Training in progress, step 1570, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8e6c870be5ceb8d82d0276ee27cb8d12f00d46d0db1c5f7fbed3b4273a62fbd
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8954329d1712a93afa49f43d0cc235897230fe1ab751f74db559f6d9500ae6dd
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c607914c335452bf5c978af3416182d3900072495f5b292a3cf9fa6af1683ef4
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0cfaa6e1371e6c425f66388060aaf89aa8e079158baefb2a1a9d5b7295faa4d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1288,6 +1288,306 @@
|
|
| 1288 |
"mean_token_accuracy": 0.7434597261250019,
|
| 1289 |
"num_tokens": 5910222.0,
|
| 1290 |
"step": 1270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1291 |
}
|
| 1292 |
],
|
| 1293 |
"logging_steps": 10,
|
|
@@ -1307,7 +1607,7 @@
|
|
| 1307 |
"attributes": {}
|
| 1308 |
}
|
| 1309 |
},
|
| 1310 |
-
"total_flos":
|
| 1311 |
"train_batch_size": 4,
|
| 1312 |
"trial_name": null,
|
| 1313 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.33493333333333336,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1288 |
"mean_token_accuracy": 0.7434597261250019,
|
| 1289 |
"num_tokens": 5910222.0,
|
| 1290 |
"step": 1270
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 0.9681669734418392,
|
| 1294 |
+
"epoch": 0.2730666666666667,
|
| 1295 |
+
"grad_norm": 0.2539491653442383,
|
| 1296 |
+
"learning_rate": 9.715648094050087e-05,
|
| 1297 |
+
"loss": 1.0889246940612793,
|
| 1298 |
+
"mean_token_accuracy": 0.7573506951332092,
|
| 1299 |
+
"num_tokens": 5958487.0,
|
| 1300 |
+
"step": 1280
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 0.9369139075279236,
|
| 1304 |
+
"epoch": 0.2752,
|
| 1305 |
+
"grad_norm": 0.29088094830513,
|
| 1306 |
+
"learning_rate": 9.709866524527588e-05,
|
| 1307 |
+
"loss": 1.0017178535461426,
|
| 1308 |
+
"mean_token_accuracy": 0.7683532252907753,
|
| 1309 |
+
"num_tokens": 6002949.0,
|
| 1310 |
+
"step": 1290
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 1.0060899198055266,
|
| 1314 |
+
"epoch": 0.2773333333333333,
|
| 1315 |
+
"grad_norm": 0.2669098675251007,
|
| 1316 |
+
"learning_rate": 9.704028523850392e-05,
|
| 1317 |
+
"loss": 1.0900717735290528,
|
| 1318 |
+
"mean_token_accuracy": 0.7483311414718627,
|
| 1319 |
+
"num_tokens": 6053462.0,
|
| 1320 |
+
"step": 1300
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 0.9726419121026992,
|
| 1324 |
+
"epoch": 0.27946666666666664,
|
| 1325 |
+
"grad_norm": 0.2472907453775406,
|
| 1326 |
+
"learning_rate": 9.698134161966363e-05,
|
| 1327 |
+
"loss": 1.1085708618164063,
|
| 1328 |
+
"mean_token_accuracy": 0.7585345059633255,
|
| 1329 |
+
"num_tokens": 6103810.0,
|
| 1330 |
+
"step": 1310
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 0.9410715244710446,
|
| 1334 |
+
"epoch": 0.2816,
|
| 1335 |
+
"grad_norm": 0.2315952181816101,
|
| 1336 |
+
"learning_rate": 9.692183509498659e-05,
|
| 1337 |
+
"loss": 1.04432373046875,
|
| 1338 |
+
"mean_token_accuracy": 0.7650494173169136,
|
| 1339 |
+
"num_tokens": 6149332.0,
|
| 1340 |
+
"step": 1320
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 0.9582152135670186,
|
| 1344 |
+
"epoch": 0.28373333333333334,
