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 13587864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cce123c0683ef9cd6975eb4e7a421ac1277037ddb1f56ad868f4857ff4175af
|
| 3 |
size 13587864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27273018
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8682728647446457022a625059062c8515250852f037491dc6e4ba299841c1d0
|
| 3 |
size 27273018
|
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 sha256:050e050c2c08370bd1f9ba1c8620beabe7ff029584c29e4cd6c089022f033e90
|
| 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 sha256:0cf8a26ba280c3e7ef5570adf2f8b789f2d472d32e5416b32aa7525b9226e0be
|
| 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:f3fbc12a030d5fdd31b311d40ef25f1be4dcd3dcc88032d5c293f225b052d01f
|
| 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 sha256:39522c45970a3ae5ecbf73e1051ca4989117a8b949dcd4b7f4ee9663321048b0
|
| 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:b8f008ed445b652736016defc4807eff9b5ec48a500ab7e9db898ce35023867e
|
| 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": 177.685,
|
| 1480 |
"eval_steps_per_second": 46.198,
|
| 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": 1.6708096265792847,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 1.9065776930409915,
|
| 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": 177.685,
|
| 1480 |
"eval_steps_per_second": 46.198,
|
| 1481 |
"step": 200
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.532888465204957,
|
| 1485 |
+
"grad_norm": 0.382758229970932,
|
| 1486 |
+
"learning_rate": 6.722664380155198e-05,
|
| 1487 |
+
"loss": 1.6259,
|
| 1488 |
+
"step": 201
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.5405147759771212,
|
| 1492 |
+
"grad_norm": 0.3803237974643707,
|
| 1493 |
+
"learning_rate": 6.609167332422427e-05,
|
| 1494 |
+
"loss": 1.5547,
|
| 1495 |
+
"step": 202
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.548141086749285,
|
| 1499 |
+
"grad_norm": 0.4076535701751709,
|
| 1500 |
+
"learning_rate": 6.497159807708055e-05,
|
| 1501 |
+
"loss": 1.5846,
|
| 1502 |
+
"step": 203
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.555767397521449,
|
| 1506 |
+
"grad_norm": 0.41619113087654114,
|
| 1507 |
+
"learning_rate": 6.386658673933301e-05,
|
| 1508 |
+
"loss": 1.6648,
|
| 1509 |
+
"step": 204
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.5633937082936131,
|
| 1513 |
+
"grad_norm": 0.4555559754371643,
|
| 1514 |
+
"learning_rate": 6.277680572162459e-05,
|
| 1515 |
+
"loss": 1.6636,
|
| 1516 |
+
"step": 205
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.5710200190657768,
|
| 1520 |
+
"grad_norm": 0.5715373158454895,
|
| 1521 |
+
"learning_rate": 6.170241914096804e-05,
|
| 1522 |
+
"loss": 1.7265,
|
| 1523 |
+
"step": 206
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.578646329837941,
|
| 1527 |
+
"grad_norm": 0.39986926317214966,
|
| 1528 |
+
"learning_rate": 6.06435887960305e-05,
|
| 1529 |
+
"loss": 1.614,
|
| 1530 |
+
"step": 207
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.5862726406101049,
|
| 1534 |
+
"grad_norm": 0.4014238119125366,
|
| 1535 |
+
"learning_rate": 5.960047414276724e-05,
|
| 1536 |
+
"loss": 1.5169,
|
| 1537 |
+
"step": 208
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.5938989513822688,
|
| 1541 |
+
"grad_norm": 0.40676450729370117,
|
| 1542 |
+
