Training in progress, step 99000, 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 sha256:7321a95ee1c6dd518d07fed4b53d6478fb5e6499e1d611b76a47342e8b103bc4
|
| 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 sha256:247a2784818525ce58e55a45405e27bce62778f8f8b9b6bb254b339fd0176423
|
| 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:cd1fb222de975cb835f8811fe25a1a2cff3488b6151bd99f7b0ba81728382c49
|
| 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 sha256:1f96518fc2ee0662fd8930e66ddb8c07ad98783af09c46abe5caf68d8cfbf6ed
|
| 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:dc20c8f48c78b9db2657a541eba363f80b5e404b57239d08a67dcb86d5f59935
|
| 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 sha256:0f311ce0b83d560c11d10a1c2f1f1b35778f093e2c5ec8b8ed5f4f9dddb6f299
|
| 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 sha256:94c08fce94de721061c0ab4d342e026c399e16f871e83ab6074a1a79492c6ff9
|
| 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,
|
|
@@ -34308,6 +34308,356 @@
|
|
| 34308 |
"learning_rate": 0.00047592293878486396,
|
| 34309 |
"loss": 15.928,
|
| 34310 |
"step": 98000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34311 |
}
|
| 34312 |
],
|
| 34313 |
"logging_steps": 20,
|
|
@@ -34327,7 +34677,7 @@
|
|
| 34327 |
"attributes": {}
|
| 34328 |
}
|
| 34329 |
},
|
| 34330 |
-
"total_flos": 7.
|
| 34331 |
"train_batch_size": 48,
|
| 34332 |
"trial_name": null,
|
| 34333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.14665015494551725,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 99000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 34308 |
"learning_rate": 0.00047592293878486396,
|
| 34309 |
"loss": 15.928,
|
| 34310 |
"step": 98000
|
| 34311 |
+
},
|
| 34312 |
+
{
|
| 34313 |
+
"epoch": 0.14519846654302626,
|
| 34314 |
+
"grad_norm": 6.125,
|
| 34315 |
+
"learning_rate": 0.0004759179998498564,
|
| 34316 |
+
"loss": 15.9109,
|
| 34317 |
+
"step": 98020
|
| 34318 |
+
},
|
| 34319 |
+
{
|
| 34320 |
+
"epoch": 0.14522809283695465,
|
| 34321 |
+
"grad_norm": 6.4375,
|
| 34322 |
+
"learning_rate": 0.0004759130609148488,
|
| 34323 |
+
"loss": 15.8922,
|
| 34324 |
+
"step": 98040
|
| 34325 |
+
},
|
| 34326 |
+
{
|
| 34327 |
+
"epoch": 0.14525771913088303,
|
| 34328 |
+
"grad_norm": 6.3125,
|
| 34329 |
+
"learning_rate": 0.00047590812197984125,
|
| 34330 |
+
"loss": 15.9058,
|
| 34331 |
+
"step": 98060
|
| 34332 |
+
},
|
| 34333 |
+
{
|
| 34334 |
+
"epoch": 0.14528734542481142,
|
| 34335 |
+
"grad_norm": 6.09375,
|
| 34336 |
+
"learning_rate": 0.0004759031830448337,
|
| 34337 |
+
"loss": 15.8909,
|
| 34338 |
+
"step": 98080
|
| 34339 |
+
},
|
| 34340 |
+