|
| 1345 |
+
"grad_norm": 0.28324106335639954,
|
| 1346 |
+
"learning_rate": 9.686176637744884e-05,
|
| 1347 |
+
"loss": 1.0879361152648925,
|
| 1348 |
+
"mean_token_accuracy": 0.7590656578540802,
|
| 1349 |
+
"num_tokens": 6193221.0,
|
| 1350 |
+
"step": 1330
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 0.8448746472597122,
|
| 1354 |
+
"epoch": 0.28586666666666666,
|
| 1355 |
+
"grad_norm": 0.27708905935287476,
|
| 1356 |
+
"learning_rate": 9.680113618676229e-05,
|
| 1357 |
+
"loss": 0.9311987876892089,
|
| 1358 |
+
"mean_token_accuracy": 0.7856365889310837,
|
| 1359 |
+
"num_tokens": 6238920.0,
|
| 1360 |
+
"step": 1340
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 0.9729965463280678,
|
| 1364 |
+
"epoch": 0.288,
|
| 1365 |
+
"grad_norm": 0.2840976119041443,
|
| 1366 |
+
"learning_rate": 9.673994524936615e-05,
|
| 1367 |
+
"loss": 1.0606694221496582,
|
| 1368 |
+
"mean_token_accuracy": 0.7592033997178078,
|
| 1369 |
+
"num_tokens": 6286552.0,
|
| 1370 |
+
"step": 1350
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 0.9429876990616322,
|
| 1374 |
+
"epoch": 0.29013333333333335,
|
| 1375 |
+
"grad_norm": 0.2964062988758087,
|
| 1376 |
+
"learning_rate": 9.667819429841817e-05,
|
| 1377 |
+
"loss": 1.0691003799438477,
|
| 1378 |
+
"mean_token_accuracy": 0.7747758001089096,
|
| 1379 |
+
"num_tokens": 6331573.0,
|
| 1380 |
+
"step": 1360
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 1.0872648723423481,
|
| 1384 |
+
"epoch": 0.2922666666666667,
|
| 1385 |
+
"grad_norm": 0.2675784230232239,
|
| 1386 |
+
"learning_rate": 9.661588407378596e-05,
|
| 1387 |
+
"loss": 1.2234331130981446,
|
| 1388 |
+
"mean_token_accuracy": 0.7345306605100632,
|
| 1389 |
+
"num_tokens": 6383986.0,
|
| 1390 |
+
"step": 1370
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 0.8609121344983578,
|
| 1394 |
+
"epoch": 0.2944,
|
| 1395 |
+
"grad_norm": 0.22704993188381195,
|
| 1396 |
+
"learning_rate": 9.655301532203797e-05,
|
| 1397 |
+
"loss": 0.934294605255127,
|
| 1398 |
+
"mean_token_accuracy": 0.7782075613737106,
|
| 1399 |
+
"num_tokens": 6426867.0,
|
| 1400 |
+
"step": 1380
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 0.8974170722067356,
|
| 1404 |
+
"epoch": 0.2965333333333333,
|
| 1405 |
+
"grad_norm": 0.2712918221950531,
|
| 1406 |
+
"learning_rate": 9.648958879643467e-05,
|
| 1407 |
+
"loss": 0.9794875144958496,
|
| 1408 |
+
"mean_token_accuracy": 0.768825002014637,
|
| 1409 |
+
"num_tokens": 6470272.0,
|
| 1410 |
+
"step": 1390
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 0.9115433268249035,
|
| 1414 |
+
"epoch": 0.2986666666666667,
|
| 1415 |
+
"grad_norm": 0.2932375371456146,
|
| 1416 |
+
"learning_rate": 9.642560525691948e-05,
|
| 1417 |
+
"loss": 0.9729208946228027,
|
| 1418 |
+
"mean_token_accuracy": 0.7670300453901291,
|
| 1419 |
+
"num_tokens": 6513165.0,
|
| 1420 |
+
"step": 1400
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 0.8882284432649612,
|
| 1424 |
+
"epoch": 0.3008,
|
| 1425 |
+
"grad_norm": 0.28009793162345886,
|
| 1426 |
+
"learning_rate": 9.63610654701097e-05,
|
| 1427 |
+
"loss": 0.9678432464599609,
|
| 1428 |
+
"mean_token_accuracy": 0.7733970731496811,
|
