Alex Spangher
commited on
Commit
·
dc209d3
1
Parent(s):
b763a7c
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +687 -3
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 731622405
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de12922da6650e9a750157f2d56f18c6a6231eabfc8c0aa2da93e17480f30ee1
|
| 3 |
size 731622405
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 509949681
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1941dd9c551eff6459b42989c78eb6514b639b2d02202840012315447e88233
|
| 3 |
size 509949681
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc33da413769d37bb1e11d9c4626efbaf418efd2bff1d3b6b3ade7067311d219
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec7e47f7f5b0d7b1a4f2877ddbda6ecbad6a56a50f484f6701523f4b9da5906a
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 3000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1371,13 +1371,697 @@
|
|
| 1371 |
"learning_rate": 3.0013845157544496e-05,
|
| 1372 |
"loss": 1.1827,
|
| 1373 |
"step": 89500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1374 |
}
|
| 1375 |
],
|
| 1376 |
"logging_steps": 500,
|
| 1377 |
"max_steps": 223905,
|
| 1378 |
"num_train_epochs": 5,
|
| 1379 |
"save_steps": 500,
|
| 1380 |
-
"total_flos":
|
| 1381 |
"trial_name": null,
|
| 1382 |
"trial_params": null
|
| 1383 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 3000,
|
| 6 |
+
"global_step": 134343,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1371 |
"learning_rate": 3.0013845157544496e-05,
|
| 1372 |
"loss": 1.1827,
|
| 1373 |
"step": 89500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 2.01,
|
| 1377 |
+
"learning_rate": 2.9902190661217926e-05,
|
| 1378 |
+
"loss": 0.9657,
|
| 1379 |
+
"step": 90000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 2.01,
|
| 1383 |
+
"eval_e": 0.6182643221781055,
|
| 1384 |
+
"eval_f1": 0.5581679626998242,
|
| 1385 |
+
"eval_loss": 2.8641064167022705,
|
| 1386 |
+
"eval_runtime": 287.6124,
|
| 1387 |
+
"eval_samples_per_second": 12.26,
|
| 1388 |
+
"eval_steps_per_second": 12.26,
|
| 1389 |
+
"step": 90000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.02,
|
| 1393 |
+
"learning_rate": 2.9790536164891362e-05,
|
| 1394 |
+
"loss": 0.8826,
|
| 1395 |
+
"step": 90500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.03,
|
| 1399 |
+
"learning_rate": 2.9678881668564795e-05,
|
| 1400 |
+
"loss": 0.9352,
|
| 1401 |
+
"step": 91000
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.04,
|
| 1405 |
+
"learning_rate": 2.9567227172238225e-05,
|
| 1406 |
+
"loss": 0.9967,
|
| 1407 |
+
"step": 91500
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 2.05,
|
| 1411 |
+
"learning_rate": 2.9455572675911658e-05,
|
| 1412 |
+
"loss": 0.9126,
|
| 1413 |
+
"step": 92000
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.07,
|
| 1417 |
+
"learning_rate": 2.9343918179585094e-05,
|
| 1418 |
+
"loss": 0.9895,
|
| 1419 |
+
"step": 92500
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.08,
|
| 1423 |
+
"learning_rate": 2.9232263683258527e-05,
|
| 1424 |
+
"loss": 0.9691,
|
| 1425 |
+
"step": 93000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.08,
|
| 1429 |
+
"eval_e": 0.6154282473057289,
|
| 1430 |
+
"eval_f1": 0.5556482680765841,
|
| 1431 |
+
"eval_loss": 2.8704285621643066,
|
| 1432 |
+
"eval_runtime": 287.9206,
|
| 1433 |
+
"eval_samples_per_second": 12.246,
|
| 1434 |
+
"eval_steps_per_second": 12.246,
|
| 1435 |
+
"step": 93000
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 2.09,
|
| 1439 |
+
"learning_rate": 2.9120609186931957e-05,
|
| 1440 |
+
"loss": 0.8332,
|
| 1441 |
+
"step": 93500
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.1,
|
| 1445 |
+
