Training in progress, step 85000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:843cf6ef35243e684d27456ba49a9e3f5c8e5ee1f8a5e77bbe805da28ef9df23
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d3023955b5dc4f2a91972896eb7fc2a48dbbd33f071e6772509d7b3310d7750
|
| 3 |
size 402029570
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4aca33d91db7ece935e9587ad37b8b8bbc606ca21923c11f0d71c66c347d72d
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6234904d28bb3d4cccb54d2313926220701147aa5fd064469323099845a2147f
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bba07bb512ceb7c978a6ff3be2bb670073dd67c37434a7a0e1ea7416dae53545
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8b86906f34daac86a7fba68db92436b4f06bbdc7074f871e13a7042f167cc91
|
| 3 |
size 14960
|
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 sha256:04330f2c7f4f6117d01c2bbdd70062b29086bf16826528e3403e9d580336fb15
|
| 3 |
size 1064
|
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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -29408,6 +29408,356 @@
|
|
| 29408 |
"learning_rate": 0.00047938019329016047,
|
| 29409 |
"loss": 16.1804,
|
| 29410 |
"step": 84000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29411 |
}
|
| 29412 |
],
|
| 29413 |
"logging_steps": 20,
|
|
@@ -29427,7 +29777,7 @@
|
|
| 29427 |
"attributes": {}
|
| 29428 |
}
|
| 29429 |
},
|
| 29430 |
-
"total_flos": 6.
|
| 29431 |
"train_batch_size": 48,
|
| 29432 |
"trial_name": null,
|
| 29433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12591174919564613,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 85000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 29408 |
"learning_rate": 0.00047938019329016047,
|
| 29409 |
"loss": 16.1804,
|
| 29410 |
"step": 84000
|
| 29411 |
+
},
|
| 29412 |
+
{
|
| 29413 |
+
"epoch": 0.12446006079315514,
|
| 29414 |
+
"grad_norm": 5.90625,
|
| 29415 |
+
"learning_rate": 0.00047937525435515286,
|
| 29416 |
+
"loss": 16.1324,
|
| 29417 |
+
"step": 84020
|
| 29418 |
+
},
|
| 29419 |
+
{
|
| 29420 |
+
"epoch": 0.12448968708708352,
|
| 29421 |
+
"grad_norm": 6.96875,
|
| 29422 |
+
"learning_rate": 0.0004793703154201453,
|
| 29423 |
+
"loss": 16.1368,
|
| 29424 |
+
"step": 84040
|
| 29425 |
+
},
|
| 29426 |
+
{
|
| 29427 |
+
"epoch": 0.12451931338101191,
|
| 29428 |
+
"grad_norm": 7.09375,
|
| 29429 |
+
"learning_rate": 0.00047936537648513776,
|
| 29430 |
+
"loss": 16.176,
|
| 29431 |
+
"step": 84060
|
| 29432 |
+
},
|
| 29433 |
+
{
|
| 29434 |
+
"epoch": 0.12454893967494031,
|
| 29435 |
+
"grad_norm": 6.625,
|
| 29436 |
+
"learning_rate": 0.0004793604375501302,
|
| 29437 |
+
"loss": 16.1863,
|
| 29438 |
+
