Training in progress, step 1800, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1370666272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19a8c4ff78657e1ad6849d03827d74a166332e2c92b5ee4c34966f79e091caa
|
| 3 |
size 1370666272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 697294462
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c0470d53e83293b301fcaf8b6ed1125194ec8f54fe9618703c1367bf9a41e7
|
| 3 |
size 697294462
|
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:d290a2c62404485bacce37c57039bbf078af94d6cf0884b19d2a678f11aec096
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -12257,6 +12257,356 @@
|
|
| 12257 |
"learning_rate": 0.0001967750823269455,
|
| 12258 |
"loss": 0.8951,
|
| 12259 |
"step": 1750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12260 |
}
|
| 12261 |
],
|
| 12262 |
"logging_steps": 1,
|
|
@@ -12276,7 +12626,7 @@
|
|
| 12276 |
"attributes": {}
|
| 12277 |
}
|
| 12278 |
},
|
| 12279 |
-
"total_flos": 7.
|
| 12280 |
"train_batch_size": 32,
|
| 12281 |
"trial_name": null,
|
| 12282 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4177788093303934,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 12257 |
"learning_rate": 0.0001967750823269455,
|
| 12258 |
"loss": 0.8951,
|
| 12259 |
"step": 1750
|
| 12260 |
+
},
|
| 12261 |
+
{
|
| 12262 |
+
"epoch": 0.40640594174306605,
|
| 12263 |
+
"grad_norm": 0.6410776972770691,
|
| 12264 |
+
"learning_rate": 0.00019677140721822734,
|
| 12265 |
+
"loss": 0.8931,
|
| 12266 |
+
"step": 1751
|
| 12267 |
+
},
|
| 12268 |
+
{
|
| 12269 |
+
"epoch": 0.4066380410815829,
|
| 12270 |
+
"grad_norm": 0.7138279676437378,
|
| 12271 |
+
"learning_rate": 0.00019676773005098766,
|
| 12272 |
+
"loss": 0.9195,
|
| 12273 |
+
"step": 1752
|
| 12274 |
+
},
|
| 12275 |
+
{
|
| 12276 |
+
"epoch": 0.4068701404200998,
|
| 12277 |
+
"grad_norm": 0.5348248481750488,
|
| 12278 |
+
"learning_rate": 0.00019676405082530476,
|
| 12279 |
+
"loss": 0.9232,
|
| 12280 |
+
"step": 1753
|
| 12281 |
+
},
|
| 12282 |
+
{
|
| 12283 |
+
"epoch": 0.4071022397586167,
|
| 12284 |
+
"grad_norm": 0.6424762010574341,
|
| 12285 |
+
"learning_rate": 0.00019676036954125684,
|
| 12286 |
+
"loss": 0.9068,
|
| 12287 |
+
"step": 1754
|
| 12288 |
+
},
|
| 12289 |
+
{
|
| 12290 |
+
"epoch": 0.40733433909713357,
|
| 12291 |
+
"grad_norm": 0.6323909759521484,
|
| 12292 |
+
"learning_rate": 0.00019675668619892228,
|
| 12293 |
+
"loss": 0.929,
|
| 12294 |
+
"step": 1755
|
| 12295 |
+
},
|
| 12296 |
+
{
|
| 12297 |
+
"epoch": 0.40756643843565044,
|
| 12298 |
+
"grad_norm": 0.541854977607727,
|
| 12299 |
+
"learning_rate": 0.00019675300079837935,
|
| 12300 |
+
"loss": 0.9729,
|