"learning_rate": 2.9008954690605393e-05,
|
| 1446 |
+
"loss": 1.0427,
|
| 1447 |
+
"step": 94000
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 2.11,
|
| 1451 |
+
"learning_rate": 2.8897300194278826e-05,
|
| 1452 |
+
"loss": 1.0371,
|
| 1453 |
+
"step": 94500
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.12,
|
| 1457 |
+
"learning_rate": 2.8785645697952256e-05,
|
| 1458 |
+
"loss": 0.8845,
|
| 1459 |
+
"step": 95000
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.13,
|
| 1463 |
+
"learning_rate": 2.867399120162569e-05,
|
| 1464 |
+
"loss": 0.8747,
|
| 1465 |
+
"step": 95500
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.14,
|
| 1469 |
+
"learning_rate": 2.8562336705299125e-05,
|
| 1470 |
+
"loss": 0.97,
|
| 1471 |
+
"step": 96000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.14,
|
| 1475 |
+
"eval_e": 0.6134429948950653,
|
| 1476 |
+
"eval_f1": 0.5550596343239774,
|
| 1477 |
+
"eval_loss": 2.79943585395813,
|
| 1478 |
+
"eval_runtime": 282.8048,
|
| 1479 |
+
"eval_samples_per_second": 12.468,
|
| 1480 |
+
"eval_steps_per_second": 12.468,
|
| 1481 |
+
"step": 96000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.15,
|
| 1485 |
+
"learning_rate": 2.8450682208972558e-05,
|
| 1486 |
+
"loss": 1.0791,
|
| 1487 |
+
"step": 96500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.17,
|
| 1491 |
+
"learning_rate": 2.8339027712645988e-05,
|
| 1492 |
+
"loss": 1.008,
|
| 1493 |
+
"step": 97000
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.18,
|
| 1497 |
+
"learning_rate": 2.8227373216319424e-05,
|
| 1498 |
+
"loss": 0.8047,
|
| 1499 |
+
"step": 97500
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 2.19,
|
| 1503 |
+
"learning_rate": 2.8115718719992857e-05,
|
| 1504 |
+
"loss": 0.8778,
|
| 1505 |
+
"step": 98000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 2.2,
|
| 1509 |
+
"learning_rate": 2.8004064223666287e-05,
|
| 1510 |
+
"loss": 0.8398,
|
| 1511 |
+
"step": 98500
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 2.21,
|
| 1515 |
+
"learning_rate": 2.789240972733972e-05,
|
| 1516 |
+
"loss": 1.0125,
|
| 1517 |
+
"step": 99000
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 2.21,
|
| 1521 |
+
"eval_e": 0.6176971072036301,
|
| 1522 |
+
"eval_f1": 0.5549828088169888,
|
| 1523 |
+
"eval_loss": 2.8314826488494873,
|
| 1524 |
+
"eval_runtime": 283.0891,
|
| 1525 |
+
"eval_samples_per_second": 12.455,
|
| 1526 |
+
"eval_steps_per_second": 12.455,
|
| 1527 |
+
"step": 99000
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 2.22,
|
| 1531 |
+
"learning_rate": 2.7780755231013156e-05,
|
| 1532 |
+
"loss": 0.7736,
|
| 1533 |
+
"step": 99500
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 2.23,
|
| 1537 |
+
"learning_rate": 2.7669100734686586e-05,
|
| 1538 |
+
"loss": 0.8345,
|
| 1539 |
+
"step": 100000
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 2.24,
|
| 1543 |
+
"learning_rate": 2.755744623836002e-05,
|
| 1544 |
+
"loss": 0.9044,
|
| 1545 |
+
"step": 100500
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.26,
|
| 1549 |
+
"learning_rate": 2.7445791742033455e-05,
|
| 1550 |
+
"loss": 0.9082,
|
| 1551 |
+
"step": 101000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.27,
|
| 1555 |
+
"learning_rate": 2.7334137245706888e-05,
|
| 1556 |
+
"loss": 0.8307,
|
| 1557 |
+
"step": 101500
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.28,
|
| 1561 |
+
"learning_rate": 2.7222482749380318e-05,
|
| 1562 |
+
"loss": 1.0004,
|
| 1563 |
+
"step": 102000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.28,
|
| 1567 |
+
"eval_e": 0.6165626772546795,
|
| 1568 |
+
"eval_f1": 0.5601784958413148,
|
| 1569 |
+
"eval_loss": 2.6772687435150146,
|
| 1570 |
+
"eval_runtime": 280.257,
