Training in progress, step 2500, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa4cf5ab1fb087d029d4381bb5e28a055d9c817a87979d4b736175862d080f9b
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6572beb7bcdb366917f4d9b45d34f2485f10958107a6631df832abba4e4d9c9c
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff46ad6a9496f04d82a8799741e7a0a0edd57f04423aee3b129229a16b468b4
|
| 3 |
size 14244
|
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:a929be8c5a8f87235cd3c7ec1fa0db3faf4d300da6627139836df2b8a53bd9f3
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1367,13 +1367,353 @@
|
|
| 1367 |
"eval_samples_per_second": 90.523,
|
| 1368 |
"eval_steps_per_second": 11.364,
|
| 1369 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1370 |
}
|
| 1371 |
],
|
| 1372 |
"logging_steps": 10,
|
| 1373 |
"max_steps": 6130,
|
| 1374 |
"num_train_epochs": 10,
|
| 1375 |
"save_steps": 500,
|
| 1376 |
-
"total_flos":
|
| 1377 |
"trial_name": null,
|
| 1378 |
"trial_params": null
|
| 1379 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4399421811103821,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-2500",
|
| 4 |
+
"epoch": 4.078303425774878,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1367 |
"eval_samples_per_second": 90.523,
|
| 1368 |
"eval_steps_per_second": 11.364,
|
| 1369 |
"step": 2000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 3.28,
|
| 1373 |
+
"learning_rate": 0.0007317939609236234,
|
| 1374 |
+
"loss": 0.4824,
|
| 1375 |
+
"step": 2010
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.3,
|
| 1379 |
+
"learning_rate": 0.0007300177619893427,
|
| 1380 |
+
"loss": 0.4741,
|
| 1381 |
+
"step": 2020
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.31,
|
| 1385 |
+
"learning_rate": 0.0007282415630550621,
|
| 1386 |
+
"loss": 0.4649,
|
| 1387 |
+
"step": 2030
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 3.33,
|
| 1391 |
+
"learning_rate": 0.0007264653641207815,
|
| 1392 |
+
"loss": 0.471,
|
| 1393 |
+
"step": 2040
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 3.34,
|
| 1397 |
+
"learning_rate": 0.0007246891651865008,
|
| 1398 |
+
"loss": 0.4411,
|
| 1399 |
+
"step": 2050
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 3.36,
|
| 1403 |
+
"learning_rate": 0.0007229129662522202,
|
| 1404 |
+
"loss": 0.4435,
|
| 1405 |
+
"step": 2060
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 3.38,
|
| 1409 |
+
"learning_rate": 0.0007211367673179397,
|
| 1410 |
+
"loss": 0.4464,
|
| 1411 |
+
"step": 2070
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 3.39,
|
| 1415 |
+
"learning_rate": 0.000719360568383659,
|
| 1416 |
+
"loss": 0.4268,
|
| 1417 |
+
"step": 2080
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.41,
|
| 1421 |
+
"learning_rate": 0.0007175843694493784,
|
| 1422 |
+
"loss": 0.4648,
|
| 1423 |
+
"step": 2090
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 3.43,
|
| 1427 |
+
"learning_rate": 0.0007158081705150978,
|
| 1428 |
+
"loss": 0.4746,
|
| 1429 |
+
"step": 2100
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 3.43,
|
| 1433 |
+
"eval_loss": 0.44933727383613586,
|
| 1434 |
+
"eval_runtime": 12.9431,
|
| 1435 |
+
"eval_samples_per_second": 90.473,
|
| 1436 |
+
"eval_steps_per_second": 11.357,
|
| 1437 |
+
"step": 2100
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 3.44,
|
| 1441 |
+
"learning_rate": 0.0007140319715808172,
|
| 1442 |
+
"loss": 0.4758,
|
| 1443 |
+
"step": 2110
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 3.46,
|
| 1447 |
+
"learning_rate": 0.0007122557726465364,
|
| 1448 |
+
"loss": 0.4585,
|
| 1449 |
+
"step": 2120
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 3.47,
|
| 1453 |
+
"learning_rate": 0.0007104795737122558,
|
| 1454 |
+
"loss": 0.4386,
|
| 1455 |
+