"step": 84080
|
| 29439 |
+
},
|
| 29440 |
+
{
|
| 29441 |
+
"epoch": 0.1245785659688687,
|
| 29442 |
+
"grad_norm": 6.5,
|
| 29443 |
+
"learning_rate": 0.0004793554986151226,
|
| 29444 |
+
"loss": 16.1856,
|
| 29445 |
+
"step": 84100
|
| 29446 |
+
},
|
| 29447 |
+
{
|
| 29448 |
+
"epoch": 0.12460819226279708,
|
| 29449 |
+
"grad_norm": 6.0625,
|
| 29450 |
+
"learning_rate": 0.0004793505596801151,
|
| 29451 |
+
"loss": 16.1133,
|
| 29452 |
+
"step": 84120
|
| 29453 |
+
},
|
| 29454 |
+
{
|
| 29455 |
+
"epoch": 0.12463781855672547,
|
| 29456 |
+
"grad_norm": 6.1875,
|
| 29457 |
+
"learning_rate": 0.0004793456207451075,
|
| 29458 |
+
"loss": 16.1372,
|
| 29459 |
+
"step": 84140
|
| 29460 |
+
},
|
| 29461 |
+
{
|
| 29462 |
+
"epoch": 0.12466744485065386,
|
| 29463 |
+
"grad_norm": 6.3125,
|
| 29464 |
+
"learning_rate": 0.00047934068181009994,
|
| 29465 |
+
"loss": 16.1905,
|
| 29466 |
+
"step": 84160
|
| 29467 |
+
},
|
| 29468 |
+
{
|
| 29469 |
+
"epoch": 0.12469707114458224,
|
| 29470 |
+
"grad_norm": 6.59375,
|
| 29471 |
+
"learning_rate": 0.00047933574287509234,
|
| 29472 |
+
"loss": 16.14,
|
| 29473 |
+
"step": 84180
|
| 29474 |
+
},
|
| 29475 |
+
{
|
| 29476 |
+
"epoch": 0.12472669743851063,
|
| 29477 |
+
"grad_norm": 6.375,
|
| 29478 |
+
"learning_rate": 0.00047933080394008484,
|
| 29479 |
+
"loss": 16.1066,
|
| 29480 |
+
"step": 84200
|
| 29481 |
+
},
|
| 29482 |
+
{
|
| 29483 |
+
"epoch": 0.12475632373243901,
|
| 29484 |
+
"grad_norm": 6.125,
|
| 29485 |
+
"learning_rate": 0.00047932586500507723,
|
| 29486 |
+
"loss": 16.0997,
|
| 29487 |
+
"step": 84220
|
| 29488 |
+
},
|
| 29489 |
+
{
|
| 29490 |
+
"epoch": 0.1247859500263674,
|
| 29491 |
+
"grad_norm": 6.625,
|
| 29492 |
+
"learning_rate": 0.0004793209260700697,
|
| 29493 |
+
"loss": 16.1655,
|
| 29494 |
+
"step": 84240
|
| 29495 |
+
},
|
| 29496 |
+
{
|
| 29497 |
+
"epoch": 0.12481557632029579,
|
| 29498 |
+
"grad_norm": 6.4375,
|
| 29499 |
+
"learning_rate": 0.0004793159871350621,
|
| 29500 |
+
"loss": 16.1648,
|
| 29501 |
+
"step": 84260
|
| 29502 |
+
},
|
| 29503 |
+
{
|
| 29504 |
+
"epoch": 0.12484520261422417,
|
| 29505 |
+
"grad_norm": 7.5,
|
| 29506 |
+
"learning_rate": 0.0004793110482000546,
|
| 29507 |
+
"loss": 16.2026,
|
| 29508 |
+
"step": 84280
|
| 29509 |
+
},
|
| 29510 |
+
{
|
| 29511 |
+
"epoch": 0.12487482890815256,
|
| 29512 |
+
"grad_norm": 7.15625,
|
| 29513 |
+
"learning_rate": 0.00047930610926504697,
|
| 29514 |
+
"loss": 16.1487,
|
| 29515 |
+
"step": 84300
|
| 29516 |
+
},
|
| 29517 |
+
{
|
| 29518 |
+
"epoch": 0.12490445520208095,
|
| 29519 |
+
"grad_norm": 7.0,
|
| 29520 |
+
"learning_rate": 0.0004793011703300394,
|
| 29521 |
+
