ZeroUniqueness
commited on
Commit
β’
c59800f
1
Parent(s):
faadcb1
Training in progress, step 23000
Browse files- adapter_model.bin +1 -1
- {checkpoint-19000 β checkpoint-22000/adapter_model}/README.md +0 -0
- {checkpoint-19000 β checkpoint-22000/adapter_model}/adapter_config.json +0 -0
- {checkpoint-19000 β checkpoint-22000/adapter_model}/adapter_model.bin +1 -1
- {checkpoint-19000/adapter_model β checkpoint-23000}/README.md +0 -0
- {checkpoint-19000/adapter_model β checkpoint-23000}/adapter_config.json +0 -0
- {checkpoint-19000/adapter_model β checkpoint-23000}/adapter_model.bin +1 -1
- {checkpoint-19000 β checkpoint-23000}/optimizer.pt +1 -1
- {checkpoint-19000 β checkpoint-23000}/rng_state.pth +1 -1
- {checkpoint-19000 β checkpoint-23000}/scheduler.pt +1 -1
- {checkpoint-19000 β checkpoint-23000}/trainer_state.json +277 -5
- {checkpoint-19000 β checkpoint-23000}/training_args.bin +0 -0
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500897101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b09fbcc84f52583b6b795b011e1c5f0c43a3db60e66b9f20591fcc7e4f4c5a5c
|
3 |
size 500897101
|
{checkpoint-19000 β checkpoint-22000/adapter_model}/README.md
RENAMED
File without changes
|
{checkpoint-19000 β checkpoint-22000/adapter_model}/adapter_config.json
RENAMED
File without changes
|
{checkpoint-19000 β checkpoint-22000/adapter_model}/adapter_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500897101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d90531691a4bd22a7fc951651aaad0da90ed5d3154cec0eed731f4f8c1da5c1
|
3 |
size 500897101
|
{checkpoint-19000/adapter_model β checkpoint-23000}/README.md
RENAMED
File without changes
|
{checkpoint-19000/adapter_model β checkpoint-23000}/adapter_config.json
RENAMED
File without changes
|
{checkpoint-19000/adapter_model β checkpoint-23000}/adapter_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500897101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b09fbcc84f52583b6b795b011e1c5f0c43a3db60e66b9f20591fcc7e4f4c5a5c
|
3 |
size 500897101
|
{checkpoint-19000 β checkpoint-23000}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001723453
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbfed6747bc76cf76b9beff591f4900ea3c29204b46ce6523ace5f8336472f0d
|
3 |
size 1001723453
|
{checkpoint-19000 β checkpoint-23000}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed2325c64a2e205df19d31c415cd90ef5d3f44b07c5241eed503aa4caf9c6bce
|
3 |
size 14575
|
{checkpoint-19000 β checkpoint-23000}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43a0198723866985e385225cfff961adcdcef3bedd49c15e274c7317774fe0f2
|
3 |
size 627
|
{checkpoint-19000 β checkpoint-23000}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./qlora-out/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1298,11 +1298,283 @@
|
|
1298 |
"eval_samples_per_second": 0.422,
|
1299 |
"eval_steps_per_second": 0.422,
|
1300 |
"step": 19000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1301 |
}
|
1302 |
],
|
1303 |
"max_steps": 80463,
|
1304 |
"num_train_epochs": 3,
|
1305 |
-
"total_flos":
|
1306 |
"trial_name": null,
|
1307 |
"trial_params": null
|
1308 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6180054545402527,
|
3 |
+
"best_model_checkpoint": "./qlora-out/checkpoint-23000",
|
4 |
+
"epoch": 0.8575370045859587,
|
5 |
+
"global_step": 23000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1298 |
"eval_samples_per_second": 0.422,
|
1299 |
"eval_steps_per_second": 0.422,
|
1300 |
"step": 19000
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 0.71,
|
1304 |
+
"learning_rate": 0.00017347885166694825,
|
1305 |
+
"loss": 0.6213,
|
1306 |
+
"step": 19100
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.72,
|
1310 |
+
"learning_rate": 0.00017321342561755297,
|
1311 |