"step": 2130
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 3.49,
|
| 1459 |
+
"learning_rate": 0.0007087033747779752,
|
| 1460 |
+
"loss": 0.4575,
|
| 1461 |
+
"step": 2140
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 3.51,
|
| 1465 |
+
"learning_rate": 0.0007069271758436945,
|
| 1466 |
+
"loss": 0.46,
|
| 1467 |
+
"step": 2150
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 3.52,
|
| 1471 |
+
"learning_rate": 0.0007051509769094139,
|
| 1472 |
+
"loss": 0.4529,
|
| 1473 |
+
"step": 2160
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.54,
|
| 1477 |
+
"learning_rate": 0.0007033747779751333,
|
| 1478 |
+
"loss": 0.4723,
|
| 1479 |
+
"step": 2170
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.56,
|
| 1483 |
+
"learning_rate": 0.0007015985790408526,
|
| 1484 |
+
"loss": 0.47,
|
| 1485 |
+
"step": 2180
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 3.57,
|
| 1489 |
+
"learning_rate": 0.000699822380106572,
|
| 1490 |
+
"loss": 0.4952,
|
| 1491 |
+
"step": 2190
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 3.59,
|
| 1495 |
+
"learning_rate": 0.0006980461811722914,
|
| 1496 |
+
"loss": 0.4488,
|
| 1497 |
+
"step": 2200
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 3.59,
|
| 1501 |
+
"eval_loss": 0.43646687269210815,
|
| 1502 |
+
"eval_runtime": 13.2627,
|
| 1503 |
+
"eval_samples_per_second": 88.293,
|
| 1504 |
+
"eval_steps_per_second": 11.084,
|
| 1505 |
+
"step": 2200
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.61,
|
| 1509 |
+
"learning_rate": 0.0006962699822380107,
|
| 1510 |
+
"loss": 0.4558,
|
| 1511 |
+
"step": 2210
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 3.62,
|
| 1515 |
+
"learning_rate": 0.0006944937833037301,
|
| 1516 |
+
"loss": 0.4657,
|
| 1517 |
+
"step": 2220
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.64,
|
| 1521 |
+
"learning_rate": 0.0006927175843694495,
|
| 1522 |
+
"loss": 0.4671,
|
| 1523 |
+
"step": 2230
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 3.65,
|
| 1527 |
+
"learning_rate": 0.0006909413854351687,
|
| 1528 |
+
"loss": 0.5003,
|
| 1529 |
+
"step": 2240
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.67,
|
| 1533 |
+
"learning_rate": 0.0006891651865008881,
|
| 1534 |
+
"loss": 0.4523,
|
| 1535 |
+
"step": 2250
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.69,
|
| 1539 |
+
"learning_rate": 0.0006873889875666075,
|
| 1540 |
+
"loss": 0.4466,
|
| 1541 |
+
"step": 2260
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 3.7,
|
| 1545 |
+
"learning_rate": 0.0006856127886323268,
|
| 1546 |
+
"loss": 0.4448,
|
| 1547 |
+
"step": 2270
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 3.72,
|
| 1551 |
+
"learning_rate": 0.0006838365896980462,
|
| 1552 |
+
"loss": 0.4491,
|
| 1553 |
+
"step": 2280
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 3.74,
|
| 1557 |
+
"learning_rate": 0.0006820603907637656,
|
| 1558 |
+
"loss": 0.4719,
|
| 1559 |
+
"step": 2290
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 3.75,
|
| 1563 |
+
"learning_rate": 0.0006802841918294849,
|
| 1564 |
+
"loss": 0.4742,
|
| 1565 |
+
"step": 2300
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 3.75,
|
| 1569 |
+
"eval_loss": 0.43938902020454407,
|
| 1570 |
+
"eval_runtime": 13.1019,
|
| 1571 |
+
"eval_samples_per_second": 89.376,
|
| 1572 |
+
"eval_steps_per_second": 11.22,
|
| 1573 |
+
"step": 2300
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 3.77,
|
| 1577 |
+
"learning_rate": 0.0006785079928952043,
|
| 1578 |
+
"loss": 0.4709,
|
| 1579 |
+
"step": 2310
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 3.78,
|
| 1583 |
+
"learning_rate": 0.0006767317939609237,
|
| 1584 |
+
"loss": 0.4575,
|
| 1585 |
+
"step": 2320
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.8,