{
|
| 34341 |
+
"epoch": 0.1453169717187398,
|
| 34342 |
+
"grad_norm": 6.71875,
|
| 34343 |
+
"learning_rate": 0.00047589824410982615,
|
| 34344 |
+
"loss": 15.9371,
|
| 34345 |
+
"step": 98100
|
| 34346 |
+
},
|
| 34347 |
+
{
|
| 34348 |
+
"epoch": 0.1453465980126682,
|
| 34349 |
+
"grad_norm": 7.4375,
|
| 34350 |
+
"learning_rate": 0.00047589330517481854,
|
| 34351 |
+
"loss": 15.9048,
|
| 34352 |
+
"step": 98120
|
| 34353 |
+
},
|
| 34354 |
+
{
|
| 34355 |
+
"epoch": 0.14537622430659658,
|
| 34356 |
+
"grad_norm": 6.5625,
|
| 34357 |
+
"learning_rate": 0.000475888366239811,
|
| 34358 |
+
"loss": 15.9081,
|
| 34359 |
+
"step": 98140
|
| 34360 |
+
},
|
| 34361 |
+
{
|
| 34362 |
+
"epoch": 0.14540585060052497,
|
| 34363 |
+
"grad_norm": 6.28125,
|
| 34364 |
+
"learning_rate": 0.00047588342730480344,
|
| 34365 |
+
"loss": 15.9338,
|
| 34366 |
+
"step": 98160
|
| 34367 |
+
},
|
| 34368 |
+
{
|
| 34369 |
+
"epoch": 0.14543547689445335,
|
| 34370 |
+
"grad_norm": 7.03125,
|
| 34371 |
+
"learning_rate": 0.0004758784883697959,
|
| 34372 |
+
"loss": 15.9044,
|
| 34373 |
+
"step": 98180
|
| 34374 |
+
},
|
| 34375 |
+
{
|
| 34376 |
+
"epoch": 0.14546510318838174,
|
| 34377 |
+
"grad_norm": 6.625,
|
| 34378 |
+
"learning_rate": 0.0004758735494347883,
|
| 34379 |
+
"loss": 15.8738,
|
| 34380 |
+
"step": 98200
|
| 34381 |
+
},
|
| 34382 |
+
{
|
| 34383 |
+
"epoch": 0.14549472948231015,
|
| 34384 |
+
"grad_norm": 6.125,
|
| 34385 |
+
"learning_rate": 0.00047586861049978067,
|
| 34386 |
+
"loss": 15.8199,
|
| 34387 |
+
"step": 98220
|
| 34388 |
+
},
|
| 34389 |
+
{
|
| 34390 |
+
"epoch": 0.14552435577623854,
|
| 34391 |
+
"grad_norm": 6.34375,
|
| 34392 |
+
"learning_rate": 0.0004758636715647732,
|
| 34393 |
+
"loss": 15.9296,
|
| 34394 |
+
"step": 98240
|
| 34395 |
+
},
|
| 34396 |
+
{
|
| 34397 |
+
"epoch": 0.14555398207016693,
|
| 34398 |
+
"grad_norm": 7.25,
|
| 34399 |
+
"learning_rate": 0.00047585873262976557,
|
| 34400 |
+
"loss": 15.8733,
|
| 34401 |
+
"step": 98260
|
| 34402 |
+
},
|
| 34403 |
+
{
|
| 34404 |
+
"epoch": 0.1455836083640953,
|
| 34405 |
+
"grad_norm": 6.46875,
|
| 34406 |
+
"learning_rate": 0.000475853793694758,
|
| 34407 |
+
"loss": 15.8756,
|
| 34408 |
+
"step": 98280
|
| 34409 |
+
},
|
| 34410 |
+
{
|
| 34411 |
+
"epoch": 0.1456132346580237,
|
| 34412 |
+
"grad_norm": 6.5625,
|
| 34413 |
+
"learning_rate": 0.00047584885475975046,
|
| 34414 |
+
"loss": 15.9448,
|
| 34415 |
+
"step": 98300
|
| 34416 |
+
},
|
| 34417 |
+
{
|
| 34418 |
+
"epoch": 0.14564286095195209,
|
| 34419 |
+
"grad_norm": 6.65625,
|
| 34420 |
+
"learning_rate": 0.0004758439158247429,
|
| 34421 |
+
"loss": 15.9173,
|
| 34422 |
