Training in progress, step 402, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 101184122
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c66af201cb46ea48affe25fb60a01d856a9c1e55da9025eceeb12b4646d97a3
|
3 |
size 101184122
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2e15289dd51850b5a4dbc37418946479cd95b898dc0f170f28090e10a296940
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d06506b9f2dd31a09d0da656752ae957a35f8f281429519bfaef30401c384c3
|
3 |
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3db034fd3734680c05eeb36af77b84676a988b958f10cc056cb79e17603f274
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 201,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1430,6 +1430,1421 @@
|
|
1430 |
"eval_samples_per_second": 22.363,
|
1431 |
"eval_steps_per_second": 5.595,
|
1432 |
"step": 201
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1433 |
}
|
1434 |
],
|
1435 |
"logging_steps": 1,
|
@@ -1449,7 +2864,7 @@
|
|
1449 |
"attributes": {}
|
1450 |
}
|
1451 |
},
|
1452 |
-
"total_flos":
|
1453 |
"train_batch_size": 2,
|
1454 |
"trial_name": null,
|
1455 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5014031805425632,
|
5 |
"eval_steps": 201,
|
6 |
+
"global_step": 402,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1430 |
"eval_samples_per_second": 22.363,
|
1431 |
"eval_steps_per_second": 5.595,
|
1432 |
"step": 201
|
1433 |
+
},
|
1434 |
+
{
|
1435 |
+
"epoch": 0.251948861864671,
|
1436 |
+
"grad_norm": NaN,
|
1437 |
+
"learning_rate": 0.00018045682064347275,
|
1438 |
+
"loss": 0.0,
|
1439 |
+
"step": 202
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 0.25319613345806047,
|
1443 |
+
"grad_norm": NaN,
|
1444 |
+
"learning_rate": 0.00018020769303234962,
|
1445 |
+
"loss": 0.0,
|
1446 |
+
"step": 203
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 0.25444340505144997,
|
1450 |
+
"grad_norm": NaN,
|
1451 |
+
"learning_rate": 0.00017995716184739284,
|
1452 |
+
"loss": 0.0,
|
1453 |
+
"step": 204
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 0.2556906766448394,
|
1457 |
+
"grad_norm": NaN,
|
1458 |
+
"learning_rate": 0.00017970523147270822,
|
1459 |
+
"loss": 0.0,
|
1460 |
+
"step": 205
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 0.25693794823822885,
|
1464 |
+
"grad_norm": NaN,
|
1465 |
+
"learning_rate": 0.0001794519063168864,
|
1466 |
+
"loss": 0.0,
|
1467 |
+
"step": 206
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.25818521983161835,
|
1471 |
+
"grad_norm": NaN,
|
1472 |
+
"learning_rate": 0.0001791971908129256,
|
1473 |
+
"loss": 0.0,
|
1474 |
+
"step": 207
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.2594324914250078,
|
1478 |
+
"grad_norm": NaN,
|
1479 |
+
"learning_rate": 0.000178941089418154,
|
1480 |
+
"loss": 0.0,
|
1481 |
+
"step": 208
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 0.26067976301839724,
|
1485 |
+
"grad_norm": NaN,
|
1486 |
+
"learning_rate": 0.000178683606614152,
|
1487 |
+
"loss": 0.0,
|
1488 |
+
"step": 209
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 0.26192703461178674,
|
1492 |
+
"grad_norm": NaN,
|
1493 |
+
"learning_rate": 0.00017842474690667344,
|
1494 |
+
"loss": 0.0,
|
1495 |
+
"step": 210
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 0.2631743062051762,
|
1499 |
+
"grad_norm": NaN,
|
1500 |
+
"learning_rate": 0.00017816451482556702,
|
1501 |
+
"loss": 0.0,
|
1502 |
+
"step": 211
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 0.2644215777985656,
|
1506 |
+
"grad_norm": NaN,
|
1507 |
+
"learning_rate": 0.0001779029149246969,
|
1508 |
+
"loss": 0.0,
|
1509 |
+
"step": 212
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.2656688493919551,
|
1513 |
+
"grad_norm": NaN,
|
1514 |
+
"learning_rate": 0.00017763995178186307,
|
1515 |
+
"loss": 0.0,
|
1516 |
+
"step": 213
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 0.26691612098534456,
|
1520 |
+
"grad_norm": NaN,
|
1521 |
+
"learning_rate": 0.00017737562999872118,
|
1522 |
+
"loss": 0.0,
|
1523 |
+
"step": 214
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 0.268163392578734,
|
1527 |
+
"grad_norm": NaN,
|
1528 |
+
"learning_rate": 0.00017710995420070215,
|
1529 |
+
"loss": 0.0,
|
1530 |
+
"step": 215
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 0.2694106641721235,
|
1534 |
+
"grad_norm": NaN,
|
1535 |
+
"learning_rate": 0.00017684292903693102,
|
1536 |
+
"loss": 0.0,
|
1537 |
+
"step": 216
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.27065793576551295,
|
1541 |
+
"grad_norm": NaN,
|
1542 |
+
"learning_rate": 0.00017657455918014582,
|
1543 |
+
"loss": 0.0,
|
1544 |
+
"step": 217
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 0.2719052073589024,
|
1548 |
+
"grad_norm": NaN,
|
1549 |
+
"learning_rate": 0.00017630484932661559,
|
1550 |
+
"loss": 0.0,
|
1551 |
+
"step": 218
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.2731524789522919,
|
1555 |
+
"grad_norm": NaN,
|
1556 |
+
"learning_rate": 0.0001760338041960583,
|
1557 |
+
"loss": 0.0,
|
1558 |
+
"step": 219
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 0.27439975054568133,
|
1562 |
+
"grad_norm": NaN,
|
1563 |
+
"learning_rate": 0.00017576142853155838,
|
1564 |
+
"loss": 0.0,
|
1565 |
+
"step": 220
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 0.2756470221390708,
|
1569 |
+