|
| 1571 |
+
"eval_samples_per_second": 12.581,
|
| 1572 |
+
"eval_steps_per_second": 12.581,
|
| 1573 |
+
"step": 102000
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 2.29,
|
| 1577 |
+
"learning_rate": 2.711082825305375e-05,
|
| 1578 |
+
"loss": 0.948,
|
| 1579 |
+
"step": 102500
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.3,
|
| 1583 |
+
"learning_rate": 2.6999173756727187e-05,
|
| 1584 |
+
"loss": 0.8935,
|
| 1585 |
+
"step": 103000
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.31,
|
| 1589 |
+
"learning_rate": 2.6887519260400617e-05,
|
| 1590 |
+
"loss": 0.8814,
|
| 1591 |
+
"step": 103500
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.32,
|
| 1595 |
+
"learning_rate": 2.677586476407405e-05,
|
| 1596 |
+
"loss": 0.9694,
|
| 1597 |
+
"step": 104000
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 2.33,
|
| 1601 |
+
"learning_rate": 2.6664210267747486e-05,
|
| 1602 |
+
"loss": 0.8705,
|
| 1603 |
+
"step": 104500
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 2.34,
|
| 1607 |
+
"learning_rate": 2.655255577142092e-05,
|
| 1608 |
+
"loss": 1.0145,
|
| 1609 |
+
"step": 105000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 2.34,
|
| 1613 |
+
"eval_e": 0.5998298355076574,
|
| 1614 |
+
"eval_f1": 0.5481616751996528,
|
| 1615 |
+
"eval_loss": 2.488840341567993,
|
| 1616 |
+
"eval_runtime": 279.9287,
|
| 1617 |
+
"eval_samples_per_second": 12.596,
|
| 1618 |
+
"eval_steps_per_second": 12.596,
|
| 1619 |
+
"step": 105000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.36,
|
| 1623 |
+
"learning_rate": 2.644090127509435e-05,
|
| 1624 |
+
"loss": 0.9333,
|
| 1625 |
+
"step": 105500
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 2.37,
|
| 1629 |
+
"learning_rate": 2.632924677876778e-05,
|
| 1630 |
+
"loss": 1.1367,
|
| 1631 |
+
"step": 106000
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 2.38,
|
| 1635 |
+
"learning_rate": 2.6217592282441218e-05,
|
| 1636 |
+
"loss": 0.9492,
|
| 1637 |
+
"step": 106500
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 2.39,
|
| 1641 |
+
"learning_rate": 2.6105937786114647e-05,
|
| 1642 |
+
"loss": 1.0456,
|
| 1643 |
+
"step": 107000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.4,
|
| 1647 |
+
"learning_rate": 2.599428328978808e-05,
|
| 1648 |
+
"loss": 0.8105,
|
| 1649 |
+
"step": 107500
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.41,
|
| 1653 |
+
"learning_rate": 2.5882628793461517e-05,
|
| 1654 |
+
"loss": 1.0848,
|
| 1655 |
+
"step": 108000
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.41,
|
| 1659 |
+
"eval_e": 0.6089052750992626,
|
| 1660 |
+
"eval_f1": 0.5539872559411191,
|
| 1661 |
+
"eval_loss": 2.320396661758423,
|
| 1662 |
+
"eval_runtime": 280.0515,
|
| 1663 |
+
"eval_samples_per_second": 12.591,
|
| 1664 |
+
"eval_steps_per_second": 12.591,
|
| 1665 |
+
"step": 108000
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.42,
|
| 1669 |
+
"learning_rate": 2.5770974297134946e-05,
|
| 1670 |
+
"loss": 0.9052,
|
| 1671 |
+
"step": 108500
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.43,
|
| 1675 |
+
"learning_rate": 2.565931980080838e-05,
|
| 1676 |
+
"loss": 0.9562,
|
| 1677 |
+
"step": 109000
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.45,
|
| 1681 |
+
"learning_rate": 2.554766530448181e-05,
|
| 1682 |
+
"loss": 0.9221,
|
| 1683 |
+
"step": 109500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.46,
|
| 1687 |
+
"learning_rate": 2.543601080815525e-05,
|
| 1688 |
+
"loss": 0.9997,
|
| 1689 |
+
"step": 110000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.47,
|
| 1693 |
+
"learning_rate": 2.532435631182868e-05,
|
| 1694 |
+
"loss": 0.9698,
|
| 1695 |
+