| 12301 |
+
"step": 1756
|
| 12302 |
+
},
|
| 12303 |
+
{
|
| 12304 |
+
"epoch": 0.40779853777416736,
|
| 12305 |
+
"grad_norm": 0.7092952132225037,
|
| 12306 |
+
"learning_rate": 0.00019674931333970647,
|
| 12307 |
+
"loss": 0.9005,
|
| 12308 |
+
"step": 1757
|
| 12309 |
+
},
|
| 12310 |
+
{
|
| 12311 |
+
"epoch": 0.4080306371126842,
|
| 12312 |
+
"grad_norm": 0.5437161922454834,
|
| 12313 |
+
"learning_rate": 0.0001967456238229821,
|
| 12314 |
+
"loss": 0.9944,
|
| 12315 |
+
"step": 1758
|
| 12316 |
+
},
|
| 12317 |
+
{
|
| 12318 |
+
"epoch": 0.4082627364512011,
|
| 12319 |
+
"grad_norm": 0.5253750681877136,
|
| 12320 |
+
"learning_rate": 0.00019674193224828473,
|
| 12321 |
+
"loss": 0.9535,
|
| 12322 |
+
"step": 1759
|
| 12323 |
+
},
|
| 12324 |
+
{
|
| 12325 |
+
"epoch": 0.408494835789718,
|
| 12326 |
+
"grad_norm": 0.6329406499862671,
|
| 12327 |
+
"learning_rate": 0.00019673823861569286,
|
| 12328 |
+
"loss": 0.8904,
|
| 12329 |
+
"step": 1760
|
| 12330 |
+
},
|
| 12331 |
+
{
|
| 12332 |
+
"epoch": 0.4087269351282349,
|
| 12333 |
+
"grad_norm": 0.5530345439910889,
|
| 12334 |
+
"learning_rate": 0.00019673454292528508,
|
| 12335 |
+
"loss": 0.934,
|
| 12336 |
+
"step": 1761
|
| 12337 |
+
},
|
| 12338 |
+
{
|
| 12339 |
+
"epoch": 0.40895903446675175,
|
| 12340 |
+
"grad_norm": 0.6421835422515869,
|
| 12341 |
+
"learning_rate": 0.00019673084517714,
|
| 12342 |
+
"loss": 0.9014,
|
| 12343 |
+
"step": 1762
|
| 12344 |
+
},
|
| 12345 |
+
{
|
| 12346 |
+
"epoch": 0.40919113380526867,
|
| 12347 |
+
"grad_norm": 0.5271580219268799,
|
| 12348 |
+
"learning_rate": 0.00019672714537133628,
|
| 12349 |
+
"loss": 0.923,
|
| 12350 |
+
"step": 1763
|
| 12351 |
+
},
|
| 12352 |
+
{
|
| 12353 |
+
"epoch": 0.40942323314378554,
|
| 12354 |
+
"grad_norm": 0.5356336236000061,
|
| 12355 |
+
"learning_rate": 0.00019672344350795258,
|
| 12356 |
+
"loss": 0.9246,
|
| 12357 |
+
"step": 1764
|
| 12358 |
+
},
|
| 12359 |
+
{
|
| 12360 |
+
"epoch": 0.4096553324823024,
|
| 12361 |
+
"grad_norm": 0.6168617606163025,
|
| 12362 |
+
"learning_rate": 0.0001967197395870677,
|
| 12363 |
+
"loss": 0.923,
|
| 12364 |
+
"step": 1765
|
| 12365 |
+
},
|
| 12366 |
+
{
|
| 12367 |
+
"epoch": 0.4098874318208193,
|
| 12368 |
+
"grad_norm": 0.49557581543922424,
|
| 12369 |
+
"learning_rate": 0.00019671603360876043,
|
| 12370 |
+
"loss": 0.9448,
|
| 12371 |
+
"step": 1766
|
| 12372 |
+
},
|
| 12373 |
+
{
|
| 12374 |
+
"epoch": 0.4101195311593362,
|
| 12375 |
+
"grad_norm": 0.5493084192276001,
|
| 12376 |
+
"learning_rate": 0.00019671232557310958,
|
| 12377 |
+
"loss": 0.9362,
|
| 12378 |
+
"step": 1767
|
| 12379 |
+
},
|
| 12380 |
+
{
|
| 12381 |
+
