Training in progress, step 102000, 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:d7f5ea86071f8a443230b23461cfbfb9011f2eb0c114ed9f153b2befd1980b09
|
| 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:e2436d9ce5048c7b249db87baeb4a99589f5cb4ba3d6a5e83bf03cb11fe8f0be
|
| 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 sha256:6f0b98a5ebb9ed78e7e8e5b9ffb2e444a0031c547ea9bedbf7d34b7fa2ad1116
|
| 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 sha256:9cfcb9518936230adad38b3ece3c6f950bb8431417e2c158d94db199da5ecc7f
|
| 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 sha256:3ca0fc3fe7a9627836bbdc1a3373de9ea1ca12bc7235315729c74c1a4f443961
|
| 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 sha256:5b7069c2c37db8f9fc224f696a3a2d7a164145b4eecb3137491caa9925d870ba
|
| 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 sha256:922cd08a83c902a03c338945ddd81b7601735a1921c4a20e3f521ea886a2772d
|
| 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,
|
|
@@ -35358,6 +35358,356 @@
|
|
| 35358 |
"learning_rate": 0.000475182098533729,
|
| 35359 |
"loss": 15.8686,
|
| 35360 |
"step": 101000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35361 |
}
|
| 35362 |
],
|
| 35363 |
"logging_steps": 20,
|
|
@@ -35377,7 +35727,7 @@
|
|
| 35377 |
"attributes": {}
|
| 35378 |
}
|
| 35379 |
},
|
| 35380 |
-
"total_flos": 7.
|
| 35381 |
"train_batch_size": 48,
|
| 35382 |
"trial_name": null,
|
| 35383 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.15109409903477533,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 102000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 35358 |
"learning_rate": 0.000475182098533729,
|
| 35359 |
"loss": 15.8686,
|
| 35360 |
"step": 101000
|
| 35361 |
+
},
|
| 35362 |
+
{
|
| 35363 |
+
"epoch": 0.14964241063228437,
|
| 35364 |
+
"grad_norm": 6.21875,
|
| 35365 |
+
"learning_rate": 0.0004751771595987214,
|
| 35366 |
+
"loss": 15.8408,
|
| 35367 |
+
"step": 101020
|
| 35368 |
+
},
|
| 35369 |
+
{
|
| 35370 |
+
"epoch": 0.14967203692621275,
|
| 35371 |
+
"grad_norm": 6.46875,
|
| 35372 |
+
"learning_rate": 0.00047517222066371386,
|
| 35373 |
+
"loss": 15.8667,
|
| 35374 |
+
"step": 101040
|
| 35375 |
+
},
|
| 35376 |
+
{
|
| 35377 |
+
"epoch": 0.14970166322014114,
|
| 35378 |
+
"grad_norm": 8.25,
|
| 35379 |
+
"learning_rate": 0.00047516728172870625,
|
| 35380 |
+
"loss": 15.8582,
|
| 35381 |
+
"step": 101060
|
| 35382 |
+
},
|
| 35383 |
+
{
|
| 35384 |
+
"epoch": 0.14973128951406953,
|
| 35385 |
+
"grad_norm": 6.78125,
|
| 35386 |
+
"learning_rate": 0.00047516234279369876,
|
| 35387 |
+
"loss": 15.8413,
|
| 35388 |
+
"step": 101080
|
| 35389 |
+
},
|
| 35390 |
+
{