"learning_rate": 5.857323227040816e-05,
|
| 1543 |
+
"loss": 1.5836,
|
| 1544 |
+
"step": 209
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.601525262154433,
|
| 1548 |
+
"grad_norm": 0.38130614161491394,
|
| 1549 |
+
"learning_rate": 5.756201787780074e-05,
|
| 1550 |
+
"loss": 1.5636,
|
| 1551 |
+
"step": 210
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.6091515729265966,
|
| 1555 |
+
"grad_norm": 0.4001769721508026,
|
| 1556 |
+
"learning_rate": 5.656698325011295e-05,
|
| 1557 |
+
"loss": 1.5641,
|
| 1558 |
+
"step": 211
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.6167778836987607,
|
| 1562 |
+
"grad_norm": 0.3762960433959961,
|
| 1563 |
+
"learning_rate": 5.5588278235899724e-05,
|
| 1564 |
+
"loss": 1.615,
|
| 1565 |
+
"step": 212
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.6244041944709247,
|
| 1569 |
+
"grad_norm": 0.372916042804718,
|
| 1570 |
+
"learning_rate": 5.462605022453621e-05,
|
| 1571 |
+
"loss": 1.6307,
|
| 1572 |
+
"step": 213
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.6320305052430886,
|
| 1576 |
+
"grad_norm": 0.4022381603717804,
|
| 1577 |
+
"learning_rate": 5.368044412402161e-05,
|
| 1578 |
+
"loss": 1.5634,
|
| 1579 |
+
"step": 214
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.6396568160152527,
|
| 1583 |
+
"grad_norm": 0.39602571725845337,
|
| 1584 |
+
"learning_rate": 5.275160233915637e-05,
|
| 1585 |
+
"loss": 1.6328,
|
| 1586 |
+
"step": 215
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.6472831267874166,
|
| 1590 |
+
"grad_norm": 0.4366743266582489,
|
| 1591 |
+
"learning_rate": 5.183966475009686e-05,
|
| 1592 |
+
"loss": 1.6038,
|
| 1593 |
+
"step": 216
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.6549094375595805,
|
| 1597 |
+
"grad_norm": 0.458132803440094,
|
| 1598 |
+
"learning_rate": 5.0944768691289534e-05,
|
| 1599 |
+
"loss": 1.6384,
|
| 1600 |
+
"step": 217
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.6625357483317447,
|
| 1604 |
+
"grad_norm": 0.4853437840938568,
|
| 1605 |
+
"learning_rate": 5.0067048930789196e-05,
|
| 1606 |
+
"loss": 1.6787,
|
| 1607 |
+
"step": 218
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.6701620591039084,
|
| 1611 |
+
"grad_norm": 0.4034062325954437,
|
| 1612 |
+
"learning_rate": 4.920663764996328e-05,
|
| 1613 |
+
"loss": 1.5721,
|
| 1614 |
+
"step": 219
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.6777883698760725,
|
| 1618 |
+
"grad_norm": 0.4523112177848816,
|
| 1619 |
+
"learning_rate": 4.8363664423585795e-05,
|
| 1620 |
+
"loss": 1.6327,
|
| 1621 |
+
"step": 220
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.6854146806482364,
|
| 1625 |
+
"grad_norm": 0.4193178415298462,
|
| 1626 |
+
"learning_rate": 4.753825620032397e-05,
|
| 1627 |
+
"loss": 1.5354,
|
| 1628 |
+
"step": 221
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.6930409914204003,
|
| 1632 |
+
"grad_norm": 0.3819790482521057,
|
| 1633 |
+
"learning_rate": 4.673053728362012e-05,
|
| 1634 |
+
"loss": 1.5833,
|
| 1635 |
+
"step": 222
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.7006673021925645,
|
| 1639 |
+
"grad_norm": 0.3742893636226654,
|
| 1640 |
+
"learning_rate": 4.5940629312972085e-05,
|
| 1641 |
+
"loss": 1.5805,
|
| 1642 |
+
"step": 223
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.7082936129647281,
|
| 1646 |
+
"grad_norm": 0.37698328495025635,
|
| 1647 |
+