|
| 1589 |
+
"learning_rate": 0.000674955595026643,
|
| 1590 |
+
"loss": 0.4688,
|
| 1591 |
+
"step": 2330
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 3.82,
|
| 1595 |
+
"learning_rate": 0.0006731793960923623,
|
| 1596 |
+
"loss": 0.4552,
|
| 1597 |
+
"step": 2340
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 3.83,
|
| 1601 |
+
"learning_rate": 0.0006714031971580817,
|
| 1602 |
+
"loss": 0.4515,
|
| 1603 |
+
"step": 2350
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 3.85,
|
| 1607 |
+
"learning_rate": 0.0006696269982238011,
|
| 1608 |
+
"loss": 0.455,
|
| 1609 |
+
"step": 2360
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 3.87,
|
| 1613 |
+
"learning_rate": 0.0006678507992895204,
|
| 1614 |
+
"loss": 0.4465,
|
| 1615 |
+
"step": 2370
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 3.88,
|
| 1619 |
+
"learning_rate": 0.0006660746003552398,
|
| 1620 |
+
"loss": 0.479,
|
| 1621 |
+
"step": 2380
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 3.9,
|
| 1625 |
+
"learning_rate": 0.0006642984014209592,
|
| 1626 |
+
"loss": 0.4492,
|
| 1627 |
+
"step": 2390
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.92,
|
| 1631 |
+
"learning_rate": 0.0006625222024866785,
|
| 1632 |
+
"loss": 0.4465,
|
| 1633 |
+
"step": 2400
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.92,
|
| 1637 |
+
"eval_loss": 0.4411802589893341,
|
| 1638 |
+
"eval_runtime": 12.9494,
|
| 1639 |
+
"eval_samples_per_second": 90.429,
|
| 1640 |
+
"eval_steps_per_second": 11.352,
|
| 1641 |
+
"step": 2400
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.93,
|
| 1645 |
+
"learning_rate": 0.0006607460035523979,
|
| 1646 |
+
"loss": 0.4851,
|
| 1647 |
+
"step": 2410
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.95,
|
| 1651 |
+
"learning_rate": 0.0006589698046181173,
|
| 1652 |
+
"loss": 0.4414,
|
| 1653 |
+
"step": 2420
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 3.96,
|
| 1657 |
+
"learning_rate": 0.0006571936056838366,
|
| 1658 |
+
"loss": 0.4333,
|
| 1659 |
+
"step": 2430
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 3.98,
|
| 1663 |
+
"learning_rate": 0.000655417406749556,
|
| 1664 |
+
"loss": 0.4733,
|
| 1665 |
+
"step": 2440
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 4.0,
|
| 1669 |
+
"learning_rate": 0.0006536412078152753,
|
| 1670 |
+
"loss": 0.4667,
|
| 1671 |
+
"step": 2450
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 4.01,
|
| 1675 |
+
"learning_rate": 0.0006518650088809946,
|
| 1676 |
+
"loss": 0.4381,
|
| 1677 |
+
"step": 2460
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 4.03,
|
| 1681 |
+
"learning_rate": 0.000650088809946714,
|
| 1682 |
+
"loss": 0.4267,
|
| 1683 |
+
"step": 2470
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 4.05,
|
| 1687 |
+
"learning_rate": 0.0006483126110124334,
|
| 1688 |
+
"loss": 0.4361,
|
| 1689 |
+
"step": 2480
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.06,
|
| 1693 |
+
"learning_rate": 0.0006465364120781527,
|
| 1694 |
+
"loss": 0.4636,
|
| 1695 |
+
"step": 2490
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 4.08,
|
| 1699 |
+
"learning_rate": 0.0006447602131438721,
|
| 1700 |
+
"loss": 0.4578,
|
| 1701 |
+
"step": 2500
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 4.08,
|
| 1705 |
+
"eval_loss": 0.4399421811103821,
|
| 1706 |
+
"eval_runtime": 13.1521,
|
| 1707 |
+
"eval_samples_per_second": 89.035,
|
| 1708 |
+
"eval_steps_per_second": 11.177,
|
| 1709 |
+
"step": 2500
|
| 1710 |
}
|
| 1711 |
],
|
| 1712 |
"logging_steps": 10,
|
| 1713 |
"max_steps": 6130,
|
| 1714 |
"num_train_epochs": 10,
|
| 1715 |
"save_steps": 500,
|
| 1716 |
+
"total_flos": 4719092173406208.0,
|
| 1717 |
"trial_name": null,
|
| 1718 |
"trial_params": null
|
| 1719 |
}
|