|
| 35391 |
+
"epoch": 0.1497609158079979,
|
| 35392 |
+
"grad_norm": 6.84375,
|
| 35393 |
+
"learning_rate": 0.00047515740385869115,
|
| 35394 |
+
"loss": 15.837,
|
| 35395 |
+
"step": 101100
|
| 35396 |
+
},
|
| 35397 |
+
{
|
| 35398 |
+
"epoch": 0.1497905421019263,
|
| 35399 |
+
"grad_norm": 6.8125,
|
| 35400 |
+
"learning_rate": 0.0004751524649236836,
|
| 35401 |
+
"loss": 15.8153,
|
| 35402 |
+
"step": 101120
|
| 35403 |
+
},
|
| 35404 |
+
{
|
| 35405 |
+
"epoch": 0.14982016839585469,
|
| 35406 |
+
"grad_norm": 5.875,
|
| 35407 |
+
"learning_rate": 0.000475147525988676,
|
| 35408 |
+
"loss": 15.8841,
|
| 35409 |
+
"step": 101140
|
| 35410 |
+
},
|
| 35411 |
+
{
|
| 35412 |
+
"epoch": 0.14984979468978307,
|
| 35413 |
+
"grad_norm": 6.9375,
|
| 35414 |
+
"learning_rate": 0.0004751425870536685,
|
| 35415 |
+
"loss": 15.7932,
|
| 35416 |
+
"step": 101160
|
| 35417 |
+
},
|
| 35418 |
+
{
|
| 35419 |
+
"epoch": 0.14987942098371146,
|
| 35420 |
+
"grad_norm": 6.65625,
|
| 35421 |
+
"learning_rate": 0.0004751376481186609,
|
| 35422 |
+
"loss": 15.8238,
|
| 35423 |
+
"step": 101180
|
| 35424 |
+
},
|
| 35425 |
+
{
|
| 35426 |
+
"epoch": 0.14990904727763985,
|
| 35427 |
+
"grad_norm": 6.53125,
|
| 35428 |
+
"learning_rate": 0.00047513270918365333,
|
| 35429 |
+
"loss": 15.8007,
|
| 35430 |
+
"step": 101200
|
| 35431 |
+
},
|
| 35432 |
+
{
|
| 35433 |
+
"epoch": 0.14993867357156823,
|
| 35434 |
+
"grad_norm": 6.6875,
|
| 35435 |
+
"learning_rate": 0.00047512777024864573,
|
| 35436 |
+
"loss": 15.8114,
|
| 35437 |
+
"step": 101220
|
| 35438 |
+
},
|
| 35439 |
+
{
|
| 35440 |
+
"epoch": 0.14996829986549662,
|
| 35441 |
+
"grad_norm": 6.40625,
|
| 35442 |
+
"learning_rate": 0.00047512283131363823,
|
| 35443 |
+
"loss": 15.8998,
|
| 35444 |
+
"step": 101240
|
| 35445 |
+
},
|
| 35446 |
+
{
|
| 35447 |
+
"epoch": 0.149997926159425,
|
| 35448 |
+
"grad_norm": 7.28125,
|
| 35449 |
+
"learning_rate": 0.0004751178923786306,
|
| 35450 |
+
"loss": 15.7957,
|
| 35451 |
+
"step": 101260
|
| 35452 |
+
},
|
| 35453 |
+
{
|
| 35454 |
+
"epoch": 0.1500275524533534,
|
| 35455 |
+
"grad_norm": 6.9375,
|
| 35456 |
+
"learning_rate": 0.000475112953443623,
|
| 35457 |
+
"loss": 15.792,
|
| 35458 |
+
"step": 101280
|
| 35459 |
+
},
|
| 35460 |
+
{
|
| 35461 |
+
"epoch": 0.15005717874728178,
|
| 35462 |
+
"grad_norm": 6.90625,
|
| 35463 |
+
"learning_rate": 0.00047510801450861547,
|
| 35464 |
+
"loss": 15.858,
|
| 35465 |
+
"step": 101300
|
| 35466 |
+
},
|
| 35467 |
+
{
|
| 35468 |
+
"epoch": 0.15008680504121016,
|
| 35469 |
+
"grad_norm": 6.3125,
|
| 35470 |
+
"learning_rate": 0.0004751030755736079,
|
| 35471 |
+
"loss": 15.9071,
|
| 35472 |