+
"step": 98320
|
| 34423 |
+
},
|
| 34424 |
+
{
|
| 34425 |
+
"epoch": 0.14567248724588047,
|
| 34426 |
+
"grad_norm": 6.5625,
|
| 34427 |
+
"learning_rate": 0.0004758389768897353,
|
| 34428 |
+
"loss": 15.8801,
|
| 34429 |
+
"step": 98340
|
| 34430 |
+
},
|
| 34431 |
+
{
|
| 34432 |
+
"epoch": 0.14570211353980886,
|
| 34433 |
+
"grad_norm": 6.46875,
|
| 34434 |
+
"learning_rate": 0.00047583403795472775,
|
| 34435 |
+
"loss": 15.8762,
|
| 34436 |
+
"step": 98360
|
| 34437 |
+
},
|
| 34438 |
+
{
|
| 34439 |
+
"epoch": 0.14573173983373724,
|
| 34440 |
+
"grad_norm": 7.125,
|
| 34441 |
+
"learning_rate": 0.0004758290990197202,
|
| 34442 |
+
"loss": 15.8996,
|
| 34443 |
+
"step": 98380
|
| 34444 |
+
},
|
| 34445 |
+
{
|
| 34446 |
+
"epoch": 0.14576136612766563,
|
| 34447 |
+
"grad_norm": 8.1875,
|
| 34448 |
+
"learning_rate": 0.00047582416008471265,
|
| 34449 |
+
"loss": 15.9118,
|
| 34450 |
+
"step": 98400
|
| 34451 |
+
},
|
| 34452 |
+
{
|
| 34453 |
+
"epoch": 0.14579099242159402,
|
| 34454 |
+
"grad_norm": 6.96875,
|
| 34455 |
+
"learning_rate": 0.00047581922114970504,
|
| 34456 |
+
"loss": 15.9532,
|
| 34457 |
+
"step": 98420
|
| 34458 |
+
},
|
| 34459 |
+
{
|
| 34460 |
+
"epoch": 0.1458206187155224,
|
| 34461 |
+
"grad_norm": 6.3125,
|
| 34462 |
+
"learning_rate": 0.0004758142822146975,
|
| 34463 |
+
"loss": 15.8629,
|
| 34464 |
+
"step": 98440
|
| 34465 |
+
},
|
| 34466 |
+
{
|
| 34467 |
+
"epoch": 0.1458502450094508,
|
| 34468 |
+
"grad_norm": 6.6875,
|
| 34469 |
+
"learning_rate": 0.00047580934327968994,
|
| 34470 |
+
"loss": 15.8175,
|
| 34471 |
+
"step": 98460
|
| 34472 |
+
},
|
| 34473 |
+
{
|
| 34474 |
+
"epoch": 0.14587987130337918,
|
| 34475 |
+
"grad_norm": 7.03125,
|
| 34476 |
+
"learning_rate": 0.0004758044043446824,
|
| 34477 |
+
"loss": 15.8885,
|
| 34478 |
+
"step": 98480
|
| 34479 |
+
},
|
| 34480 |
+
{
|
| 34481 |
+
"epoch": 0.14590949759730756,
|
| 34482 |
+
"grad_norm": 6.78125,
|
| 34483 |
+
"learning_rate": 0.0004757994654096748,
|
| 34484 |
+
"loss": 15.9055,
|
| 34485 |
+
"step": 98500
|
| 34486 |
+
},
|
| 34487 |
+
{
|
| 34488 |
+
"epoch": 0.14593912389123595,
|
| 34489 |
+
"grad_norm": 6.59375,
|
| 34490 |
+
"learning_rate": 0.0004757945264746672,
|
| 34491 |
+
"loss": 15.8714,
|
| 34492 |
+
"step": 98520
|
| 34493 |
+
},
|
| 34494 |
+
{
|
| 34495 |
+
"epoch": 0.14596875018516434,
|
| 34496 |
+
"grad_norm": 7.21875,
|
| 34497 |
+
"learning_rate": 0.0004757895875396597,
|
| 34498 |
+
"loss": 15.9081,
|
| 34499 |
+
"step": 98540
|
| 34500 |
+
},
|
| 34501 |
+
{
|
| 34502 |
+
"epoch": 0.14599837647909272,
|
| 34503 |
+
"grad_norm": 6.15625,
|
| 34504 |
+
"learning_rate": 0.00047578464860465207,
