Training in progress, step 2000, 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 735217848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:784ba4d6b323f80b32bdeb7a699b9493ed33877eb1f5a4680739df590c874265
|
| 3 |
size 735217848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470521978
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:463d10606216eaac5990abb66ecffc932b652d3d4835e35f52c38d3e543733ff
|
| 3 |
size 1470521978
|
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 sha256:0886b5e6b4eb6c54d008834760837138a75d96ac8156628b1654cc847af0e990
|
| 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 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd992b247e47b39b5cc00365846a4ed7e75fe3dd899b2263e283f44789d5c49b
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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,
|
|
@@ -1297,6 +1297,436 @@
|
|
| 1297 |
"eval_spearman_manhattan": 0.8335300441487923,
|
| 1298 |
"eval_steps_per_second": 15.221,
|
| 1299 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1300 |
}
|
| 1301 |
],
|
| 1302 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9372071227741331,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1297 |
"eval_spearman_manhattan": 0.8335300441487923,
|
| 1298 |
"eval_steps_per_second": 15.221,
|
| 1299 |
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.7075913776944704,
|
| 1303 |
+
"grad_norm": 1.3322237730026245,
|
| 1304 |
+
"learning_rate": 4.5577553889409565e-05,
|
| 1305 |
+
"loss": 0.27,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.7122774133083412,
|
| 1310 |
+
"grad_norm": 1.707694172859192,
|
| 1311 |
+
"learning_rate": 4.5548266166822874e-05,
|
| 1312 |
+
"loss": 0.3249,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.7169634489222118,
|
| 1317 |
+
"grad_norm": 1.280220627784729,
|
| 1318 |
+
"learning_rate": 4.5518978444236176e-05,
|
| 1319 |
+
"loss": 0.3021,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.7216494845360825,
|
| 1324 |
+
"grad_norm": 1.2478505373001099,
|
| 1325 |
+
"learning_rate": 4.5489690721649484e-05,
|
| 1326 |
+
"loss": 0.3033,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.7263355201499532,
|
| 1331 |
+
"grad_norm": 1.5291355848312378,
|
| 1332 |
+
"learning_rate": 4.546040299906279e-05,
|
| 1333 |
+
"loss": 0.2789,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.7310215557638238,
|
| 1338 |
+
"grad_norm": 1.6631042957305908,
|
| 1339 |
+
"learning_rate": 4.543111527647611e-05,
|
| 1340 |
+
"loss": 0.3271,
|
| 1341 |
+
"step": 1560
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.7357075913776945,
|
| 1345 |
+
"grad_norm": 1.5178686380386353,
|
| 1346 |
+
"learning_rate": 4.540182755388942e-05,
|
| 1347 |
+
"loss": 0.3092,
|
| 1348 |
+
"step": 1570
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.7403936269915652,
|
| 1352 |
+
"grad_norm": 1.043636441230774,
|
| 1353 |
+
"learning_rate": 4.537253983130272e-05,
|
| 1354 |
+
"loss": 0.2863,
|
| 1355 |
+
"step": 1580
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.7450796626054358,
|
| 1359 |
+
"grad_norm": 1.2474050521850586,
|
| 1360 |
+
"learning_rate": 4.534325210871603e-05,
|
| 1361 |
+
"loss": 0.3184,
|
| 1362 |
+
"step": 1590
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.7497656982193065,
|
| 1366 |
+
"grad_norm": 1.5337306261062622,
|
| 1367 |
+
"learning_rate": 4.5313964386129336e-05,
|
| 1368 |
+
"loss": 0.3201,
|
| 1369 |
+
"step": 1600
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.7497656982193065,
|
| 1373 |
+
"eval_loss": 0.04666765406727791,
|
| 1374 |
+
"eval_pearson_cosine": 0.8247560159233132,
|
| 1375 |
+
"eval_pearson_dot": 0.7799855816644161,
|
| 1376 |
+
"eval_pearson_euclidean": 0.8221947952436466,
|
| 1377 |
+
"eval_pearson_manhattan": 0.823206574209081,
|
| 1378 |
+
"eval_runtime": 6.3641,
|
| 1379 |
+
"eval_samples_per_second": 235.697,
|
| 1380 |
+
