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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c37dc9cd45148160db4b80fa4db4da68c9b444487ae1c9fdf7890466cd3b11
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77dfb0dfb6c162187d26607f9585f8626cc40ff65b297436f2124b2fe6a83c10
|
| 3 |
size 938825803
|
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:a7e057f5b72466889872d74430f3ee9303ae077763a80c9351cb7f41490bb946
|
| 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:f253e447661d715656ec6271ae4c4ea6bd1781e5f900ea4b2d9b76d2fc849b12
|
| 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": 84.143,
|
| 1257 |
"eval_steps_per_second": 21.036,
|
| 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": 0.18181818181818182,
|
| 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": 84.143,
|
| 1257 |
"eval_steps_per_second": 21.036,
|
| 1258 |
"step": 16000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.14636363636363636,
|
| 1262 |
+
"grad_norm": 0.23435284197330475,
|
| 1263 |
+
"learning_rate": 0.0009488831727520647,
|
| 1264 |
+
"loss": 2.925650939941406,
|
| 1265 |
+
"step": 16100
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.14727272727272728,
|
| 1269 |
+
"grad_norm": 0.1385786384344101,
|
| 1270 |
+
"learning_rate": 0.0009482514864632905,
|
| 1271 |
+
"loss": 2.935544738769531,
|
| 1272 |
+
"step": 16200
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.1481818181818182,
|
| 1276 |
+
"grad_norm": 0.15425068140029907,
|
| 1277 |
+
"learning_rate": 0.0009476161339330484,
|
| 1278 |
+
"loss": 2.8958169555664064,
|
| 1279 |
+
"step": 16300
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.14909090909090908,
|
| 1283 |
+
"grad_norm": 0.16746921837329865,
|
| 1284 |
+
"learning_rate": 0.0009469771203578765,
|
| 1285 |
+
"loss": 2.886453857421875,
|
| 1286 |
+
"step": 16400
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.15,
|
| 1290 |
+
"grad_norm": 0.15813444554805756,
|
| 1291 |
+
"learning_rate": 0.000946334450964256,
|
| 1292 |
+
"loss": 2.8945297241210937,
|
| 1293 |
+
"step": 16500
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.1509090909090909,
|
| 1297 |
+
"grad_norm": 0.16391652822494507,
|
| 1298 |
+
"learning_rate": 0.0009456881310085692,
|
| 1299 |
+
"loss": 2.871600341796875,
|
| 1300 |
+
"step": 16600
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.15181818181818182,
|
| 1304 |
+
"grad_norm": 0.14185769855976105,
|
| 1305 |
+
"learning_rate": 0.0009450381657770563,
|
| 1306 |
+
"loss": 2.8975213623046874,
|
| 1307 |
+
"step": 16700
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.15272727272727274,
|
| 1311 |
+
"grad_norm": 0.16267341375350952,
|
| 1312 |
+
"learning_rate": 0.0009443845605857722,
|
| 1313 |
+
"loss": 2.894129333496094,
|
| 1314 |
+
"step": 16800
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.15363636363636363,
|
| 1318 |
+
"grad_norm": 0.15159358084201813,
|
| 1319 |
+
"learning_rate": 0.0009437273207805428,
|
| 1320 |
+
"loss": 2.9036929321289064,
|
| 1321 |
+
"step": 16900
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.15454545454545454,
|
| 1325 |
+
"grad_norm": 0.19526581466197968,
|
| 1326 |
+
"learning_rate": 0.0009430664517369216,
|
| 1327 |
+
"loss": 2.9116668701171875,
|
| 1328 |
+
"step": 17000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.15454545454545454,
|
| 1332 |
+
"eval_loss": 3.2496325969696045,
|
| 1333 |
+
"eval_runtime": 6.8339,
|
| 1334 |
+
"eval_samples_per_second": 84.285,
|
| 1335 |
+
"eval_steps_per_second": 21.071,
|
| 1336 |
+
"step": 17000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.15545454545454546,
|
| 1340 |
+
"grad_norm": 0.1410096138715744,
|
| 1341 |
+
"learning_rate": 0.0009424019588601458,
|
| 1342 |
+
"loss": 2.879241943359375,
|
| 1343 |
+
"step": 17100
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.15636363636363637,
|
| 1347 |
+
"grad_norm": 0.1442963033914566,
|
| 1348 |
+