"learning_rate": 4.516865124561473e-05,
|
| 1648 |
+
"loss": 1.5632,
|
| 1649 |
+
"step": 224
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.7159199237368923,
|
| 1653 |
+
"grad_norm": 0.39410701394081116,
|
| 1654 |
+
"learning_rate": 4.4414719338605445e-05,
|
| 1655 |
+
"loss": 1.6016,
|
| 1656 |
+
"step": 225
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.7159199237368923,
|
| 1660 |
+
"eval_loss": 1.6763724088668823,
|
| 1661 |
+
"eval_runtime": 0.281,
|
| 1662 |
+
"eval_samples_per_second": 177.963,
|
| 1663 |
+
"eval_steps_per_second": 46.27,
|
| 1664 |
+
"step": 225
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.7235462345090562,
|
| 1668 |
+
"grad_norm": 0.41081416606903076,
|
| 1669 |
+
"learning_rate": 4.367894713131622e-05,
|
| 1670 |
+
"loss": 1.5998,
|
| 1671 |
+
"step": 226
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.73117254528122,
|
| 1675 |
+
"grad_norm": 0.4001181721687317,
|
| 1676 |
+
"learning_rate": 4.296144542833515e-05,
|
| 1677 |
+
"loss": 1.6213,
|
| 1678 |
+
"step": 227
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.7387988560533842,
|
| 1682 |
+
"grad_norm": 0.4368586242198944,
|
| 1683 |
+
"learning_rate": 4.226232228277948e-05,
|
| 1684 |
+
"loss": 1.6338,
|
| 1685 |
+
"step": 228
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.7464251668255482,
|
| 1689 |
+
"grad_norm": 0.4104710817337036,
|
| 1690 |
+
"learning_rate": 4.1581682980023354e-05,
|
| 1691 |
+
"loss": 1.6433,
|
| 1692 |
+
"step": 229
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.754051477597712,
|
| 1696 |
+
"grad_norm": 0.4876128137111664,
|
| 1697 |
+
"learning_rate": 4.0919630021842204e-05,
|
| 1698 |
+
"loss": 1.6381,
|
| 1699 |
+
"step": 230
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 1.7616777883698762,
|
| 1703 |
+
"grad_norm": 0.5875245332717896,
|
| 1704 |
+
"learning_rate": 4.027626311097629e-05,
|
| 1705 |
+
"loss": 1.7134,
|
| 1706 |
+
"step": 231
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.76930409914204,
|
| 1710 |
+
"grad_norm": 0.40997183322906494,
|
| 1711 |
+
"learning_rate": 3.965167913611591e-05,
|
| 1712 |
+
"loss": 1.5599,
|
| 1713 |
+
"step": 232
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 1.776930409914204,
|
| 1717 |
+
"grad_norm": 0.42695024609565735,
|
| 1718 |
+
"learning_rate": 3.9045972157310256e-05,
|
| 1719 |
+
"loss": 1.5685,
|
| 1720 |
+
"step": 233
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 1.784556720686368,
|
| 1724 |
+
"grad_norm": 0.4017082452774048,
|
| 1725 |
+
"learning_rate": 3.845923339180239e-05,
|
| 1726 |
+
"loss": 1.5493,
|
| 1727 |
+
"step": 234
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 1.7921830314585319,
|
| 1731 |
+
"grad_norm": 0.38347816467285156,
|
| 1732 |
+
"learning_rate": 3.78915512002922e-05,
|
| 1733 |
+
"loss": 1.5464,
|
| 1734 |
+
"step": 235
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 1.799809342230696,
|
| 1738 |
+
"grad_norm": 0.40365535020828247,
|
| 1739 |
+
"learning_rate": 3.734301107362964e-05,
|
| 1740 |
+
"loss": 1.6257,
|
| 1741 |
+
"step": 236
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 1.80743565300286,
|
| 1745 |
+
"grad_norm": 0.3748120963573456,
|
| 1746 |
+
"learning_rate": 3.681369561994005e-05,
|
| 1747 |
+
"loss": 1.5456,
|
| 1748 |
+
"step": 237
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.8150619637750238,
|
| 1752 |
+
