Training in progress, epoch 5, 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 37789864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b127cfb645d1c75f132a876553609b5374befd9def67d558e5974fa97067d21c
|
| 3 |
size 37789864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2622266
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54d9a221b97b4a103c3bbd0fd8abf8231538258d0486fa04d26296da0b8c69c4
|
| 3 |
size 2622266
|
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 sha256:9c9b188ef411c860fa162f3665ea4a77b4e06ff07ab727a5f17c10e78d9237ed
|
| 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 sha256:29fd4cd191139dd97c05600899e5a66a54004c5898470ac779c283abb76b7689
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1307,13 +1307,338 @@
|
|
| 1307 |
"eval_steps_per_second": 0.291,
|
| 1308 |
"eval_translation_length": 5805056,
|
| 1309 |
"step": 102044
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1310 |
}
|
| 1311 |
],
|
| 1312 |
"logging_steps": 500,
|
| 1313 |
"max_steps": 765330,
|
| 1314 |
"num_train_epochs": 30,
|
| 1315 |
"save_steps": 1000,
|
| 1316 |
-
"total_flos":
|
| 1317 |
"trial_name": null,
|
| 1318 |
"trial_params": null
|
| 1319 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.8255138397216797,
|
| 3 |
+
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-127555",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 127555,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1307 |
"eval_steps_per_second": 0.291,
|
| 1308 |
"eval_translation_length": 5805056,
|
| 1309 |
"step": 102044
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 4.02,
|
| 1313 |
+
"learning_rate": 7.65403033800726e-05,
|
| 1314 |
+
"loss": 2.9547,
|
| 1315 |
+
"step": 102500
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 4.04,
|
| 1319 |
+
"learning_rate": 7.6506805368716e-05,
|
| 1320 |
+
"loss": 2.8596,
|
| 1321 |
+
"step": 103000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 4.06,
|
| 1325 |
+
"learning_rate": 7.647315337052083e-05,
|
| 1326 |
+
"loss": 2.9155,
|
| 1327 |
+
"step": 103500
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 4.08,
|
| 1331 |
+
"learning_rate": 7.643934752743228e-05,
|
| 1332 |
+
"loss": 2.8802,
|
| 1333 |
+
"step": 104000
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 4.1,
|
| 1337 |
+
"learning_rate": 7.640538798204443e-05,
|
| 1338 |
+
"loss": 2.9248,
|
| 1339 |
+
"step": 104500
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.12,
|
| 1343 |
+
"learning_rate": 7.63712748775997e-05,
|
| 1344 |
+
"loss": 2.8865,
|
| 1345 |
+
"step": 105000
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 4.14,
|
| 1349 |
+
"learning_rate": 7.633700835798824e-05,
|
| 1350 |
+
"loss": 2.9383,
|
| 1351 |
+
"step": 105500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 4.16,
|
| 1355 |
+
"learning_rate": 7.630258856774726e-05,
|
| 1356 |
+
"loss": 2.8581,
|
| 1357 |
+
"step": 106000
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 4.17,
|
| 1361 |
+
"learning_rate": 7.626801565206054e-05,
|
| 1362 |
+
"loss": 2.9359,
|
| 1363 |
+
"step": 106500
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 4.19,
|
| 1367 |
+
"learning_rate": 7.623328975675768e-05,
|
| 1368 |
+
"loss": 2.9459,
|
| 1369 |
+
"step": 107000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 4.21,
|
| 1373 |
+
"learning_rate": 7.619841102831362e-05,
|
| 1374 |
+
"loss": 2.9888,
|
| 1375 |
+
"step": 107500
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 4.23,
|
| 1379 |
+
"learning_rate": 7.616337961384787e-05,
|
| 1380 |
+
"loss": 2.8815,
|
| 1381 |
+
"step": 108000
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.25,
|
| 1385 |
+
"learning_rate": 7.612819566112408e-05,