"epoch": 0.41035163049785306,
|
| 12382 |
+
"grad_norm": 0.6057862639427185,
|
| 12383 |
+
"learning_rate": 0.00019670861548019405,
|
| 12384 |
+
"loss": 0.9443,
|
| 12385 |
+
"step": 1768
|
| 12386 |
+
},
|
| 12387 |
+
{
|
| 12388 |
+
"epoch": 0.41058372983637,
|
| 12389 |
+
"grad_norm": 0.5347152948379517,
|
| 12390 |
+
"learning_rate": 0.0001967049033300927,
|
| 12391 |
+
"loss": 0.9054,
|
| 12392 |
+
"step": 1769
|
| 12393 |
+
},
|
| 12394 |
+
{
|
| 12395 |
+
"epoch": 0.41081582917488685,
|
| 12396 |
+
"grad_norm": 0.5570089817047119,
|
| 12397 |
+
"learning_rate": 0.0001967011891228846,
|
| 12398 |
+
"loss": 0.9094,
|
| 12399 |
+
"step": 1770
|
| 12400 |
+
},
|
| 12401 |
+
{
|
| 12402 |
+
"epoch": 0.4110479285134037,
|
| 12403 |
+
"grad_norm": 0.5425180792808533,
|
| 12404 |
+
"learning_rate": 0.00019669747285864863,
|
| 12405 |
+
"loss": 0.9072,
|
| 12406 |
+
"step": 1771
|
| 12407 |
+
},
|
| 12408 |
+
{
|
| 12409 |
+
"epoch": 0.41128002785192064,
|
| 12410 |
+
"grad_norm": 0.5784744024276733,
|
| 12411 |
+
"learning_rate": 0.00019669375453746396,
|
| 12412 |
+
"loss": 1.0027,
|
| 12413 |
+
"step": 1772
|
| 12414 |
+
},
|
| 12415 |
+
{
|
| 12416 |
+
"epoch": 0.4115121271904375,
|
| 12417 |
+
"grad_norm": 0.6552026867866516,
|
| 12418 |
+
"learning_rate": 0.0001966900341594096,
|
| 12419 |
+
"loss": 0.9353,
|
| 12420 |
+
"step": 1773
|
| 12421 |
+
},
|
| 12422 |
+
{
|
| 12423 |
+
"epoch": 0.41174422652895437,
|
| 12424 |
+
"grad_norm": 0.4845140874385834,
|
| 12425 |
+
"learning_rate": 0.0001966863117245648,
|
| 12426 |
+
"loss": 0.9227,
|
| 12427 |
+
"step": 1774
|
| 12428 |
+
},
|
| 12429 |
+
{
|
| 12430 |
+
"epoch": 0.4119763258674713,
|
| 12431 |
+
"grad_norm": 0.5522558689117432,
|
| 12432 |
+
"learning_rate": 0.0001966825872330086,
|
| 12433 |
+
"loss": 0.9159,
|
| 12434 |
+
"step": 1775
|
| 12435 |
+
},
|
| 12436 |
+
{
|
| 12437 |
+
"epoch": 0.41220842520598816,
|
| 12438 |
+
"grad_norm": 0.6886111497879028,
|
| 12439 |
+
"learning_rate": 0.0001966788606848203,
|
| 12440 |
+
"loss": 0.8733,
|
| 12441 |
+
"step": 1776
|
| 12442 |
+
},
|
| 12443 |
+
{
|
| 12444 |
+
"epoch": 0.412440524544505,
|
| 12445 |
+
"grad_norm": 0.5358473062515259,
|
| 12446 |
+
"learning_rate": 0.0001966751320800792,
|
| 12447 |
+
"loss": 0.8916,
|
| 12448 |
+
"step": 1777
|
| 12449 |
+
},
|
| 12450 |
+
{
|
| 12451 |
+
"epoch": 0.41267262388302195,
|
| 12452 |
+
"grad_norm": 0.574971079826355,
|
| 12453 |
+
"learning_rate": 0.0001966714014188646,
|
| 12454 |
+
"loss": 0.8828,
|
| 12455 |
+
"step": 1778
|
| 12456 |
+
},
|
| 12457 |
+
{
|
| 12458 |
+
"epoch": 0.4129047232215388,
|
| 12459 |
+
"grad_norm": 0.5384320616722107,
|
| 12460 |
