Training in progress, step 250, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9673f5c538d25226208e38879b11b84e7b08dc590346252753c5765f721b166e
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671466706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc3b7f396e94b5c01515136dab2845f30a8396c6116b3a57a21a501b269973cb
|
| 3 |
size 671466706
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab86666bba215d8157e01ca4c9792340a267e944bc15a3825c4fc06dfcf6769
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95257588fe95d10ac956b632106ff6f12e7937db72584b9a733c438c45ceb5e6
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21e8b4ca53b6fa203a8a39a3f071a2ac443ac0f397a1c60092f796f738b22064
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ff07190894088c64f4a404fba8324ea487de10207a25951b0d8408873174d89
|
| 3 |
size 15024
|
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:ade38049e8578e04485773405771d5332d20ae49fe12dd361f1372908e9c39b6
|
| 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": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1479,6 +1479,372 @@
|
|
| 1479 |
"eval_samples_per_second": 20.272,
|
| 1480 |
"eval_steps_per_second": 5.271,
|
| 1481 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
@@ -1507,7 +1873,7 @@
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
-
"total_flos":
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.25331181287765503,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 1.2936610608020698,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1479 |
"eval_samples_per_second": 20.272,
|
| 1480 |
"eval_steps_per_second": 5.271,
|
| 1481 |
"step": 200
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.0401034928848643,
|
| 1485 |
+
"grad_norm": 23.252429962158203,
|
| 1486 |
+
"learning_rate": 6.662093344405984e-05,
|
| 1487 |
+
"loss": 13.1921,
|
| 1488 |
+
"step": 201
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.0452781371280724,
|
| 1492 |
+
"grad_norm": 28.73088264465332,
|
| 1493 |
+
"learning_rate": 6.630953069365224e-05,
|
| 1494 |
+
"loss": 15.5549,
|
| 1495 |
+
"step": 202
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.0504527813712807,
|
| 1499 |
+
"grad_norm": 31.25390625,
|
| 1500 |
+
"learning_rate": 6.599754876340666e-05,
|
| 1501 |
+
"loss": 15.7923,
|
| 1502 |
+
"step": 203
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.055627425614489,
|
| 1506 |
+
"grad_norm": 30.26934051513672,
|
| 1507 |
+
"learning_rate": 6.568500363043561e-05,
|
| 1508 |
+
"loss": 15.6786,
|
| 1509 |
+
"step": 204
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.0608020698576972,
|
| 1513 |
+
"grad_norm": 28.995391845703125,
|
| 1514 |
+
"learning_rate": 6.53719113006941e-05,
|
| 1515 |
+
"loss": 13.8926,
|
| 1516 |
+
"step": 205
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.0659767141009056,
|
| 1520 |
+
"grad_norm": 30.825397491455078,
|
| 1521 |
+
"learning_rate": 6.505828780815993e-05,
|
| 1522 |
+
"loss": 14.5311,
|
| 1523 |
+
"step": 206
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.071151358344114,
|
| 1527 |
+
"grad_norm": 33.358097076416016,
|
| 1528 |
+
"learning_rate": 6.474414921401274e-05,
|
| 1529 |
+
"loss": 14.9333,
|
| 1530 |
+
"step": 207
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.076326002587322,
|
| 1534 |
+
"grad_norm": 27.46910858154297,
|
| 1535 |
+
"learning_rate": 6.442951160581135e-05,
|
| 1536 |
+
"loss": 14.4327,
|
| 1537 |
+
"step": 208