"loss": 16.1867,
|
| 29522 |
+
"step": 84320
|
| 29523 |
+
},
|
| 29524 |
+
{
|
| 29525 |
+
"epoch": 0.12493408149600933,
|
| 29526 |
+
"grad_norm": 6.21875,
|
| 29527 |
+
"learning_rate": 0.0004792962313950318,
|
| 29528 |
+
"loss": 16.1449,
|
| 29529 |
+
"step": 84340
|
| 29530 |
+
},
|
| 29531 |
+
{
|
| 29532 |
+
"epoch": 0.12496370778993772,
|
| 29533 |
+
"grad_norm": 6.25,
|
| 29534 |
+
"learning_rate": 0.0004792912924600243,
|
| 29535 |
+
"loss": 16.2187,
|
| 29536 |
+
"step": 84360
|
| 29537 |
+
},
|
| 29538 |
+
{
|
| 29539 |
+
"epoch": 0.1249933340838661,
|
| 29540 |
+
"grad_norm": 7.09375,
|
| 29541 |
+
"learning_rate": 0.0004792863535250167,
|
| 29542 |
+
"loss": 16.1159,
|
| 29543 |
+
"step": 84380
|
| 29544 |
+
},
|
| 29545 |
+
{
|
| 29546 |
+
"epoch": 0.1250229603777945,
|
| 29547 |
+
"grad_norm": 6.84375,
|
| 29548 |
+
"learning_rate": 0.0004792814145900091,
|
| 29549 |
+
"loss": 16.0993,
|
| 29550 |
+
"step": 84400
|
| 29551 |
+
},
|
| 29552 |
+
{
|
| 29553 |
+
"epoch": 0.1250525866717229,
|
| 29554 |
+
"grad_norm": 9.125,
|
| 29555 |
+
"learning_rate": 0.0004792764756550016,
|
| 29556 |
+
"loss": 16.1437,
|
| 29557 |
+
"step": 84420
|
| 29558 |
+
},
|
| 29559 |
+
{
|
| 29560 |
+
"epoch": 0.12508221296565128,
|
| 29561 |
+
"grad_norm": 6.78125,
|
| 29562 |
+
"learning_rate": 0.000479271536719994,
|
| 29563 |
+
"loss": 16.138,
|
| 29564 |
+
"step": 84440
|
| 29565 |
+
},
|
| 29566 |
+
{
|
| 29567 |
+
"epoch": 0.12511183925957967,
|
| 29568 |
+
"grad_norm": 5.96875,
|
| 29569 |
+
"learning_rate": 0.00047926659778498644,
|
| 29570 |
+
"loss": 16.1112,
|
| 29571 |
+
"step": 84460
|
| 29572 |
+
},
|
| 29573 |
+
{
|
| 29574 |
+
"epoch": 0.12514146555350805,
|
| 29575 |
+
"grad_norm": 6.90625,
|
| 29576 |
+
"learning_rate": 0.00047926165884997884,
|
| 29577 |
+
"loss": 16.152,
|
| 29578 |
+
"step": 84480
|
| 29579 |
+
},
|
| 29580 |
+
{
|
| 29581 |
+
"epoch": 0.12517109184743644,
|
| 29582 |
+
"grad_norm": 7.53125,
|
| 29583 |
+
"learning_rate": 0.00047925671991497134,
|
| 29584 |
+
"loss": 16.1693,
|
| 29585 |
+
"step": 84500
|
| 29586 |
+
},
|
| 29587 |
+
{
|
| 29588 |
+
"epoch": 0.12520071814136483,
|
| 29589 |
+
"grad_norm": 7.5,
|
| 29590 |
+
"learning_rate": 0.00047925178097996373,
|
| 29591 |
+
"loss": 16.1587,
|
| 29592 |
+
"step": 84520
|
| 29593 |
+
},
|
| 29594 |
+
{
|
| 29595 |
+
"epoch": 0.1252303444352932,
|
| 29596 |
+
"grad_norm": 6.5625,
|
| 29597 |
+
"learning_rate": 0.0004792468420449562,
|
| 29598 |
+
"loss": 16.2107,
|
| 29599 |
+
"step": 84540
|
| 29600 |
+
},
|
| 29601 |
+
{
|
| 29602 |
+
"epoch": 0.1252599707292216,
|
| 29603 |
+
"grad_norm": 6.59375,
|
| 29604 |
+