"grad_norm": NaN,
|
1570 |
+
"learning_rate": 0.00017548772709948343,
|
1571 |
+
"loss": 0.0,
|
1572 |
+
"step": 221
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 0.2768942937324602,
|
1576 |
+
"grad_norm": NaN,
|
1577 |
+
"learning_rate": 0.0001752127046894011,
|
1578 |
+
"loss": 0.0,
|
1579 |
+
"step": 222
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 0.2781415653258497,
|
1583 |
+
"grad_norm": NaN,
|
1584 |
+
"learning_rate": 0.0001749363661139951,
|
1585 |
+
"loss": 0.0,
|
1586 |
+
"step": 223
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 0.27938883691923916,
|
1590 |
+
"grad_norm": NaN,
|
1591 |
+
"learning_rate": 0.00017465871620898102,
|
1592 |
+
"loss": 0.0,
|
1593 |
+
"step": 224
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.2806361085126286,
|
1597 |
+
"grad_norm": NaN,
|
1598 |
+
"learning_rate": 0.00017437975983302178,
|
1599 |
+
"loss": 0.0,
|
1600 |
+
"step": 225
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.2818833801060181,
|
1604 |
+
"grad_norm": NaN,
|
1605 |
+
"learning_rate": 0.0001740995018676425,
|
1606 |
+
"loss": 0.0,
|
1607 |
+
"step": 226
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 0.28313065169940754,
|
1611 |
+
"grad_norm": NaN,
|
1612 |
+
"learning_rate": 0.0001738179472171452,
|
1613 |
+
"loss": 0.0,
|
1614 |
+
"step": 227
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 0.284377923292797,
|
1618 |
+
"grad_norm": NaN,
|
1619 |
+
"learning_rate": 0.00017353510080852282,
|
1620 |
+
"loss": 0.0,
|
1621 |
+
"step": 228
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 0.2856251948861865,
|
1625 |
+
"grad_norm": NaN,
|
1626 |
+
"learning_rate": 0.0001732509675913731,
|
1627 |
+
"loss": 0.0,
|
1628 |
+
"step": 229
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 0.2868724664795759,
|
1632 |
+
"grad_norm": NaN,
|
1633 |
+
"learning_rate": 0.000172965552537812,
|
1634 |
+
"loss": 0.0,
|
1635 |
+
"step": 230
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.28811973807296537,
|
1639 |
+
"grad_norm": NaN,
|
1640 |
+
"learning_rate": 0.00017267886064238662,
|
1641 |
+
"loss": 0.0,
|
1642 |
+
"step": 231
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 0.28936700966635487,
|
1646 |
+
"grad_norm": NaN,
|
1647 |
+
"learning_rate": 0.00017239089692198785,
|
1648 |
+
"loss": 0.0,
|
1649 |
+
"step": 232
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 0.2906142812597443,
|
1653 |
+
"grad_norm": NaN,
|
1654 |
+
"learning_rate": 0.0001721016664157625,
|
1655 |
+
"loss": 0.0,
|
1656 |
+
"step": 233
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.29186155285313375,
|
1660 |
+
"grad_norm": NaN,
|
1661 |
+
"learning_rate": 0.00017181117418502525,
|
1662 |
+
"loss": 0.0,
|
1663 |
+
"step": 234
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.29310882444652325,
|
1667 |
+
"grad_norm": NaN,
|
1668 |
+
"learning_rate": 0.00017151942531316988,
|
1669 |
+
"loss": 0.0,
|
1670 |
+
"step": 235
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.2943560960399127,
|
1674 |
+
"grad_norm": NaN,
|
1675 |
+
"learning_rate": 0.00017122642490558055,
|
1676 |
+
"loss": 0.0,
|
1677 |
+
"step": 236
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.29560336763330214,
|
1681 |
+
"grad_norm": NaN,
|
1682 |
+
"learning_rate": 0.00017093217808954232,
|
1683 |
+
"loss": 0.0,
|
1684 |
+
"step": 237
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.29685063922669164,
|
1688 |
+
"grad_norm": NaN,
|
1689 |
+
"learning_rate": 0.00017063669001415145,
|
1690 |
+
"loss": 0.0,
|
1691 |
+
"step": 238
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.2980979108200811,
|
1695 |
+
"grad_norm": NaN,
|
1696 |
+
"learning_rate": 0.00017033996585022528,
|
1697 |
+
"loss": 0.0,
|
1698 |
+
"step": 239
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.2993451824134705,
|
1702 |
+
"grad_norm": NaN,
|
1703 |
+
"learning_rate": 0.00017004201079021176,
|
1704 |
+
"loss": 0.0,
|
1705 |
+
"step": 240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.30059245400686,
|
1709 |
+
"grad_norm": NaN,
|
1710 |
+
"learning_rate": 0.00016974283004809858,
|
1711 |
+
"loss": 0.0,
|
1712 |
+
"step": 241
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.30183972560024946,
|
1716 |
+
"grad_norm": NaN,
|
1717 |
+
"learning_rate": 0.00016944242885932206,
|
1718 |
+
"loss": 0.0,
|
1719 |
+
"step": 242
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.3030869971936389,
|
1723 |
+
"grad_norm": NaN,
|
1724 |
+
"learning_rate": 0.0001691408124806752,
|
1725 |
+
"loss": 0.0,
|
1726 |
+
"step": 243
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.30433426878702835,
|
1730 |
+
"grad_norm": NaN,
|
1731 |
+
"learning_rate": 0.00016883798619021608,
|
1732 |
+
"loss": 0.0,
|
1733 |
+
"step": 244
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.30558154038041785,
|
1737 |
+
"grad_norm": NaN,
|
1738 |
+
"learning_rate": 0.0001685339552871752,
|
1739 |
+
"loss": 0.0,
|
1740 |
+
"step": 245
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.3068288119738073,
|
1744 |
+
"grad_norm": NaN,
|
1745 |
+
"learning_rate": 0.00016822872509186297,
|
1746 |
+
"loss": 0.0,
|
1747 |
+
"step": 246
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.30807608356719673,
|
1751 |
+
"grad_norm": NaN,
|
1752 |
+
"learning_rate": 0.0001679223009455764,
|
1753 |
+
