Training in progress, step 12000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1153648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:884809754302970ee5d7aba079837ab66c8fc8d3dfda9203edb7e82af169c0c4
|
| 3 |
size 1153648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2334411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfb47a75980f44d762259b2dae2273b219e560e2e41f90e8ce969c250b5db47a
|
| 3 |
size 2334411
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bdb5039faf0b6224e3e45823160baf2c84d5d38912d0fdcad74d563a97cccf7
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e11bd5a7f48710bd0b6af42537786e3d78933acfc7271e07f7ceab7552c955ab
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:615e6d9847ad66fd7ca766a07f134dd024f43d2111d12bda979dcfa96e7de84d
|
| 3 |
size 1465
|
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 +1408,286 @@
|
|
| 1408 |
"learning_rate": 0.0009000536340531358,
|
| 1409 |
"loss": 5.097496643066406,
|
| 1410 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 50,
|
|
@@ -1427,7 +1707,7 @@
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
-
"total_flos":
|
| 1431 |
"train_batch_size": 16,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2457555960597186,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1408 |
"learning_rate": 0.0009000536340531358,
|
| 1409 |
"loss": 5.097496643066406,
|
| 1410 |
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.20582031170001433,
|
| 1414 |
+
"grad_norm": 0.5461782813072205,
|
| 1415 |
+
"learning_rate": 0.0008990867158331287,
|
| 1416 |
+
"loss": 5.099080200195313,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.20684429335026316,
|
| 1421 |
+
"grad_norm": 0.6475767493247986,
|
| 1422 |
+
"learning_rate": 0.000898115667604188,
|
| 1423 |
+
"loss": 5.090173034667969,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.207868275000512,
|
| 1428 |
+
"grad_norm": 0.5918726921081543,
|
| 1429 |
+
"learning_rate": 0.0008971404994153523,
|
| 1430 |
+
"loss": 5.089554748535156,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.2088922566507608,
|
| 1435 |
+
"grad_norm": 0.8444413542747498,
|
| 1436 |
+
"learning_rate": 0.0008961612213582966,
|
| 1437 |
+
"loss": 5.091931457519531,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.20991623830100964,
|
| 1442 |
+
"grad_norm": 0.7469403147697449,
|
| 1443 |
+
"learning_rate": 0.0008951778435672271,
|
| 1444 |
+
"loss": 5.089012756347656,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.21094021995125847,
|
| 1449 |
+
"grad_norm": 0.9174968600273132,
|
| 1450 |
+
"learning_rate": 0.0008941903762187766,
|
| 1451 |
+
"loss": 5.089004211425781,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.2119642016015073,
|
| 1456 |
+
"grad_norm": 0.780366837978363,
|
| 1457 |
+
"learning_rate": 0.0008931988295319,
|
| 1458 |
+
"loss": 5.107621459960938,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.21298818325175614,
|
| 1463 |
+
"grad_norm": 1.0522842407226562,
|
| 1464 |
+
"learning_rate": 0.0008922032137677671,
|
| 1465 |
+
"loss": 5.095304260253906,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.21401216490200495,
|
| 1470 |
+
"grad_norm": 0.6593838334083557,
|
| 1471 |
+
"learning_rate": 0.0008912035392296576,
|
| 1472 |
+
"loss": 5.10793212890625,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.21503614655225378,
|
| 1477 |
+
"grad_norm": 1.3583625555038452,
|
| 1478 |
+
"learning_rate": 0.0008901998162628537,
|
| 1479 |
+
"loss": 5.08461181640625,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.21606012820250262,
|
| 1484 |
+
"grad_norm": 0.6266817450523376,
