Training in progress, step 79000, 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:c756f34d6447d0a12191f2f228e5fca6325d2585555740b00f437d7c3e7004bb
|
| 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 sha256:3e5534657658835263ae3eba8ff79c99616131e773d428fcce31ad61af86046b
|
| 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:f9cd212ee37c184ab654cd81424bd96e3d051626e53abebd61cf8f11452e1283
|
| 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 sha256:4ec46da082cb75a7e3753cfb221c9d642f2a32f3a83b3b478de73eadc477388c
|
| 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 sha256:3a45666dfa471b8966a5f388cff9679b0f97f0a453b0c8aca6fb55a560f78c7c
|
| 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:ba2d0810d74e907463868f0c583c57c89e9a4bad46de26ffd127e43e9b609736
|
| 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:cb0dc069b89d8c308dec795d21a2ac94397c5df6c87082b4999d15bf441c0a2e
|
| 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,
|
|
@@ -27308,6 +27308,356 @@
|
|
| 27308 |
"learning_rate": 0.0004808618737924304,
|
| 27309 |
"loss": 16.2962,
|
| 27310 |
"step": 78000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27311 |
}
|
| 27312 |
],
|
| 27313 |
"logging_steps": 20,
|
|
@@ -27327,7 +27677,7 @@
|
|
| 27327 |
"attributes": {}
|
| 27328 |
}
|
| 27329 |
},
|
| 27330 |
-
"total_flos": 5.
|
| 27331 |
"train_batch_size": 48,
|
| 27332 |
"trial_name": null,
|
| 27333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11702386101712993,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 79000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 27308 |
"learning_rate": 0.0004808618737924304,
|
| 27309 |
"loss": 16.2962,
|
| 27310 |
"step": 78000
|
| 27311 |
+
},
|
| 27312 |
+
{
|
| 27313 |
+
"epoch": 0.11557217261463894,
|
| 27314 |
+
"grad_norm": 6.46875,
|
| 27315 |
+
"learning_rate": 0.0004808569348574228,
|
| 27316 |
+
"loss": 16.2507,
|
| 27317 |
+
"step": 78020
|
| 27318 |
+
},
|
| 27319 |
+
{
|
| 27320 |
+
"epoch": 0.11560179890856734,
|
| 27321 |
+
"grad_norm": 6.28125,
|
| 27322 |
+
"learning_rate": 0.00048085199592241525,
|
| 27323 |
+
"loss": 16.3604,
|
| 27324 |
+
"step": 78040
|
| 27325 |
+
},
|
| 27326 |
+
{
|
| 27327 |
+
"epoch": 0.11563142520249572,
|
| 27328 |
+
"grad_norm": 6.09375,
|
| 27329 |
+
"learning_rate": 0.0004808470569874077,
|
| 27330 |
+
"loss": 16.3038,
|
| 27331 |
+
"step": 78060
|
| 27332 |
+
},
|
| 27333 |
+
{
|
| 27334 |
+
"epoch": 0.11566105149642411,
|
| 27335 |
+
"grad_norm": 7.4375,
|
| 27336 |
+
"learning_rate": 0.00048084211805240015,
|
| 27337 |
+
"loss": 16.3236,
|
| 27338 |
+
"step": 78080
|
| 27339 |
+
},
|
| 27340 |
+
{
|
| 27341 |