|
| 34505 |
+
"loss": 15.8911,
|
| 34506 |
+
"step": 98560
|
| 34507 |
+
},
|
| 34508 |
+
{
|
| 34509 |
+
"epoch": 0.1460280027730211,
|
| 34510 |
+
"grad_norm": 6.78125,
|
| 34511 |
+
"learning_rate": 0.0004757797096696445,
|
| 34512 |
+
"loss": 15.8988,
|
| 34513 |
+
"step": 98580
|
| 34514 |
+
},
|
| 34515 |
+
{
|
| 34516 |
+
"epoch": 0.1460576290669495,
|
| 34517 |
+
"grad_norm": 6.0,
|
| 34518 |
+
"learning_rate": 0.00047577477073463696,
|
| 34519 |
+
"loss": 15.8897,
|
| 34520 |
+
"step": 98600
|
| 34521 |
+
},
|
| 34522 |
+
{
|
| 34523 |
+
"epoch": 0.14608725536087788,
|
| 34524 |
+
"grad_norm": 6.125,
|
| 34525 |
+
"learning_rate": 0.0004757698317996294,
|
| 34526 |
+
"loss": 15.8422,
|
| 34527 |
+
"step": 98620
|
| 34528 |
+
},
|
| 34529 |
+
{
|
| 34530 |
+
"epoch": 0.14611688165480627,
|
| 34531 |
+
"grad_norm": 7.03125,
|
| 34532 |
+
"learning_rate": 0.0004757648928646218,
|
| 34533 |
+
"loss": 15.8942,
|
| 34534 |
+
"step": 98640
|
| 34535 |
+
},
|
| 34536 |
+
{
|
| 34537 |
+
"epoch": 0.14614650794873466,
|
| 34538 |
+
"grad_norm": 6.4375,
|
| 34539 |
+
"learning_rate": 0.00047575995392961425,
|
| 34540 |
+
"loss": 15.8585,
|
| 34541 |
+
"step": 98660
|
| 34542 |
+
},
|
| 34543 |
+
{
|
| 34544 |
+
"epoch": 0.14617613424266304,
|
| 34545 |
+
"grad_norm": 7.9375,
|
| 34546 |
+
"learning_rate": 0.0004757550149946067,
|
| 34547 |
+
"loss": 15.8967,
|
| 34548 |
+
"step": 98680
|
| 34549 |
+
},
|
| 34550 |
+
{
|
| 34551 |
+
"epoch": 0.14620576053659143,
|
| 34552 |
+
"grad_norm": 6.09375,
|
| 34553 |
+
"learning_rate": 0.00047575007605959915,
|
| 34554 |
+
"loss": 15.9617,
|
| 34555 |
+
"step": 98700
|
| 34556 |
+
},
|
| 34557 |
+
{
|
| 34558 |
+
"epoch": 0.14623538683051981,
|
| 34559 |
+
"grad_norm": 6.3125,
|
| 34560 |
+
"learning_rate": 0.00047574513712459154,
|
| 34561 |
+
"loss": 15.8791,
|
| 34562 |
+
"step": 98720
|
| 34563 |
+
},
|
| 34564 |
+
{
|
| 34565 |
+
"epoch": 0.1462650131244482,
|
| 34566 |
+
"grad_norm": 6.1875,
|
| 34567 |
+
"learning_rate": 0.000475740198189584,
|
| 34568 |
+
"loss": 15.8744,
|
| 34569 |
+
"step": 98740
|
| 34570 |
+
},
|
| 34571 |
+
{
|
| 34572 |
+
"epoch": 0.1462946394183766,
|
| 34573 |
+
"grad_norm": 6.15625,
|
| 34574 |
+
"learning_rate": 0.00047573525925457644,
|
| 34575 |
+
"loss": 15.8701,
|
| 34576 |
+
"step": 98760
|
| 34577 |
+
},
|
| 34578 |
+
{
|
| 34579 |
+
"epoch": 0.14632426571230497,
|
| 34580 |
+
"grad_norm": 6.25,
|
| 34581 |
+
"learning_rate": 0.0004757303203195689,
|
| 34582 |
+
"loss": 15.8425,
|
| 34583 |
+
"step": 98780
|
| 34584 |
+
},
|
| 34585 |
+
{
|
| 34586 |
+
"epoch": 0.14635389200623336,
|
| 34587 |
+