"learning_rate": 0.0009417338475850911,
|
| 1349 |
+
"loss": 2.892339172363281,
|
| 1350 |
+
"step": 17200
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1572727272727273,
|
| 1354 |
+
"grad_norm": 0.16006037592887878,
|
| 1355 |
+
"learning_rate": 0.000941062123376229,
|
| 1356 |
+
"loss": 2.8745999145507812,
|
| 1357 |
+
"step": 17300
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.15818181818181817,
|
| 1361 |
+
"grad_norm": 0.15137411653995514,
|
| 1362 |
+
"learning_rate": 0.0009403867917275805,
|
| 1363 |
+
"loss": 2.9007733154296873,
|
| 1364 |
+
"step": 17400
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.1590909090909091,
|
| 1368 |
+
"grad_norm": 0.15556079149246216,
|
| 1369 |
+
"learning_rate": 0.0009397078581626718,
|
| 1370 |
+
"loss": 2.8890725708007814,
|
| 1371 |
+
"step": 17500
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.16,
|
| 1375 |
+
"grad_norm": 0.1370605081319809,
|
| 1376 |
+
"learning_rate": 0.0009390253282344894,
|
| 1377 |
+
"loss": 2.8879302978515624,
|
| 1378 |
+
"step": 17600
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.16090909090909092,
|
| 1382 |
+
"grad_norm": 0.15012328326702118,
|
| 1383 |
+
"learning_rate": 0.0009383392075254342,
|
| 1384 |
+
"loss": 2.870147399902344,
|
| 1385 |
+
"step": 17700
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1618181818181818,
|
| 1389 |
+
"grad_norm": 0.15628907084465027,
|
| 1390 |
+
"learning_rate": 0.0009376495016472762,
|
| 1391 |
+
"loss": 2.899383239746094,
|
| 1392 |
+
"step": 17800
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.16272727272727272,
|
| 1396 |
+
"grad_norm": 0.172128364443779,
|
| 1397 |
+
"learning_rate": 0.0009369562162411083,
|
| 1398 |
+
"loss": 2.8812881469726563,
|
| 1399 |
+
"step": 17900
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.16363636363636364,
|
| 1403 |
+
"grad_norm": 0.15035715699195862,
|
| 1404 |
+
"learning_rate": 0.0009362593569773001,
|
| 1405 |
+
"loss": 2.893328857421875,
|
| 1406 |
+
"step": 18000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.16363636363636364,
|
| 1410 |
+
"eval_loss": 3.241589069366455,
|
| 1411 |
+
"eval_runtime": 6.7941,
|
| 1412 |
+
"eval_samples_per_second": 84.779,
|
| 1413 |
+
"eval_steps_per_second": 21.195,
|
| 1414 |
+
"step": 18000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.16454545454545455,
|
| 1418 |
+
"grad_norm": 0.14139075577259064,
|
| 1419 |
+
"learning_rate": 0.0009355589295554522,
|
| 1420 |
+
"loss": 2.9356817626953124,
|
| 1421 |
+
"step": 18100
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.16545454545454547,
|
| 1425 |
+
"grad_norm": 0.22561536729335785,
|
| 1426 |
+
"learning_rate": 0.0009348549397043489,
|
| 1427 |
+
"loss": 2.8875466918945314,
|
| 1428 |
+
"step": 18200
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.16636363636363635,
|
| 1432 |
+
"grad_norm": 0.1523270159959793,
|
| 1433 |
+
"learning_rate": 0.0009341473931819113,
|
| 1434 |
+
"loss": 2.917890930175781,
|
| 1435 |
+
"step": 18300
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.16727272727272727,
|
| 1439 |
+
"grad_norm": 0.14544081687927246,
|
| 1440 |
+
"learning_rate": 0.0009334362957751506,
|
| 1441 |
+
"loss": 2.901419677734375,
|
| 1442 |
+
"step": 18400
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.16818181818181818,
|
| 1446 |
+
"grad_norm": 0.13483288884162903,
|
| 1447 |
+
"learning_rate": 0.000932721653300121,
|
| 1448 |
+
"loss": 2.9169821166992187,
|
| 1449 |
+
"step": 18500
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.1690909090909091,
|
| 1453 |
+
"grad_norm": 0.17061568796634674,
|
| 1454 |
+
"learning_rate": 0.0009320034716018713,
|
| 1455 |
+
"loss": 2.865706481933594,
|
| 1456 |
+
"step": 18600
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.17,
|
| 1460 |
+
"grad_norm": 0.15831294655799866,
|
| 1461 |
+
"learning_rate": 0.0009312817565543976,
|
| 1462 |
+
"loss": 2.9071807861328125,
|
