Training in progress, step 5000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +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 +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 244223098
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90cea3a8340cec08e34ced4da765631e6db28abf8817feeed163c0e9c4b11ac3
|
| 3 |
size 244223098
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 381944306
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:912b33949a4c4a5135f3934f50a931c756811b6fce9fd2d0fc113fe06b76e2ff
|
| 3 |
size 381944306
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:713f31844510266a6aaf0fd1a741e369134d7639e6348f2c3f314fbeefcc20d5
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52545127c71a1946352fb17594e3e07a11f861d44a5967e65c013fc075f2b33b
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64acbf91972e1bafe6a29fc33ce22360fae9505884f49f47fc18fd23b4185146
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:792a97342813a4d8afe83608b0715e6c9006e4c3a6e127f187733d5eda7e9ecd
|
| 3 |
size 14960
|
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:fa0463e866a9b23c4e6a252da90bbf03928b724cc52f61d6cbe8645375c20dbd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1408,6 +1408,356 @@
|
|
| 1408 |
"learning_rate": 0.0004991359333204263,
|
| 1409 |
"loss": 31.326,
|
| 1410 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 20,
|
|
@@ -1427,7 +1777,7 @@
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
-
"total_flos":
|
| 1431 |
"train_batch_size": 48,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.007406573482096831,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1408 |
"learning_rate": 0.0004991359333204263,
|
| 1409 |
"loss": 31.326,
|
| 1410 |
"step": 4000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.0059548850796058515,
|
| 1414 |
+
"grad_norm": 36.0,
|
| 1415 |
+
"learning_rate": 0.0004991309943854187,
|
| 1416 |
+
"loss": 31.2502,
|
| 1417 |
+
"step": 4020
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.005984511373534239,
|
| 1421 |
+
"grad_norm": 28.125,
|
| 1422 |
+
"learning_rate": 0.0004991260554504111,
|
| 1423 |
+
"loss": 31.206,
|
| 1424 |
+
"step": 4040
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.006014137667462626,
|
| 1428 |
+
"grad_norm": 27.875,
|
| 1429 |
+
"learning_rate": 0.0004991211165154035,
|
| 1430 |
+
"loss": 31.1183,
|
| 1431 |
+
"step": 4060
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.006043763961391013,
|
| 1435 |
+
"grad_norm": 26.625,
|
| 1436 |
+
"learning_rate": 0.000499116177580396,
|
| 1437 |
+
"loss": 31.0616,
|
| 1438 |
+
"step": 4080
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.006073390255319401,
|
| 1442 |
+
"grad_norm": 33.25,
|
| 1443 |
+
"learning_rate": 0.0004991112386453884,
|
| 1444 |
+
"loss": 31.0764,
|
| 1445 |
+
"step": 4100
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.006103016549247788,
|
| 1449 |
+
"grad_norm": 33.25,
|
| 1450 |
+
"learning_rate": 0.0004991062997103809,
|
| 1451 |
+
"loss": 31.1013,
|
| 1452 |
+
"step": 4120
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.006132642843176175,
|
| 1456 |
+
"grad_norm": 25.875,
|
| 1457 |
+
"learning_rate": 0.0004991013607753733,
|
| 1458 |
+
"loss": 30.9594,
|
| 1459 |
+
"step": 4140
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.006162269137104563,
|
| 1463 |
+
"grad_norm": 35.5,
|
| 1464 |
+
"learning_rate": 0.0004990964218403658,
|
| 1465 |
+
"loss": 30.9666,
|
| 1466 |
+
"step": 4160
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.00619189543103295,
|
| 1470 |
+
"grad_norm": 31.125,
|
| 1471 |
+
"learning_rate": 0.0004990914829053582,
|
| 1472 |
+
"loss": 30.9864,
|
| 1473 |
+
"step": 4180
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.006221521724961337,
|
| 1477 |
+
"grad_norm": 39.75,
|
| 1478 |
+
"learning_rate": 0.0004990865439703506,
|
| 1479 |
+
"loss": 30.8923,
|
| 1480 |
+
"step": 4200
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.006251148018889725,
|
| 1484 |
+
"grad_norm": 36.75,
|
| 1485 |
+
"learning_rate": 0.0004990816050353431,
|
| 1486 |
+
"loss": 30.8131,
|
| 1487 |
+
"step": 4220
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.006280774312818112,
|
| 1491 |
+
"grad_norm": 33.25,
|
| 1492 |
+
"learning_rate": 0.0004990766661003355,