"loss": 0.0,
|
1754 |
+
"step": 247
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.30932335516058623,
|
1758 |
+
"grad_norm": NaN,
|
1759 |
+
"learning_rate": 0.00016761468821050585,
|
1760 |
+
"loss": 0.0,
|
1761 |
+
"step": 248
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.3105706267539757,
|
1765 |
+
"grad_norm": NaN,
|
1766 |
+
"learning_rate": 0.00016730589226964098,
|
1767 |
+
"loss": 0.0,
|
1768 |
+
"step": 249
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.3118178983473651,
|
1772 |
+
"grad_norm": NaN,
|
1773 |
+
"learning_rate": 0.00016699591852667673,
|
1774 |
+
"loss": 0.0,
|
1775 |
+
"step": 250
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.3130651699407546,
|
1779 |
+
"grad_norm": NaN,
|
1780 |
+
"learning_rate": 0.00016668477240591864,
|
1781 |
+
"loss": 0.0,
|
1782 |
+
"step": 251
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.31431244153414406,
|
1786 |
+
"grad_norm": NaN,
|
1787 |
+
"learning_rate": 0.00016637245935218799,
|
1788 |
+
"loss": 0.0,
|
1789 |
+
"step": 252
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.3155597131275335,
|
1793 |
+
"grad_norm": NaN,
|
1794 |
+
"learning_rate": 0.00016605898483072648,
|
1795 |
+
"loss": 0.0,
|
1796 |
+
"step": 253
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.316806984720923,
|
1800 |
+
"grad_norm": NaN,
|
1801 |
+
"learning_rate": 0.00016574435432710068,
|
1802 |
+
"loss": 0.0,
|
1803 |
+
"step": 254
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.31805425631431244,
|
1807 |
+
"grad_norm": NaN,
|
1808 |
+
"learning_rate": 0.0001654285733471059,
|
1809 |
+
"loss": 0.0,
|
1810 |
+
"step": 255
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.3193015279077019,
|
1814 |
+
"grad_norm": NaN,
|
1815 |
+
"learning_rate": 0.0001651116474166699,
|
1816 |
+
"loss": 0.0,
|
1817 |
+
"step": 256
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.3205487995010914,
|
1821 |
+
"grad_norm": NaN,
|
1822 |
+
"learning_rate": 0.00016479358208175627,
|
1823 |
+
"loss": 0.0,
|
1824 |
+
"step": 257
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.32179607109448083,
|
1828 |
+
"grad_norm": NaN,
|
1829 |
+
"learning_rate": 0.00016447438290826733,
|
1830 |
+
"loss": 0.0,
|
1831 |
+
"step": 258
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.32304334268787027,
|
1835 |
+
"grad_norm": NaN,
|
1836 |
+
"learning_rate": 0.00016415405548194663,
|
1837 |
+
"loss": 0.0,
|
1838 |
+
"step": 259
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 0.32429061428125977,
|
1842 |
+
"grad_norm": NaN,
|
1843 |
+
"learning_rate": 0.00016383260540828135,
|
1844 |
+
"loss": 0.0,
|
1845 |
+
"step": 260
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.3255378858746492,
|
1849 |
+
"grad_norm": NaN,
|
1850 |
+
"learning_rate": 0.00016351003831240415,
|
1851 |
+
"loss": 0.0,
|
1852 |
+
"step": 261
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 0.32678515746803866,
|
1856 |
+
"grad_norm": NaN,
|
1857 |
+
"learning_rate": 0.00016318635983899465,
|
1858 |
+
"loss": 0.0,
|
1859 |
+
"step": 262
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 0.3280324290614281,
|
1863 |
+
"grad_norm": NaN,
|
1864 |
+
"learning_rate": 0.0001628615756521809,
|
1865 |
+
"loss": 0.0,
|
1866 |
+
"step": 263
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 0.3292797006548176,
|
1870 |
+
"grad_norm": NaN,
|
1871 |
+
"learning_rate": 0.0001625356914354399,
|
1872 |
+
"loss": 0.0,
|
1873 |
+
"step": 264
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 0.33052697224820704,
|
1877 |
+
"grad_norm": NaN,
|
1878 |
+
"learning_rate": 0.0001622087128914985,
|
1879 |
+
"loss": 0.0,
|
1880 |
+
"step": 265
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.3317742438415965,
|
1884 |
+
"grad_norm": NaN,
|
1885 |
+
"learning_rate": 0.00016188064574223335,
|
1886 |
+
"loss": 0.0,
|
1887 |
+
"step": 266
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.333021515434986,
|
1891 |
+
"grad_norm": NaN,
|
1892 |
+
"learning_rate": 0.0001615514957285709,
|
1893 |
+
"loss": 0.0,
|
1894 |
+
"step": 267
|
1895 |
+
},
|
1896 |
+
{
|
1897 |
+
"epoch": 0.3342687870283754,
|
1898 |
+
"grad_norm": NaN,
|
1899 |
+
"learning_rate": 0.00016122126861038688,
|
1900 |
+
"loss": 0.0,
|
1901 |
+
"step": 268
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 0.33551605862176487,
|
1905 |
+
"grad_norm": NaN,
|
1906 |
+
"learning_rate": 0.00016088997016640562,
|
1907 |
+
"loss": 0.0,
|
1908 |
+
"step": 269
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 0.33676333021515437,
|
1912 |
+
"grad_norm": NaN,
|
1913 |
+
"learning_rate": 0.00016055760619409877,
|
1914 |
+
"loss": 0.0,
|
1915 |
+
"step": 270
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.3380106018085438,
|
1919 |
+
"grad_norm": NaN,
|
1920 |
+
"learning_rate": 0.00016022418250958385,
|
1921 |
+
"loss": 0.0,
|
1922 |
+
"step": 271
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 0.33925787340193325,
|
1926 |
+
"grad_norm": NaN,
|
1927 |
+
"learning_rate": 0.00015988970494752272,
|
1928 |
+
"loss": 0.0,
|
1929 |
+
"step": 272
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.34050514499532275,
|
1933 |
+
"grad_norm": NaN,
|
1934 |
+
"learning_rate": 0.00015955417936101913,
|
1935 |
+
"loss": 0.0,
|
1936 |
+
"step": 273
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 0.3417524165887122,
