1768 |
+
"grad_norm": 3.2361204624176025,
|
| 1769 |
+
"learning_rate": 2.422891884458241e-05,
|
| 1770 |
+
"loss": 0.0536,
|
| 1771 |
+
"step": 246
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 2.0539419087136928,
|
| 1775 |
+
"grad_norm": 4.026633262634277,
|
| 1776 |
+
"learning_rate": 2.3846459617521128e-05,
|
| 1777 |
+
"loss": 0.2692,
|
| 1778 |
+
"step": 247
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 2.0622406639004147,
|
| 1782 |
+
"grad_norm": 3.3415215015411377,
|
| 1783 |
+
"learning_rate": 2.346609553071093e-05,
|
| 1784 |
+
"loss": 0.0902,
|
| 1785 |
+
"step": 248
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 2.070539419087137,
|
| 1789 |
+
"grad_norm": 0.9877287745475769,
|
| 1790 |
+
"learning_rate": 2.308785705482982e-05,
|
| 1791 |
+
"loss": 0.0222,
|
| 1792 |
+
"step": 249
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 2.078838174273859,
|
| 1796 |
+
"grad_norm": 1.6253547668457031,
|
| 1797 |
+
"learning_rate": 2.2711774490274766e-05,
|
| 1798 |
+
"loss": 0.0311,
|
| 1799 |
+
"step": 250
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 2.078838174273859,
|
| 1803 |
+
"eval_loss": 0.4097523093223572,
|
| 1804 |
+
"eval_runtime": 7.1697,
|
| 1805 |
+
"eval_samples_per_second": 28.314,
|
| 1806 |
+
"eval_steps_per_second": 7.113,
|
| 1807 |
+
"step": 250
|
| 1808 |
}
|
| 1809 |
],
|
| 1810 |
"logging_steps": 1,
|
|
|
|
| 1833 |
"attributes": {}
|
| 1834 |
}
|
| 1835 |
},
|
| 1836 |
+
"total_flos": 9.9341486260224e+16,
|
| 1837 |
"train_batch_size": 8,
|
| 1838 |
"trial_name": null,
|
| 1839 |
"trial_params": null
|