Training in progress, step 1000, 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 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d2fe0f6c71fc451029e15d3adda76c167de5a1de26fc9f1e9f7395acc07ef0
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c7d3c211b32962f1c875c875c023927c7b5b2b29912c2c797fbd8a9e787a13a
|
| 3 |
size 469516363
|
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:d193220051de5dc024d5f45a08741acdec0884c4a3d4ecd0669567f27b83c7d4
|
| 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 sha256:68aec417c91400a5fbe9c98d7447dabd74ed3b0812272a5f21d640985e919bad
|
| 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":
|
| 6 |
"eval_steps": 50,
|
| 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": 5.502,
|
| 1257 |
"eval_steps_per_second": 2.825,
|
| 1258 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1259 |
}
|
| 1260 |
],
|
| 1261 |
"logging_steps": 5,
|
|
@@ -1270,12 +1582,12 @@
|
|
| 1270 |
"should_evaluate": false,
|
| 1271 |
"should_log": false,
|
| 1272 |
"should_save": true,
|
| 1273 |
-
"should_training_stop":
|
| 1274 |
},
|
| 1275 |
"attributes": {}
|
| 1276 |
}
|
| 1277 |
},
|
| 1278 |
-
"total_flos": 2.
|
| 1279 |
"train_batch_size": 2,
|
| 1280 |
"trial_name": null,
|
| 1281 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
"eval_steps": 50,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1256 |
"eval_samples_per_second": 5.502,
|
| 1257 |
"eval_steps_per_second": 2.825,
|
| 1258 |
"step": 800
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.805,
|
| 1262 |
+
"grad_norm": 8.3125,
|
| 1263 |
+
"learning_rate": 5e-05,
|
| 1264 |
+
"loss": 2.9799240112304686,
|
| 1265 |
+
"step": 805
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.81,
|
| 1269 |
+
"grad_norm": 7.9375,
|
| 1270 |
+
"learning_rate": 5e-05,
|
| 1271 |
+
"loss": 3.0026453018188475,
|
| 1272 |
+
"step": 810
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.815,
|
| 1276 |
+
"grad_norm": 1.65625,
|
| 1277 |
+
"learning_rate": 5e-05,
|
| 1278 |
+
"loss": 2.999722480773926,
|
| 1279 |
+
"step": 815
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.82,
|
| 1283 |
+
"grad_norm": 1.265625,
|
| 1284 |
+
"learning_rate": 5e-05,
|
| 1285 |
+
"loss": 2.966134452819824,
|
| 1286 |
+
"step": 820
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.825,
|
| 1290 |
+
"grad_norm": 340.0,
|
| 1291 |
+
"learning_rate": 5e-05,
|
| 1292 |
+
"loss": 2.979732322692871,
|
| 1293 |
+
"step": 825
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.83,
|
| 1297 |
+
"grad_norm": 34.5,
|
| 1298 |
+
"learning_rate": 5e-05,
|
| 1299 |
+
"loss": 3.0184419631958006,
|
| 1300 |
+
"step": 830
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.835,
|
| 1304 |
+
"grad_norm": 4.71875,
|
| 1305 |
+
"learning_rate": 5e-05,
|
| 1306 |
+
"loss": 2.978903961181641,
|
| 1307 |
+
"step": 835
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.84,
|
| 1311 |
+
"grad_norm": 7.75,
|
| 1312 |
+
"learning_rate": 5e-05,
|
| 1313 |
+
"loss": 3.000539016723633,
|
| 1314 |
+
"step": 840
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.845,
|
| 1318 |
+
"grad_norm": 3.0,
|
| 1319 |
+
"learning_rate": 5e-05,
|
| 1320 |
+
"loss": 2.962353515625,
|
| 1321 |
+
"step": 845
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.85,
|
| 1325 |
+
"grad_norm": 2.171875,
|
| 1326 |
+
"learning_rate": 5e-05,
|
| 1327 |
+
"loss": 2.9898805618286133,
|
| 1328 |
+
"step": 850
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.85,
|
| 1332 |
+
"eval_loss": 3.2711822986602783,
|
| 1333 |
+
"eval_runtime": 6.7266,
|
| 1334 |
+