"learning_rate": 0.0004792419031099486,
|
| 29605 |
+
"loss": 16.183,
|
| 29606 |
+
"step": 84560
|
| 29607 |
+
},
|
| 29608 |
+
{
|
| 29609 |
+
"epoch": 0.12528959702314998,
|
| 29610 |
+
"grad_norm": 7.375,
|
| 29611 |
+
"learning_rate": 0.0004792369641749411,
|
| 29612 |
+
"loss": 16.1448,
|
| 29613 |
+
"step": 84580
|
| 29614 |
+
},
|
| 29615 |
+
{
|
| 29616 |
+
"epoch": 0.12531922331707837,
|
| 29617 |
+
"grad_norm": 6.28125,
|
| 29618 |
+
"learning_rate": 0.00047923202523993347,
|
| 29619 |
+
"loss": 16.2097,
|
| 29620 |
+
"step": 84600
|
| 29621 |
+
},
|
| 29622 |
+
{
|
| 29623 |
+
"epoch": 0.12534884961100676,
|
| 29624 |
+
"grad_norm": 6.3125,
|
| 29625 |
+
"learning_rate": 0.0004792270863049259,
|
| 29626 |
+
"loss": 16.1846,
|
| 29627 |
+
"step": 84620
|
| 29628 |
+
},
|
| 29629 |
+
{
|
| 29630 |
+
"epoch": 0.12537847590493514,
|
| 29631 |
+
"grad_norm": 6.90625,
|
| 29632 |
+
"learning_rate": 0.0004792221473699183,
|
| 29633 |
+
"loss": 16.183,
|
| 29634 |
+
"step": 84640
|
| 29635 |
+
},
|
| 29636 |
+
{
|
| 29637 |
+
"epoch": 0.12540810219886353,
|
| 29638 |
+
"grad_norm": 6.0,
|
| 29639 |
+
"learning_rate": 0.0004792172084349108,
|
| 29640 |
+
"loss": 16.1176,
|
| 29641 |
+
"step": 84660
|
| 29642 |
+
},
|
| 29643 |
+
{
|
| 29644 |
+
"epoch": 0.12543772849279192,
|
| 29645 |
+
"grad_norm": 6.71875,
|
| 29646 |
+
"learning_rate": 0.0004792122694999032,
|
| 29647 |
+
"loss": 16.1527,
|
| 29648 |
+
"step": 84680
|
| 29649 |
+
},
|
| 29650 |
+
{
|
| 29651 |
+
"epoch": 0.1254673547867203,
|
| 29652 |
+
"grad_norm": 6.875,
|
| 29653 |
+
"learning_rate": 0.0004792073305648956,
|
| 29654 |
+
"loss": 16.1153,
|
| 29655 |
+
"step": 84700
|
| 29656 |
+
},
|
| 29657 |
+
{
|
| 29658 |
+
"epoch": 0.1254969810806487,
|
| 29659 |
+
"grad_norm": 6.90625,
|
| 29660 |
+
"learning_rate": 0.0004792023916298881,
|
| 29661 |
+
"loss": 16.137,
|
| 29662 |
+
"step": 84720
|
| 29663 |
+
},
|
| 29664 |
+
{
|
| 29665 |
+
"epoch": 0.12552660737457708,
|
| 29666 |
+
"grad_norm": 7.0,
|
| 29667 |
+
"learning_rate": 0.0004791974526948805,
|
| 29668 |
+
"loss": 16.1581,
|
| 29669 |
+
"step": 84740
|
| 29670 |
+
},
|
| 29671 |
+
{
|
| 29672 |
+
"epoch": 0.12555623366850546,
|
| 29673 |
+
"grad_norm": 7.03125,
|
| 29674 |
+
"learning_rate": 0.00047919251375987294,
|
| 29675 |
+
"loss": 16.131,
|
| 29676 |
+
"step": 84760
|
| 29677 |
+
},
|
| 29678 |
+
{
|
| 29679 |
+
"epoch": 0.12558585996243385,
|
| 29680 |
+
"grad_norm": 6.46875,
|
| 29681 |
+
"learning_rate": 0.00047918757482486534,
|
| 29682 |
+
"loss": 16.1786,
|
| 29683 |
+
"step": 84780
|
| 29684 |
+
},
|
| 29685 |
+
{
|
| 29686 |
+
"epoch": 0.12561548625636224,
|
| 29687 |
+