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.0815006468305304,
|
| 1541 |
+
"grad_norm": 20.020809173583984,
|
| 1542 |
+
"learning_rate": 6.411439109666985e-05,
|
| 1543 |
+
"loss": 13.5841,
|
| 1544 |
+
"step": 209
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.0866752910737387,
|
| 1548 |
+
"grad_norm": 19.188369750976562,
|
| 1549 |
+
"learning_rate": 6.379880382443258e-05,
|
| 1550 |
+
"loss": 13.0085,
|
| 1551 |
+
"step": 210
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.0918499353169469,
|
| 1555 |
+
"grad_norm": 21.89851951599121,
|
| 1556 |
+
"learning_rate": 6.348276595084753e-05,
|
| 1557 |
+
"loss": 13.0352,
|
| 1558 |
+
"step": 211
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.0970245795601552,
|
| 1562 |
+
"grad_norm": 21.02280616760254,
|
| 1563 |
+
"learning_rate": 6.316629366073878e-05,
|
| 1564 |
+
"loss": 12.7803,
|
| 1565 |
+
"step": 212
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.1021992238033635,
|
| 1569 |
+
"grad_norm": 19.258726119995117,
|
| 1570 |
+
"learning_rate": 6.284940316117752e-05,
|
| 1571 |
+
"loss": 12.5569,
|
| 1572 |
+
"step": 213
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.107373868046572,
|
| 1576 |
+
"grad_norm": 20.88226890563965,
|
| 1577 |
+
"learning_rate": 6.253211068065226e-05,
|
| 1578 |
+
"loss": 13.1239,
|
| 1579 |
+
"step": 214
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.11254851228978,
|
| 1583 |
+
"grad_norm": 31.86823081970215,
|
| 1584 |
+
"learning_rate": 6.221443246823753e-05,
|
| 1585 |
+
"loss": 16.8635,
|
| 1586 |
+
"step": 215
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.1177231565329884,
|
| 1590 |
+
"grad_norm": 31.060880661010742,
|
| 1591 |
+
"learning_rate": 6.189638479276184e-05,
|
| 1592 |
+
"loss": 15.6448,
|
| 1593 |
+
"step": 216
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.1228978007761967,
|
| 1597 |
+
"grad_norm": 31.630598068237305,
|
| 1598 |
+
"learning_rate": 6.157798394197457e-05,
|
| 1599 |
+
"loss": 14.1736,
|
| 1600 |
+
"step": 217
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.1280724450194048,
|
| 1604 |
+
"grad_norm": 32.00862503051758,
|
| 1605 |
+
"learning_rate": 6.125924622171172e-05,
|
| 1606 |
+
"loss": 13.641,
|
| 1607 |
+
"step": 218
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.1332470892626132,
|
| 1611 |
+
"grad_norm": 27.68526840209961,
|
| 1612 |
+
"learning_rate": 6.094018795506101e-05,
|
| 1613 |
+
"loss": 14.6795,
|
| 1614 |
+
"step": 219
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.1384217335058215,
|
| 1618 |
+
"grad_norm": 25.928890228271484,
|
| 1619 |
+
"learning_rate": 6.062082548152581e-05,
|
| 1620 |
+
"loss": 14.1199,
|
| 1621 |
+
"step": 220
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.1435963777490297,
|
| 1625 |
+
"grad_norm": 20.779417037963867,
|
| 1626 |
+
"learning_rate": 6.030117515618848e-05,
|
| 1627 |
+
"loss": 13.4476,
|
| 1628 |
+
"step": 221
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.148771021992238,
|
| 1632 |
+
"grad_norm": 19.63215446472168,
|
| 1633 |
+
"learning_rate": 5.9981253348872704e-05,
|
| 1634 |
+
"loss": 13.0655,
|
| 1635 |
+
"step": 222
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.1539456662354464,
|
| 1639 |
+
"grad_norm": 18.548025131225586,
|
| 1640 |
+
"learning_rate": 5.966107644330524e-05,
|
| 1641 |
+
"loss": 12.8281,
|
| 1642 |
+
"step": 223
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.1591203104786545,