+
"learning_rate": 0.0001966676687012558,
|
| 12461 |
+
"loss": 0.8881,
|
| 12462 |
+
"step": 1779
|
| 12463 |
+
},
|
| 12464 |
+
{
|
| 12465 |
+
"epoch": 0.4131368225600557,
|
| 12466 |
+
"grad_norm": 0.6178532838821411,
|
| 12467 |
+
"learning_rate": 0.00019666393392733228,
|
| 12468 |
+
"loss": 0.9724,
|
| 12469 |
+
"step": 1780
|
| 12470 |
+
},
|
| 12471 |
+
{
|
| 12472 |
+
"epoch": 0.4133689218985726,
|
| 12473 |
+
"grad_norm": 0.5532113313674927,
|
| 12474 |
+
"learning_rate": 0.00019666019709717344,
|
| 12475 |
+
"loss": 0.9535,
|
| 12476 |
+
"step": 1781
|
| 12477 |
+
},
|
| 12478 |
+
{
|
| 12479 |
+
"epoch": 0.4136010212370895,
|
| 12480 |
+
"grad_norm": 0.5668889880180359,
|
| 12481 |
+
"learning_rate": 0.00019665645821085876,
|
| 12482 |
+
"loss": 0.9127,
|
| 12483 |
+
"step": 1782
|
| 12484 |
+
},
|
| 12485 |
+
{
|
| 12486 |
+
"epoch": 0.41383312057560634,
|
| 12487 |
+
"grad_norm": 0.5764045715332031,
|
| 12488 |
+
"learning_rate": 0.00019665271726846783,
|
| 12489 |
+
"loss": 0.9412,
|
| 12490 |
+
"step": 1783
|
| 12491 |
+
},
|
| 12492 |
+
{
|
| 12493 |
+
"epoch": 0.41406521991412326,
|
| 12494 |
+
"grad_norm": 0.5341030955314636,
|
| 12495 |
+
"learning_rate": 0.00019664897427008014,
|
| 12496 |
+
"loss": 0.9349,
|
| 12497 |
+
"step": 1784
|
| 12498 |
+
},
|
| 12499 |
+
{
|
| 12500 |
+
"epoch": 0.41429731925264013,
|
| 12501 |
+
"grad_norm": 0.6231575012207031,
|
| 12502 |
+
"learning_rate": 0.00019664522921577544,
|
| 12503 |
+
"loss": 0.8928,
|
| 12504 |
+
"step": 1785
|
| 12505 |
+
},
|
| 12506 |
+
{
|
| 12507 |
+
"epoch": 0.414529418591157,
|
| 12508 |
+
"grad_norm": 0.5901029706001282,
|
| 12509 |
+
"learning_rate": 0.00019664148210563328,
|
| 12510 |
+
"loss": 0.9054,
|
| 12511 |
+
"step": 1786
|
| 12512 |
+
},
|
| 12513 |
+
{
|
| 12514 |
+
"epoch": 0.4147615179296739,
|
| 12515 |
+
"grad_norm": 0.5409894585609436,
|
| 12516 |
+
"learning_rate": 0.0001966377329397334,
|
| 12517 |
+
"loss": 0.8859,
|
| 12518 |
+
"step": 1787
|
| 12519 |
+
},
|
| 12520 |
+
{
|
| 12521 |
+
"epoch": 0.4149936172681908,
|
| 12522 |
+
"grad_norm": 0.6134136915206909,
|
| 12523 |
+
"learning_rate": 0.00019663398171815554,
|
| 12524 |
+
"loss": 0.8984,
|
| 12525 |
+
"step": 1788
|
| 12526 |
+
},
|
| 12527 |
+
{
|
| 12528 |
+
"epoch": 0.41522571660670765,
|
| 12529 |
+
"grad_norm": 0.5341612696647644,
|
| 12530 |
+
"learning_rate": 0.00019663022844097956,
|
| 12531 |
+
"loss": 0.8723,
|
| 12532 |
+
"step": 1789
|
| 12533 |
+
},
|
| 12534 |
+
{
|
| 12535 |
+
"epoch": 0.4154578159452246,
|
| 12536 |
+
"grad_norm": 0.5658878684043884,
|
| 12537 |
+
"learning_rate": 0.00019662647310828523,
|
| 12538 |
+
"loss": 0.8559,