| 1463 |
+
"step": 18700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.1709090909090909,
|
| 1467 |
+
"grad_norm": 0.1500754952430725,
|
| 1468 |
+
"learning_rate": 0.0009305565140605957,
|
| 1469 |
+
"loss": 2.8990237426757814,
|
| 1470 |
+
"step": 18800
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.17181818181818181,
|
| 1474 |
+
"grad_norm": 0.16387759149074554,
|
| 1475 |
+
"learning_rate": 0.0009298277500522112,
|
| 1476 |
+
"loss": 2.884671325683594,
|
| 1477 |
+
"step": 18900
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.17272727272727273,
|
| 1481 |
+
"grad_norm": 0.13598468899726868,
|
| 1482 |
+
"learning_rate": 0.0009290954704897934,
|
| 1483 |
+
"loss": 2.886610412597656,
|
| 1484 |
+
"step": 19000
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.17272727272727273,
|
| 1488 |
+
"eval_loss": 3.222428560256958,
|
| 1489 |
+
"eval_runtime": 6.8544,
|
| 1490 |
+
"eval_samples_per_second": 84.034,
|
| 1491 |
+
"eval_steps_per_second": 21.008,
|
| 1492 |
+
"step": 19000
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.17363636363636364,
|
| 1496 |
+
"grad_norm": 0.17809490859508514,
|
| 1497 |
+
"learning_rate": 0.0009283596813626444,
|
| 1498 |
+
"loss": 2.8785455322265623,
|
| 1499 |
+
"step": 19100
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.17454545454545456,
|
| 1503 |
+
"grad_norm": 0.15393967926502228,
|
| 1504 |
+
"learning_rate": 0.0009276203886887714,
|
| 1505 |
+
"loss": 2.9021951293945314,
|
| 1506 |
+
"step": 19200
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.17545454545454545,
|
| 1510 |
+
"grad_norm": 0.1531384289264679,
|
| 1511 |
+
"learning_rate": 0.0009268775985148369,
|
| 1512 |
+
"loss": 2.900225830078125,
|
| 1513 |
+
"step": 19300
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.17636363636363636,
|
| 1517 |
+
"grad_norm": 0.1720549464225769,
|
| 1518 |
+
"learning_rate": 0.0009261313169161094,
|
| 1519 |
+
"loss": 2.8924365234375,
|
| 1520 |
+
"step": 19400
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.17727272727272728,
|
| 1524 |
+
"grad_norm": 0.17175054550170898,
|
| 1525 |
+
"learning_rate": 0.0009253815499964135,
|
| 1526 |
+
"loss": 2.8840255737304688,
|
| 1527 |
+
"step": 19500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.1781818181818182,
|
| 1531 |
+
"grad_norm": 0.1715477555990219,
|
| 1532 |
+
"learning_rate": 0.0009246283038880809,
|
| 1533 |
+
"loss": 2.8627389526367186,
|
| 1534 |
+
"step": 19600
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.17909090909090908,
|
| 1538 |
+
"grad_norm": 0.17474284768104553,
|
| 1539 |
+
"learning_rate": 0.0009238715847518984,
|
| 1540 |
+
"loss": 2.887270812988281,
|
| 1541 |
+
"step": 19700
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.18,
|
| 1545 |
+
"grad_norm": 0.15692177414894104,
|
| 1546 |
+
"learning_rate": 0.0009231113987770599,
|
| 1547 |
+
"loss": 2.890269775390625,
|
| 1548 |
+
"step": 19800
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.1809090909090909,
|
| 1552 |
+
"grad_norm": 0.15938249230384827,
|
| 1553 |
+
"learning_rate": 0.0009223477521811132,
|
| 1554 |
+
"loss": 2.9025338745117186,
|
| 1555 |
+
"step": 19900
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.18181818181818182,
|
| 1559 |
+
"grad_norm": 0.14352673292160034,
|
| 1560 |
+
"learning_rate": 0.0009215806512099115,
|
| 1561 |
+
"loss": 2.9029974365234374,
|
| 1562 |
+
"step": 20000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.18181818181818182,
|
| 1566 |
+
"eval_loss": 3.218810558319092,
|
| 1567 |
+
"eval_runtime": 6.8249,
|
| 1568 |
+
"eval_samples_per_second": 84.397,
|
| 1569 |
+
"eval_steps_per_second": 21.099,
|
| 1570 |
+
"step": 20000
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 100,
|
|
|
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
+
"total_flos": 4.9829161992192e+17,
|
| 1591 |
"train_batch_size": 22,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|