+
"step": 101320
|
| 35473 |
+
},
|
| 35474 |
+
{
|
| 35475 |
+
"epoch": 0.15011643133513855,
|
| 35476 |
+
"grad_norm": 5.875,
|
| 35477 |
+
"learning_rate": 0.00047509813663860036,
|
| 35478 |
+
"loss": 15.8434,
|
| 35479 |
+
"step": 101340
|
| 35480 |
+
},
|
| 35481 |
+
{
|
| 35482 |
+
"epoch": 0.15014605762906694,
|
| 35483 |
+
"grad_norm": 6.84375,
|
| 35484 |
+
"learning_rate": 0.00047509319770359275,
|
| 35485 |
+
"loss": 15.8702,
|
| 35486 |
+
"step": 101360
|
| 35487 |
+
},
|
| 35488 |
+
{
|
| 35489 |
+
"epoch": 0.15017568392299532,
|
| 35490 |
+
"grad_norm": 6.96875,
|
| 35491 |
+
"learning_rate": 0.00047508825876858526,
|
| 35492 |
+
"loss": 15.8149,
|
| 35493 |
+
"step": 101380
|
| 35494 |
+
},
|
| 35495 |
+
{
|
| 35496 |
+
"epoch": 0.15020531021692374,
|
| 35497 |
+
"grad_norm": 6.78125,
|
| 35498 |
+
"learning_rate": 0.00047508331983357765,
|
| 35499 |
+
"loss": 15.8167,
|
| 35500 |
+
"step": 101400
|
| 35501 |
+
},
|
| 35502 |
+
{
|
| 35503 |
+
"epoch": 0.15023493651085212,
|
| 35504 |
+
"grad_norm": 5.71875,
|
| 35505 |
+
"learning_rate": 0.0004750783808985701,
|
| 35506 |
+
"loss": 15.8355,
|
| 35507 |
+
"step": 101420
|
| 35508 |
+
},
|
| 35509 |
+
{
|
| 35510 |
+
"epoch": 0.1502645628047805,
|
| 35511 |
+
"grad_norm": 6.125,
|
| 35512 |
+
"learning_rate": 0.0004750734419635625,
|
| 35513 |
+
"loss": 15.8727,
|
| 35514 |
+
"step": 101440
|
| 35515 |
+
},
|
| 35516 |
+
{
|
| 35517 |
+
"epoch": 0.1502941890987089,
|
| 35518 |
+
"grad_norm": 6.625,
|
| 35519 |
+
"learning_rate": 0.000475068503028555,
|
| 35520 |
+
"loss": 15.8786,
|
| 35521 |
+
"step": 101460
|
| 35522 |
+
},
|
| 35523 |
+
{
|
| 35524 |
+
"epoch": 0.15032381539263728,
|
| 35525 |
+
"grad_norm": 7.21875,
|
| 35526 |
+
"learning_rate": 0.0004750635640935474,
|
| 35527 |
+
"loss": 15.8171,
|
| 35528 |
+
"step": 101480
|
| 35529 |
+
},
|
| 35530 |
+
{
|
| 35531 |
+
"epoch": 0.15035344168656567,
|
| 35532 |
+
"grad_norm": 6.84375,
|
| 35533 |
+
"learning_rate": 0.00047505862515853983,
|
| 35534 |
+
"loss": 15.7871,
|
| 35535 |
+
"step": 101500
|
| 35536 |
+
},
|
| 35537 |
+
{
|
| 35538 |
+
"epoch": 0.15038306798049406,
|
| 35539 |
+
"grad_norm": 6.53125,
|
| 35540 |
+
"learning_rate": 0.00047505368622353223,
|
| 35541 |
+
"loss": 15.8054,
|
| 35542 |
+
"step": 101520
|
| 35543 |
+
},
|
| 35544 |
+
{
|
| 35545 |
+
"epoch": 0.15041269427442244,
|
| 35546 |
+
"grad_norm": 7.375,
|
| 35547 |
+
"learning_rate": 0.00047504874728852473,
|
| 35548 |
+
"loss": 15.834,
|
| 35549 |
+
"step": 101540
|
| 35550 |
+
},
|
| 35551 |
+
{
|
| 35552 |
+
"epoch": 0.15044232056835083,
|
| 35553 |
+
"grad_norm": 6.65625,
|
| 35554 |
+
"learning_rate": 0.0004750438083535171,