| 1429 |
+
"num_tokens": 6556342.0,
|
| 1430 |
+
"step": 1410
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 0.8777762867510319,
|
| 1434 |
+
"epoch": 0.30293333333333333,
|
| 1435 |
+
"grad_norm": 0.23763342201709747,
|
| 1436 |
+
"learning_rate": 9.629597020928722e-05,
|
| 1437 |
+
"loss": 0.9687582969665527,
|
| 1438 |
+
"mean_token_accuracy": 0.7792320027947426,
|
| 1439 |
+
"num_tokens": 6601597.0,
|
| 1440 |
+
"step": 1420
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 0.9160067647695541,
|
| 1444 |
+
"epoch": 0.30506666666666665,
|
| 1445 |
+
"grad_norm": 0.31182846426963806,
|
| 1446 |
+
"learning_rate": 9.623032025438939e-05,
|
| 1447 |
+
"loss": 0.9827415466308593,
|
| 1448 |
+
"mean_token_accuracy": 0.7696192592382431,
|
| 1449 |
+
"num_tokens": 6649545.0,
|
| 1450 |
+
"step": 1430
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 0.9564003840088844,
|
| 1454 |
+
"epoch": 0.3072,
|
| 1455 |
+
"grad_norm": 0.23129577934741974,
|
| 1456 |
+
"learning_rate": 9.61641163919996e-05,
|
| 1457 |
+
"loss": 1.0380489349365234,
|
| 1458 |
+
"mean_token_accuracy": 0.7621255874633789,
|
| 1459 |
+
"num_tokens": 6696196.0,
|
| 1460 |
+
"step": 1440
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 1.05502300709486,
|
| 1464 |
+
"epoch": 0.30933333333333335,
|
| 1465 |
+
"grad_norm": 0.27563098073005676,
|
| 1466 |
+
"learning_rate": 9.609735941533788e-05,
|
| 1467 |
+
"loss": 1.150872802734375,
|
| 1468 |
+
"mean_token_accuracy": 0.7396457836031913,
|
| 1469 |
+
"num_tokens": 6745953.0,
|
| 1470 |
+
"step": 1450
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 0.9179727308452129,
|
| 1474 |
+
"epoch": 0.31146666666666667,
|
| 1475 |
+
"grad_norm": 0.2697086036205292,
|
| 1476 |
+
"learning_rate": 9.603005012425135e-05,
|
| 1477 |
+
"loss": 1.0098464012145996,
|
| 1478 |
+
"mean_token_accuracy": 0.7658590793609619,
|
| 1479 |
+
"num_tokens": 6794497.0,
|
| 1480 |
+
"step": 1460
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 1.1471355110406876,
|
| 1484 |
+
"epoch": 0.3136,
|
| 1485 |
+
"grad_norm": 0.2717576026916504,
|
| 1486 |
+
"learning_rate": 9.596218932520468e-05,
|
| 1487 |
+
"loss": 1.2438765525817872,
|
| 1488 |
+
"mean_token_accuracy": 0.7290126971900464,
|
| 1489 |
+
"num_tokens": 6841976.0,
|
| 1490 |
+
"step": 1470
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 0.9211908876895905,
|
| 1494 |
+
"epoch": 0.3157333333333333,
|
| 1495 |
+
"grad_norm": 0.23845043778419495,
|
| 1496 |
+
"learning_rate": 9.589377783127047e-05,
|
| 1497 |
+
"loss": 1.0137989044189453,
|
| 1498 |
+
"mean_token_accuracy": 0.767640671133995,
|
| 1499 |
+
"num_tokens": 6882780.0,
|
| 1500 |
+
"step": 1480
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 0.8538284994661808,
|
| 1504 |
+
"epoch": 0.3178666666666667,
|
| 1505 |
+
"grad_norm": 0.23966865241527557,
|
| 1506 |
+
"learning_rate": 9.58248164621194e-05,
|
| 1507 |
+
"loss": 0.908942985534668,
|
| 1508 |
+
"mean_token_accuracy": 0.7838981494307518,
|
| 1509 |
+
"num_tokens": 6922694.0,
|
| 1510 |
+
"step": 1490
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"entropy": 0.9744522646069527,
|
| 1514 |
+
"epoch": 0.32,
|
| 1515 |
+
