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 201361312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5504b01f824496911206c6925b08a7f5eb88501e7b210146b47c543b883fae
|
| 3 |
size 201361312
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402868986
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b24d0aff819e665e40cc3e1aa115b4339eb6001763fc1c71c2df8be31491b57
|
| 3 |
size 402868986
|
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:faf413ce85e53dad5fd896a4b1ae1aaa2069cef4f2b9073d0ebb053f65f5ccc4
|
| 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 sha256:75baa741c51e818866811bbf8445882df11134e1052988b82271b62eedf5ab53
|
| 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 sha256:380f47f61a8d8eb565b9b87c756b2c3edda1b69f64feb293423756fddb12fc9f
|
| 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 sha256:457d72eb3963f32683229c13f9baa3b831a4fde4ed13fe968d7330b16c2ec80b
|
| 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": 1.
|
| 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": 43.416,
|
| 1480 |
"eval_steps_per_second": 11.288,
|
| 1481 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
@@ -1507,7 +1873,7 @@
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
-
"total_flos": 2.
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.358162522315979,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 1.6191054442420563,
|
| 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": 43.416,
|
| 1480 |
"eval_steps_per_second": 11.288,
|
| 1481 |
"step": 200
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.3017607771706132,
|
| 1485 |
+
"grad_norm": 7.395152568817139,
|
| 1486 |
+
"learning_rate": 6.662093344405984e-05,
|
| 1487 |
+
"loss": 86.9395,
|
| 1488 |
+
"step": 201
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.3082371989475814,
|
| 1492 |
+
"grad_norm": 7.946622371673584,
|
| 1493 |
+
"learning_rate": 6.630953069365224e-05,
|
| 1494 |
+
"loss": 84.3904,
|
| 1495 |
+
"step": 202
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.3147136207245498,
|
| 1499 |
+
"grad_norm": 8.76561164855957,
|
| 1500 |
+
"learning_rate": 6.599754876340666e-05,
|
| 1501 |
+
"loss": 87.8727,
|
| 1502 |
+
"step": 203
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.321190042501518,
|
| 1506 |
+
"grad_norm": 10.111847877502441,
|
| 1507 |
+
"learning_rate": 6.568500363043561e-05,
|
| 1508 |
+
"loss": 88.9806,
|
| 1509 |
+
"step": 204
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.3276664642784861,
|
| 1513 |
+
"grad_norm": 7.7700982093811035,
|
| 1514 |
+
"learning_rate": 6.53719113006941e-05,
|
| 1515 |
+
"loss": 85.9951,
|
| 1516 |
+
"step": 205
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.3341428860554543,
|
| 1520 |
+
"grad_norm": 7.805271148681641,
|
| 1521 |
+
"learning_rate": 6.505828780815993e-05,
|
| 1522 |
+
"loss": 88.9993,
|
| 1523 |
+
"step": 206
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.3406193078324227,
|
| 1527 |
+
"grad_norm": 7.5320258140563965,
|
| 1528 |
+
"learning_rate": 6.474414921401274e-05,
|
| 1529 |
+
"loss": 88.5286,
|
| 1530 |
+
"step": 207
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.3470957296093908,
|
| 1534 |
+
"grad_norm": 11.297571182250977,
|
| 1535 |
+
"learning_rate": 6.442951160581135e-05,
|
| 1536 |
+
"loss": 85.9591,
|
| 1537 |
+
"step": 208
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.353572151386359,