|
| 12539 |
+
"step": 1790
|
| 12540 |
+
},
|
| 12541 |
+
{
|
| 12542 |
+
"epoch": 0.41568991528374144,
|
| 12543 |
+
"grad_norm": 0.49125760793685913,
|
| 12544 |
+
"learning_rate": 0.00019662271572015247,
|
| 12545 |
+
"loss": 0.8786,
|
| 12546 |
+
"step": 1791
|
| 12547 |
+
},
|
| 12548 |
+
{
|
| 12549 |
+
"epoch": 0.4159220146222583,
|
| 12550 |
+
"grad_norm": 0.6301273703575134,
|
| 12551 |
+
"learning_rate": 0.00019661895627666115,
|
| 12552 |
+
"loss": 0.8943,
|
| 12553 |
+
"step": 1792
|
| 12554 |
+
},
|
| 12555 |
+
{
|
| 12556 |
+
"epoch": 0.41615411396077523,
|
| 12557 |
+
"grad_norm": 0.5750293731689453,
|
| 12558 |
+
"learning_rate": 0.00019661519477789135,
|
| 12559 |
+
"loss": 0.8957,
|
| 12560 |
+
"step": 1793
|
| 12561 |
+
},
|
| 12562 |
+
{
|
| 12563 |
+
"epoch": 0.4163862132992921,
|
| 12564 |
+
"grad_norm": 0.5299922823905945,
|
| 12565 |
+
"learning_rate": 0.000196611431223923,
|
| 12566 |
+
"loss": 0.963,
|
| 12567 |
+
"step": 1794
|
| 12568 |
+
},
|
| 12569 |
+
{
|
| 12570 |
+
"epoch": 0.41661831263780896,
|
| 12571 |
+
"grad_norm": 0.7080173492431641,
|
| 12572 |
+
"learning_rate": 0.00019660766561483618,
|
| 12573 |
+
"loss": 0.9599,
|
| 12574 |
+
"step": 1795
|
| 12575 |
+
},
|
| 12576 |
+
{
|
| 12577 |
+
"epoch": 0.4168504119763259,
|
| 12578 |
+
"grad_norm": 0.5741339921951294,
|
| 12579 |
+
"learning_rate": 0.00019660389795071097,
|
| 12580 |
+
"loss": 0.941,
|
| 12581 |
+
"step": 1796
|
| 12582 |
+
},
|
| 12583 |
+
{
|
| 12584 |
+
"epoch": 0.41708251131484275,
|
| 12585 |
+
"grad_norm": 0.5957292318344116,
|
| 12586 |
+
"learning_rate": 0.00019660012823162755,
|
| 12587 |
+
"loss": 0.91,
|
| 12588 |
+
"step": 1797
|
| 12589 |
+
},
|
| 12590 |
+
{
|
| 12591 |
+
"epoch": 0.4173146106533596,
|
| 12592 |
+
"grad_norm": 0.5832741856575012,
|
| 12593 |
+
"learning_rate": 0.0001965963564576661,
|
| 12594 |
+
"loss": 0.9038,
|
| 12595 |
+
"step": 1798
|
| 12596 |
+
},
|
| 12597 |
+
{
|
| 12598 |
+
"epoch": 0.41754670999187654,
|
| 12599 |
+
"grad_norm": 0.613530158996582,
|
| 12600 |
+
"learning_rate": 0.00019659258262890683,
|
| 12601 |
+
"loss": 0.9392,
|
| 12602 |
+
"step": 1799
|
| 12603 |
+
},
|
| 12604 |
+
{
|
| 12605 |
+
"epoch": 0.4177788093303934,
|
| 12606 |
+
"grad_norm": 0.5645830631256104,
|
| 12607 |
+
"learning_rate": 0.00019658880674543004,
|
| 12608 |
+
"loss": 0.9393,
|
| 12609 |
+
"step": 1800
|
| 12610 |
}
|
| 12611 |
],
|
| 12612 |
"logging_steps": 1,
|
|
|
|
| 12626 |
"attributes": {}
|
| 12627 |
}
|
| 12628 |
},
|
| 12629 |
+
"total_flos": 7.989780893663232e+17,
|
| 12630 |
"train_batch_size": 32,
|
| 12631 |
"trial_name": null,
|
| 12632 |
"trial_params": null
|