+
"epoch": 0.1156906777903525,
|
| 27342 |
+
"grad_norm": 6.0625,
|
| 27343 |
+
"learning_rate": 0.00048083717911739254,
|
| 27344 |
+
"loss": 16.3219,
|
| 27345 |
+
"step": 78100
|
| 27346 |
+
},
|
| 27347 |
+
{
|
| 27348 |
+
"epoch": 0.11572030408428088,
|
| 27349 |
+
"grad_norm": 6.625,
|
| 27350 |
+
"learning_rate": 0.00048083224018238504,
|
| 27351 |
+
"loss": 16.345,
|
| 27352 |
+
"step": 78120
|
| 27353 |
+
},
|
| 27354 |
+
{
|
| 27355 |
+
"epoch": 0.11574993037820927,
|
| 27356 |
+
"grad_norm": 6.34375,
|
| 27357 |
+
"learning_rate": 0.00048082730124737744,
|
| 27358 |
+
"loss": 16.3579,
|
| 27359 |
+
"step": 78140
|
| 27360 |
+
},
|
| 27361 |
+
{
|
| 27362 |
+
"epoch": 0.11577955667213766,
|
| 27363 |
+
"grad_norm": 7.0,
|
| 27364 |
+
"learning_rate": 0.0004808223623123699,
|
| 27365 |
+
"loss": 16.3603,
|
| 27366 |
+
"step": 78160
|
| 27367 |
+
},
|
| 27368 |
+
{
|
| 27369 |
+
"epoch": 0.11580918296606604,
|
| 27370 |
+
"grad_norm": 5.9375,
|
| 27371 |
+
"learning_rate": 0.0004808174233773623,
|
| 27372 |
+
"loss": 16.2884,
|
| 27373 |
+
"step": 78180
|
| 27374 |
+
},
|
| 27375 |
+
{
|
| 27376 |
+
"epoch": 0.11583880925999443,
|
| 27377 |
+
"grad_norm": 6.03125,
|
| 27378 |
+
"learning_rate": 0.0004808124844423548,
|
| 27379 |
+
"loss": 16.3097,
|
| 27380 |
+
"step": 78200
|
| 27381 |
+
},
|
| 27382 |
+
{
|
| 27383 |
+
"epoch": 0.11586843555392282,
|
| 27384 |
+
"grad_norm": 6.75,
|
| 27385 |
+
"learning_rate": 0.00048080754550734717,
|
| 27386 |
+
"loss": 16.3178,
|
| 27387 |
+
"step": 78220
|
| 27388 |
+
},
|
| 27389 |
+
{
|
| 27390 |
+
"epoch": 0.1158980618478512,
|
| 27391 |
+
"grad_norm": 7.15625,
|
| 27392 |
+
"learning_rate": 0.0004808026065723396,
|
| 27393 |
+
"loss": 16.3025,
|
| 27394 |
+
"step": 78240
|
| 27395 |
+
},
|
| 27396 |
+
{
|
| 27397 |
+
"epoch": 0.11592768814177959,
|
| 27398 |
+
"grad_norm": 6.15625,
|
| 27399 |
+
"learning_rate": 0.000480797667637332,
|
| 27400 |
+
"loss": 16.2479,
|
| 27401 |
+
"step": 78260
|
| 27402 |
+
},
|
| 27403 |
+
{
|
| 27404 |
+
"epoch": 0.11595731443570798,
|
| 27405 |
+
"grad_norm": 7.65625,
|
| 27406 |
+
"learning_rate": 0.0004807927287023245,
|
| 27407 |
+
"loss": 16.3029,
|
| 27408 |
+
"step": 78280
|
| 27409 |
+
},
|
| 27410 |
+
{
|
| 27411 |
+
"epoch": 0.11598694072963636,
|
| 27412 |
+
"grad_norm": 6.28125,
|
| 27413 |
+
"learning_rate": 0.0004807877897673169,
|
| 27414 |
+
"loss": 16.316,
|
| 27415 |
+
"step": 78300
|
| 27416 |
+
},
|
| 27417 |
+
{
|
| 27418 |
+
"epoch": 0.11601656702356475,
|
| 27419 |
+
"grad_norm": 6.9375,
|
| 27420 |
+
"learning_rate": 0.0004807828508323093,
|
| 27421 |
+
"loss": 16.2811,
|
| 27422 |
+