|
| 1646 |
+
"grad_norm": 18.990293502807617,
|
| 1647 |
+
"learning_rate": 5.934066083627683e-05,
|
| 1648 |
+
"loss": 13.0235,
|
| 1649 |
+
"step": 224
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.1642949547218628,
|
| 1653 |
+
"grad_norm": 18.953563690185547,
|
| 1654 |
+
"learning_rate": 5.902002293680253e-05,
|
| 1655 |
+
"loss": 12.7765,
|
| 1656 |
+
"step": 225
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.1642949547218628,
|
| 1660 |
+
"eval_loss": 0.25752800703048706,
|
| 1661 |
+
"eval_runtime": 2.4647,
|
| 1662 |
+
"eval_samples_per_second": 20.287,
|
| 1663 |
+
"eval_steps_per_second": 5.275,
|
| 1664 |
+
"step": 225
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.1694695989650712,
|
| 1668 |
+
"grad_norm": 18.577194213867188,
|
| 1669 |
+
"learning_rate": 5.869917916528134e-05,
|
| 1670 |
+
"loss": 12.4563,
|
| 1671 |
+
"step": 226
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.1746442432082795,
|
| 1675 |
+
"grad_norm": 26.236631393432617,
|
| 1676 |
+
"learning_rate": 5.837814595265534e-05,
|
| 1677 |
+
"loss": 15.1902,
|
| 1678 |
+
"step": 227
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.1798188874514877,
|
| 1682 |
+
"grad_norm": 32.05315017700195,
|
| 1683 |
+
"learning_rate": 5.805693973956819e-05,
|
| 1684 |
+
"loss": 16.2573,
|
| 1685 |
+
"step": 228
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.184993531694696,
|
| 1689 |
+
"grad_norm": 30.340524673461914,
|
| 1690 |
+
"learning_rate": 5.77355769755232e-05,
|
| 1691 |
+
"loss": 14.6824,
|
| 1692 |
+
"step": 229
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.1901681759379044,
|
| 1696 |
+
"grad_norm": 32.33549499511719,
|
| 1697 |
+
"learning_rate": 5.7414074118040863e-05,
|
| 1698 |
+
"loss": 14.5922,
|
| 1699 |
+
"step": 230
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 1.1953428201811125,
|
| 1703 |
+
"grad_norm": 29.838163375854492,
|
| 1704 |
+
"learning_rate": 5.709244763181616e-05,
|
| 1705 |
+
"loss": 13.9425,
|
| 1706 |
+
"step": 231
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.2005174644243208,
|
| 1710 |
+
"grad_norm": 24.2996883392334,
|
| 1711 |
+
"learning_rate": 5.677071398787526e-05,
|
| 1712 |
+
"loss": 14.2088,
|
| 1713 |
+
"step": 232
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 1.2056921086675292,
|
| 1717 |
+
"grad_norm": 22.018768310546875,
|
| 1718 |
+
"learning_rate": 5.644888966273209e-05,
|
| 1719 |
+
"loss": 13.7443,
|
| 1720 |
+
"step": 233
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 1.2108667529107373,
|
| 1724 |
+
"grad_norm": 20.227397918701172,
|
| 1725 |
+
"learning_rate": 5.612699113754446e-05,
|
| 1726 |
+
"loss": 13.9549,
|
| 1727 |
+
"step": 234
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 1.2160413971539457,
|
| 1731 |
+
"grad_norm": 18.701120376586914,
|
| 1732 |
+
"learning_rate": 5.5805034897270144e-05,
|
| 1733 |
+
"loss": 13.0652,
|
| 1734 |
+
"step": 235
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.221216041397154,
|
| 1738 |
+
"grad_norm": 18.025367736816406,
|
| 1739 |
+
"learning_rate": 5.5483037429822585e-05,
|
| 1740 |
+
"loss": 12.821,
|
| 1741 |
+
"step": 236
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 1.2263906856403621,
|
| 1745 |
+
"grad_norm": 18.975017547607422,
|
| 1746 |
+
"learning_rate": 5.516101522522651e-05,
|
| 1747 |
+
"loss": 12.5231,
|
| 1748 |
+
"step": 237
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.2315653298835705,
