Training in progress, step 20000, 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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424b403b05bd2545c2a14424fd014bcf57732428b67aad097d07f185a6bc5bb2
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0098b151fd7135a628ba22af2fdd6e87cb9087d29b7db0fa633dfc8d1f2500a
|
| 3 |
size 1082379659
|
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 sha256:12d8b6c71ec5842a7f720763e6312f0db9384dc999ad47a74f64d26d1c1cb7ce
|
| 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:bfa5d29ca2c7a5e4464c7ab7540a14b1b7182a94f039f78dc78638842bee89e8
|
| 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": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1256,6 +1256,318 @@
|
|
| 1256 |
"eval_samples_per_second": 39.693,
|
| 1257 |
"eval_steps_per_second": 9.923,
|
| 1258 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1259 |
}
|
| 1260 |
],
|
| 1261 |
"logging_steps": 100,
|
|
@@ -1275,7 +1587,7 @@
|
|
| 1275 |
"attributes": {}
|
| 1276 |
}
|
| 1277 |
},
|
| 1278 |
-
"total_flos":
|
| 1279 |
"train_batch_size": 22,
|
| 1280 |
"trial_name": null,
|
| 1281 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2597402597402597,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 20000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1256 |
"eval_samples_per_second": 39.693,
|
| 1257 |
"eval_steps_per_second": 9.923,
|
| 1258 |
"step": 16000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.20909090909090908,
|
| 1262 |
+
"grad_norm": 0.19923605024814606,
|
| 1263 |
+
"learning_rate": 0.0009536579887612396,
|
| 1264 |
+
"loss": 2.9049,
|
| 1265 |
+
"step": 16100
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.21038961038961038,
|
| 1269 |
+
"grad_norm": 0.1969510018825531,
|
| 1270 |
+
"learning_rate": 0.0009530499168942252,
|
| 1271 |
+
"loss": 2.9263,
|
| 1272 |
+
"step": 16200
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.21168831168831168,
|
| 1276 |
+
"grad_norm": 0.3835534155368805,
|
| 1277 |
+
"learning_rate": 0.0009524380780670223,
|
| 1278 |
+
"loss": 2.9207,
|
| 1279 |
+
"step": 16300
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.21298701298701297,
|
| 1283 |
+
"grad_norm": 0.18829414248466492,
|
| 1284 |
+
"learning_rate": 0.0009518224773668678,
|
| 1285 |
+
"loss": 2.9247,
|
| 1286 |
+
"step": 16400
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.21428571428571427,
|
| 1290 |
+
"grad_norm": 0.18950419127941132,
|
| 1291 |
+
"learning_rate": 0.0009512031199122779,
|
| 1292 |
+
"loss": 2.914,
|
| 1293 |
+
"step": 16500
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.21558441558441557,
|
| 1297 |
+
"grad_norm": 0.23597006499767303,
|
| 1298 |
+
"learning_rate": 0.0009505800108530054,
|
| 1299 |
+
"loss": 2.9064,
|
| 1300 |
+
"step": 16600
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.21688311688311687,
|
| 1304 |
+
"grad_norm": 0.18245990574359894,
|
| 1305 |
+
"learning_rate": 0.0009499531553699957,
|
| 1306 |
+
"loss": 2.9219,
|
| 1307 |
+
"step": 16700
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.21818181818181817,
|
| 1311 |
+
"grad_norm": 0.20525243878364563,
|
| 1312 |
+
"learning_rate": 0.0009493225586753449,
|
| 1313 |
+
"loss": 2.9373,
|
| 1314 |
+
"step": 16800
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.21948051948051947,
|
| 1318 |
+
"grad_norm": 0.17929033935070038,
|
| 1319 |
+
"learning_rate": 0.0009486882260122557,
|
| 1320 |
+
"loss": 2.8947,
|
| 1321 |
+
"step": 16900
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.22077922077922077,
|
| 1325 |
+
"grad_norm": 0.18927592039108276,
|
| 1326 |
+
"learning_rate": 0.0009480501626549945,
|
| 1327 |
+
"loss": 2.903,
|
| 1328 |
+
"step": 17000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.22077922077922077,
|
| 1332 |
+
"eval_loss": 3.2817673683166504,
|
| 1333 |
+
"eval_runtime": 16.3954,
|
| 1334 |
+
"eval_samples_per_second": 35.132,
|
| 1335 |
+
"eval_steps_per_second": 8.783,
|
| 1336 |