"grad_norm": 8.5,
|
| 29688 |
+
"learning_rate": 0.00047918263588985784,
|
| 29689 |
+
"loss": 16.1971,
|
| 29690 |
+
"step": 84800
|
| 29691 |
+
},
|
| 29692 |
+
{
|
| 29693 |
+
"epoch": 0.12564511255029062,
|
| 29694 |
+
"grad_norm": 6.53125,
|
| 29695 |
+
"learning_rate": 0.00047917769695485023,
|
| 29696 |
+
"loss": 16.1351,
|
| 29697 |
+
"step": 84820
|
| 29698 |
+
},
|
| 29699 |
+
{
|
| 29700 |
+
"epoch": 0.125674738844219,
|
| 29701 |
+
"grad_norm": 6.28125,
|
| 29702 |
+
"learning_rate": 0.0004791727580198427,
|
| 29703 |
+
"loss": 16.1387,
|
| 29704 |
+
"step": 84840
|
| 29705 |
+
},
|
| 29706 |
+
{
|
| 29707 |
+
"epoch": 0.1257043651381474,
|
| 29708 |
+
"grad_norm": 7.34375,
|
| 29709 |
+
"learning_rate": 0.0004791678190848351,
|
| 29710 |
+
"loss": 16.1013,
|
| 29711 |
+
"step": 84860
|
| 29712 |
+
},
|
| 29713 |
+
{
|
| 29714 |
+
"epoch": 0.1257339914320758,
|
| 29715 |
+
"grad_norm": 6.625,
|
| 29716 |
+
"learning_rate": 0.0004791628801498276,
|
| 29717 |
+
"loss": 16.1586,
|
| 29718 |
+
"step": 84880
|
| 29719 |
+
},
|
| 29720 |
+
{
|
| 29721 |
+
"epoch": 0.1257636177260042,
|
| 29722 |
+
"grad_norm": 6.5625,
|
| 29723 |
+
"learning_rate": 0.00047915794121481997,
|
| 29724 |
+
"loss": 16.1316,
|
| 29725 |
+
"step": 84900
|
| 29726 |
+
},
|
| 29727 |
+
{
|
| 29728 |
+
"epoch": 0.12579324401993258,
|
| 29729 |
+
"grad_norm": 6.5625,
|
| 29730 |
+
"learning_rate": 0.0004791530022798124,
|
| 29731 |
+
"loss": 16.1637,
|
| 29732 |
+
"step": 84920
|
| 29733 |
+
},
|
| 29734 |
+
{
|
| 29735 |
+
"epoch": 0.12582287031386097,
|
| 29736 |
+
"grad_norm": 5.96875,
|
| 29737 |
+
"learning_rate": 0.0004791480633448048,
|
| 29738 |
+
"loss": 16.2086,
|
| 29739 |
+
"step": 84940
|
| 29740 |
+
},
|
| 29741 |
+
{
|
| 29742 |
+
"epoch": 0.12585249660778935,
|
| 29743 |
+
"grad_norm": 7.09375,
|
| 29744 |
+
"learning_rate": 0.0004791431244097973,
|
| 29745 |
+
"loss": 16.1053,
|
| 29746 |
+
"step": 84960
|
| 29747 |
+
},
|
| 29748 |
+
{
|
| 29749 |
+
"epoch": 0.12588212290171774,
|
| 29750 |
+
"grad_norm": 7.25,
|
| 29751 |
+
"learning_rate": 0.0004791381854747897,
|
| 29752 |
+
"loss": 16.1161,
|
| 29753 |
+
"step": 84980
|
| 29754 |
+
},
|
| 29755 |
+
{
|
| 29756 |
+
"epoch": 0.12591174919564613,
|
| 29757 |
+
"grad_norm": 6.0625,
|
| 29758 |
+
"learning_rate": 0.00047913324653978216,
|
| 29759 |
+
"loss": 16.1565,
|
| 29760 |
+
"step": 85000
|
| 29761 |
}
|
| 29762 |
],
|
| 29763 |
"logging_steps": 20,
|
|
|
|
| 29777 |
"attributes": {}
|
| 29778 |
}
|
| 29779 |
},
|
| 29780 |
+
"total_flos": 6.249681123538895e+19,
|
| 29781 |
"train_batch_size": 48,
|
| 29782 |
"trial_name": null,
|
| 29783 |
"trial_params": null
|