|
| 1752 |
+
"grad_norm": 18.821386337280273,
|
| 1753 |
+
"learning_rate": 5.483898477477349e-05,
|
| 1754 |
+
"loss": 12.1627,
|
| 1755 |
+
"step": 238
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 1.2367399741267788,
|
| 1759 |
+
"grad_norm": 20.068571090698242,
|
| 1760 |
+
"learning_rate": 5.451696257017742e-05,
|
| 1761 |
+
"loss": 12.9422,
|
| 1762 |
+
"step": 239
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.2419146183699872,
|
| 1766 |
+
"grad_norm": 29.721097946166992,
|
| 1767 |
+
"learning_rate": 5.419496510272985e-05,
|
| 1768 |
+
"loss": 16.7573,
|
| 1769 |
+
"step": 240
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.2470892626131953,
|
| 1773 |
+
"grad_norm": 30.7767333984375,
|
| 1774 |
+
"learning_rate": 5.3873008862455546e-05,
|
| 1775 |
+
"loss": 15.5081,
|
| 1776 |
+
"step": 241
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.2522639068564037,
|
| 1780 |
+
"grad_norm": 33.22428512573242,
|
| 1781 |
+
"learning_rate": 5.355111033726792e-05,
|
| 1782 |
+
"loss": 14.5065,
|
| 1783 |
+
"step": 242
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.2574385510996118,
|
| 1787 |
+
"grad_norm": 34.72373580932617,
|
| 1788 |
+
"learning_rate": 5.3229286012124745e-05,
|
| 1789 |
+
"loss": 13.6778,
|
| 1790 |
+
"step": 243
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.2626131953428201,
|
| 1794 |
+
"grad_norm": 28.375368118286133,
|
| 1795 |
+
"learning_rate": 5.2907552368183847e-05,
|
| 1796 |
+
"loss": 13.8995,
|
| 1797 |
+
"step": 244
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.2677878395860285,
|
| 1801 |
+
"grad_norm": 23.931262969970703,
|
| 1802 |
+
"learning_rate": 5.258592588195914e-05,
|
| 1803 |
+
"loss": 14.0703,
|
| 1804 |
+
"step": 245
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.2729624838292368,
|
| 1808 |
+
"grad_norm": 22.0262451171875,
|
| 1809 |
+
"learning_rate": 5.2264423024476816e-05,
|
| 1810 |
+
"loss": 13.3074,
|
| 1811 |
+
"step": 246
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.278137128072445,
|
| 1815 |
+
"grad_norm": 19.251508712768555,
|
| 1816 |
+
"learning_rate": 5.194306026043181e-05,
|
| 1817 |
+
"loss": 13.1502,
|
| 1818 |
+
"step": 247
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.2833117723156533,
|
| 1822 |
+
"grad_norm": 19.375770568847656,
|
| 1823 |
+
"learning_rate": 5.1621854047344665e-05,
|
| 1824 |
+
"loss": 13.1682,
|
| 1825 |
+
"step": 248
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 1.2884864165588616,
|
| 1829 |
+
"grad_norm": 19.607303619384766,
|
| 1830 |
+
"learning_rate": 5.1300820834718664e-05,
|
| 1831 |
+
"loss": 12.7231,
|
| 1832 |
+
"step": 249
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 1.2936610608020698,
|
| 1836 |
+
"grad_norm": 19.82145118713379,
|
| 1837 |
+
"learning_rate": 5.0979977063197494e-05,
|
| 1838 |
+
"loss": 12.3949,
|
| 1839 |
+
"step": 250
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.2936610608020698,
|
| 1843 |
+
"eval_loss": 0.25331181287765503,
|
| 1844 |
+
"eval_runtime": 2.4661,
|
| 1845 |
+
"eval_samples_per_second": 20.275,
|
| 1846 |
+
"eval_steps_per_second": 5.271,
|
| 1847 |
+
"step": 250
|
| 1848 |
}
|
| 1849 |
],
|
| 1850 |
"logging_steps": 1,
|
|
|
|
| 1873 |
"attributes": {}
|
| 1874 |
}
|
| 1875 |
},
|
| 1876 |
+
"total_flos": 5.834834404442112e+18,
|
| 1877 |
"train_batch_size": 1,
|
| 1878 |
"trial_name": null,
|
| 1879 |
"trial_params": null
|