|
| 35555 |
+
"loss": 15.906,
|
| 35556 |
+
"step": 101560
|
| 35557 |
+
},
|
| 35558 |
+
{
|
| 35559 |
+
"epoch": 0.15047194686227922,
|
| 35560 |
+
"grad_norm": 6.59375,
|
| 35561 |
+
"learning_rate": 0.00047503886941850957,
|
| 35562 |
+
"loss": 15.8236,
|
| 35563 |
+
"step": 101580
|
| 35564 |
+
},
|
| 35565 |
+
{
|
| 35566 |
+
"epoch": 0.1505015731562076,
|
| 35567 |
+
"grad_norm": 7.875,
|
| 35568 |
+
"learning_rate": 0.00047503393048350197,
|
| 35569 |
+
"loss": 15.8215,
|
| 35570 |
+
"step": 101600
|
| 35571 |
+
},
|
| 35572 |
+
{
|
| 35573 |
+
"epoch": 0.150531199450136,
|
| 35574 |
+
"grad_norm": 6.625,
|
| 35575 |
+
"learning_rate": 0.0004750289915484944,
|
| 35576 |
+
"loss": 15.8343,
|
| 35577 |
+
"step": 101620
|
| 35578 |
+
},
|
| 35579 |
+
{
|
| 35580 |
+
"epoch": 0.15056082574406437,
|
| 35581 |
+
"grad_norm": 6.875,
|
| 35582 |
+
"learning_rate": 0.00047502405261348686,
|
| 35583 |
+
"loss": 15.7763,
|
| 35584 |
+
"step": 101640
|
| 35585 |
+
},
|
| 35586 |
+
{
|
| 35587 |
+
"epoch": 0.15059045203799276,
|
| 35588 |
+
"grad_norm": 7.0,
|
| 35589 |
+
"learning_rate": 0.00047501911367847925,
|
| 35590 |
+
"loss": 15.8537,
|
| 35591 |
+
"step": 101660
|
| 35592 |
+
},
|
| 35593 |
+
{
|
| 35594 |
+
"epoch": 0.15062007833192115,
|
| 35595 |
+
"grad_norm": 6.5,
|
| 35596 |
+
"learning_rate": 0.00047501417474347176,
|
| 35597 |
+
"loss": 15.902,
|
| 35598 |
+
"step": 101680
|
| 35599 |
+
},
|
| 35600 |
+
{
|
| 35601 |
+
"epoch": 0.15064970462584953,
|
| 35602 |
+
"grad_norm": 6.15625,
|
| 35603 |
+
"learning_rate": 0.00047500923580846415,
|
| 35604 |
+
"loss": 15.8103,
|
| 35605 |
+
"step": 101700
|
| 35606 |
+
},
|
| 35607 |
+
{
|
| 35608 |
+
"epoch": 0.15067933091977792,
|
| 35609 |
+
"grad_norm": 6.40625,
|
| 35610 |
+
"learning_rate": 0.0004750042968734566,
|
| 35611 |
+
"loss": 15.8109,
|
| 35612 |
+
"step": 101720
|
| 35613 |
+
},
|
| 35614 |
+
{
|
| 35615 |
+
"epoch": 0.1507089572137063,
|
| 35616 |
+
"grad_norm": 7.3125,
|
| 35617 |
+
"learning_rate": 0.000474999357938449,
|
| 35618 |
+
"loss": 15.8841,
|
| 35619 |
+
"step": 101740
|
| 35620 |
+
},
|
| 35621 |
+
{
|
| 35622 |
+
"epoch": 0.1507385835076347,
|
| 35623 |
+
"grad_norm": 6.375,
|
| 35624 |
+
"learning_rate": 0.0004749944190034415,
|
| 35625 |
+
"loss": 15.8348,
|
| 35626 |
+
"step": 101760
|
| 35627 |
+
},
|
| 35628 |
+
{
|
| 35629 |
+
"epoch": 0.15076820980156308,
|
| 35630 |
+
"grad_norm": 7.09375,
|
| 35631 |
+
"learning_rate": 0.0004749894800684339,
|
| 35632 |
+
"loss": 15.851,
|
| 35633 |
+
"step": 101780
|
| 35634 |
+
},
|
| 35635 |
+
{
|
| 35636 |
+
"epoch": 0.15079783609549147,
|
| 35637 |
+
"grad_norm": 6.59375,