"eval_samples_per_second": 5.501,
|
| 1335 |
+
"eval_steps_per_second": 2.825,
|
| 1336 |
+
"step": 850
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.855,
|
| 1340 |
+
"grad_norm": 4.34375,
|
| 1341 |
+
"learning_rate": 5e-05,
|
| 1342 |
+
"loss": 2.973104476928711,
|
| 1343 |
+
"step": 855
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.86,
|
| 1347 |
+
"grad_norm": 6.21875,
|
| 1348 |
+
"learning_rate": 5e-05,
|
| 1349 |
+
"loss": 3.00762996673584,
|
| 1350 |
+
"step": 860
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.865,
|
| 1354 |
+
"grad_norm": 3.96875,
|
| 1355 |
+
"learning_rate": 5e-05,
|
| 1356 |
+
"loss": 2.9680364608764647,
|
| 1357 |
+
"step": 865
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.87,
|
| 1361 |
+
"grad_norm": 3.546875,
|
| 1362 |
+
"learning_rate": 5e-05,
|
| 1363 |
+
"loss": 2.9908233642578126,
|
| 1364 |
+
"step": 870
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.875,
|
| 1368 |
+
"grad_norm": 5.25,
|
| 1369 |
+
"learning_rate": 5e-05,
|
| 1370 |
+
"loss": 2.9942108154296876,
|
| 1371 |
+
"step": 875
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.88,
|
| 1375 |
+
"grad_norm": 7.25,
|
| 1376 |
+
"learning_rate": 5e-05,
|
| 1377 |
+
"loss": 2.966433525085449,
|
| 1378 |
+
"step": 880
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.885,
|
| 1382 |
+
"grad_norm": 6.84375,
|
| 1383 |
+
"learning_rate": 5e-05,
|
| 1384 |
+
"loss": 2.9872104644775392,
|
| 1385 |
+
"step": 885
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.89,
|
| 1389 |
+
"grad_norm": 2.3125,
|
| 1390 |
+
"learning_rate": 5e-05,
|
| 1391 |
+
"loss": 2.9889734268188475,
|
| 1392 |
+
"step": 890
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.895,
|
| 1396 |
+
"grad_norm": 4.46875,
|
| 1397 |
+
"learning_rate": 5e-05,
|
| 1398 |
+
"loss": 2.9673152923583985,
|
| 1399 |
+
"step": 895
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.9,
|
| 1403 |
+
"grad_norm": 5.15625,
|
| 1404 |
+
"learning_rate": 5e-05,
|
| 1405 |
+
"loss": 2.992472267150879,
|
| 1406 |
+
"step": 900
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.9,
|
| 1410 |
+
"eval_loss": 3.269010066986084,
|
| 1411 |
+
"eval_runtime": 6.7827,
|
| 1412 |
+
"eval_samples_per_second": 5.455,
|
| 1413 |
+
"eval_steps_per_second": 2.801,
|
| 1414 |
+
"step": 900
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.905,
|
| 1418 |
+
"grad_norm": 1.7890625,
|
| 1419 |
+
"learning_rate": 5e-05,
|
| 1420 |
+
"loss": 2.982642936706543,
|
| 1421 |
+
"step": 905
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.91,
|
| 1425 |
+
"grad_norm": 7.4375,
|
| 1426 |
+
"learning_rate": 5e-05,
|
| 1427 |
+
"loss": 3.015847396850586,
|
| 1428 |
+
"step": 910
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.915,
|
| 1432 |
+
"grad_norm": 5376.0,
|
| 1433 |
+
"learning_rate": 5e-05,
|
| 1434 |
+
"loss": 3.003455924987793,
|
| 1435 |
+
"step": 915
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.92,
|
| 1439 |
+
"grad_norm": 0.83984375,
|
| 1440 |
+
"learning_rate": 5e-05,
|
| 1441 |
+
"loss": 2.987352180480957,
|
| 1442 |
+
"step": 920
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.925,
|
| 1446 |
+
"grad_norm": 1.9921875,
|
| 1447 |
+
"learning_rate": 5e-05,
|
| 1448 |
+
"loss": 2.9890872955322267,
|
| 1449 |
+
"step": 925
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.93,
|
| 1453 |
+
"grad_norm": 352.0,
|
| 1454 |
+
"learning_rate": 5e-05,
|
| 1455 |
+
"loss": 2.990787315368652,
|
| 1456 |
+
"step": 930
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.935,
|
| 1460 |
+
"grad_norm": 9.5,
