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 sha256:4531cecc4e308a35dc907f81b5204f58f87403a6008584884dae9f8d5e3178ad
|
| 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 sha256:41adcafe7f4fb36e8df90cb2a36c6fc9005eadf99b272fd5a69c8b1c71c58878
|
| 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 sha256:5146063efca63e5eea8f3db237a9d2214ab60b2b370c91142e2b5e596c8cc2ad
|
| 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": 0.8025975518083548,
|
| 1298 |
"eval_steps_per_second": 20.154,
|
| 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": 0.8025975518083548,
|
| 1298 |
"eval_steps_per_second": 20.154,
|
| 1299 |
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.7075913776944704,
|
| 1303 |
+
"grad_norm": 1.590140700340271,
|
| 1304 |
+
"learning_rate": 9.115510777881913e-05,
|
| 1305 |
+
"loss": 0.2743,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.7122774133083412,
|
| 1310 |
+
"grad_norm": 1.7297847270965576,
|
| 1311 |
+
"learning_rate": 9.109653233364575e-05,
|
| 1312 |
+
"loss": 0.3274,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.7169634489222118,
|
| 1317 |
+
"grad_norm": 1.7958931922912598,
|
| 1318 |
+
"learning_rate": 9.103795688847235e-05,
|
| 1319 |
+
"loss": 0.3184,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.7216494845360825,
|
| 1324 |
+
"grad_norm": 1.4942468404769897,
|
| 1325 |
+
"learning_rate": 9.097938144329897e-05,
|
| 1326 |
+
"loss": 0.3055,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.7263355201499532,
|
| 1331 |
+
"grad_norm": 1.6255275011062622,
|
| 1332 |
+
"learning_rate": 9.092080599812559e-05,
|
| 1333 |
+
"loss": 0.3008,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.7310215557638238,
|
| 1338 |
+
"grad_norm": 1.8744940757751465,
|
| 1339 |
+
"learning_rate": 9.086223055295222e-05,
|
| 1340 |
+
"loss": 0.3223,
|
| 1341 |
+
"step": 1560
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.7357075913776945,
|
| 1345 |
+
"grad_norm": 2.46989369392395,
|
| 1346 |
+
"learning_rate": 9.080365510777883e-05,
|
| 1347 |
+
"loss": 0.3255,
|
| 1348 |
+
"step": 1570
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.7403936269915652,
|
| 1352 |
+
"grad_norm": 1.6579105854034424,
|
| 1353 |
+
"learning_rate": 9.074507966260544e-05,
|
| 1354 |
+
"loss": 0.3162,
|
| 1355 |
+
"step": 1580
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.7450796626054358,
|
| 1359 |
+
"grad_norm": 1.74732506275177,
|
| 1360 |
+
"learning_rate": 9.068650421743205e-05,
|
| 1361 |
+
"loss": 0.3602,
|
| 1362 |
+
"step": 1590
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.7497656982193065,
|
| 1366 |
+
"grad_norm": 2.1454904079437256,
|
| 1367 |
+
"learning_rate": 9.062792877225867e-05,
|
| 1368 |
+
"loss": 0.3411,
|
| 1369 |
+
"step": 1600
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.7497656982193065,
|
| 1373 |
+
"eval_loss": 0.04926175996661186,
|
| 1374 |
+
"eval_pearson_cosine": 0.8161287135448276,
|
| 1375 |
+
"eval_pearson_dot": 0.8223874860494362,
|
| 1376 |
+
"eval_pearson_euclidean": 0.8018699359881083,
|
| 1377 |
+
"eval_pearson_manhattan": 0.8013834703697782,
|
| 1378 |
+
"eval_runtime": 4.7094,
|
| 1379 |
+
"eval_samples_per_second": 318.509,
|
| 1380 |
+
"eval_spearman_cosine": 0.8189562831716073,
|
| 1381 |
+
"eval_spearman_dot": 0.8236193691999756,
|
| 1382 |
+
"eval_spearman_euclidean": 0.8078062231815545,
|
| 1383 |
+
"eval_spearman_manhattan": 0.8072727629308311,
|
| 1384 |
+
"eval_steps_per_second": 19.96,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.7544517338331771,
|
| 1389 |
+
"grad_norm": 2.28283953666687,
|
| 1390 |
+
"learning_rate": 9.056935332708529e-05,
|
| 1391 |
+
"loss": 0.3234,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.7591377694470478,