|
| 1493 |
+
"loss": 30.7942,
|
| 1494 |
+
"step": 4240
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.006310400606746499,
|
| 1498 |
+
"grad_norm": 25.625,
|
| 1499 |
+
"learning_rate": 0.0004990717271653279,
|
| 1500 |
+
"loss": 30.6945,
|
| 1501 |
+
"step": 4260
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.006340026900674887,
|
| 1505 |
+
"grad_norm": 36.5,
|
| 1506 |
+
"learning_rate": 0.0004990667882303204,
|
| 1507 |
+
"loss": 30.5995,
|
| 1508 |
+
"step": 4280
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.006369653194603274,
|
| 1512 |
+
"grad_norm": 29.0,
|
| 1513 |
+
"learning_rate": 0.0004990618492953128,
|
| 1514 |
+
"loss": 30.6263,
|
| 1515 |
+
"step": 4300
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.006399279488531661,
|
| 1519 |
+
"grad_norm": 25.625,
|
| 1520 |
+
"learning_rate": 0.0004990569103603052,
|
| 1521 |
+
"loss": 30.5024,
|
| 1522 |
+
"step": 4320
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.0064289057824600485,
|
| 1526 |
+
"grad_norm": 27.375,
|
| 1527 |
+
"learning_rate": 0.0004990519714252977,
|
| 1528 |
+
"loss": 30.5216,
|
| 1529 |
+
"step": 4340
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.006458532076388436,
|
| 1533 |
+
"grad_norm": 29.625,
|
| 1534 |
+
"learning_rate": 0.00049904703249029,
|
| 1535 |
+
"loss": 30.4789,
|
| 1536 |
+
"step": 4360
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.006488158370316823,
|
| 1540 |
+
"grad_norm": 29.0,
|
| 1541 |
+
"learning_rate": 0.0004990420935552825,
|
| 1542 |
+
"loss": 30.3852,
|
| 1543 |
+
"step": 4380
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.006517784664245211,
|
| 1547 |
+
"grad_norm": 36.25,
|
| 1548 |
+
"learning_rate": 0.0004990371546202749,
|
| 1549 |
+
"loss": 30.4001,
|
| 1550 |
+
"step": 4400
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.006547410958173599,
|
| 1554 |
+
"grad_norm": 27.75,
|
| 1555 |
+
"learning_rate": 0.0004990322156852673,
|
| 1556 |
+
"loss": 30.4478,
|
| 1557 |
+
"step": 4420
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.006577037252101986,
|
| 1561 |
+
"grad_norm": 35.25,
|
| 1562 |
+
"learning_rate": 0.0004990272767502597,
|
| 1563 |
+
"loss": 30.3411,
|
| 1564 |
+
"step": 4440
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.006606663546030373,
|
| 1568 |
+
"grad_norm": 25.625,
|
| 1569 |
+
"learning_rate": 0.0004990223378152522,
|
| 1570 |
+
"loss": 30.2584,
|
| 1571 |
+
"step": 4460
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.006636289839958761,
|
| 1575 |
+
"grad_norm": 27.625,
|
| 1576 |
+
"learning_rate": 0.0004990173988802446,
|
| 1577 |
+
"loss": 30.2584,
|
| 1578 |
+
"step": 4480
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.006665916133887148,
|
| 1582 |
+
"grad_norm": 28.25,
|
| 1583 |
+
"learning_rate": 0.0004990124599452371,
|
| 1584 |
+
"loss": 30.2201,
|
| 1585 |
+
"step": 4500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.006695542427815535,
|
| 1589 |
+
"grad_norm": 29.0,
|
| 1590 |
+
"learning_rate": 0.0004990075210102295,
|
| 1591 |
+
"loss": 30.1349,
|
| 1592 |
+
"step": 4520
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.0067251687217439226,
|
| 1596 |
+
"grad_norm": 21.375,
|
| 1597 |
+
"learning_rate": 0.000499002582075222,
|
| 1598 |
+
"loss": 30.1322,
|
| 1599 |
+
"step": 4540
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.00675479501567231,
|
| 1603 |
+
"grad_norm": 34.5,
|
| 1604 |
+
"learning_rate": 0.0004989976431402144,
|
| 1605 |
+
"loss": 30.1664,
|
| 1606 |
+
"step": 4560
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.006784421309600697,
|
| 1610 |
+
"grad_norm": 28.0,
|
| 1611 |
+
"learning_rate": 0.0004989927042052068,
|
| 1612 |
+
"loss": 30.1264,
|
| 1613 |
+
"step": 4580
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.0068140476035290845,
|
| 1617 |
+
"grad_norm": 29.875,
|
| 1618 |
+
"learning_rate": 0.0004989877652701993,
|
| 1619 |
+
"loss": 29.9802,
|
| 1620 |
+
"step": 4600
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.006843673897457472,
|
| 1624 |
+
"grad_norm": 31.625,
|
| 1625 |
+
"learning_rate": 0.0004989828263351917,
|
| 1626 |
+
"loss": 30.0028,
|
| 1627 |
+
"step": 4620
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.006873300191385859,
|
| 1631 |
+
"grad_norm": 33.5,