+
"loss": 0.6217,
|
1312 |
+
"step": 19200
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.72,
|
1316 |
+
"learning_rate": 0.00017294688320515506,
|
1317 |
+
"loss": 0.6127,
|
1318 |
+
"step": 19300
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.72,
|
1322 |
+
"learning_rate": 0.00017267922849401024,
|
1323 |
+
"loss": 0.6145,
|
1324 |
+
"step": 19400
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"epoch": 0.73,
|
1328 |
+
"learning_rate": 0.00017241046556533472,
|
1329 |
+
"loss": 0.5936,
|
1330 |
+
"step": 19500
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.73,
|
1334 |
+
"learning_rate": 0.0001721405985172428,
|
1335 |
+
"loss": 0.6273,
|
1336 |
+
"step": 19600
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 0.73,
|
1340 |
+
"learning_rate": 0.0001718696314646846,
|
1341 |
+
"loss": 0.6059,
|
1342 |
+
"step": 19700
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 0.74,
|
1346 |
+
"learning_rate": 0.000171597568539383,
|
1347 |
+
"loss": 0.5934,
|
1348 |
+
"step": 19800
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.74,
|
1352 |
+
"learning_rate": 0.000171324413889771,
|
1353 |
+
"loss": 0.6243,
|
1354 |
+
"step": 19900
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.75,
|
1358 |
+
"learning_rate": 0.00017105017168092808,
|
1359 |
+
"loss": 0.6164,
|
1360 |
+
"step": 20000
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.75,
|
1364 |
+
"eval_loss": 0.6324757933616638,
|
1365 |
+
"eval_runtime": 1266.6769,
|
1366 |
+
"eval_samples_per_second": 0.428,
|
1367 |
+
"eval_steps_per_second": 0.428,
|
1368 |
+
"step": 20000
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.75,
|
1372 |
+
"learning_rate": 0.0001707748460945171,
|
1373 |
+
"loss": 0.5953,
|
1374 |
+
"step": 20100
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.75,
|
1378 |
+
"learning_rate": 0.0001704984413287202,
|
1379 |
+
"loss": 0.6329,
|
1380 |
+
"step": 20200
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 0.76,
|
1384 |
+
"learning_rate": 0.00017022096159817493,
|
1385 |
+
"loss": 0.6227,
|
1386 |
+
"step": 20300
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.76,
|
1390 |
+
"learning_rate": 0.00016994241113391003,
|
1391 |
+
"loss": 0.6022,
|
1392 |
+
"step": 20400
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.76,
|
1396 |
+
"learning_rate": 0.0001696627941832808,
|
1397 |
+
"loss": 0.604,
|
1398 |
+
"step": 20500
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 0.77,
|
1402 |
+
"learning_rate": 0.0001693821150099044,
|
1403 |
+
"loss": 0.6101,
|
1404 |
+
"step": 20600
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.77,
|
1408 |
+
"learning_rate": 0.00016910037789359485,
|
1409 |
+
"loss": 0.6242,
|
1410 |
+
"step": 20700
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.78,
|
1414 |
+
"learning_rate": 0.00016881758713029776,
|
1415 |
+
"loss": 0.6096,
|
1416 |
+
"step": 20800
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.78,
|
1420 |
+
"learning_rate": 0.0001685337470320248,
|
1421 |
+
"loss": 0.5948,
|
1422 |
+
"step": 20900
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 0.78,
|
1426 |
+
"learning_rate": 0.0001682488619267879,
|
1427 |
+
"loss": 0.5911,
|
1428 |
+
"step": 21000
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 0.78,
|
1432 |
+
"eval_loss": 0.6282580494880676,
|
1433 |
+
"eval_runtime": 1313.1215,
|
1434 |
+
"eval_samples_per_second": 0.413,
|
1435 |
+
"eval_steps_per_second": 0.413,
|
1436 |
+
"step": 21000
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 0.79,
|
1440 |
+
"learning_rate": 0.0001679629361585335,
|
1441 |
+
"loss": 0.5716,
|
1442 |
+
"step": 21100
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 0.79,
|
1446 |
+
"learning_rate": 0.00016767597408707594,
|
1447 |