"step": 78320
|
| 27423 |
+
},
|
| 27424 |
+
{
|
| 27425 |
+
"epoch": 0.11604619331749313,
|
| 27426 |
+
"grad_norm": 6.125,
|
| 27427 |
+
"learning_rate": 0.00048077791189730175,
|
| 27428 |
+
"loss": 16.2406,
|
| 27429 |
+
"step": 78340
|
| 27430 |
+
},
|
| 27431 |
+
{
|
| 27432 |
+
"epoch": 0.11607581961142154,
|
| 27433 |
+
"grad_norm": 6.4375,
|
| 27434 |
+
"learning_rate": 0.0004807729729622942,
|
| 27435 |
+
"loss": 16.323,
|
| 27436 |
+
"step": 78360
|
| 27437 |
+
},
|
| 27438 |
+
{
|
| 27439 |
+
"epoch": 0.11610544590534992,
|
| 27440 |
+
"grad_norm": 6.25,
|
| 27441 |
+
"learning_rate": 0.00048076803402728665,
|
| 27442 |
+
"loss": 16.3224,
|
| 27443 |
+
"step": 78380
|
| 27444 |
+
},
|
| 27445 |
+
{
|
| 27446 |
+
"epoch": 0.11613507219927831,
|
| 27447 |
+
"grad_norm": 6.875,
|
| 27448 |
+
"learning_rate": 0.00048076309509227904,
|
| 27449 |
+
"loss": 16.2637,
|
| 27450 |
+
"step": 78400
|
| 27451 |
+
},
|
| 27452 |
+
{
|
| 27453 |
+
"epoch": 0.1161646984932067,
|
| 27454 |
+
"grad_norm": 5.71875,
|
| 27455 |
+
"learning_rate": 0.00048075815615727154,
|
| 27456 |
+
"loss": 16.2791,
|
| 27457 |
+
"step": 78420
|
| 27458 |
+
},
|
| 27459 |
+
{
|
| 27460 |
+
"epoch": 0.11619432478713508,
|
| 27461 |
+
"grad_norm": 6.34375,
|
| 27462 |
+
"learning_rate": 0.00048075321722226394,
|
| 27463 |
+
"loss": 16.2131,
|
| 27464 |
+
"step": 78440
|
| 27465 |
+
},
|
| 27466 |
+
{
|
| 27467 |
+
"epoch": 0.11622395108106347,
|
| 27468 |
+
"grad_norm": 6.59375,
|
| 27469 |
+
"learning_rate": 0.0004807482782872564,
|
| 27470 |
+
"loss": 16.2892,
|
| 27471 |
+
"step": 78460
|
| 27472 |
+
},
|
| 27473 |
+
{
|
| 27474 |
+
"epoch": 0.11625357737499185,
|
| 27475 |
+
"grad_norm": 6.90625,
|
| 27476 |
+
"learning_rate": 0.0004807433393522488,
|
| 27477 |
+
"loss": 16.3267,
|
| 27478 |
+
"step": 78480
|
| 27479 |
+
},
|
| 27480 |
+
{
|
| 27481 |
+
"epoch": 0.11628320366892024,
|
| 27482 |
+
"grad_norm": 7.09375,
|
| 27483 |
+
"learning_rate": 0.0004807384004172413,
|
| 27484 |
+
"loss": 16.2359,
|
| 27485 |
+
"step": 78500
|
| 27486 |
+
},
|
| 27487 |
+
{
|
| 27488 |
+
"epoch": 0.11631282996284863,
|
| 27489 |
+
"grad_norm": 6.46875,
|
| 27490 |
+
"learning_rate": 0.00048073346148223367,
|
| 27491 |
+
"loss": 16.2849,
|
| 27492 |
+
"step": 78520
|
| 27493 |
+
},
|
| 27494 |
+
{
|
| 27495 |
+
"epoch": 0.11634245625677701,
|
| 27496 |
+
"grad_norm": 7.125,
|
| 27497 |
+
"learning_rate": 0.0004807285225472261,
|
| 27498 |
+
"loss": 16.2734,
|
| 27499 |
+
"step": 78540
|
| 27500 |
+
},
|
| 27501 |
+
{
|
| 27502 |
+
"epoch": 0.1163720825507054,
|
| 27503 |
+
"grad_norm": 7.21875,
|
| 27504 |
+
"learning_rate": 0.0004807235836122185,