"step": 110500
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 2.48,
|
| 1699 |
+
"learning_rate": 2.521270181550211e-05,
|
| 1700 |
+
"loss": 0.9949,
|
| 1701 |
+
"step": 111000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 2.48,
|
| 1705 |
+
"eval_e": 0.6168462847419172,
|
| 1706 |
+
"eval_f1": 0.556568464310343,
|
| 1707 |
+
"eval_loss": 2.4436562061309814,
|
| 1708 |
+
"eval_runtime": 283.2598,
|
| 1709 |
+
"eval_samples_per_second": 12.448,
|
| 1710 |
+
"eval_steps_per_second": 12.448,
|
| 1711 |
+
"step": 111000
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.49,
|
| 1715 |
+
"learning_rate": 2.5101047319175548e-05,
|
| 1716 |
+
"loss": 0.9329,
|
| 1717 |
+
"step": 111500
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.5,
|
| 1721 |
+
"learning_rate": 2.4989392822848977e-05,
|
| 1722 |
+
"loss": 0.9796,
|
| 1723 |
+
"step": 112000
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 2.51,
|
| 1727 |
+
"learning_rate": 2.487773832652241e-05,
|
| 1728 |
+
"loss": 0.7865,
|
| 1729 |
+
"step": 112500
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.52,
|
| 1733 |
+
"learning_rate": 2.4766083830195843e-05,
|
| 1734 |
+
"loss": 0.9462,
|
| 1735 |
+
"step": 113000
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 2.53,
|
| 1739 |
+
"learning_rate": 2.4654429333869276e-05,
|
| 1740 |
+
"loss": 0.9154,
|
| 1741 |
+
"step": 113500
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 2.55,
|
| 1745 |
+
"learning_rate": 2.454277483754271e-05,
|
| 1746 |
+
"loss": 0.9923,
|
| 1747 |
+
"step": 114000
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.55,
|
| 1751 |
+
"eval_e": 0.6145774248440159,
|
| 1752 |
+
"eval_f1": 0.5539626796675543,
|
| 1753 |
+
"eval_loss": 2.7537660598754883,
|
| 1754 |
+
"eval_runtime": 286.2619,
|
| 1755 |
+
"eval_samples_per_second": 12.317,
|
| 1756 |
+
"eval_steps_per_second": 12.317,
|
| 1757 |
+
"step": 114000
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 2.56,
|
| 1761 |
+
"learning_rate": 2.4431120341216142e-05,
|
| 1762 |
+
"loss": 0.8292,
|
| 1763 |
+
"step": 114500
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 2.57,
|
| 1767 |
+
"learning_rate": 2.4319465844889575e-05,
|
| 1768 |
+
"loss": 0.8699,
|
| 1769 |
+
"step": 115000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.58,
|
| 1773 |
+
"learning_rate": 2.4207811348563008e-05,
|
| 1774 |
+
"loss": 0.9969,
|
| 1775 |
+
"step": 115500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.59,
|
| 1779 |
+
"learning_rate": 2.409615685223644e-05,
|
| 1780 |
+
"loss": 0.6963,
|
| 1781 |
+
"step": 116000
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.6,
|
| 1785 |
+
"learning_rate": 2.3984502355909874e-05,
|
| 1786 |
+
"loss": 0.9601,
|
| 1787 |
+
"step": 116500
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.61,
|
| 1791 |
+
"learning_rate": 2.3872847859583307e-05,
|
| 1792 |
+
"loss": 1.0571,
|
| 1793 |
+
"step": 117000
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 2.61,
|
| 1797 |
+
"eval_e": 0.6216676120249575,
|
| 1798 |
+
"eval_f1": 0.5614300304448882,
|
| 1799 |
+
"eval_loss": 2.4599826335906982,
|
| 1800 |
+
"eval_runtime": 284.3149,
|
| 1801 |
+
"eval_samples_per_second": 12.402,
|
| 1802 |
+
"eval_steps_per_second": 12.402,
|
| 1803 |
+
"step": 117000
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.62,
|
| 1807 |
+
"learning_rate": 2.376119336325674e-05,
|
| 1808 |
+
"loss": 0.9524,
|
| 1809 |
+
"step": 117500
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.64,
|
| 1813 |
+
"learning_rate": 2.3649538866930173e-05,
|
| 1814 |
+
"loss": 1.1019,
|
| 1815 |
+
"step": 118000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.65,
|
| 1819 |
+