|
| 1485 |
+
"learning_rate": 0.0008891920552545338,
|
| 1486 |
+
"loss": 5.122800903320313,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.21708410985275145,
|
| 1491 |
+
"grad_norm": 0.9504562616348267,
|
| 1492 |
+
"learning_rate": 0.0008881802666336643,
|
| 1493 |
+
"loss": 5.081485595703125,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.21810809150300026,
|
| 1498 |
+
"grad_norm": 0.7504943013191223,
|
| 1499 |
+
"learning_rate": 0.0008871644608708918,
|
| 1500 |
+
"loss": 5.081528625488281,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.2191320731532491,
|
| 1505 |
+
"grad_norm": 0.8670194745063782,
|
| 1506 |
+
"learning_rate": 0.0008861446484784351,
|
| 1507 |
+
"loss": 5.086711730957031,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.22015605480349792,
|
| 1512 |
+
"grad_norm": 0.938003659248352,
|
| 1513 |
+
"learning_rate": 0.0008851208400099765,
|
| 1514 |
+
"loss": 5.099390869140625,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.22118003645374676,
|
| 1519 |
+
"grad_norm": 0.5790009498596191,
|
| 1520 |
+
"learning_rate": 0.0008840930460605518,
|
| 1521 |
+
"loss": 5.101390991210938,
|
| 1522 |
+
"step": 10800
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.22220401810399557,
|
| 1526 |
+
"grad_norm": 0.6272426247596741,
|
| 1527 |
+
"learning_rate": 0.0008830612772664412,
|
| 1528 |
+
"loss": 5.091133117675781,
|
| 1529 |
+
"step": 10850
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.2232279997542444,
|
| 1533 |
+
"grad_norm": 0.6544851064682007,
|
| 1534 |
+
"learning_rate": 0.0008820255443050597,
|
| 1535 |
+
"loss": 5.082786865234375,
|
| 1536 |
+
"step": 10900
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.22425198140449323,
|
| 1540 |
+
"grad_norm": 0.7002019286155701,
|
| 1541 |
+
"learning_rate": 0.0008809858578948456,
|
| 1542 |
+
"loss": 5.050909118652344,
|
| 1543 |
+
"step": 10950
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.22527596305474207,
|
| 1547 |
+
"grad_norm": 0.8050152659416199,
|
| 1548 |
+
"learning_rate": 0.0008799422287951499,
|
| 1549 |
+
"loss": 5.097827453613281,
|
| 1550 |
+
"step": 11000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.22629994470499087,
|
| 1554 |
+
"grad_norm": 0.7166301608085632,
|
| 1555 |
+
"learning_rate": 0.0008788946678061256,
|
| 1556 |
+
"loss": 5.089942321777344,
|
| 1557 |
+
"step": 11050
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.2273239263552397,
|
| 1561 |
+
"grad_norm": 0.7180762887001038,
|
| 1562 |
+
"learning_rate": 0.0008778431857686152,
|
| 1563 |
+
"loss": 5.085594482421875,
|
| 1564 |
+
"step": 11100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.22834790800548854,
|
| 1568 |
+
"grad_norm": 0.6210533380508423,
|
| 1569 |
+
"learning_rate": 0.0008767877935640389,
|
| 1570 |
+
"loss": 5.083946838378906,
|
| 1571 |
+
"step": 11150
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.22937188965573738,
|
| 1575 |
+
"grad_norm": 0.6428560018539429,
|
| 1576 |
+
"learning_rate": 0.0008757285021142815,
|
| 1577 |
+
"loss": 5.081972351074219,
|
| 1578 |
+
"step": 11200
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.23039587130598618,
|
| 1582 |
+
"grad_norm": 0.6180407404899597,
|
| 1583 |
+
"learning_rate": 0.0008746653223815801,
|
| 1584 |
+
"loss": 5.076778869628907,
|
| 1585 |
+
"step": 11250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.23141985295623502,
|
| 1589 |
+
"grad_norm": 0.6733253002166748,
|
| 1590 |
+
"learning_rate": 0.0008735982653684102,
|
| 1591 |
+
"loss": 5.083547973632813,
|
| 1592 |
+