|
| 1541 |
+
"grad_norm": 6.681571006774902,
|
| 1542 |
+
"learning_rate": 6.411439109666985e-05,
|
| 1543 |
+
"loss": 84.0142,
|
| 1544 |
+
"step": 209
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.3600485731633274,
|
| 1548 |
+
"grad_norm": 6.609443187713623,
|
| 1549 |
+
"learning_rate": 6.379880382443258e-05,
|
| 1550 |
+
"loss": 84.1161,
|
| 1551 |
+
"step": 210
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.3665249949402956,
|
| 1555 |
+
"grad_norm": 6.309790134429932,
|
| 1556 |
+
"learning_rate": 6.348276595084753e-05,
|
| 1557 |
+
"loss": 83.4006,
|
| 1558 |
+
"step": 211
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.3730014167172637,
|
| 1562 |
+
"grad_norm": 6.506324768066406,
|
| 1563 |
+
"learning_rate": 6.316629366073878e-05,
|
| 1564 |
+
"loss": 84.3522,
|
| 1565 |
+
"step": 212
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.379477838494232,
|
| 1569 |
+
"grad_norm": 6.594834804534912,
|
| 1570 |
+
"learning_rate": 6.284940316117752e-05,
|
| 1571 |
+
"loss": 83.8696,
|
| 1572 |
+
"step": 213
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.3859542602712,
|
| 1576 |
+
"grad_norm": 7.250606536865234,
|
| 1577 |
+
"learning_rate": 6.253211068065226e-05,
|
| 1578 |
+
"loss": 84.9643,
|
| 1579 |
+
"step": 214
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.3924306820481684,
|
| 1583 |
+
"grad_norm": 8.0385160446167,
|
| 1584 |
+
"learning_rate": 6.221443246823753e-05,
|
| 1585 |
+
"loss": 86.0789,
|
| 1586 |
+
"step": 215
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.3989071038251366,
|
| 1590 |
+
"grad_norm": 8.668357849121094,
|
| 1591 |
+
"learning_rate": 6.189638479276184e-05,
|
| 1592 |
+
"loss": 86.9037,
|
| 1593 |
+
"step": 216
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.4053835256021048,
|
| 1597 |
+
"grad_norm": 12.026268005371094,
|
| 1598 |
+
"learning_rate": 6.157798394197457e-05,
|
| 1599 |
+
"loss": 85.4328,
|
| 1600 |
+
"step": 217
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.4118599473790732,
|
| 1604 |
+
"grad_norm": 7.798686504364014,
|
| 1605 |
+
"learning_rate": 6.125924622171172e-05,
|
| 1606 |
+
"loss": 86.2251,
|
| 1607 |
+
"step": 218
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.4183363691560413,
|
| 1611 |
+
"grad_norm": 7.524980545043945,
|
| 1612 |
+
"learning_rate": 6.094018795506101e-05,
|
| 1613 |
+
"loss": 88.9988,
|
| 1614 |
+
"step": 219
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.4248127909330095,
|
| 1618 |
+
"grad_norm": 7.057831287384033,
|
| 1619 |
+
"learning_rate": 6.062082548152581e-05,
|
| 1620 |
+
"loss": 85.9796,
|
| 1621 |
+
"step": 220
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.4312892127099777,
|
| 1625 |
+
"grad_norm": 6.44320821762085,
|
| 1626 |
+
"learning_rate": 6.030117515618848e-05,
|
| 1627 |
+
"loss": 84.572,
|
| 1628 |
+
"step": 221
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.4377656344869458,
|
| 1632 |
+
"grad_norm": 6.346105098724365,
|
| 1633 |
+
"learning_rate": 5.9981253348872704e-05,
|
| 1634 |
+
"loss": 84.6194,
|
| 1635 |
+
"step": 222
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.4442420562639142,
|
| 1639 |
+
"grad_norm": 6.338534355163574,
|
| 1640 |
+
"learning_rate": 5.966107644330524e-05,
|
| 1641 |
+
"loss": 83.8731,
|
| 1642 |
+
"step": 223
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.4507184780408824,
|
| 1646 |
+
"grad_norm": 6.344674110412598,