|
1940 |
+
"grad_norm": NaN,
|
1941 |
+
"learning_rate": 0.00015921761162151653,
|
1942 |
+
"loss": 0.0,
|
1943 |
+
"step": 274
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 0.34299968818210164,
|
1947 |
+
"grad_norm": NaN,
|
1948 |
+
"learning_rate": 0.00015888000761869528,
|
1949 |
+
"loss": 0.0,
|
1950 |
+
"step": 275
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 0.34424695977549113,
|
1954 |
+
"grad_norm": NaN,
|
1955 |
+
"learning_rate": 0.0001585413732603695,
|
1956 |
+
"loss": 0.0,
|
1957 |
+
"step": 276
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 0.3454942313688806,
|
1961 |
+
"grad_norm": NaN,
|
1962 |
+
"learning_rate": 0.00015820171447238383,
|
1963 |
+
"loss": 0.0,
|
1964 |
+
"step": 277
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 0.34674150296227,
|
1968 |
+
"grad_norm": NaN,
|
1969 |
+
"learning_rate": 0.0001578610371985096,
|
1970 |
+
"loss": 0.0,
|
1971 |
+
"step": 278
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.3479887745556595,
|
1975 |
+
"grad_norm": NaN,
|
1976 |
+
"learning_rate": 0.00015751934740034092,
|
1977 |
+
"loss": 0.0,
|
1978 |
+
"step": 279
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.34923604614904896,
|
1982 |
+
"grad_norm": NaN,
|
1983 |
+
"learning_rate": 0.00015717665105719015,
|
1984 |
+
"loss": 0.0,
|
1985 |
+
"step": 280
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 0.3504833177424384,
|
1989 |
+
"grad_norm": NaN,
|
1990 |
+
"learning_rate": 0.00015683295416598367,
|
1991 |
+
"loss": 0.0,
|
1992 |
+
"step": 281
|
1993 |
+
},
|
1994 |
+
{
|
1995 |
+
"epoch": 0.3517305893358279,
|
1996 |
+
"grad_norm": NaN,
|
1997 |
+
"learning_rate": 0.00015648826274115653,
|
1998 |
+
"loss": 0.0,
|
1999 |
+
"step": 282
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 0.35297786092921735,
|
2003 |
+
"grad_norm": NaN,
|
2004 |
+
"learning_rate": 0.00015614258281454734,
|
2005 |
+
"loss": 0.0,
|
2006 |
+
"step": 283
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 0.3542251325226068,
|
2010 |
+
"grad_norm": NaN,
|
2011 |
+
"learning_rate": 0.00015579592043529292,
|
2012 |
+
"loss": 0.0,
|
2013 |
+
"step": 284
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.35547240411599623,
|
2017 |
+
"grad_norm": NaN,
|
2018 |
+
"learning_rate": 0.00015544828166972203,
|
2019 |
+
"loss": 0.0,
|
2020 |
+
"step": 285
|
2021 |
+
},
|
2022 |
+
{
|
2023 |
+
"epoch": 0.35671967570938573,
|
2024 |
+
"grad_norm": NaN,
|
2025 |
+
"learning_rate": 0.00015509967260124964,
|
2026 |
+
"loss": 0.0,
|
2027 |
+
"step": 286
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 0.3579669473027752,
|
2031 |
+
"grad_norm": NaN,
|
2032 |
+
"learning_rate": 0.0001547500993302702,
|
2033 |
+
"loss": 0.0,
|
2034 |
+
"step": 287
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 0.3592142188961646,
|
2038 |
+
"grad_norm": NaN,
|
2039 |
+
"learning_rate": 0.000154399567974051,
|
2040 |
+
"loss": 0.0,
|
2041 |
+
"step": 288
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 0.3604614904895541,
|
2045 |
+
"grad_norm": NaN,
|
2046 |
+
"learning_rate": 0.00015404808466662508,
|
2047 |
+
"loss": 0.0,
|
2048 |
+
"step": 289
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 0.36170876208294356,
|
2052 |
+
"grad_norm": NaN,
|
2053 |
+
"learning_rate": 0.0001536956555586839,
|
2054 |
+
"loss": 0.0,
|
2055 |
+
"step": 290
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.362956033676333,
|
2059 |
+
"grad_norm": NaN,
|
2060 |
+
"learning_rate": 0.0001533422868174697,
|
2061 |
+
"loss": 0.0,
|
2062 |
+
"step": 291
|
2063 |
+
},
|
2064 |
+
{
|
2065 |
+
"epoch": 0.3642033052697225,
|
2066 |
+
"grad_norm": NaN,
|
2067 |
+
"learning_rate": 0.00015298798462666765,
|
2068 |
+
"loss": 0.0,
|
2069 |
+
"step": 292
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 0.36545057686311194,
|
2073 |
+
"grad_norm": NaN,
|
2074 |
+
"learning_rate": 0.00015263275518629754,
|
2075 |
+
"loss": 0.0,
|
2076 |
+
"step": 293
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 0.3666978484565014,
|
2080 |
+
"grad_norm": NaN,
|
2081 |
+
"learning_rate": 0.00015227660471260528,
|
2082 |
+
"loss": 0.0,
|
2083 |
+
"step": 294
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 0.3679451200498909,
|
2087 |
+
"grad_norm": NaN,
|
2088 |
+
"learning_rate": 0.00015191953943795427,
|
2089 |
+
"loss": 0.0,
|
2090 |
+
"step": 295
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 0.3691923916432803,
|
2094 |
+
"grad_norm": NaN,
|
2095 |
+
"learning_rate": 0.00015156156561071612,
|
2096 |
+
"loss": 0.0,
|
2097 |
+
"step": 296
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.37043966323666977,
|
2101 |
+
"grad_norm": NaN,
|
2102 |
+
"learning_rate": 0.0001512026894951615,
|
2103 |
+
"loss": 0.0,
|
2104 |
+
"step": 297
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 0.37168693483005927,
|
2108 |
+
"grad_norm": NaN,
|
2109 |
+
"learning_rate": 0.00015084291737135048,
|
2110 |
+
"loss": 0.0,
|
2111 |
+
"step": 298
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 0.3729342064234487,
|
2115 |
+
"grad_norm": NaN,
|
2116 |
+
"learning_rate": 0.00015048225553502244,
|
2117 |
+
"loss": 0.0,
|
2118 |
+
"step": 299
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 0.37418147801683815,
|
2122 |
+
"grad_norm": NaN,
|
2123 |