|
| 1386 |
+
"loss": 2.9105,
|
| 1387 |
+
"step": 108500
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 4.27,
|
| 1391 |
+
"learning_rate": 7.609285931854922e-05,
|
| 1392 |
+
"loss": 2.9028,
|
| 1393 |
+
"step": 109000
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 4.29,
|
| 1397 |
+
"learning_rate": 7.605737073517308e-05,
|
| 1398 |
+
"loss": 2.9141,
|
| 1399 |
+
"step": 109500
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 4.31,
|
| 1403 |
+
"learning_rate": 7.602173006068763e-05,
|
| 1404 |
+
"loss": 2.9244,
|
| 1405 |
+
"step": 110000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 4.33,
|
| 1409 |
+
"learning_rate": 7.598593744542632e-05,
|
| 1410 |
+
"loss": 2.8534,
|
| 1411 |
+
"step": 110500
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.35,
|
| 1415 |
+
"learning_rate": 7.594999304036352e-05,
|
| 1416 |
+
"loss": 2.8936,
|
| 1417 |
+
"step": 111000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 4.37,
|
| 1421 |
+
"learning_rate": 7.591389699711384e-05,
|
| 1422 |
+
"loss": 2.8866,
|
| 1423 |
+
"step": 111500
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 4.39,
|
| 1427 |
+
"learning_rate": 7.587764946793153e-05,
|
| 1428 |
+
"loss": 2.9335,
|
| 1429 |
+
"step": 112000
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 4.41,
|
| 1433 |
+
"learning_rate": 7.584125060570976e-05,
|
| 1434 |
+
"loss": 2.7982,
|
| 1435 |
+
"step": 112500
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 4.43,
|
| 1439 |
+
"learning_rate": 7.58047005639801e-05,
|
| 1440 |
+
"loss": 2.8565,
|
| 1441 |
+
"step": 113000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 4.45,
|
| 1445 |
+
"learning_rate": 7.576799949691174e-05,
|
| 1446 |
+
"loss": 2.8682,
|
| 1447 |
+
"step": 113500
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 4.47,
|
| 1451 |
+
"learning_rate": 7.573114755931093e-05,
|
| 1452 |
+
"loss": 2.887,
|
| 1453 |
+
"step": 114000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 4.49,
|
| 1457 |
+
"learning_rate": 7.569414490662027e-05,
|
| 1458 |
+
"loss": 2.9001,
|
| 1459 |
+
"step": 114500
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 4.51,
|
| 1463 |
+
"learning_rate": 7.565699169491811e-05,
|
| 1464 |
+
"loss": 2.8804,
|
| 1465 |
+
"step": 115000
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 4.53,
|
| 1469 |
+
"learning_rate": 7.561968808091784e-05,
|
| 1470 |
+
"loss": 2.9395,
|
| 1471 |
+
"step": 115500
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 4.55,
|
| 1475 |
+
"learning_rate": 7.558223422196728e-05,
|
| 1476 |
+
"loss": 2.922,
|
| 1477 |
+
"step": 116000
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 4.57,
|
| 1481 |
+
"learning_rate": 7.554463027604798e-05,
|
| 1482 |
+
"loss": 2.8777,
|
| 1483 |
+
"step": 116500
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.59,
|
| 1487 |
+
"learning_rate": 7.550687640177451e-05,
|
| 1488 |
+
"loss": 2.8746,
|
| 1489 |
+
"step": 117000
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 4.61,
|
| 1493 |
+
"learning_rate": 7.54689727583939e-05,
|
| 1494 |
+
"loss": 2.9362,
|
| 1495 |
+
"step": 117500
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.63,
|
| 1499 |
+
"learning_rate": 7.543091950578492e-05,
|
| 1500 |
+
"loss": 2.8282,
|
| 1501 |
+
"step": 118000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 4.65,
|
| 1505 |
+
"learning_rate": 7.539271680445734e-05,
|
| 1506 |
+
"loss": 2.8902,
|
| 1507 |
+
"step": 118500
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 4.66,
|
| 1511 |
+
"learning_rate": 7.535436481555135e-05,
|
| 1512 |
+
"loss": 2.9123,
|
| 1513 |
+
"step": 119000
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 4.68,
|
| 1517 |