+
"step": 17000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22207792207792207,
|
| 1340 |
+
"grad_norm": 0.22612017393112183,
|
| 1341 |
+
"learning_rate": 0.0009474083739088471,
|
| 1342 |
+
"loss": 2.91,
|
| 1343 |
+
"step": 17100
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.22337662337662337,
|
| 1347 |
+
"grad_norm": 0.19862578809261322,
|
| 1348 |
+
"learning_rate": 0.0009467628651100745,
|
| 1349 |
+
"loss": 2.9319,
|
| 1350 |
+
"step": 17200
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22467532467532467,
|
| 1354 |
+
"grad_norm": 0.19449101388454437,
|
| 1355 |
+
"learning_rate": 0.0009461136416258689,
|
| 1356 |
+
"loss": 2.9244,
|
| 1357 |
+
"step": 17300
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.22597402597402597,
|
| 1361 |
+
"grad_norm": 0.18568117916584015,
|
| 1362 |
+
"learning_rate": 0.0009454607088543088,
|
| 1363 |
+
"loss": 2.9118,
|
| 1364 |
+
"step": 17400
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.22727272727272727,
|
| 1368 |
+
"grad_norm": 0.174198180437088,
|
| 1369 |
+
"learning_rate": 0.000944804072224314,
|
| 1370 |
+
"loss": 2.9134,
|
| 1371 |
+
"step": 17500
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.22857142857142856,
|
| 1375 |
+
"grad_norm": 0.18078738451004028,
|
| 1376 |
+
"learning_rate": 0.0009441437371956013,
|
| 1377 |
+
"loss": 2.9039,
|
| 1378 |
+
"step": 17600
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.22987012987012986,
|
| 1382 |
+
"grad_norm": 0.20317985117435455,
|
| 1383 |
+
"learning_rate": 0.0009434797092586377,
|
| 1384 |
+
"loss": 2.8848,
|
| 1385 |
+
"step": 17700
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.23116883116883116,
|
| 1389 |
+
"grad_norm": 0.17165842652320862,
|
| 1390 |
+
"learning_rate": 0.0009428119939345959,
|
| 1391 |
+
"loss": 2.8846,
|
| 1392 |
+
"step": 17800
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.23246753246753246,
|
| 1396 |
+
"grad_norm": 0.21153512597084045,
|
| 1397 |
+
"learning_rate": 0.0009421405967753078,
|
| 1398 |
+
"loss": 2.8944,
|
| 1399 |
+
"step": 17900
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23376623376623376,
|
| 1403 |
+
"grad_norm": 0.22300300002098083,
|
| 1404 |
+
"learning_rate": 0.000941465523363219,
|
| 1405 |
+
"loss": 2.8981,
|
| 1406 |
+
"step": 18000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23376623376623376,
|
| 1410 |
+
"eval_loss": 3.2792882919311523,
|
| 1411 |
+
"eval_runtime": 15.157,
|
| 1412 |
+
"eval_samples_per_second": 38.002,
|
| 1413 |
+
"eval_steps_per_second": 9.501,
|
| 1414 |
+
"step": 18000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.23506493506493506,
|
| 1418 |
+
"grad_norm": 0.17719519138336182,
|
| 1419 |
+
"learning_rate": 0.0009407867793113414,
|
| 1420 |
+
"loss": 2.9096,
|
| 1421 |
+
"step": 18100
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.23636363636363636,
|
| 1425 |
+
"grad_norm": 0.17834420502185822,
|
| 1426 |
+
"learning_rate": 0.0009401043702632071,
|
| 1427 |
+
"loss": 2.8922,
|
| 1428 |
+
"step": 18200
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.23766233766233766,
|
| 1432 |
+
"grad_norm": 0.20472975075244904,
|
| 1433 |
+
"learning_rate": 0.000939418301892822,
|
| 1434 |
+
"loss": 2.8927,
|
| 1435 |
+
"step": 18300
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.23896103896103896,
|
| 1439 |
+
"grad_norm": 0.1972654014825821,
|
| 1440 |
+
"learning_rate": 0.0009387285799046174,
|
| 1441 |
+
"loss": 2.904,
|
| 1442 |
+
"step": 18400
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.24025974025974026,
|
| 1446 |
+
"grad_norm": 0.1871407926082611,
|
| 1447 |
+
"learning_rate": 0.0009380352100334035,
|
| 1448 |
+
"loss": 2.8829,
|
| 1449 |
+
"step": 18500
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.24155844155844156,
|
| 1453 |
+
"grad_norm": 0.1807365119457245,
|
| 1454 |
+
"learning_rate": 0.0009373381980443212,
|
| 1455 |
+
"loss": 2.8977,
|
| 1456 |
+
"step": 18600