"learning_rate": 2.3537884370603606e-05,
|
| 1820 |
+
"loss": 0.8693,
|
| 1821 |
+
"step": 118500
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 2.66,
|
| 1825 |
+
"learning_rate": 2.342622987427704e-05,
|
| 1826 |
+
"loss": 0.8238,
|
| 1827 |
+
"step": 119000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 2.67,
|
| 1831 |
+
"learning_rate": 2.3314575377950472e-05,
|
| 1832 |
+
"loss": 1.0947,
|
| 1833 |
+
"step": 119500
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 2.68,
|
| 1837 |
+
"learning_rate": 2.3202920881623905e-05,
|
| 1838 |
+
"loss": 0.887,
|
| 1839 |
+
"step": 120000
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.68,
|
| 1843 |
+
"eval_e": 0.6091888825865003,
|
| 1844 |
+
"eval_f1": 0.5543750338048291,
|
| 1845 |
+
"eval_loss": 2.853802442550659,
|
| 1846 |
+
"eval_runtime": 280.8484,
|
| 1847 |
+
"eval_samples_per_second": 12.555,
|
| 1848 |
+
"eval_steps_per_second": 12.555,
|
| 1849 |
+
"step": 120000
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 2.69,
|
| 1853 |
+
"learning_rate": 2.3091266385297335e-05,
|
| 1854 |
+
"loss": 0.8148,
|
| 1855 |
+
"step": 120500
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 2.7,
|
| 1859 |
+
"learning_rate": 2.297961188897077e-05,
|
| 1860 |
+
"loss": 0.8113,
|
| 1861 |
+
"step": 121000
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 2.71,
|
| 1865 |
+
"learning_rate": 2.2867957392644204e-05,
|
| 1866 |
+
"loss": 1.0991,
|
| 1867 |
+
"step": 121500
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 2.72,
|
| 1871 |
+
"learning_rate": 2.2756302896317637e-05,
|
| 1872 |
+
"loss": 0.7902,
|
| 1873 |
+
"step": 122000
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.74,
|
| 1877 |
+
"learning_rate": 2.264464839999107e-05,
|
| 1878 |
+
"loss": 0.9871,
|
| 1879 |
+
"step": 122500
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.75,
|
| 1883 |
+
"learning_rate": 2.25329939036645e-05,
|
| 1884 |
+
"loss": 0.861,
|
| 1885 |
+
"step": 123000
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.75,
|
| 1889 |
+
"eval_e": 0.6074872376630743,
|
| 1890 |
+
"eval_f1": 0.551903563769941,
|
| 1891 |
+
"eval_loss": 2.6797034740448,
|
| 1892 |
+
"eval_runtime": 288.8697,
|
| 1893 |
+
"eval_samples_per_second": 12.206,
|
| 1894 |
+
"eval_steps_per_second": 12.206,
|
| 1895 |
+
"step": 123000
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.76,
|
| 1899 |
+
"learning_rate": 2.2421339407337936e-05,
|
| 1900 |
+
"loss": 0.8356,
|
| 1901 |
+
"step": 123500
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 2.77,
|
| 1905 |
+
"learning_rate": 2.2309684911011366e-05,
|
| 1906 |
+
"loss": 0.9589,
|
| 1907 |
+
"step": 124000
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.78,
|
| 1911 |
+
"learning_rate": 2.2198030414684802e-05,
|
| 1912 |
+
"loss": 1.1244,
|
| 1913 |
+
"step": 124500
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.79,
|
| 1917 |
+
"learning_rate": 2.2086375918358235e-05,
|
| 1918 |
+
"loss": 1.0342,
|
| 1919 |
+
"step": 125000
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 2.8,
|
| 1923 |
+
"learning_rate": 2.1974721422031664e-05,
|
| 1924 |
+
"loss": 0.995,
|
| 1925 |
+
"step": 125500
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 2.81,
|
| 1929 |
+
"learning_rate": 2.18630669257051e-05,
|
| 1930 |
+
"loss": 1.2528,
|
| 1931 |
+
"step": 126000
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 2.81,
|
| 1935 |
+
"eval_e": 0.6213840045377198,
|
| 1936 |
+
"eval_f1": 0.5634895725291656,
|
| 1937 |
+
"eval_loss": 2.4178013801574707,
|
| 1938 |
+
"eval_runtime": 286.5357,
|
| 1939 |
+
"eval_samples_per_second": 12.306,
|
| 1940 |
+
"eval_steps_per_second": 12.306,
|
| 1941 |
+
"step": 126000