"step": 11300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.23244383460648385,
|
| 1596 |
+
"grad_norm": 0.60187828540802,
|
| 1597 |
+
"learning_rate": 0.0008725273421173719,
|
| 1598 |
+
"loss": 5.070328369140625,
|
| 1599 |
+
"step": 11350
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.23346781625673269,
|
| 1603 |
+
"grad_norm": 0.5819737911224365,
|
| 1604 |
+
"learning_rate": 0.0008714525637110754,
|
| 1605 |
+
"loss": 5.071551208496094,
|
| 1606 |
+
"step": 11400
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.23449179790698152,
|
| 1610 |
+
"grad_norm": 0.7740217447280884,
|
| 1611 |
+
"learning_rate": 0.000870373941272027,
|
| 1612 |
+
"loss": 5.074407653808594,
|
| 1613 |
+
"step": 11450
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.23551577955723033,
|
| 1617 |
+
"grad_norm": 0.8642405271530151,
|
| 1618 |
+
"learning_rate": 0.0008692914859625132,
|
| 1619 |
+
"loss": 5.088779602050781,
|
| 1620 |
+
"step": 11500
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.23653976120747916,
|
| 1624 |
+
"grad_norm": 0.7088413238525391,
|
| 1625 |
+
"learning_rate": 0.0008682052089844857,
|
| 1626 |
+
"loss": 5.077694702148437,
|
| 1627 |
+
"step": 11550
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.237563742857728,
|
| 1631 |
+
"grad_norm": 0.6237403154373169,
|
| 1632 |
+
"learning_rate": 0.0008671151215794453,
|
| 1633 |
+
"loss": 5.071099853515625,
|
| 1634 |
+
"step": 11600
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.23858772450797683,
|
| 1638 |
+
"grad_norm": 0.8367547988891602,
|
| 1639 |
+
"learning_rate": 0.0008660212350283255,
|
| 1640 |
+
"loss": 5.075140075683594,
|
| 1641 |
+
"step": 11650
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.23961170615822563,
|
| 1645 |
+
"grad_norm": 1.2495672702789307,
|
| 1646 |
+
"learning_rate": 0.0008649235606513759,
|
| 1647 |
+
"loss": 5.085387268066406,
|
| 1648 |
+
"step": 11700
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.24063568780847447,
|
| 1652 |
+
"grad_norm": 0.7375836968421936,
|
| 1653 |
+
"learning_rate": 0.000863822109808045,
|
| 1654 |
+
"loss": 5.1009423828125,
|
| 1655 |
+
"step": 11750
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.2416596694587233,
|
| 1659 |
+
"grad_norm": 0.7800421714782715,
|
| 1660 |
+
"learning_rate": 0.0008627168938968626,
|
| 1661 |
+
"loss": 5.088766479492188,
|
| 1662 |
+
"step": 11800
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.24268365110897214,
|
| 1666 |
+
"grad_norm": 0.6453808546066284,
|
| 1667 |
+
"learning_rate": 0.0008616079243553217,
|
| 1668 |
+
"loss": 5.083224792480468,
|
| 1669 |
+
"step": 11850
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.24370763275922094,
|
| 1673 |
+
"grad_norm": 0.6847288608551025,
|
| 1674 |
+
"learning_rate": 0.0008604952126597608,
|
| 1675 |
+
"loss": 5.090411071777344,
|
| 1676 |
+
"step": 11900
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.24473161440946978,
|
| 1680 |
+
"grad_norm": 0.7905821800231934,
|
| 1681 |
+
"learning_rate": 0.000859378770325244,
|
| 1682 |
+
"loss": 5.093881530761719,
|
| 1683 |
+
"step": 11950
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.2457555960597186,
|
| 1687 |
+
"grad_norm": 0.7534177899360657,
|
| 1688 |
+
"learning_rate": 0.000858258608905443,
|
| 1689 |
+
"loss": 5.078074951171875,
|
| 1690 |
+
"step": 12000
|
| 1691 |
}
|
| 1692 |
],
|
| 1693 |
"logging_steps": 50,
|
|
|
|
| 1707 |
"attributes": {}
|
| 1708 |
}
|
| 1709 |
},
|
| 1710 |
+
"total_flos": 156393013248000.0,
|
| 1711 |
"train_batch_size": 16,
|
| 1712 |
"trial_name": null,
|
| 1713 |
"trial_params": null
|