|
| 1461 |
+
"learning_rate": 5e-05,
|
| 1462 |
+
"loss": 2.950652313232422,
|
| 1463 |
+
"step": 935
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.94,
|
| 1467 |
+
"grad_norm": 84.5,
|
| 1468 |
+
"learning_rate": 5e-05,
|
| 1469 |
+
"loss": 2.978129768371582,
|
| 1470 |
+
"step": 940
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.945,
|
| 1474 |
+
"grad_norm": 900.0,
|
| 1475 |
+
"learning_rate": 5e-05,
|
| 1476 |
+
"loss": 2.9651300430297853,
|
| 1477 |
+
"step": 945
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.95,
|
| 1481 |
+
"grad_norm": 17.75,
|
| 1482 |
+
"learning_rate": 5e-05,
|
| 1483 |
+
"loss": 2.940041351318359,
|
| 1484 |
+
"step": 950
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.95,
|
| 1488 |
+
"eval_loss": 3.2654120922088623,
|
| 1489 |
+
"eval_runtime": 6.7595,
|
| 1490 |
+
"eval_samples_per_second": 5.474,
|
| 1491 |
+
"eval_steps_per_second": 2.811,
|
| 1492 |
+
"step": 950
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.955,
|
| 1496 |
+
"grad_norm": 5.25,
|
| 1497 |
+
"learning_rate": 5e-05,
|
| 1498 |
+
"loss": 2.9906681060791014,
|
| 1499 |
+
"step": 955
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.96,
|
| 1503 |
+
"grad_norm": 1.65625,
|
| 1504 |
+
"learning_rate": 5e-05,
|
| 1505 |
+
"loss": 2.965926933288574,
|
| 1506 |
+
"step": 960
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.965,
|
| 1510 |
+
"grad_norm": 1.9609375,
|
| 1511 |
+
"learning_rate": 5e-05,
|
| 1512 |
+
"loss": 3.0010139465332033,
|
| 1513 |
+
"step": 965
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.97,
|
| 1517 |
+
"grad_norm": 24.625,
|
| 1518 |
+
"learning_rate": 5e-05,
|
| 1519 |
+
"loss": 2.9550275802612305,
|
| 1520 |
+
"step": 970
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.975,
|
| 1524 |
+
"grad_norm": 2.515625,
|
| 1525 |
+
"learning_rate": 5e-05,
|
| 1526 |
+
"loss": 2.970465660095215,
|
| 1527 |
+
"step": 975
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.98,
|
| 1531 |
+
"grad_norm": 3.4375,
|
| 1532 |
+
"learning_rate": 5e-05,
|
| 1533 |
+
"loss": 2.9523544311523438,
|
| 1534 |
+
"step": 980
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.985,
|
| 1538 |
+
"grad_norm": 14.625,
|
| 1539 |
+
"learning_rate": 5e-05,
|
| 1540 |
+
"loss": 3.002934455871582,
|
| 1541 |
+
"step": 985
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.99,
|
| 1545 |
+
"grad_norm": 2.921875,
|
| 1546 |
+
"learning_rate": 5e-05,
|
| 1547 |
+
"loss": 2.964326286315918,
|
| 1548 |
+
"step": 990
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.995,
|
| 1552 |
+
"grad_norm": 3.625,
|
| 1553 |
+
"learning_rate": 5e-05,
|
| 1554 |
+
"loss": 2.9944055557250975,
|
| 1555 |
+
"step": 995
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.0,
|
| 1559 |
+
"grad_norm": 11.9375,
|
| 1560 |
+
"learning_rate": 5e-05,
|
| 1561 |
+
"loss": 2.9779850006103517,
|
| 1562 |
+
"step": 1000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.0,
|
| 1566 |
+
"eval_loss": 3.2615818977355957,
|
| 1567 |
+
"eval_runtime": 6.7329,
|
| 1568 |
+
"eval_samples_per_second": 5.495,
|
| 1569 |
+
"eval_steps_per_second": 2.822,
|
| 1570 |
+
"step": 1000
|
| 1571 |
}
|
| 1572 |
],
|
| 1573 |
"logging_steps": 5,
|
|
|
|
| 1582 |
"should_evaluate": false,
|
| 1583 |
"should_log": false,
|
| 1584 |
"should_save": true,
|
| 1585 |
+
"should_training_stop": true
|
| 1586 |
},
|
| 1587 |
"attributes": {}
|
| 1588 |
}
|
| 1589 |
},
|
| 1590 |
+
"total_flos": 2.89915124318208e+17,
|
| 1591 |
"train_batch_size": 2,
|
| 1592 |
"trial_name": null,
|
| 1593 |
"trial_params": null
|