|
| 1396 |
+
"grad_norm": 1.6917240619659424,
|
| 1397 |
+
"learning_rate": 9.051077788191192e-05,
|
| 1398 |
+
"loss": 0.352,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.7638238050609185,
|
| 1403 |
+
"grad_norm": 1.712475061416626,
|
| 1404 |
+
"learning_rate": 9.045220243673852e-05,
|
| 1405 |
+
"loss": 0.3107,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.7685098406747891,
|
| 1410 |
+
"grad_norm": 1.6429861783981323,
|
| 1411 |
+
"learning_rate": 9.039362699156514e-05,
|
| 1412 |
+
"loss": 0.3175,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.7731958762886598,
|
| 1417 |
+
"grad_norm": 1.5003321170806885,
|
| 1418 |
+
"learning_rate": 9.033505154639176e-05,
|
| 1419 |
+
"loss": 0.3502,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.7778819119025304,
|
| 1424 |
+
"grad_norm": 1.9713871479034424,
|
| 1425 |
+
"learning_rate": 9.027647610121837e-05,
|
| 1426 |
+
"loss": 0.3691,
|
| 1427 |
+
"step": 1660
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.7825679475164011,
|
| 1431 |
+
"grad_norm": 2.0830156803131104,
|
| 1432 |
+
"learning_rate": 9.021790065604499e-05,
|
| 1433 |
+
"loss": 0.3226,
|
| 1434 |
+
"step": 1670
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.7872539831302718,
|
| 1438 |
+
"grad_norm": 2.0364925861358643,
|
| 1439 |
+
"learning_rate": 9.015932521087161e-05,
|
| 1440 |
+
"loss": 0.3344,
|
| 1441 |
+
"step": 1680
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.7919400187441424,
|
| 1445 |
+
"grad_norm": 1.7688632011413574,
|
| 1446 |
+
"learning_rate": 9.010074976569822e-05,
|
| 1447 |
+
"loss": 0.328,
|
| 1448 |
+
"step": 1690
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.7966260543580131,
|
| 1452 |
+
"grad_norm": 2.0706257820129395,
|
| 1453 |
+
"learning_rate": 9.004217432052484e-05,
|
| 1454 |
+
"loss": 0.3284,
|
| 1455 |
+
"step": 1700
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.7966260543580131,
|
| 1459 |
+
"eval_loss": 0.042656708508729935,
|
| 1460 |
+
"eval_pearson_cosine": 0.8112926503111737,
|
| 1461 |
+
"eval_pearson_dot": 0.818754256660867,
|
| 1462 |
+
"eval_pearson_euclidean": 0.7946703633011838,
|
| 1463 |
+
"eval_pearson_manhattan": 0.7944877991875288,
|
| 1464 |
+
"eval_runtime": 4.8215,
|
| 1465 |
+
"eval_samples_per_second": 311.103,
|
| 1466 |
+
"eval_spearman_cosine": 0.812852551114096,
|
| 1467 |
+
"eval_spearman_dot": 0.8198186422414758,
|
| 1468 |
+
"eval_spearman_euclidean": 0.8004155438327007,
|
| 1469 |
+
"eval_spearman_manhattan": 0.8002132702523219,
|
| 1470 |
+
"eval_steps_per_second": 19.496,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.8013120899718837,
|
| 1475 |
+
"grad_norm": 1.6608582735061646,
|
| 1476 |
+
"learning_rate": 8.998359887535146e-05,
|
| 1477 |
+
"loss": 0.3321,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.8059981255857545,
|
| 1482 |
+
"grad_norm": 2.178337574005127,
|
| 1483 |
+
"learning_rate": 8.992502343017808e-05,
|
| 1484 |
+
"loss": 0.3289,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.8106841611996252,
|
| 1489 |
+
"grad_norm": 2.123746633529663,
|
| 1490 |
+
"learning_rate": 8.986644798500469e-05,
|
| 1491 |
+
"loss": 0.3393,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.8153701968134958,
|
| 1496 |
+
"grad_norm": 1.5920015573501587,
|
| 1497 |
+
"learning_rate": 8.980787253983131e-05,
|
| 1498 |
+
"loss": 0.3137,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.8200562324273665,
|
| 1503 |
+
"grad_norm": 1.6964048147201538,
|
| 1504 |
+
"learning_rate": 8.974929709465793e-05,
|
| 1505 |
+
"loss": 0.3242,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.8247422680412371,
|
| 1510 |
+
"grad_norm": 2.2545530796051025,
|
| 1511 |
+