+
"loss": 0.5957,
|
1448 |
+
"step": 21200
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 0.79,
|
1452 |
+
"learning_rate": 0.00016738798008803128,
|
1453 |
+
"loss": 0.6308,
|
1454 |
+
"step": 21300
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 0.8,
|
1458 |
+
"learning_rate": 0.00016709895855275048,
|
1459 |
+
"loss": 0.5891,
|
1460 |
+
"step": 21400
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.8,
|
1464 |
+
"learning_rate": 0.00016680891388825243,
|
1465 |
+
"loss": 0.6104,
|
1466 |
+
"step": 21500
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.81,
|
1470 |
+
"learning_rate": 0.00016651785051715674,
|
1471 |
+
"loss": 0.6344,
|
1472 |
+
"step": 21600
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.81,
|
1476 |
+
"learning_rate": 0.0001662257728776163,
|
1477 |
+
"loss": 0.604,
|
1478 |
+
"step": 21700
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 0.81,
|
1482 |
+
"learning_rate": 0.0001659326854232497,
|
1483 |
+
"loss": 0.6066,
|
1484 |
+
"step": 21800
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 0.82,
|
1488 |
+
"learning_rate": 0.0001656385926230732,
|
1489 |
+
"loss": 0.6324,
|
1490 |
+
"step": 21900
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 0.82,
|
1494 |
+
"learning_rate": 0.00016534349896143264,
|
1495 |
+
"loss": 0.5819,
|
1496 |
+
"step": 22000
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 0.82,
|
1500 |
+
"eval_loss": 0.6218891143798828,
|
1501 |
+
"eval_runtime": 1296.6038,
|
1502 |
+
"eval_samples_per_second": 0.418,
|
1503 |
+
"eval_steps_per_second": 0.418,
|
1504 |
+
"step": 22000
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 0.82,
|
1508 |
+
"learning_rate": 0.00016504740893793512,
|
1509 |
+
"loss": 0.6145,
|
1510 |
+
"step": 22100
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.83,
|
1514 |
+
"learning_rate": 0.00016475032706738023,
|
1515 |
+
"loss": 0.6109,
|
1516 |
+
"step": 22200
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.83,
|
1520 |
+
"learning_rate": 0.0001644522578796914,
|
1521 |
+
"loss": 0.608,
|
1522 |
+
"step": 22300
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.84,
|
1526 |
+
"learning_rate": 0.0001641532059198466,
|
1527 |
+
"loss": 0.565,
|
1528 |
+
"step": 22400
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.84,
|
1532 |
+
"learning_rate": 0.00016385317574780942,
|
1533 |
+
"loss": 0.6139,
|
1534 |
+
"step": 22500
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 0.84,
|
1538 |
+
"learning_rate": 0.000163552171938459,
|
1539 |
+
"loss": 0.5888,
|
1540 |
+
"step": 22600
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 0.85,
|
1544 |
+
"learning_rate": 0.00016325019908152078,
|
1545 |
+
"loss": 0.6065,
|
1546 |
+
"step": 22700
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.85,
|
1550 |
+
"learning_rate": 0.0001629472617814962,
|
1551 |
+
"loss": 0.5959,
|
1552 |
+
"step": 22800
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 0.85,
|
1556 |
+
"learning_rate": 0.00016264336465759258,
|
1557 |
+
"loss": 0.5918,
|
1558 |
+
"step": 22900
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.86,
|
1562 |
+
"learning_rate": 0.0001623385123436528,
|
1563 |
+
"loss": 0.6083,
|
1564 |
+
"step": 23000
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.86,
|
1568 |
+
"eval_loss": 0.6180054545402527,
|
1569 |
+
"eval_runtime": 1278.5639,
|
1570 |
+
"eval_samples_per_second": 0.424,
|
1571 |
+
"eval_steps_per_second": 0.424,
|
1572 |
+
"step": 23000
|
1573 |
}
|
1574 |
],
|
1575 |
"max_steps": 80463,
|
1576 |
"num_train_epochs": 3,
|
1577 |
+
"total_flos": 6.446449236379976e+18,
|
1578 |
"trial_name": null,
|
1579 |
"trial_params": null
|
1580 |
}
|
{checkpoint-19000 β checkpoint-23000}/training_args.bin
RENAMED
File without changes
|