+
"learning_rate": 0.00015012071029748614,
|
2124 |
+
"loss": 0.0,
|
2125 |
+
"step": 300
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 0.37542874961022765,
|
2129 |
+
"grad_norm": NaN,
|
2130 |
+
"learning_rate": 0.00014975828798550933,
|
2131 |
+
"loss": 0.0,
|
2132 |
+
"step": 301
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 0.3766760212036171,
|
2136 |
+
"grad_norm": NaN,
|
2137 |
+
"learning_rate": 0.00014939499494120761,
|
2138 |
+
"loss": 0.0,
|
2139 |
+
"step": 302
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.37792329279700654,
|
2143 |
+
"grad_norm": NaN,
|
2144 |
+
"learning_rate": 0.00014903083752193397,
|
2145 |
+
"loss": 0.0,
|
2146 |
+
"step": 303
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 0.379170564390396,
|
2150 |
+
"grad_norm": NaN,
|
2151 |
+
"learning_rate": 0.0001486658221001672,
|
2152 |
+
"loss": 0.0,
|
2153 |
+
"step": 304
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 0.3804178359837855,
|
2157 |
+
"grad_norm": NaN,
|
2158 |
+
"learning_rate": 0.0001482999550634006,
|
2159 |
+
"loss": 0.0,
|
2160 |
+
"step": 305
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 0.3816651075771749,
|
2164 |
+
"grad_norm": NaN,
|
2165 |
+
"learning_rate": 0.0001479332428140299,
|
2166 |
+
"loss": 0.0,
|
2167 |
+
"step": 306
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 0.38291237917056437,
|
2171 |
+
"grad_norm": NaN,
|
2172 |
+
"learning_rate": 0.00014756569176924153,
|
2173 |
+
"loss": 0.0,
|
2174 |
+
"step": 307
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 0.38415965076395386,
|
2178 |
+
"grad_norm": NaN,
|
2179 |
+
"learning_rate": 0.0001471973083609002,
|
2180 |
+
"loss": 0.0,
|
2181 |
+
"step": 308
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.3854069223573433,
|
2185 |
+
"grad_norm": NaN,
|
2186 |
+
"learning_rate": 0.00014682809903543632,
|
2187 |
+
"loss": 0.0,
|
2188 |
+
"step": 309
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"epoch": 0.38665419395073275,
|
2192 |
+
"grad_norm": NaN,
|
2193 |
+
"learning_rate": 0.00014645807025373328,
|
2194 |
+
"loss": 0.0,
|
2195 |
+
"step": 310
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 0.38790146554412225,
|
2199 |
+
"grad_norm": NaN,
|
2200 |
+
"learning_rate": 0.0001460872284910143,
|
2201 |
+
"loss": 0.0,
|
2202 |
+
"step": 311
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 0.3891487371375117,
|
2206 |
+
"grad_norm": NaN,
|
2207 |
+
"learning_rate": 0.000145715580236729,
|
2208 |
+
"loss": 0.0,
|
2209 |
+
"step": 312
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 0.39039600873090113,
|
2213 |
+
"grad_norm": NaN,
|
2214 |
+
"learning_rate": 0.00014534313199444031,
|
2215 |
+
"loss": 0.0,
|
2216 |
+
"step": 313
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 0.39164328032429063,
|
2220 |
+
"grad_norm": NaN,
|
2221 |
+
"learning_rate": 0.00014496989028171012,
|
2222 |
+
"loss": 0.0,
|
2223 |
+
"step": 314
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.3928905519176801,
|
2227 |
+
"grad_norm": NaN,
|
2228 |
+
"learning_rate": 0.00014459586162998545,
|
2229 |
+
"loss": 0.0,
|
2230 |
+
"step": 315
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 0.3941378235110695,
|
2234 |
+
"grad_norm": NaN,
|
2235 |
+
"learning_rate": 0.00014422105258448425,
|
2236 |
+
"loss": 0.0,
|
2237 |
+
"step": 316
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 0.395385095104459,
|
2241 |
+
"grad_norm": NaN,
|
2242 |
+
"learning_rate": 0.00014384546970408067,
|
2243 |
+
"loss": 0.0,
|
2244 |
+
"step": 317
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 0.39663236669784846,
|
2248 |
+
"grad_norm": NaN,
|
2249 |
+
"learning_rate": 0.0001434691195611905,
|
2250 |
+
"loss": 0.0,
|
2251 |
+
"step": 318
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 0.3978796382912379,
|
2255 |
+
"grad_norm": NaN,
|
2256 |
+
"learning_rate": 0.000143092008741656,
|
2257 |
+
"loss": 0.0,
|
2258 |
+
"step": 319
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 0.3991269098846274,
|
2262 |
+
"grad_norm": NaN,
|
2263 |
+
"learning_rate": 0.00014271414384463063,
|
2264 |
+
"loss": 0.0,
|
2265 |
+
"step": 320
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.40037418147801684,
|
2269 |
+
"grad_norm": NaN,
|
2270 |
+
"learning_rate": 0.00014233553148246364,
|
2271 |
+
"loss": 0.0,
|
2272 |
+
"step": 321
|
2273 |
+
},
|
2274 |
+
{
|
2275 |
+
"epoch": 0.4016214530714063,
|
2276 |
+
"grad_norm": NaN,
|
2277 |
+
"learning_rate": 0.00014195617828058446,
|
2278 |
+
"loss": 0.0,
|
2279 |
+
"step": 322
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 0.4028687246647958,
|
2283 |
+
"grad_norm": NaN,
|
2284 |
+
"learning_rate": 0.00014157609087738656,
|
2285 |
+
"loss": 0.0,
|
2286 |
+
"step": 323
|
2287 |
+
},
|
2288 |
+
{
|
2289 |
+
"epoch": 0.40411599625818523,
|
2290 |
+
"grad_norm": NaN,
|
2291 |
+
"learning_rate": 0.00014119527592411146,
|
2292 |
+
"loss": 0.0,
|
2293 |
+
"step": 324
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 0.40536326785157467,
|
2297 |
+
"grad_norm": NaN,
|
2298 |
+
"learning_rate": 0.00014081374008473213,
|
2299 |
+
"loss": 0.0,
|
2300 |
+
"step": 325
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 0.4066105394449641,
|
2304 |
+
"grad_norm": NaN,
|
2305 |
+
"learning_rate": 0.0001404314900358366,
|
2306 |