"grad_norm": 0.27710849046707153,
|
| 1516 |
+
"learning_rate": 9.575530604401051e-05,
|
| 1517 |
+
"loss": 1.0989601135253906,
|
| 1518 |
+
"mean_token_accuracy": 0.7573227554559707,
|
| 1519 |
+
"num_tokens": 6972307.0,
|
| 1520 |
+
"step": 1500
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"entropy": 1.0386228650808333,
|
| 1524 |
+
"epoch": 0.3221333333333333,
|
| 1525 |
+
"grad_norm": 0.2898867428302765,
|
| 1526 |
+
"learning_rate": 9.56852474097812e-05,
|
| 1527 |
+
"loss": 1.1454790115356446,
|
| 1528 |
+
"mean_token_accuracy": 0.7430783316493035,
|
| 1529 |
+
"num_tokens": 7020126.0,
|
| 1530 |
+
"step": 1510
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"entropy": 0.9898950323462486,
|
| 1534 |
+
"epoch": 0.32426666666666665,
|
| 1535 |
+
"grad_norm": 0.2526203393936157,
|
| 1536 |
+
"learning_rate": 9.561464139883737e-05,
|
| 1537 |
+
"loss": 1.1016074180603028,
|
| 1538 |
+
"mean_token_accuracy": 0.7571706652641297,
|
| 1539 |
+
"num_tokens": 7068804.0,
|
| 1540 |
+
"step": 1520
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 0.999041261523962,
|
| 1544 |
+
"epoch": 0.3264,
|
| 1545 |
+
"grad_norm": 0.24795448780059814,
|
| 1546 |
+
"learning_rate": 9.554348885714326e-05,
|
| 1547 |
+
"loss": 1.0913206100463868,
|
| 1548 |
+
"mean_token_accuracy": 0.7498321965336799,
|
| 1549 |
+
"num_tokens": 7120053.0,
|
| 1550 |
+
"step": 1530
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"entropy": 0.9470011726021766,
|
| 1554 |
+
"epoch": 0.32853333333333334,
|
| 1555 |
+
"grad_norm": 0.2526148557662964,
|
| 1556 |
+
"learning_rate": 9.547179063721139e-05,
|
| 1557 |
+
"loss": 1.0380746841430664,
|
| 1558 |
+
"mean_token_accuracy": 0.7631630048155784,
|
| 1559 |
+
"num_tokens": 7166553.0,
|
| 1560 |
+
"step": 1540
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"entropy": 0.9413013480603695,
|
| 1564 |
+
"epoch": 0.33066666666666666,
|
| 1565 |
+
"grad_norm": 0.2717132866382599,
|
| 1566 |
+
"learning_rate": 9.539954759809226e-05,
|
| 1567 |
+
"loss": 1.0266976356506348,
|
| 1568 |
+
"mean_token_accuracy": 0.7626717418432236,
|
| 1569 |
+
"num_tokens": 7211784.0,
|
| 1570 |
+
"step": 1550
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"entropy": 1.0694061882793904,
|
| 1574 |
+
"epoch": 0.3328,
|
| 1575 |
+
"grad_norm": 0.2959578335285187,
|
| 1576 |
+
"learning_rate": 9.532676060536419e-05,
|
| 1577 |
+
"loss": 1.1947439193725586,
|
| 1578 |
+
"mean_token_accuracy": 0.7360827416181565,
|
| 1579 |
+
"num_tokens": 7256909.0,
|
| 1580 |
+
"step": 1560
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"entropy": 1.100894968211651,
|
| 1584 |
+
"epoch": 0.33493333333333336,
|
| 1585 |
+
"grad_norm": 0.2543633282184601,
|
| 1586 |
+
"learning_rate": 9.525343053112276e-05,
|
| 1587 |
+
"loss": 1.2262410163879394,
|
| 1588 |
+
"mean_token_accuracy": 0.7347081542015076,
|
| 1589 |
+
"num_tokens": 7305883.0,
|
| 1590 |
+
"step": 1570
|
| 1591 |
}
|
| 1592 |
],
|
| 1593 |
"logging_steps": 10,
|
|
|
|
| 1607 |
"attributes": {}
|
| 1608 |
}
|
| 1609 |
},
|
| 1610 |
+
"total_flos": 3.4627636754989056e+16,
|
| 1611 |
"train_batch_size": 4,
|
| 1612 |
"trial_name": null,
|
| 1613 |
"trial_params": null
|