"learning_rate": 8.969072164948454e-05,
|
| 1512 |
+
"loss": 0.3473,
|
| 1513 |
+
"step": 1760
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.8294283036551078,
|
| 1517 |
+
"grad_norm": 1.829145073890686,
|
| 1518 |
+
"learning_rate": 8.963214620431116e-05,
|
| 1519 |
+
"loss": 0.2871,
|
| 1520 |
+
"step": 1770
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.8341143392689785,
|
| 1524 |
+
"grad_norm": 1.7790557146072388,
|
| 1525 |
+
"learning_rate": 8.957357075913777e-05,
|
| 1526 |
+
"loss": 0.2979,
|
| 1527 |
+
"step": 1780
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.8388003748828491,
|
| 1531 |
+
"grad_norm": 1.6724668741226196,
|
| 1532 |
+
"learning_rate": 8.95149953139644e-05,
|
| 1533 |
+
"loss": 0.3094,
|
| 1534 |
+
"step": 1790
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.8434864104967198,
|
| 1538 |
+
"grad_norm": 1.939370036125183,
|
| 1539 |
+
"learning_rate": 8.945641986879101e-05,
|
| 1540 |
+
"loss": 0.2845,
|
| 1541 |
+
"step": 1800
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.8434864104967198,
|
| 1545 |
+
"eval_loss": 0.04392844811081886,
|
| 1546 |
+
"eval_pearson_cosine": 0.8097501259779989,
|
| 1547 |
+
"eval_pearson_dot": 0.8164764225020082,
|
| 1548 |
+
"eval_pearson_euclidean": 0.7921053664943116,
|
| 1549 |
+
"eval_pearson_manhattan": 0.7914097303155287,
|
| 1550 |
+
"eval_runtime": 4.6495,
|
| 1551 |
+
"eval_samples_per_second": 322.617,
|
| 1552 |
+
"eval_spearman_cosine": 0.8123240085388628,
|
| 1553 |
+
"eval_spearman_dot": 0.8183737971290131,
|
| 1554 |
+
"eval_spearman_euclidean": 0.7989029211686818,
|
| 1555 |
+
"eval_spearman_manhattan": 0.7978239561899777,
|
| 1556 |
+
"eval_steps_per_second": 20.217,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8481724461105904,
|
| 1561 |
+
"grad_norm": 1.730468511581421,
|
| 1562 |
+
"learning_rate": 8.939784442361763e-05,
|
| 1563 |
+
"loss": 0.3206,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.8528584817244611,
|
| 1568 |
+
"grad_norm": 1.5852857828140259,
|
| 1569 |
+
"learning_rate": 8.933926897844423e-05,
|
| 1570 |
+
"loss": 0.3159,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8575445173383318,
|
| 1575 |
+
"grad_norm": 1.507568597793579,
|
| 1576 |
+
"learning_rate": 8.928069353327085e-05,
|
| 1577 |
+
"loss": 0.3019,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8622305529522024,
|
| 1582 |
+
"grad_norm": 1.661995768547058,
|
| 1583 |
+
"learning_rate": 8.922211808809747e-05,
|
| 1584 |
+
"loss": 0.3407,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8669165885660731,
|
| 1589 |
+
"grad_norm": 1.877208948135376,
|
| 1590 |
+
"learning_rate": 8.91635426429241e-05,
|
| 1591 |
+
"loss": 0.322,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8716026241799437,
|
| 1596 |
+
"grad_norm": 1.6956888437271118,
|
| 1597 |
+
"learning_rate": 8.910496719775072e-05,
|
| 1598 |
+
"loss": 0.3434,
|
| 1599 |
+
"step": 1860
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8762886597938144,
|
| 1603 |
+
"grad_norm": 1.8181349039077759,
|
| 1604 |
+
"learning_rate": 8.904639175257732e-05,
|
| 1605 |
+
"loss": 0.316,
|
| 1606 |
+
"step": 1870
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8809746954076851,
|
| 1610 |
+
"grad_norm": 1.7894842624664307,
|
| 1611 |
+
"learning_rate": 8.898781630740394e-05,
|
| 1612 |
+
"loss": 0.2881,
|
| 1613 |
+
"step": 1880
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8856607310215557,
|
| 1617 |
+
"grad_norm": 2.1654884815216064,
|
| 1618 |
+
"learning_rate": 8.892924086223055e-05,
|
| 1619 |
+
"loss": 0.3423,
|
| 1620 |
+
"step": 1890
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8903467666354264,
|
| 1624 |
+
"grad_norm": 1.6889327764511108,
|
| 1625 |
+