+
"learning_rate": 7.531586370083684e-05,
|
| 1518 |
+
"loss": 2.847,
|
| 1519 |
+
"step": 119500
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 4.7,
|
| 1523 |
+
"learning_rate": 7.527721362271269e-05,
|
| 1524 |
+
"loss": 2.8664,
|
| 1525 |
+
"step": 120000
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 4.72,
|
| 1529 |
+
"learning_rate": 7.523841474420614e-05,
|
| 1530 |
+
"loss": 2.9341,
|
| 1531 |
+
"step": 120500
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 4.74,
|
| 1535 |
+
"learning_rate": 7.519946722897209e-05,
|
| 1536 |
+
"loss": 2.8942,
|
| 1537 |
+
"step": 121000
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 4.76,
|
| 1541 |
+
"learning_rate": 7.516037124129231e-05,
|
| 1542 |
+
"loss": 2.9092,
|
| 1543 |
+
"step": 121500
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 4.78,
|
| 1547 |
+
"learning_rate": 7.512112694607494e-05,
|
| 1548 |
+
"loss": 2.8891,
|
| 1549 |
+
"step": 122000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 4.8,
|
| 1553 |
+
"learning_rate": 7.508173450885361e-05,
|
| 1554 |
+
"loss": 2.9581,
|
| 1555 |
+
"step": 122500
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 4.82,
|
| 1559 |
+
"learning_rate": 7.504219409578685e-05,
|
| 1560 |
+
"loss": 3.0015,
|
| 1561 |
+
"step": 123000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 4.84,
|
| 1565 |
+
"learning_rate": 7.500250587365735e-05,
|
| 1566 |
+
"loss": 2.9472,
|
| 1567 |
+
"step": 123500
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 4.86,
|
| 1571 |
+
"learning_rate": 7.496267000987127e-05,
|
| 1572 |
+
"loss": 2.8975,
|
| 1573 |
+
"step": 124000
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 4.88,
|
| 1577 |
+
"learning_rate": 7.49226866724575e-05,
|
| 1578 |
+
"loss": 2.8226,
|
| 1579 |
+
"step": 124500
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 4.9,
|
| 1583 |
+
"learning_rate": 7.488255603006703e-05,
|
| 1584 |
+
"loss": 2.8738,
|
| 1585 |
+
"step": 125000
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 4.92,
|
| 1589 |
+
"learning_rate": 7.484227825197214e-05,
|
| 1590 |
+
"loss": 2.9323,
|
| 1591 |
+
"step": 125500
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 4.94,
|
| 1595 |
+
"learning_rate": 7.480185350806574e-05,
|
| 1596 |
+
"loss": 2.9436,
|
| 1597 |
+
"step": 126000
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 4.96,
|
| 1601 |
+
"learning_rate": 7.476128196886067e-05,
|
| 1602 |
+
"loss": 2.8861,
|
| 1603 |
+
"step": 126500
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 4.98,
|
| 1607 |
+
"learning_rate": 7.472056380548893e-05,
|
| 1608 |
+
"loss": 2.9255,
|
| 1609 |
+
"step": 127000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 5.0,
|
| 1613 |
+
"learning_rate": 7.467969918970099e-05,
|
| 1614 |
+
"loss": 2.8591,
|
| 1615 |
+
"step": 127500
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 5.0,
|
| 1619 |
+
"eval_bleu": 1.0,
|
| 1620 |
+
"eval_brevity_penalty": 1.0,
|
| 1621 |
+
"eval_length_ratio": 1.0,
|
| 1622 |
+
"eval_loss": 2.8255138397216797,
|
| 1623 |
+
"eval_precisions": [
|
| 1624 |
+
1.0,
|
| 1625 |
+
1.0,
|
| 1626 |
+
1.0,
|
| 1627 |
+
1.0
|
| 1628 |
+
],
|
| 1629 |
+
"eval_reference_length": 5805056,
|
| 1630 |
+
"eval_runtime": 10189.5043,
|
| 1631 |
+
"eval_samples_per_second": 1.113,
|
| 1632 |
+
"eval_steps_per_second": 0.278,
|
| 1633 |
+
"eval_translation_length": 5805056,
|
| 1634 |
+
"step": 127555
|
| 1635 |
}
|
| 1636 |
],
|
| 1637 |
"logging_steps": 500,
|
| 1638 |
"max_steps": 765330,
|
| 1639 |
"num_train_epochs": 30,
|
| 1640 |
"save_steps": 1000,
|
| 1641 |
+
"total_flos": 4.378268597873541e+18,
|
| 1642 |
"trial_name": null,
|
| 1643 |
"trial_params": null
|
| 1644 |
}
|