+
"loss": 0.0,
|
2307 |
+
"step": 326
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.4078578110383536,
|
2311 |
+
"grad_norm": NaN,
|
2312 |
+
"learning_rate": 0.00014004853246651092,
|
2313 |
+
"loss": 0.0,
|
2314 |
+
"step": 327
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 0.40910508263174306,
|
2318 |
+
"grad_norm": NaN,
|
2319 |
+
"learning_rate": 0.0001396648740782224,
|
2320 |
+
"loss": 0.0,
|
2321 |
+
"step": 328
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 0.4103523542251325,
|
2325 |
+
"grad_norm": NaN,
|
2326 |
+
"learning_rate": 0.000139280521584702,
|
2327 |
+
"loss": 0.0,
|
2328 |
+
"step": 329
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 0.411599625818522,
|
2332 |
+
"grad_norm": NaN,
|
2333 |
+
"learning_rate": 0.00013889548171182702,
|
2334 |
+
"loss": 0.0,
|
2335 |
+
"step": 330
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 0.41284689741191144,
|
2339 |
+
"grad_norm": NaN,
|
2340 |
+
"learning_rate": 0.0001385097611975034,
|
2341 |
+
"loss": 0.0,
|
2342 |
+
"step": 331
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 0.4140941690053009,
|
2346 |
+
"grad_norm": NaN,
|
2347 |
+
"learning_rate": 0.00013812336679154777,
|
2348 |
+
"loss": 0.0,
|
2349 |
+
"step": 332
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.4153414405986904,
|
2353 |
+
"grad_norm": NaN,
|
2354 |
+
"learning_rate": 0.0001377363052555693,
|
2355 |
+
"loss": 0.0,
|
2356 |
+
"step": 333
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"epoch": 0.4165887121920798,
|
2360 |
+
"grad_norm": NaN,
|
2361 |
+
"learning_rate": 0.00013734858336285162,
|
2362 |
+
"loss": 0.0,
|
2363 |
+
"step": 334
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 0.41783598378546927,
|
2367 |
+
"grad_norm": NaN,
|
2368 |
+
"learning_rate": 0.00013696020789823388,
|
2369 |
+
"loss": 0.0,
|
2370 |
+
"step": 335
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 0.41908325537885877,
|
2374 |
+
"grad_norm": NaN,
|
2375 |
+
"learning_rate": 0.00013657118565799236,
|
2376 |
+
"loss": 0.0,
|
2377 |
+
"step": 336
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 0.4203305269722482,
|
2381 |
+
"grad_norm": NaN,
|
2382 |
+
"learning_rate": 0.00013618152344972142,
|
2383 |
+
"loss": 0.0,
|
2384 |
+
"step": 337
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 0.42157779856563765,
|
2388 |
+
"grad_norm": NaN,
|
2389 |
+
"learning_rate": 0.00013579122809221432,
|
2390 |
+
"loss": 0.0,
|
2391 |
+
"step": 338
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.42282507015902715,
|
2395 |
+
"grad_norm": NaN,
|
2396 |
+
"learning_rate": 0.00013540030641534404,
|
2397 |
+
"loss": 0.0,
|
2398 |
+
"step": 339
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 0.4240723417524166,
|
2402 |
+
"grad_norm": NaN,
|
2403 |
+
"learning_rate": 0.00013500876525994354,
|
2404 |
+
"loss": 0.0,
|
2405 |
+
"step": 340
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 0.42531961334580604,
|
2409 |
+
"grad_norm": NaN,
|
2410 |
+
"learning_rate": 0.00013461661147768633,
|
2411 |
+
"loss": 0.0,
|
2412 |
+
"step": 341
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 0.42656688493919553,
|
2416 |
+
"grad_norm": NaN,
|
2417 |
+
"learning_rate": 0.00013422385193096636,
|
2418 |
+
"loss": 0.0,
|
2419 |
+
"step": 342
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"epoch": 0.427814156532585,
|
2423 |
+
"grad_norm": NaN,
|
2424 |
+
"learning_rate": 0.000133830493492778,
|
2425 |
+
"loss": 0.0,
|
2426 |
+
"step": 343
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 0.4290614281259744,
|
2430 |
+
"grad_norm": NaN,
|
2431 |
+
"learning_rate": 0.00013343654304659574,
|
2432 |
+
"loss": 0.0,
|
2433 |
+
"step": 344
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 0.4303086997193639,
|
2437 |
+
"grad_norm": NaN,
|
2438 |
+
"learning_rate": 0.00013304200748625377,
|
2439 |
+
"loss": 0.0,
|
2440 |
+
"step": 345
|
2441 |
+
},
|
2442 |
+
{
|
2443 |
+
"epoch": 0.43155597131275336,
|
2444 |
+
"grad_norm": NaN,
|
2445 |
+
"learning_rate": 0.0001326468937158254,
|
2446 |
+
"loss": 0.0,
|
2447 |
+
"step": 346
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 0.4328032429061428,
|
2451 |
+
"grad_norm": NaN,
|
2452 |
+
"learning_rate": 0.00013225120864950217,
|
2453 |
+
"loss": 0.0,
|
2454 |
+
"step": 347
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"epoch": 0.43405051449953225,
|
2458 |
+
"grad_norm": NaN,
|
2459 |
+
"learning_rate": 0.00013185495921147272,
|
2460 |
+
"loss": 0.0,
|
2461 |
+
"step": 348
|
2462 |
+
},
|
2463 |
+
{
|
2464 |
+
"epoch": 0.43529778609292175,
|
2465 |
+
"grad_norm": NaN,
|
2466 |
+
"learning_rate": 0.00013145815233580192,
|
2467 |
+
"loss": 0.0,
|
2468 |
+
"step": 349
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 0.4365450576863112,
|
2472 |
+
"grad_norm": NaN,
|
2473 |
+
"learning_rate": 0.00013106079496630937,
|
2474 |
+
"loss": 0.0,
|
2475 |
+
"step": 350
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 0.43779232927970063,
|
2479 |
+
"grad_norm": NaN,
|
2480 |
+
"learning_rate": 0.00013066289405644778,
|
2481 |
+
"loss": 0.0,
|
2482 |
+
"step": 351
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 0.43903960087309013,
|
2486 |
+
"grad_norm": NaN,
|
2487 |
+
"learning_rate": 0.00013026445656918155,
|
2488 |
+
"loss": 0.0,
|
2489 |
+