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.24285714285714285,
|
| 1460 |
+
"grad_norm": 0.19222930073738098,
|
| 1461 |
+
"learning_rate": 0.000936637549732795,
|
| 1462 |
+
"loss": 2.8991,
|
| 1463 |
+
"step": 18700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.24415584415584415,
|
| 1467 |
+
"grad_norm": 0.2098565548658371,
|
| 1468 |
+
"learning_rate": 0.0009359332709244837,
|
| 1469 |
+
"loss": 2.8827,
|
| 1470 |
+
"step": 18800
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.24545454545454545,
|
| 1474 |
+
"grad_norm": 0.2327863723039627,
|
| 1475 |
+
"learning_rate": 0.0009352253674752325,
|
| 1476 |
+
"loss": 2.8909,
|
| 1477 |
+
"step": 18900
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.24675324675324675,
|
| 1481 |
+
"grad_norm": 0.1913413554430008,
|
| 1482 |
+
"learning_rate": 0.0009345138452710245,
|
| 1483 |
+
"loss": 2.8913,
|
| 1484 |
+
"step": 19000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.24675324675324675,
|
| 1488 |
+
"eval_loss": 3.2709906101226807,
|
| 1489 |
+
"eval_runtime": 14.4105,
|
| 1490 |
+
"eval_samples_per_second": 39.971,
|
| 1491 |
+
"eval_steps_per_second": 9.993,
|
| 1492 |
+
"step": 19000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.24805194805194805,
|
| 1496 |
+
"grad_norm": 0.17969286441802979,
|
| 1497 |
+
"learning_rate": 0.0009337987102279313,
|
| 1498 |
+
"loss": 2.8998,
|
| 1499 |
+
"step": 19100
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.24935064935064935,
|
| 1503 |
+
"grad_norm": 0.18576957285404205,
|
| 1504 |
+
"learning_rate": 0.0009330799682920645,
|
| 1505 |
+
"loss": 2.8886,
|
| 1506 |
+
"step": 19200
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.2506493506493506,
|
| 1510 |
+
"grad_norm": 0.17968888580799103,
|
| 1511 |
+
"learning_rate": 0.0009323576254395253,
|
| 1512 |
+
"loss": 2.8998,
|
| 1513 |
+
"step": 19300
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.2519480519480519,
|
| 1517 |
+
"grad_norm": 0.1743050366640091,
|
| 1518 |
+
"learning_rate": 0.0009316316876763557,
|
| 1519 |
+
"loss": 2.8837,
|
| 1520 |
+
"step": 19400
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.2532467532467532,
|
| 1524 |
+
"grad_norm": 0.17573101818561554,
|
| 1525 |
+
"learning_rate": 0.0009309021610384879,
|
| 1526 |
+
"loss": 2.8681,
|
| 1527 |
+
"step": 19500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.2545454545454545,
|
| 1531 |
+
"grad_norm": 0.199496790766716,
|
| 1532 |
+
"learning_rate": 0.0009301690515916948,
|
| 1533 |
+
"loss": 2.8717,
|
| 1534 |
+
"step": 19600
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.2558441558441558,
|
| 1538 |
+
"grad_norm": 0.1846366673707962,
|
| 1539 |
+
"learning_rate": 0.0009294323654315387,
|
| 1540 |
+
"loss": 2.9166,
|
| 1541 |
+
"step": 19700
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.2571428571428571,
|
| 1545 |
+
"grad_norm": 0.18776021897792816,
|
| 1546 |
+
"learning_rate": 0.0009286921086833214,
|
| 1547 |
+
"loss": 2.8916,
|
| 1548 |
+
"step": 19800
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.2584415584415584,
|
| 1552 |
+
"grad_norm": 0.1786223202943802,
|
| 1553 |
+
"learning_rate": 0.000927948287502033,
|
| 1554 |
+
"loss": 2.9013,
|
| 1555 |
+
"step": 19900
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.2597402597402597,
|
| 1559 |
+
"grad_norm": 0.18665452301502228,
|
| 1560 |
+
"learning_rate": 0.0009272009080723005,
|
| 1561 |
+
"loss": 2.9108,
|
| 1562 |
+
"step": 20000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.2597402597402597,
|
| 1566 |
+
"eval_loss": 3.2676138877868652,
|
| 1567 |
+
"eval_runtime": 15.0403,
|
| 1568 |
+
"eval_samples_per_second": 38.297,
|
| 1569 |
+
"eval_steps_per_second": 9.574,
|
| 1570 |
+
"step": 20000
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 100,
|
|
|
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
+
"total_flos": 5.953862762496e+17,
|
| 1591 |
"train_batch_size": 22,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|