"learning_rate": 8.887066541705717e-05,
|
| 1626 |
+
"loss": 0.3199,
|
| 1627 |
+
"step": 1900
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8903467666354264,
|
| 1631 |
+
"eval_loss": 0.05001167580485344,
|
| 1632 |
+
"eval_pearson_cosine": 0.8149866383088806,
|
| 1633 |
+
"eval_pearson_dot": 0.8233746991643329,
|
| 1634 |
+
"eval_pearson_euclidean": 0.7989509074968737,
|
| 1635 |
+
"eval_pearson_manhattan": 0.7988165127794176,
|
| 1636 |
+
"eval_runtime": 4.7223,
|
| 1637 |
+
"eval_samples_per_second": 317.643,
|
| 1638 |
+
"eval_spearman_cosine": 0.819837111960085,
|
| 1639 |
+
"eval_spearman_dot": 0.8273224990756979,
|
| 1640 |
+
"eval_spearman_euclidean": 0.805295090022205,
|
| 1641 |
+
"eval_spearman_manhattan": 0.8050664910203635,
|
| 1642 |
+
"eval_steps_per_second": 19.906,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.895032802249297,
|
| 1647 |
+
"grad_norm": 2.3411951065063477,
|
| 1648 |
+
"learning_rate": 8.88120899718838e-05,
|
| 1649 |
+
"loss": 0.3137,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.8997188378631678,
|
| 1654 |
+
"grad_norm": 2.0821354389190674,
|
| 1655 |
+
"learning_rate": 8.87535145267104e-05,
|
| 1656 |
+
"loss": 0.2934,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.9044048734770385,
|
| 1661 |
+
"grad_norm": 1.8365401029586792,
|
| 1662 |
+
"learning_rate": 8.869493908153702e-05,
|
| 1663 |
+
"loss": 0.3322,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.9090909090909091,
|
| 1668 |
+
"grad_norm": 2.154188632965088,
|
| 1669 |
+
"learning_rate": 8.863636363636364e-05,
|
| 1670 |
+
"loss": 0.2862,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.9137769447047798,
|
| 1675 |
+
"grad_norm": 2.136406421661377,
|
| 1676 |
+
"learning_rate": 8.857778819119026e-05,
|
| 1677 |
+
"loss": 0.3336,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 0.9184629803186504,
|
| 1682 |
+
"grad_norm": 2.426302671432495,
|
| 1683 |
+
"learning_rate": 8.851921274601687e-05,
|
| 1684 |
+
"loss": 0.3486,
|
| 1685 |
+
"step": 1960
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 0.9231490159325211,
|
| 1689 |
+
"grad_norm": 2.407034397125244,
|
| 1690 |
+
"learning_rate": 8.846063730084349e-05,
|
| 1691 |
+
"loss": 0.3377,
|
| 1692 |
+
"step": 1970
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 0.9278350515463918,
|
| 1696 |
+
"grad_norm": 2.170762062072754,
|
| 1697 |
+
"learning_rate": 8.840206185567011e-05,
|
| 1698 |
+
"loss": 0.2904,
|
| 1699 |
+
"step": 1980
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 0.9325210871602624,
|
| 1703 |
+
"grad_norm": 1.6726795434951782,
|
| 1704 |
+
"learning_rate": 8.834348641049672e-05,
|
| 1705 |
+
"loss": 0.3535,
|
| 1706 |
+
"step": 1990
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.9372071227741331,
|
| 1710 |
+
"grad_norm": 1.835772156715393,
|
| 1711 |
+
"learning_rate": 8.828491096532334e-05,
|
| 1712 |
+
"loss": 0.3544,
|
| 1713 |
+
"step": 2000
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.9372071227741331,
|
| 1717 |
+
"eval_loss": 0.06010111793875694,
|
| 1718 |
+
"eval_pearson_cosine": 0.7969487570615001,
|
| 1719 |
+
"eval_pearson_dot": 0.8113433756657784,
|
| 1720 |
+
"eval_pearson_euclidean": 0.7775976461343248,
|
| 1721 |
+
"eval_pearson_manhattan": 0.7779361917572194,
|
| 1722 |
+
"eval_runtime": 4.7319,
|
| 1723 |
+
"eval_samples_per_second": 316.998,
|
| 1724 |
+
"eval_spearman_cosine": 0.8015033854161633,
|
| 1725 |
+
"eval_spearman_dot": 0.8149867800941926,
|
| 1726 |
+
"eval_spearman_euclidean": 0.7812746949762143,
|
| 1727 |
+
"eval_spearman_manhattan": 0.7818782293686074,
|
| 1728 |
+
"eval_steps_per_second": 19.865,
|
| 1729 |
+
"step": 2000
|
| 1730 |
}
|
| 1731 |
],
|
| 1732 |
"logging_steps": 10,
|