|
| 1647 |
+
"learning_rate": 5.934066083627683e-05,
|
| 1648 |
+
"loss": 83.7774,
|
| 1649 |
+
"step": 224
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.4571948998178508,
|
| 1653 |
+
"grad_norm": 7.0422797203063965,
|
| 1654 |
+
"learning_rate": 5.902002293680253e-05,
|
| 1655 |
+
"loss": 86.4043,
|
| 1656 |
+
"step": 225
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.4571948998178508,
|
| 1660 |
+
"eval_loss": 1.3590971231460571,
|
| 1661 |
+
"eval_runtime": 1.1496,
|
| 1662 |
+
"eval_samples_per_second": 43.495,
|
| 1663 |
+
"eval_steps_per_second": 11.309,
|
| 1664 |
+
"step": 225
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.463671321594819,
|
| 1668 |
+
"grad_norm": 7.233029842376709,
|
| 1669 |
+
"learning_rate": 5.869917916528134e-05,
|
| 1670 |
+
"loss": 85.8549,
|
| 1671 |
+
"step": 226
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.470147743371787,
|
| 1675 |
+
"grad_norm": 7.845042705535889,
|
| 1676 |
+
"learning_rate": 5.837814595265534e-05,
|
| 1677 |
+
"loss": 85.77,
|
| 1678 |
+
"step": 227
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.4766241651487553,
|
| 1682 |
+
"grad_norm": 8.548230171203613,
|
| 1683 |
+
"learning_rate": 5.805693973956819e-05,
|
| 1684 |
+
"loss": 87.5861,
|
| 1685 |
+
"step": 228
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.4831005869257234,
|
| 1689 |
+
"grad_norm": 9.914074897766113,
|
| 1690 |
+
"learning_rate": 5.77355769755232e-05,
|
| 1691 |
+
"loss": 87.9156,
|
| 1692 |
+
"step": 229
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.4895770087026918,
|
| 1696 |
+
"grad_norm": 8.572760581970215,
|
| 1697 |
+
"learning_rate": 5.7414074118040863e-05,
|
| 1698 |
+
"loss": 83.0358,
|
| 1699 |
+
"step": 230
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 1.49605343047966,
|
| 1703 |
+
"grad_norm": 8.278693199157715,
|
| 1704 |
+
"learning_rate": 5.709244763181616e-05,
|
| 1705 |
+
"loss": 87.8157,
|
| 1706 |
+
"step": 231
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.5025298522566282,
|
| 1710 |
+
"grad_norm": 8.25027084350586,
|
| 1711 |
+
"learning_rate": 5.677071398787526e-05,
|
| 1712 |
+
"loss": 88.9732,
|
| 1713 |
+
"step": 232
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 1.5090062740335966,
|
| 1717 |
+
"grad_norm": 7.392897129058838,
|
| 1718 |
+
"learning_rate": 5.644888966273209e-05,
|
| 1719 |
+
"loss": 86.2674,
|
| 1720 |
+
"step": 233
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 1.5154826958105647,
|
| 1724 |
+
"grad_norm": 6.923493385314941,
|
| 1725 |
+
"learning_rate": 5.612699113754446e-05,
|
| 1726 |
+
"loss": 84.8558,
|
| 1727 |
+
"step": 234
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 1.5219591175875329,
|
| 1731 |
+
"grad_norm": 6.476316452026367,
|
| 1732 |
+
"learning_rate": 5.5805034897270144e-05,
|
| 1733 |
+
"loss": 84.0044,
|
| 1734 |
+
"step": 235
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.528435539364501,
|
| 1738 |
+
"grad_norm": 6.528478145599365,
|
| 1739 |
+
"learning_rate": 5.5483037429822585e-05,
|
| 1740 |
+
"loss": 84.6853,
|
| 1741 |
+
"step": 236
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 1.5349119611414692,
|
| 1745 |
+
"grad_norm": 6.715808391571045,
|
| 1746 |
+
"learning_rate": 5.516101522522651e-05,
|
| 1747 |
+
"loss": 83.4079,
|
| 1748 |
+
"step": 237
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.5413883829184376,
|