"eval_spearman_cosine": 0.8268195350952193,
|
| 1381 |
+
"eval_spearman_dot": 0.7772130800409067,
|
| 1382 |
+
"eval_spearman_euclidean": 0.8274185345815266,
|
| 1383 |
+
"eval_spearman_manhattan": 0.8282217123816773,
|
| 1384 |
+
"eval_steps_per_second": 14.77,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.7544517338331771,
|
| 1389 |
+
"grad_norm": 1.8070961236953735,
|
| 1390 |
+
"learning_rate": 4.5284676663542644e-05,
|
| 1391 |
+
"loss": 0.2939,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.7591377694470478,
|
| 1396 |
+
"grad_norm": 1.3418357372283936,
|
| 1397 |
+
"learning_rate": 4.525538894095596e-05,
|
| 1398 |
+
"loss": 0.3122,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.7638238050609185,
|
| 1403 |
+
"grad_norm": 1.4164036512374878,
|
| 1404 |
+
"learning_rate": 4.522610121836926e-05,
|
| 1405 |
+
"loss": 0.294,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.7685098406747891,
|
| 1410 |
+
"grad_norm": 1.4862034320831299,
|
| 1411 |
+
"learning_rate": 4.519681349578257e-05,
|
| 1412 |
+
"loss": 0.3087,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.7731958762886598,
|
| 1417 |
+
"grad_norm": 1.3497341871261597,
|
| 1418 |
+
"learning_rate": 4.516752577319588e-05,
|
| 1419 |
+
"loss": 0.3135,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.7778819119025304,
|
| 1424 |
+
"grad_norm": 1.4912623167037964,
|
| 1425 |
+
"learning_rate": 4.513823805060919e-05,
|
| 1426 |
+
"loss": 0.3556,
|
| 1427 |
+
"step": 1660
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.7825679475164011,
|
| 1431 |
+
"grad_norm": 1.4625390768051147,
|
| 1432 |
+
"learning_rate": 4.5108950328022495e-05,
|
| 1433 |
+
"loss": 0.2913,
|
| 1434 |
+
"step": 1670
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.7872539831302718,
|
| 1438 |
+
"grad_norm": 1.7304317951202393,
|
| 1439 |
+
"learning_rate": 4.5079662605435804e-05,
|
| 1440 |
+
"loss": 0.3139,
|
| 1441 |
+
"step": 1680
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.7919400187441424,
|
| 1445 |
+
"grad_norm": 1.4902634620666504,
|
| 1446 |
+
"learning_rate": 4.505037488284911e-05,
|
| 1447 |
+
"loss": 0.3286,
|
| 1448 |
+
"step": 1690
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.7966260543580131,
|
| 1452 |
+
"grad_norm": 1.2882981300354004,
|
| 1453 |
+
"learning_rate": 4.502108716026242e-05,
|
| 1454 |
+
"loss": 0.3199,
|
| 1455 |
+
"step": 1700
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.7966260543580131,
|
| 1459 |
+
"eval_loss": 0.05109428986907005,
|
| 1460 |
+
"eval_pearson_cosine": 0.821506482740503,
|
| 1461 |
+
"eval_pearson_dot": 0.7701997371934368,
|
| 1462 |
+
"eval_pearson_euclidean": 0.8256940312734855,
|
| 1463 |
+
"eval_pearson_manhattan": 0.8266471352779732,
|
| 1464 |
+
"eval_runtime": 5.9909,
|
| 1465 |
+
"eval_samples_per_second": 250.381,
|
| 1466 |
+
"eval_spearman_cosine": 0.8238836226780246,
|
| 1467 |
+
"eval_spearman_dot": 0.7658343447023538,
|
| 1468 |
+
"eval_spearman_euclidean": 0.8307515392696511,
|
| 1469 |
+
"eval_spearman_manhattan": 0.8322184136990032,
|
| 1470 |
+
"eval_steps_per_second": 15.691,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.8013120899718837,
|
| 1475 |
+
"grad_norm": 1.4731862545013428,
|
| 1476 |
+
"learning_rate": 4.499179943767573e-05,
|
| 1477 |
+
"loss": 0.3262,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.8059981255857545,
|
| 1482 |
+
"grad_norm": 1.440738320350647,
|
| 1483 |
+
"learning_rate": 4.496251171508904e-05,
|
| 1484 |
+
"loss": 0.2911,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.8106841611996252,
|
| 1489 |
+
"grad_norm": 1.594072699546814,
|
| 1490 |
+
"learning_rate": 4.4933223992502347e-05,
|
| 1491 |
+
"loss": 0.3067,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.8153701968134958,
|
| 1496 |
+
"grad_norm": 1.2838362455368042,
|
| 1497 |
+
"learning_rate": 4.4903936269915655e-05,
|
| 1498 |
+