"grad_norm": 0.36911335587501526,
|
| 1753 |
+
"learning_rate": 3.6303684552183827e-05,
|
| 1754 |
+
"loss": 1.5886,
|
| 1755 |
+
"step": 238
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 1.822688274547188,
|
| 1759 |
+
"grad_norm": 0.3796713948249817,
|
| 1760 |
+
"learning_rate": 3.581305467615181e-05,
|
| 1761 |
+
"loss": 1.5858,
|
| 1762 |
+
"step": 239
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.8303145853193517,
|
| 1766 |
+
"grad_norm": 0.4003843665122986,
|
| 1767 |
+
"learning_rate": 3.5341879878898615e-05,
|
| 1768 |
+
"loss": 1.6126,
|
| 1769 |
+
"step": 240
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.8379408960915158,
|
| 1773 |
+
"grad_norm": 0.4427483379840851,
|
| 1774 |
+
"learning_rate": 3.489023111761562e-05,
|
| 1775 |
+
"loss": 1.6487,
|
| 1776 |
+
"step": 241
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.8455672068636797,
|
| 1780 |
+
"grad_norm": 0.4299188554286957,
|
| 1781 |
+
"learning_rate": 3.445817640894497e-05,
|
| 1782 |
+
"loss": 1.6723,
|
| 1783 |
+
"step": 242
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.8531935176358436,
|
| 1787 |
+
"grad_norm": 0.5241357684135437,
|
| 1788 |
+
"learning_rate": 3.404578081873656e-05,
|
| 1789 |
+
"loss": 1.6198,
|
| 1790 |
+
"step": 243
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.8608198284080077,
|
| 1794 |
+
"grad_norm": 0.40499526262283325,
|
| 1795 |
+
"learning_rate": 3.365310645224939e-05,
|
| 1796 |
+
"loss": 1.5758,
|
| 1797 |
+
"step": 244
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.8684461391801714,
|
| 1801 |
+
"grad_norm": 0.43495872616767883,
|
| 1802 |
+
"learning_rate": 3.328021244479866e-05,
|
| 1803 |
+
"loss": 1.5897,
|
| 1804 |
+
"step": 245
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.8760724499523356,
|
| 1808 |
+
"grad_norm": 0.39778581261634827,
|
| 1809 |
+
"learning_rate": 3.292715495285028e-05,
|
| 1810 |
+
"loss": 1.5267,
|
| 1811 |
+
"step": 246
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.8836987607244995,
|
| 1815 |
+
"grad_norm": 0.3671037256717682,
|
| 1816 |
+
"learning_rate": 3.259398714556389e-05,
|
| 1817 |
+
"loss": 1.5499,
|
| 1818 |
+
"step": 247
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.8913250714966634,
|
| 1822 |
+
"grad_norm": 0.38671308755874634,
|
| 1823 |
+
"learning_rate": 3.2280759196785803e-05,
|
| 1824 |
+
"loss": 1.628,
|
| 1825 |
+
"step": 248
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 1.8989513822688275,
|
| 1829 |
+
"grad_norm": 0.41623926162719727,
|
| 1830 |
+
"learning_rate": 3.1987518277492934e-05,
|
| 1831 |
+
"loss": 1.5699,
|
| 1832 |
+
"step": 249
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 1.9065776930409915,
|
| 1836 |
+
"grad_norm": 0.38484105467796326,
|
| 1837 |
+
"learning_rate": 3.171430854868911e-05,
|
| 1838 |
+
"loss": 1.5702,
|
| 1839 |
+
"step": 250
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.9065776930409915,
|
| 1843 |
+
"eval_loss": 1.6708096265792847,
|
| 1844 |
+
"eval_runtime": 0.2807,
|
| 1845 |
+
"eval_samples_per_second": 178.136,
|
| 1846 |
+
"eval_steps_per_second": 46.315,
|
| 1847 |
+
"step": 250
|
| 1848 |
}
|
| 1849 |
],
|
| 1850 |
"logging_steps": 1,
|
|
|
|
| 1873 |
"attributes": {}
|
| 1874 |
}
|
| 1875 |
},
|
| 1876 |
+
"total_flos": 1.11070068867072e+17,
|
| 1877 |
"train_batch_size": 1,
|
| 1878 |
"trial_name": null,
|
| 1879 |
"trial_params": null
|