|
| 27505 |
+
"loss": 16.2993,
|
| 27506 |
+
"step": 78560
|
| 27507 |
+
},
|
| 27508 |
+
{
|
| 27509 |
+
"epoch": 0.11640170884463379,
|
| 27510 |
+
"grad_norm": 7.0625,
|
| 27511 |
+
"learning_rate": 0.000480718644677211,
|
| 27512 |
+
"loss": 16.2808,
|
| 27513 |
+
"step": 78580
|
| 27514 |
+
},
|
| 27515 |
+
{
|
| 27516 |
+
"epoch": 0.11643133513856217,
|
| 27517 |
+
"grad_norm": 5.96875,
|
| 27518 |
+
"learning_rate": 0.0004807137057422034,
|
| 27519 |
+
"loss": 16.2739,
|
| 27520 |
+
"step": 78600
|
| 27521 |
+
},
|
| 27522 |
+
{
|
| 27523 |
+
"epoch": 0.11646096143249056,
|
| 27524 |
+
"grad_norm": 7.03125,
|
| 27525 |
+
"learning_rate": 0.0004807087668071958,
|
| 27526 |
+
"loss": 16.27,
|
| 27527 |
+
"step": 78620
|
| 27528 |
+
},
|
| 27529 |
+
{
|
| 27530 |
+
"epoch": 0.11649058772641895,
|
| 27531 |
+
"grad_norm": 6.5,
|
| 27532 |
+
"learning_rate": 0.00048070382787218825,
|
| 27533 |
+
"loss": 16.3228,
|
| 27534 |
+
"step": 78640
|
| 27535 |
+
},
|
| 27536 |
+
{
|
| 27537 |
+
"epoch": 0.11652021402034733,
|
| 27538 |
+
"grad_norm": 6.78125,
|
| 27539 |
+
"learning_rate": 0.0004806988889371807,
|
| 27540 |
+
"loss": 16.2983,
|
| 27541 |
+
"step": 78660
|
| 27542 |
+
},
|
| 27543 |
+
{
|
| 27544 |
+
"epoch": 0.11654984031427573,
|
| 27545 |
+
"grad_norm": 6.90625,
|
| 27546 |
+
"learning_rate": 0.00048069395000217315,
|
| 27547 |
+
"loss": 16.3329,
|
| 27548 |
+
"step": 78680
|
| 27549 |
+
},
|
| 27550 |
+
{
|
| 27551 |
+
"epoch": 0.11657946660820412,
|
| 27552 |
+
"grad_norm": 7.0625,
|
| 27553 |
+
"learning_rate": 0.00048068901106716554,
|
| 27554 |
+
"loss": 16.2225,
|
| 27555 |
+
"step": 78700
|
| 27556 |
+
},
|
| 27557 |
+
{
|
| 27558 |
+
"epoch": 0.1166090929021325,
|
| 27559 |
+
"grad_norm": 6.125,
|
| 27560 |
+
"learning_rate": 0.00048068407213215804,
|
| 27561 |
+
"loss": 16.3264,
|
| 27562 |
+
"step": 78720
|
| 27563 |
+
},
|
| 27564 |
+
{
|
| 27565 |
+
"epoch": 0.11663871919606089,
|
| 27566 |
+
"grad_norm": 6.03125,
|
| 27567 |
+
"learning_rate": 0.00048067913319715044,
|
| 27568 |
+
"loss": 16.2698,
|
| 27569 |
+
"step": 78740
|
| 27570 |
+
},
|
| 27571 |
+
{
|
| 27572 |
+
"epoch": 0.11666834548998928,
|
| 27573 |
+
"grad_norm": 7.40625,
|
| 27574 |
+
"learning_rate": 0.0004806741942621429,
|
| 27575 |
+
"loss": 16.2736,
|
| 27576 |
+
"step": 78760
|
| 27577 |
+
},
|
| 27578 |
+
{
|
| 27579 |
+
"epoch": 0.11669797178391766,
|
| 27580 |
+
"grad_norm": 5.875,
|
| 27581 |
+
"learning_rate": 0.0004806692553271353,
|
| 27582 |
+
"loss": 16.2845,
|
| 27583 |
+
"step": 78780
|
| 27584 |
+
},
|
| 27585 |
+
{
|
| 27586 |
+
"epoch": 0.11672759807784605,
|
| 27587 |
+
"grad_norm": 7.34375,