"loss": 0.2976,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.8200562324273665,
|
| 1503 |
+
"grad_norm": 1.3946473598480225,
|
| 1504 |
+
"learning_rate": 4.4874648547328964e-05,
|
| 1505 |
+
"loss": 0.2945,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.8247422680412371,
|
| 1510 |
+
"grad_norm": 1.5584791898727417,
|
| 1511 |
+
"learning_rate": 4.484536082474227e-05,
|
| 1512 |
+
"loss": 0.3196,
|
| 1513 |
+
"step": 1760
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.8294283036551078,
|
| 1517 |
+
"grad_norm": 1.5150123834609985,
|
| 1518 |
+
"learning_rate": 4.481607310215558e-05,
|
| 1519 |
+
"loss": 0.2792,
|
| 1520 |
+
"step": 1770
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.8341143392689785,
|
| 1524 |
+
"grad_norm": 1.5679230690002441,
|
| 1525 |
+
"learning_rate": 4.478678537956888e-05,
|
| 1526 |
+
"loss": 0.289,
|
| 1527 |
+
"step": 1780
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.8388003748828491,
|
| 1531 |
+
"grad_norm": 1.100917100906372,
|
| 1532 |
+
"learning_rate": 4.47574976569822e-05,
|
| 1533 |
+
"loss": 0.3021,
|
| 1534 |
+
"step": 1790
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.8434864104967198,
|
| 1538 |
+
"grad_norm": 1.6804919242858887,
|
| 1539 |
+
"learning_rate": 4.4728209934395506e-05,
|
| 1540 |
+
"loss": 0.2431,
|
| 1541 |
+
"step": 1800
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.8434864104967198,
|
| 1545 |
+
"eval_loss": 0.04816513508558273,
|
| 1546 |
+
"eval_pearson_cosine": 0.8270891703367056,
|
| 1547 |
+
"eval_pearson_dot": 0.7790513762200462,
|
| 1548 |
+
"eval_pearson_euclidean": 0.8276507097787587,
|
| 1549 |
+
"eval_pearson_manhattan": 0.8282151299272726,
|
| 1550 |
+
"eval_runtime": 6.0115,
|
| 1551 |
+
"eval_samples_per_second": 249.523,
|
| 1552 |
+
"eval_spearman_cosine": 0.8286758008396278,
|
| 1553 |
+
"eval_spearman_dot": 0.7748761234075037,
|
| 1554 |
+
"eval_spearman_euclidean": 0.8326421047981132,
|
| 1555 |
+
"eval_spearman_manhattan": 0.8332581593954519,
|
| 1556 |
+
"eval_steps_per_second": 15.637,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8481724461105904,
|
| 1561 |
+
"grad_norm": 1.3295296430587769,
|
| 1562 |
+
"learning_rate": 4.4698922211808815e-05,
|
| 1563 |
+
"loss": 0.2877,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8528584817244611,
|
| 1568 |
+
"grad_norm": 1.3233381509780884,
|
| 1569 |
+
"learning_rate": 4.466963448922212e-05,
|
| 1570 |
+
"loss": 0.2982,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8575445173383318,
|
| 1575 |
+
"grad_norm": 1.5737247467041016,
|
| 1576 |
+
"learning_rate": 4.4640346766635425e-05,
|
| 1577 |
+
"loss": 0.2939,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8622305529522024,
|
| 1582 |
+
"grad_norm": 1.4237866401672363,
|
| 1583 |
+
"learning_rate": 4.4611059044048734e-05,
|
| 1584 |
+
"loss": 0.3154,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8669165885660731,
|
| 1589 |
+
"grad_norm": 1.4213505983352661,
|
| 1590 |
+
"learning_rate": 4.458177132146205e-05,
|
| 1591 |
+
"loss": 0.3085,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8716026241799437,
|
| 1596 |
+
"grad_norm": 1.4691981077194214,
|
| 1597 |
+
"learning_rate": 4.455248359887536e-05,
|
| 1598 |
+
"loss": 0.3141,
|
| 1599 |
+
"step": 1860
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8762886597938144,
|
| 1603 |
+
"grad_norm": 1.2567983865737915,
|
| 1604 |
+
"learning_rate": 4.452319587628866e-05,
|
| 1605 |
+
"loss": 0.2998,
|
| 1606 |
+
"step": 1870
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8809746954076851,
|
| 1610 |
+
"grad_norm": 1.359161615371704,
|
| 1611 |
+
"learning_rate": 4.449390815370197e-05,
|
| 1612 |
+
"loss": 0.2891,
|
| 1613 |
+
"step": 1880
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8856607310215557,
|
| 1617 |
+
"grad_norm": 1.4557381868362427,
|
| 1618 |
+
"learning_rate": 4.4464620431115277e-05,
|
| 1619 |
+