| 1752 |
+
"grad_norm": 7.000762939453125,
|
| 1753 |
+
"learning_rate": 5.483898477477349e-05,
|
| 1754 |
+
"loss": 83.7282,
|
| 1755 |
+
"step": 238
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 1.5478648046954058,
|
| 1759 |
+
"grad_norm": 7.617155075073242,
|
| 1760 |
+
"learning_rate": 5.451696257017742e-05,
|
| 1761 |
+
"loss": 86.2884,
|
| 1762 |
+
"step": 239
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.5543412264723742,
|
| 1766 |
+
"grad_norm": 8.479978561401367,
|
| 1767 |
+
"learning_rate": 5.419496510272985e-05,
|
| 1768 |
+
"loss": 87.1545,
|
| 1769 |
+
"step": 240
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.5608176482493423,
|
| 1773 |
+
"grad_norm": 9.737258911132812,
|
| 1774 |
+
"learning_rate": 5.3873008862455546e-05,
|
| 1775 |
+
"loss": 88.2807,
|
| 1776 |
+
"step": 241
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.5672940700263105,
|
| 1780 |
+
"grad_norm": 13.30903148651123,
|
| 1781 |
+
"learning_rate": 5.355111033726792e-05,
|
| 1782 |
+
"loss": 87.2007,
|
| 1783 |
+
"step": 242
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.5737704918032787,
|
| 1787 |
+
"grad_norm": 7.551815986633301,
|
| 1788 |
+
"learning_rate": 5.3229286012124745e-05,
|
| 1789 |
+
"loss": 86.398,
|
| 1790 |
+
"step": 243
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.5802469135802468,
|
| 1794 |
+
"grad_norm": 7.769435882568359,
|
| 1795 |
+
"learning_rate": 5.2907552368183847e-05,
|
| 1796 |
+
"loss": 87.9565,
|
| 1797 |
+
"step": 244
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.586723335357215,
|
| 1801 |
+
"grad_norm": 7.145780563354492,
|
| 1802 |
+
"learning_rate": 5.258592588195914e-05,
|
| 1803 |
+
"loss": 87.9097,
|
| 1804 |
+
"step": 245
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.5931997571341834,
|
| 1808 |
+
"grad_norm": 6.6358442306518555,
|
| 1809 |
+
"learning_rate": 5.2264423024476816e-05,
|
| 1810 |
+
"loss": 85.2343,
|
| 1811 |
+
"step": 246
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.5996761789111515,
|
| 1815 |
+
"grad_norm": 6.325075626373291,
|
| 1816 |
+
"learning_rate": 5.194306026043181e-05,
|
| 1817 |
+
"loss": 83.2337,
|
| 1818 |
+
"step": 247
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.60615260068812,
|
| 1822 |
+
"grad_norm": 6.256945610046387,
|
| 1823 |
+
"learning_rate": 5.1621854047344665e-05,
|
| 1824 |
+
"loss": 84.8934,
|
| 1825 |
+
"step": 248
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 1.612629022465088,
|
| 1829 |
+
"grad_norm": 6.676874160766602,
|
| 1830 |
+
"learning_rate": 5.1300820834718664e-05,
|
| 1831 |
+
"loss": 82.5999,
|
| 1832 |
+
"step": 249
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 1.6191054442420563,
|
| 1836 |
+
"grad_norm": 6.871759414672852,
|
| 1837 |
+
"learning_rate": 5.0979977063197494e-05,
|
| 1838 |
+
"loss": 85.2274,
|
| 1839 |
+
"step": 250
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.6191054442420563,
|
| 1843 |
+
"eval_loss": 1.358162522315979,
|
| 1844 |
+
"eval_runtime": 1.1489,
|
| 1845 |
+
"eval_samples_per_second": 43.519,
|
| 1846 |
+
"eval_steps_per_second": 11.315,
|
| 1847 |
+
"step": 250
|
| 1848 |
}
|
| 1849 |
],
|
| 1850 |
"logging_steps": 1,
|
|
|
|
| 1873 |
"attributes": {}
|
| 1874 |
}
|
| 1875 |
},
|
| 1876 |
+
"total_flos": 2.967137622687744e+18,
|
| 1877 |
"train_batch_size": 1,
|
| 1878 |
"trial_name": null,
|
| 1879 |
"trial_params": null
|