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.82,
|
| 1945 |
+
"learning_rate": 2.175141242937853e-05,
|
| 1946 |
+
"loss": 0.9028,
|
| 1947 |
+
"step": 126500
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 2.84,
|
| 1951 |
+
"learning_rate": 2.1639757933051967e-05,
|
| 1952 |
+
"loss": 1.0706,
|
| 1953 |
+
"step": 127000
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 2.85,
|
| 1957 |
+
"learning_rate": 2.1528103436725396e-05,
|
| 1958 |
+
"loss": 0.8691,
|
| 1959 |
+
"step": 127500
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.86,
|
| 1963 |
+
"learning_rate": 2.141644894039883e-05,
|
| 1964 |
+
"loss": 0.8903,
|
| 1965 |
+
"step": 128000
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.87,
|
| 1969 |
+
"learning_rate": 2.1304794444072262e-05,
|
| 1970 |
+
"loss": 0.7932,
|
| 1971 |
+
"step": 128500
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 2.88,
|
| 1975 |
+
"learning_rate": 2.1193139947745695e-05,
|
| 1976 |
+
"loss": 0.8327,
|
| 1977 |
+
"step": 129000
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.88,
|
| 1981 |
+
"eval_e": 0.6193987521270562,
|
| 1982 |
+
"eval_f1": 0.561697084299324,
|
| 1983 |
+
"eval_loss": 2.573134660720825,
|
| 1984 |
+
"eval_runtime": 286.0117,
|
| 1985 |
+
"eval_samples_per_second": 12.328,
|
| 1986 |
+
"eval_steps_per_second": 12.328,
|
| 1987 |
+
"step": 129000
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.89,
|
| 1991 |
+
"learning_rate": 2.1081485451419132e-05,
|
| 1992 |
+
"loss": 1.0172,
|
| 1993 |
+
"step": 129500
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 2.9,
|
| 1997 |
+
"learning_rate": 2.096983095509256e-05,
|
| 1998 |
+
"loss": 0.9395,
|
| 1999 |
+
"step": 130000
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 2.91,
|
| 2003 |
+
"learning_rate": 2.0858176458765998e-05,
|
| 2004 |
+
"loss": 0.9068,
|
| 2005 |
+
"step": 130500
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.93,
|
| 2009 |
+
"learning_rate": 2.0746521962439427e-05,
|
| 2010 |
+
"loss": 1.0099,
|
| 2011 |
+
"step": 131000
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.94,
|
| 2015 |
+
"learning_rate": 2.063486746611286e-05,
|
| 2016 |
+
"loss": 0.9126,
|
| 2017 |
+
"step": 131500
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 2.95,
|
| 2021 |
+
"learning_rate": 2.0523212969786293e-05,
|
| 2022 |
+
"loss": 1.0005,
|
| 2023 |
+
"step": 132000
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 2.95,
|
| 2027 |
+
"eval_e": 0.6114577424844015,
|
| 2028 |
+
"eval_f1": 0.5556109691935686,
|
| 2029 |
+
"eval_loss": 2.36938214302063,
|
| 2030 |
+
"eval_runtime": 284.4774,
|
| 2031 |
+
"eval_samples_per_second": 12.395,
|
| 2032 |
+
"eval_steps_per_second": 12.395,
|
| 2033 |
+
"step": 132000
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.96,
|
| 2037 |
+
"learning_rate": 2.0411558473459726e-05,
|
| 2038 |
+
"loss": 0.9687,
|
| 2039 |
+
"step": 132500
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 2.97,
|
| 2043 |
+
"learning_rate": 2.0299903977133163e-05,
|
| 2044 |
+
"loss": 0.9334,
|
| 2045 |
+
"step": 133000
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 2.98,
|
| 2049 |
+
"learning_rate": 2.0188249480806592e-05,
|
| 2050 |
+
"loss": 0.8237,
|
| 2051 |
+
"step": 133500
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.99,
|
| 2055 |
+
"learning_rate": 2.0076594984480025e-05,
|
| 2056 |
+
"loss": 0.9511,
|
| 2057 |
+
"step": 134000
|
| 2058 |
}
|
| 2059 |
],
|
| 2060 |
"logging_steps": 500,
|
| 2061 |
"max_steps": 223905,
|
| 2062 |
"num_train_epochs": 5,
|
| 2063 |
"save_steps": 500,
|
| 2064 |
+
"total_flos": 8.88715715438306e+16,
|
| 2065 |
"trial_name": null,
|
| 2066 |
"trial_params": null
|
| 2067 |
}
|