"grad_norm": 6.28125,
|
| 34588 |
+
"learning_rate": 0.0004757253813845613,
|
| 34589 |
+
"loss": 15.9387,
|
| 34590 |
+
"step": 98800
|
| 34591 |
+
},
|
| 34592 |
+
{
|
| 34593 |
+
"epoch": 0.14638351830016175,
|
| 34594 |
+
"grad_norm": 6.03125,
|
| 34595 |
+
"learning_rate": 0.0004757204424495537,
|
| 34596 |
+
"loss": 15.8201,
|
| 34597 |
+
"step": 98820
|
| 34598 |
+
},
|
| 34599 |
+
{
|
| 34600 |
+
"epoch": 0.14641314459409013,
|
| 34601 |
+
"grad_norm": 6.0,
|
| 34602 |
+
"learning_rate": 0.0004757155035145462,
|
| 34603 |
+
"loss": 15.8952,
|
| 34604 |
+
"step": 98840
|
| 34605 |
+
},
|
| 34606 |
+
{
|
| 34607 |
+
"epoch": 0.14644277088801855,
|
| 34608 |
+
"grad_norm": 8.375,
|
| 34609 |
+
"learning_rate": 0.0004757105645795386,
|
| 34610 |
+
"loss": 15.9362,
|
| 34611 |
+
"step": 98860
|
| 34612 |
+
},
|
| 34613 |
+
{
|
| 34614 |
+
"epoch": 0.14647239718194693,
|
| 34615 |
+
"grad_norm": 6.5,
|
| 34616 |
+
"learning_rate": 0.000475705625644531,
|
| 34617 |
+
"loss": 15.8947,
|
| 34618 |
+
"step": 98880
|
| 34619 |
+
},
|
| 34620 |
+
{
|
| 34621 |
+
"epoch": 0.14650202347587532,
|
| 34622 |
+
"grad_norm": 6.6875,
|
| 34623 |
+
"learning_rate": 0.00047570068670952346,
|
| 34624 |
+
"loss": 15.859,
|
| 34625 |
+
"step": 98900
|
| 34626 |
+
},
|
| 34627 |
+
{
|
| 34628 |
+
"epoch": 0.1465316497698037,
|
| 34629 |
+
"grad_norm": 6.03125,
|
| 34630 |
+
"learning_rate": 0.0004756957477745159,
|
| 34631 |
+
"loss": 15.8616,
|
| 34632 |
+
"step": 98920
|
| 34633 |
+
},
|
| 34634 |
+
{
|
| 34635 |
+
"epoch": 0.1465612760637321,
|
| 34636 |
+
"grad_norm": 7.3125,
|
| 34637 |
+
"learning_rate": 0.0004756908088395083,
|
| 34638 |
+
"loss": 15.8874,
|
| 34639 |
+
"step": 98940
|
| 34640 |
+
},
|
| 34641 |
+
{
|
| 34642 |
+
"epoch": 0.14659090235766048,
|
| 34643 |
+
"grad_norm": 6.3125,
|
| 34644 |
+
"learning_rate": 0.00047568586990450075,
|
| 34645 |
+
"loss": 15.9255,
|
| 34646 |
+
"step": 98960
|
| 34647 |
+
},
|
| 34648 |
+
{
|
| 34649 |
+
"epoch": 0.14662052865158887,
|
| 34650 |
+
"grad_norm": 6.65625,
|
| 34651 |
+
"learning_rate": 0.0004756809309694932,
|
| 34652 |
+
"loss": 15.9159,
|
| 34653 |
+
"step": 98980
|
| 34654 |
+
},
|
| 34655 |
+
{
|
| 34656 |
+
"epoch": 0.14665015494551725,
|
| 34657 |
+
"grad_norm": 6.9375,
|
| 34658 |
+
"learning_rate": 0.00047567599203448565,
|
| 34659 |
+
"loss": 15.8396,
|
| 34660 |
+
"step": 99000
|
| 34661 |
}
|
| 34662 |
],
|
| 34663 |
"logging_steps": 20,
|
|
|
|
| 34677 |
"attributes": {}
|
| 34678 |
}
|
| 34679 |
},
|
| 34680 |
+
"total_flos": 7.279189042742795e+19,
|
| 34681 |
"train_batch_size": 48,
|
| 34682 |
"trial_name": null,
|
| 34683 |
"trial_params": null
|