"step": 352
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 0.4402868724664796,
|
2493 |
+
"grad_norm": NaN,
|
2494 |
+
"learning_rate": 0.00012986548947686467,
|
2495 |
+
"loss": 0.0,
|
2496 |
+
"step": 353
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 0.441534144059869,
|
2500 |
+
"grad_norm": NaN,
|
2501 |
+
"learning_rate": 0.00012946599976111883,
|
2502 |
+
"loss": 0.0,
|
2503 |
+
"step": 354
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 0.4427814156532585,
|
2507 |
+
"grad_norm": NaN,
|
2508 |
+
"learning_rate": 0.0001290659944127113,
|
2509 |
+
"loss": 0.0,
|
2510 |
+
"step": 355
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 0.44402868724664796,
|
2514 |
+
"grad_norm": NaN,
|
2515 |
+
"learning_rate": 0.0001286654804314325,
|
2516 |
+
"loss": 0.0,
|
2517 |
+
"step": 356
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 0.4452759588400374,
|
2521 |
+
"grad_norm": NaN,
|
2522 |
+
"learning_rate": 0.0001282644648259735,
|
2523 |
+
"loss": 0.0,
|
2524 |
+
"step": 357
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 0.4465232304334269,
|
2528 |
+
"grad_norm": NaN,
|
2529 |
+
"learning_rate": 0.00012786295461380344,
|
2530 |
+
"loss": 0.0,
|
2531 |
+
"step": 358
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 0.44777050202681634,
|
2535 |
+
"grad_norm": NaN,
|
2536 |
+
"learning_rate": 0.00012746095682104669,
|
2537 |
+
"loss": 0.0,
|
2538 |
+
"step": 359
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 0.4490177736202058,
|
2542 |
+
"grad_norm": NaN,
|
2543 |
+
"learning_rate": 0.00012705847848235995,
|
2544 |
+
"loss": 0.0,
|
2545 |
+
"step": 360
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 0.4502650452135953,
|
2549 |
+
"grad_norm": NaN,
|
2550 |
+
"learning_rate": 0.00012665552664080907,
|
2551 |
+
"loss": 0.0,
|
2552 |
+
"step": 361
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 0.4515123168069847,
|
2556 |
+
"grad_norm": NaN,
|
2557 |
+
"learning_rate": 0.00012625210834774585,
|
2558 |
+
"loss": 0.0,
|
2559 |
+
"step": 362
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.45275958840037417,
|
2563 |
+
"grad_norm": NaN,
|
2564 |
+
"learning_rate": 0.00012584823066268466,
|
2565 |
+
"loss": 0.0,
|
2566 |
+
"step": 363
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 0.45400685999376367,
|
2570 |
+
"grad_norm": NaN,
|
2571 |
+
"learning_rate": 0.00012544390065317887,
|
2572 |
+
"loss": 0.0,
|
2573 |
+
"step": 364
|
2574 |
+
},
|
2575 |
+
{
|
2576 |
+
"epoch": 0.4552541315871531,
|
2577 |
+
"grad_norm": NaN,
|
2578 |
+
"learning_rate": 0.00012503912539469714,
|
2579 |
+
"loss": 0.0,
|
2580 |
+
"step": 365
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 0.45650140318054255,
|
2584 |
+
"grad_norm": NaN,
|
2585 |
+
"learning_rate": 0.00012463391197049977,
|
2586 |
+
"loss": 0.0,
|
2587 |
+
"step": 366
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 0.457748674773932,
|
2591 |
+
"grad_norm": NaN,
|
2592 |
+
"learning_rate": 0.00012422826747151444,
|
2593 |
+
"loss": 0.0,
|
2594 |
+
"step": 367
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 0.4589959463673215,
|
2598 |
+
"grad_norm": NaN,
|
2599 |
+
"learning_rate": 0.00012382219899621246,
|
2600 |
+
"loss": 0.0,
|
2601 |
+
"step": 368
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 0.46024321796071094,
|
2605 |
+
"grad_norm": NaN,
|
2606 |
+
"learning_rate": 0.00012341571365048442,
|
2607 |
+
"loss": 0.0,
|
2608 |
+
"step": 369
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 0.4614904895541004,
|
2612 |
+
"grad_norm": NaN,
|
2613 |
+
"learning_rate": 0.00012300881854751568,
|
2614 |
+
"loss": 0.0,
|
2615 |
+
"step": 370
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 0.4627377611474899,
|
2619 |
+
"grad_norm": NaN,
|
2620 |
+
"learning_rate": 0.0001226015208076622,
|
2621 |
+
"loss": 0.0,
|
2622 |
+
"step": 371
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 0.4639850327408793,
|
2626 |
+
"grad_norm": NaN,
|
2627 |
+
"learning_rate": 0.0001221938275583257,
|
2628 |
+
"loss": 0.0,
|
2629 |
+
"step": 372
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 0.46523230433426876,
|
2633 |
+
"grad_norm": NaN,
|
2634 |
+
"learning_rate": 0.00012178574593382899,
|
2635 |
+
"loss": 0.0,
|
2636 |
+
"step": 373
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 0.46647957592765826,
|
2640 |
+
"grad_norm": NaN,
|
2641 |
+
"learning_rate": 0.0001213772830752912,
|
2642 |
+
"loss": 0.0,
|
2643 |
+
"step": 374
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 0.4677268475210477,
|
2647 |
+
"grad_norm": NaN,
|
2648 |
+
"learning_rate": 0.0001209684461305028,
|
2649 |
+
"loss": 0.0,
|
2650 |
+
"step": 375
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 0.46897411911443715,
|
2654 |
+
"grad_norm": NaN,
|
2655 |
+
"learning_rate": 0.00012055924225380038,
|
2656 |
+
"loss": 0.0,
|
2657 |
+
"step": 376
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 0.47022139070782665,
|
2661 |
+
"grad_norm": NaN,
|
2662 |
+
"learning_rate": 0.00012014967860594164,
|
2663 |
+
"loss": 0.0,
|
2664 |
+
"step": 377
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 0.4714686623012161,
|
2668 |
+
"grad_norm": NaN,
|
2669 |
+
"learning_rate": 0.00011973976235398,
|
2670 |
+
"loss": 0.0,
|
2671 |
+
"step": 378
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 0.47271593389460553,