|
| 1632 |
+
"learning_rate": 0.0004989778874001841,
|
| 1633 |
+
"loss": 29.954,
|
| 1634 |
+
"step": 4640
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.0069029264853142465,
|
| 1638 |
+
"grad_norm": 28.125,
|
| 1639 |
+
"learning_rate": 0.0004989729484651765,
|
| 1640 |
+
"loss": 29.8774,
|
| 1641 |
+
"step": 4660
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.006932552779242634,
|
| 1645 |
+
"grad_norm": 31.25,
|
| 1646 |
+
"learning_rate": 0.000498968009530169,
|
| 1647 |
+
"loss": 29.8508,
|
| 1648 |
+
"step": 4680
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.006962179073171021,
|
| 1652 |
+
"grad_norm": 30.0,
|
| 1653 |
+
"learning_rate": 0.0004989630705951614,
|
| 1654 |
+
"loss": 29.8786,
|
| 1655 |
+
"step": 4700
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.006991805367099408,
|
| 1659 |
+
"grad_norm": 26.0,
|
| 1660 |
+
"learning_rate": 0.0004989581316601539,
|
| 1661 |
+
"loss": 29.789,
|
| 1662 |
+
"step": 4720
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.007021431661027796,
|
| 1666 |
+
"grad_norm": 29.625,
|
| 1667 |
+
"learning_rate": 0.0004989531927251463,
|
| 1668 |
+
"loss": 29.708,
|
| 1669 |
+
"step": 4740
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.007051057954956183,
|
| 1673 |
+
"grad_norm": 32.0,
|
| 1674 |
+
"learning_rate": 0.0004989482537901388,
|
| 1675 |
+
"loss": 29.7006,
|
| 1676 |
+
"step": 4760
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.00708068424888457,
|
| 1680 |
+
"grad_norm": 25.875,
|
| 1681 |
+
"learning_rate": 0.0004989433148551312,
|
| 1682 |
+
"loss": 29.546,
|
| 1683 |
+
"step": 4780
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.007110310542812958,
|
| 1687 |
+
"grad_norm": 30.125,
|
| 1688 |
+
"learning_rate": 0.0004989383759201236,
|
| 1689 |
+
"loss": 29.5634,
|
| 1690 |
+
"step": 4800
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.007139936836741345,
|
| 1694 |
+
"grad_norm": 36.5,
|
| 1695 |
+
"learning_rate": 0.0004989334369851161,
|
| 1696 |
+
"loss": 29.5994,
|
| 1697 |
+
"step": 4820
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.007169563130669732,
|
| 1701 |
+
"grad_norm": 24.375,
|
| 1702 |
+
"learning_rate": 0.0004989284980501085,
|
| 1703 |
+
"loss": 29.5168,
|
| 1704 |
+
"step": 4840
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.00719918942459812,
|
| 1708 |
+
"grad_norm": 32.25,
|
| 1709 |
+
"learning_rate": 0.0004989235591151009,
|
| 1710 |
+
"loss": 29.4858,
|
| 1711 |
+
"step": 4860
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.007228815718526507,
|
| 1715 |
+
"grad_norm": 22.0,
|
| 1716 |
+
"learning_rate": 0.0004989186201800934,
|
| 1717 |
+
"loss": 29.4208,
|
| 1718 |
+
"step": 4880
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.007258442012454894,
|
| 1722 |
+
"grad_norm": 24.625,
|
| 1723 |
+
"learning_rate": 0.0004989136812450858,
|
| 1724 |
+
"loss": 29.4053,
|
| 1725 |
+
"step": 4900
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.007288068306383282,
|
| 1729 |
+
"grad_norm": 26.625,
|
| 1730 |
+
"learning_rate": 0.0004989087423100783,
|
| 1731 |
+
"loss": 29.4063,
|
| 1732 |
+
"step": 4920
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.007317694600311669,
|
| 1736 |
+
"grad_norm": 27.25,
|
| 1737 |
+
"learning_rate": 0.0004989038033750707,
|
| 1738 |
+
"loss": 29.3743,
|
| 1739 |
+
"step": 4940
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.007347320894240056,
|
| 1743 |
+
"grad_norm": 22.625,
|
| 1744 |
+
"learning_rate": 0.000498898864440063,
|
| 1745 |
+
"loss": 29.3818,
|
| 1746 |
+
"step": 4960
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.0073769471881684435,
|
| 1750 |
+
"grad_norm": 24.5,
|
| 1751 |
+
"learning_rate": 0.0004988939255050556,
|
| 1752 |
+
"loss": 29.2662,
|
| 1753 |
+
"step": 4980
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.007406573482096831,
|
| 1757 |
+
"grad_norm": 30.5,
|
| 1758 |
+
"learning_rate": 0.0004988889865700479,
|
| 1759 |
+
"loss": 29.3027,
|
| 1760 |
+
"step": 5000
|
| 1761 |
}
|
| 1762 |
],
|
| 1763 |
"logging_steps": 20,
|
|
|
|
| 1777 |
"attributes": {}
|
| 1778 |
}
|
| 1779 |
},
|
| 1780 |
+
"total_flos": 3.439945314675458e+18,
|
| 1781 |
"train_batch_size": 48,
|
| 1782 |
"trial_name": null,
|
| 1783 |
"trial_params": null
|