|
| 35638 |
+
"learning_rate": 0.00047498454113342634,
|
| 35639 |
+
"loss": 15.822,
|
| 35640 |
+
"step": 101800
|
| 35641 |
+
},
|
| 35642 |
+
{
|
| 35643 |
+
"epoch": 0.15082746238941985,
|
| 35644 |
+
"grad_norm": 6.46875,
|
| 35645 |
+
"learning_rate": 0.00047497960219841873,
|
| 35646 |
+
"loss": 15.8174,
|
| 35647 |
+
"step": 101820
|
| 35648 |
+
},
|
| 35649 |
+
{
|
| 35650 |
+
"epoch": 0.15085708868334824,
|
| 35651 |
+
"grad_norm": 7.0625,
|
| 35652 |
+
"learning_rate": 0.00047497466326341123,
|
| 35653 |
+
"loss": 15.8871,
|
| 35654 |
+
"step": 101840
|
| 35655 |
+
},
|
| 35656 |
+
{
|
| 35657 |
+
"epoch": 0.15088671497727663,
|
| 35658 |
+
"grad_norm": 6.75,
|
| 35659 |
+
"learning_rate": 0.0004749697243284036,
|
| 35660 |
+
"loss": 15.8636,
|
| 35661 |
+
"step": 101860
|
| 35662 |
+
},
|
| 35663 |
+
{
|
| 35664 |
+
"epoch": 0.150916341271205,
|
| 35665 |
+
"grad_norm": 6.625,
|
| 35666 |
+
"learning_rate": 0.00047496478539339607,
|
| 35667 |
+
"loss": 15.8234,
|
| 35668 |
+
"step": 101880
|
| 35669 |
+
},
|
| 35670 |
+
{
|
| 35671 |
+
"epoch": 0.1509459675651334,
|
| 35672 |
+
"grad_norm": 7.78125,
|
| 35673 |
+
"learning_rate": 0.00047495984645838847,
|
| 35674 |
+
"loss": 15.8701,
|
| 35675 |
+
"step": 101900
|
| 35676 |
+
},
|
| 35677 |
+
{
|
| 35678 |
+
"epoch": 0.15097559385906179,
|
| 35679 |
+
"grad_norm": 6.25,
|
| 35680 |
+
"learning_rate": 0.00047495490752338097,
|
| 35681 |
+
"loss": 15.826,
|
| 35682 |
+
"step": 101920
|
| 35683 |
+
},
|
| 35684 |
+
{
|
| 35685 |
+
"epoch": 0.15100522015299017,
|
| 35686 |
+
"grad_norm": 6.84375,
|
| 35687 |
+
"learning_rate": 0.00047494996858837336,
|
| 35688 |
+
"loss": 15.8412,
|
| 35689 |
+
"step": 101940
|
| 35690 |
+
},
|
| 35691 |
+
{
|
| 35692 |
+
"epoch": 0.15103484644691856,
|
| 35693 |
+
"grad_norm": 6.21875,
|
| 35694 |
+
"learning_rate": 0.00047494502965336576,
|
| 35695 |
+
"loss": 15.831,
|
| 35696 |
+
"step": 101960
|
| 35697 |
+
},
|
| 35698 |
+
{
|
| 35699 |
+
"epoch": 0.15106447274084694,
|
| 35700 |
+
"grad_norm": 6.8125,
|
| 35701 |
+
"learning_rate": 0.00047494009071835826,
|
| 35702 |
+
"loss": 15.8454,
|
| 35703 |
+
"step": 101980
|
| 35704 |
+
},
|
| 35705 |
+
{
|
| 35706 |
+
"epoch": 0.15109409903477533,
|
| 35707 |
+
"grad_norm": 6.53125,
|
| 35708 |
+
"learning_rate": 0.00047493515178335065,
|
| 35709 |
+
"loss": 15.837,
|
| 35710 |
+
"step": 102000
|
| 35711 |
}
|
| 35712 |
],
|
| 35713 |
"logging_steps": 20,
|
|
|
|
| 35727 |
"attributes": {}
|
| 35728 |
}
|
| 35729 |
},
|
| 35730 |
+
"total_flos": 7.499797585582883e+19,
|
| 35731 |
"train_batch_size": 48,
|
| 35732 |
"trial_name": null,
|
| 35733 |
"trial_params": null
|