"loss": 0.3068,
|
| 1620 |
+
"step": 1890
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8903467666354264,
|
| 1624 |
+
"grad_norm": 1.2976425886154175,
|
| 1625 |
+
"learning_rate": 4.4435332708528585e-05,
|
| 1626 |
+
"loss": 0.3051,
|
| 1627 |
+
"step": 1900
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8903467666354264,
|
| 1631 |
+
"eval_loss": 0.04645664617419243,
|
| 1632 |
+
"eval_pearson_cosine": 0.8277422687657179,
|
| 1633 |
+
"eval_pearson_dot": 0.7813512072475213,
|
| 1634 |
+
"eval_pearson_euclidean": 0.8249433703124964,
|
| 1635 |
+
"eval_pearson_manhattan": 0.8257048412620271,
|
| 1636 |
+
"eval_runtime": 6.5216,
|
| 1637 |
+
"eval_samples_per_second": 230.006,
|
| 1638 |
+
"eval_spearman_cosine": 0.829450894301767,
|
| 1639 |
+
"eval_spearman_dot": 0.778239364994612,
|
| 1640 |
+
"eval_spearman_euclidean": 0.8318708700161123,
|
| 1641 |
+
"eval_spearman_manhattan": 0.8323977739737524,
|
| 1642 |
+
"eval_steps_per_second": 14.414,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.895032802249297,
|
| 1647 |
+
"grad_norm": 2.003398895263672,
|
| 1648 |
+
"learning_rate": 4.44060449859419e-05,
|
| 1649 |
+
"loss": 0.3261,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.8997188378631678,
|
| 1654 |
+
"grad_norm": 1.5879777669906616,
|
| 1655 |
+
"learning_rate": 4.43767572633552e-05,
|
| 1656 |
+
"loss": 0.2905,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.9044048734770385,
|
| 1661 |
+
"grad_norm": 1.239495873451233,
|
| 1662 |
+
"learning_rate": 4.434746954076851e-05,
|
| 1663 |
+
"loss": 0.3005,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.9090909090909091,
|
| 1668 |
+
"grad_norm": 1.643388271331787,
|
| 1669 |
+
"learning_rate": 4.431818181818182e-05,
|
| 1670 |
+
"loss": 0.2901,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.9137769447047798,
|
| 1675 |
+
"grad_norm": 1.5589861869812012,
|
| 1676 |
+
"learning_rate": 4.428889409559513e-05,
|
| 1677 |
+
"loss": 0.269,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 0.9184629803186504,
|
| 1682 |
+
"grad_norm": 1.9895987510681152,
|
| 1683 |
+
"learning_rate": 4.4259606373008436e-05,
|
| 1684 |
+
"loss": 0.3354,
|
| 1685 |
+
"step": 1960
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 0.9231490159325211,
|
| 1689 |
+
"grad_norm": 1.5158389806747437,
|
| 1690 |
+
"learning_rate": 4.4230318650421745e-05,
|
| 1691 |
+
"loss": 0.2987,
|
| 1692 |
+
"step": 1970
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 0.9278350515463918,
|
| 1696 |
+
"grad_norm": 1.498703956604004,
|
| 1697 |
+
"learning_rate": 4.4201030927835053e-05,
|
| 1698 |
+
"loss": 0.2703,
|
| 1699 |
+
"step": 1980
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.9325210871602624,
|
| 1703 |
+
"grad_norm": 1.609595537185669,
|
| 1704 |
+
"learning_rate": 4.417174320524836e-05,
|
| 1705 |
+
"loss": 0.3511,
|
| 1706 |
+
"step": 1990
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.9372071227741331,
|
| 1710 |
+
"grad_norm": 1.5775402784347534,
|
| 1711 |
+
"learning_rate": 4.414245548266167e-05,
|
| 1712 |
+
"loss": 0.3287,
|
| 1713 |
+
"step": 2000
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.9372071227741331,
|
| 1717 |
+
"eval_loss": 0.05509389936923981,
|
| 1718 |
+
"eval_pearson_cosine": 0.8207199970543648,
|
| 1719 |
+
"eval_pearson_dot": 0.7620359249952955,
|
| 1720 |
+
"eval_pearson_euclidean": 0.8229490445973937,
|
| 1721 |
+
"eval_pearson_manhattan": 0.8238150410767417,
|
| 1722 |
+
"eval_runtime": 6.0216,
|
| 1723 |
+
"eval_samples_per_second": 249.103,
|
| 1724 |
+
"eval_spearman_cosine": 0.8243786401215701,
|
| 1725 |
+
"eval_spearman_dot": 0.7569267777069086,
|
| 1726 |
+
"eval_spearman_euclidean": 0.8286694906125902,
|
| 1727 |
+
"eval_spearman_manhattan": 0.8295593456330026,
|
| 1728 |
+
"eval_steps_per_second": 15.61,
|
| 1729 |
+
"step": 2000
|
| 1730 |
}
|
| 1731 |
],
|
| 1732 |
"logging_steps": 10,
|