|
2675 |
+
"grad_norm": NaN,
|
2676 |
+
"learning_rate": 0.0001193295006711392,
|
2677 |
+
"loss": 0.0,
|
2678 |
+
"step": 379
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 0.47396320548799503,
|
2682 |
+
"grad_norm": NaN,
|
2683 |
+
"learning_rate": 0.00011891890073668763,
|
2684 |
+
"loss": 0.0,
|
2685 |
+
"step": 380
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 0.4752104770813845,
|
2689 |
+
"grad_norm": NaN,
|
2690 |
+
"learning_rate": 0.00011850796973581302,
|
2691 |
+
"loss": 0.0,
|
2692 |
+
"step": 381
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 0.4764577486747739,
|
2696 |
+
"grad_norm": NaN,
|
2697 |
+
"learning_rate": 0.00011809671485949636,
|
2698 |
+
"loss": 0.0,
|
2699 |
+
"step": 382
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 0.4777050202681634,
|
2703 |
+
"grad_norm": NaN,
|
2704 |
+
"learning_rate": 0.00011768514330438627,
|
2705 |
+
"loss": 0.0,
|
2706 |
+
"step": 383
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 0.47895229186155286,
|
2710 |
+
"grad_norm": NaN,
|
2711 |
+
"learning_rate": 0.00011727326227267308,
|
2712 |
+
"loss": 0.0,
|
2713 |
+
"step": 384
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 0.4801995634549423,
|
2717 |
+
"grad_norm": NaN,
|
2718 |
+
"learning_rate": 0.00011686107897196255,
|
2719 |
+
"loss": 0.0,
|
2720 |
+
"step": 385
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 0.4814468350483318,
|
2724 |
+
"grad_norm": NaN,
|
2725 |
+
"learning_rate": 0.00011644860061515008,
|
2726 |
+
"loss": 0.0,
|
2727 |
+
"step": 386
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.48269410664172124,
|
2731 |
+
"grad_norm": NaN,
|
2732 |
+
"learning_rate": 0.00011603583442029426,
|
2733 |
+
"loss": 0.0,
|
2734 |
+
"step": 387
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 0.4839413782351107,
|
2738 |
+
"grad_norm": NaN,
|
2739 |
+
"learning_rate": 0.00011562278761049066,
|
2740 |
+
"loss": 0.0,
|
2741 |
+
"step": 388
|
2742 |
+
},
|
2743 |
+
{
|
2744 |
+
"epoch": 0.48518864982850013,
|
2745 |
+
"grad_norm": NaN,
|
2746 |
+
"learning_rate": 0.00011520946741374534,
|
2747 |
+
"loss": 0.0,
|
2748 |
+
"step": 389
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 0.4864359214218896,
|
2752 |
+
"grad_norm": NaN,
|
2753 |
+
"learning_rate": 0.00011479588106284848,
|
2754 |
+
"loss": 0.0,
|
2755 |
+
"step": 390
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 0.48768319301527907,
|
2759 |
+
"grad_norm": NaN,
|
2760 |
+
"learning_rate": 0.00011438203579524778,
|
2761 |
+
"loss": 0.0,
|
2762 |
+
"step": 391
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 0.4889304646086685,
|
2766 |
+
"grad_norm": NaN,
|
2767 |
+
"learning_rate": 0.00011396793885292165,
|
2768 |
+
"loss": 0.0,
|
2769 |
+
"step": 392
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 0.490177736202058,
|
2773 |
+
"grad_norm": NaN,
|
2774 |
+
"learning_rate": 0.00011355359748225279,
|
2775 |
+
"loss": 0.0,
|
2776 |
+
"step": 393
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 0.49142500779544745,
|
2780 |
+
"grad_norm": NaN,
|
2781 |
+
"learning_rate": 0.00011313901893390113,
|
2782 |
+
"loss": 0.0,
|
2783 |
+
"step": 394
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 0.4926722793888369,
|
2787 |
+
"grad_norm": NaN,
|
2788 |
+
"learning_rate": 0.00011272421046267696,
|
2789 |
+
"loss": 0.0,
|
2790 |
+
"step": 395
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 0.4939195509822264,
|
2794 |
+
"grad_norm": NaN,
|
2795 |
+
"learning_rate": 0.00011230917932741418,
|
2796 |
+
"loss": 0.0,
|
2797 |
+
"step": 396
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 0.49516682257561584,
|
2801 |
+
"grad_norm": NaN,
|
2802 |
+
"learning_rate": 0.00011189393279084308,
|
2803 |
+
"loss": 0.0,
|
2804 |
+
"step": 397
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 0.4964140941690053,
|
2808 |
+
"grad_norm": NaN,
|
2809 |
+
"learning_rate": 0.00011147847811946328,
|
2810 |
+
"loss": 0.0,
|
2811 |
+
"step": 398
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 0.4976613657623948,
|
2815 |
+
"grad_norm": NaN,
|
2816 |
+
"learning_rate": 0.00011106282258341665,
|
2817 |
+
"loss": 0.0,
|
2818 |
+
"step": 399
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 0.4989086373557842,
|
2822 |
+
"grad_norm": NaN,
|
2823 |
+
"learning_rate": 0.00011064697345636002,
|
2824 |
+
"loss": 0.0,
|
2825 |
+
"step": 400
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 0.5001559089491737,
|
2829 |
+
"grad_norm": NaN,
|
2830 |
+
"learning_rate": 0.00011023093801533785,
|
2831 |
+
"loss": 0.0,
|
2832 |
+
"step": 401
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 0.5014031805425632,
|
2836 |
+
"grad_norm": NaN,
|
2837 |
+
"learning_rate": 0.00010981472354065514,
|
2838 |
+
"loss": 0.0,
|
2839 |
+
"step": 402
|
2840 |
+
},
|
2841 |
+
{
|
2842 |
+
"epoch": 0.5014031805425632,
|
2843 |
+
"eval_loss": NaN,
|
2844 |
+
"eval_runtime": 60.5505,
|
2845 |
+
"eval_samples_per_second": 22.312,
|
2846 |
+
"eval_steps_per_second": 5.582,
|
2847 |
+
"step": 402
|
2848 |
}
|
2849 |
],
|
2850 |
"logging_steps": 1,
|
|
|
2864 |
"attributes": {}
|
2865 |
}
|
2866 |
},
|
2867 |
+
"total_flos": 1.655997012513915e+17,
|
2868 |
"train_batch_size": 2,
|
2869 |
"trial_name": null,
|
2870 |
"trial_params": null
|