|
| 27588 |
+
"learning_rate": 0.0004806643163921278,
|
| 27589 |
+
"loss": 16.3404,
|
| 27590 |
+
"step": 78800
|
| 27591 |
+
},
|
| 27592 |
+
{
|
| 27593 |
+
"epoch": 0.11675722437177444,
|
| 27594 |
+
"grad_norm": 6.71875,
|
| 27595 |
+
"learning_rate": 0.0004806593774571202,
|
| 27596 |
+
"loss": 16.3419,
|
| 27597 |
+
"step": 78820
|
| 27598 |
+
},
|
| 27599 |
+
{
|
| 27600 |
+
"epoch": 0.11678685066570282,
|
| 27601 |
+
"grad_norm": 7.0625,
|
| 27602 |
+
"learning_rate": 0.0004806544385221126,
|
| 27603 |
+
"loss": 16.3002,
|
| 27604 |
+
"step": 78840
|
| 27605 |
+
},
|
| 27606 |
+
{
|
| 27607 |
+
"epoch": 0.11681647695963121,
|
| 27608 |
+
"grad_norm": 6.0625,
|
| 27609 |
+
"learning_rate": 0.000480649499587105,
|
| 27610 |
+
"loss": 16.2805,
|
| 27611 |
+
"step": 78860
|
| 27612 |
+
},
|
| 27613 |
+
{
|
| 27614 |
+
"epoch": 0.1168461032535596,
|
| 27615 |
+
"grad_norm": 6.90625,
|
| 27616 |
+
"learning_rate": 0.0004806445606520975,
|
| 27617 |
+
"loss": 16.2746,
|
| 27618 |
+
"step": 78880
|
| 27619 |
+
},
|
| 27620 |
+
{
|
| 27621 |
+
"epoch": 0.11687572954748798,
|
| 27622 |
+
"grad_norm": 6.21875,
|
| 27623 |
+
"learning_rate": 0.0004806396217170899,
|
| 27624 |
+
"loss": 16.3208,
|
| 27625 |
+
"step": 78900
|
| 27626 |
+
},
|
| 27627 |
+
{
|
| 27628 |
+
"epoch": 0.11690535584141637,
|
| 27629 |
+
"grad_norm": 6.375,
|
| 27630 |
+
"learning_rate": 0.00048063468278208236,
|
| 27631 |
+
"loss": 16.3402,
|
| 27632 |
+
"step": 78920
|
| 27633 |
+
},
|
| 27634 |
+
{
|
| 27635 |
+
"epoch": 0.11693498213534476,
|
| 27636 |
+
"grad_norm": 7.9375,
|
| 27637 |
+
"learning_rate": 0.00048062974384707475,
|
| 27638 |
+
"loss": 16.4001,
|
| 27639 |
+
"step": 78940
|
| 27640 |
+
},
|
| 27641 |
+
{
|
| 27642 |
+
"epoch": 0.11696460842927314,
|
| 27643 |
+
"grad_norm": 6.9375,
|
| 27644 |
+
"learning_rate": 0.0004806248049120672,
|
| 27645 |
+
"loss": 16.2514,
|
| 27646 |
+
"step": 78960
|
| 27647 |
+
},
|
| 27648 |
+
{
|
| 27649 |
+
"epoch": 0.11699423472320153,
|
| 27650 |
+
"grad_norm": 6.84375,
|
| 27651 |
+
"learning_rate": 0.00048061986597705965,
|
| 27652 |
+
"loss": 16.2722,
|
| 27653 |
+
"step": 78980
|
| 27654 |
+
},
|
| 27655 |
+
{
|
| 27656 |
+
"epoch": 0.11702386101712993,
|
| 27657 |
+
"grad_norm": 6.28125,
|
| 27658 |
+
"learning_rate": 0.00048061492704205204,
|
| 27659 |
+
"loss": 16.3266,
|
| 27660 |
+
"step": 79000
|
| 27661 |
}
|
| 27662 |
],
|
| 27663 |
"logging_steps": 20,
|
|
|
|
| 27677 |
"attributes": {}
|
| 27678 |
}
|
| 27679 |
},
|
| 27680 |
+
"total_flos": 5.808462373236769e+19,
|
| 27681 |
"train_batch_size": 48,
|
| 27682 |
"trial_name": null,
|
| 27683 |
"trial_params": null
|