Training in progress, step 500, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7208c157bd2ac962f1e99c369cb0c4c876c46f9afc991bf3b63ecbdeb7a9451
+oid sha256:63b1a741aef12c15963ba453b05ab5db82600bc551f2b0abdba0db986515581e
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89219edfec65d3aa4b90d0f832ecd4bdcaccf3fb4712a0ecc1d6aa59df467d31
+oid sha256:ca7904bad979c288a95b5544959e8198018d6b678ccb1bbd085c8a3715877659
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218e0453fc5fac64040aaa58fa4791344429b196d0614a5d47a8ced8ab243fbd
+oid sha256:7197d140fd83963b935a376f4d10c9844e833c8ece7825e56a537cd1f8c644af
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea63b051bfa35d181c72cf7a4031b815beb335450b676c5742615e4549578cc
+oid sha256:8ceaa8f446e2f8dcda19c36d8e6153becc6476783cafdca7111122aee2ef02e4
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3741d486e7c952b1a341a05fb90eba765009a4d3f18020238e7b68009c9da326
+oid sha256:dc2db39bbffdd11bfa5291372b42f5e65728cd913b180ab1985ed1b3a40873fe
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382acbbb9f17f8d91e02fc3fddf64bb6a49e850cb1fc32797ea1fbf54e0125e2
+oid sha256:0e3cc4c894c659d664488312db7958b2b28c1cb0b69e1b193236f71117586abc
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1a092ae0059ebd91bef6f7f601436ce9abc41aafec2fa8a545bee852694089
+oid sha256:c1da01c95902e73134a96dda0be8f77798bec60a53a1f2dbb08b7e4384991650
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f31511e4cde2c5c81396fbebe87a2d7e68df8c667e75ce7a54c611ba8c0c836
+oid sha256:56970e8db017cc28abe4f30ae5ecc2b1b0ca78752e49befac2699bb6e88ee3b2
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be19256dff191ced79d9c98d715eacb9c3bb35cd06f1653c0747f66c86d01864
+oid sha256:3d6628c12a9e847bd7b0ae41ef60b5411f45368fdb1098e87b82df12733ebc90
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e01d478ca490497da00bd323e06c108829d4b80dedf3047a04a89fd9f2c4d0
+oid sha256:3c7006e35aa389f7a9da3b0441e6946d07bdfe96c931f880353af9a6540dbecc
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875226841aae0e2dd86a6eec797ee90621017fae322602ac196fbcca572f45dc
+oid sha256:1fc8516280fb996848d161272211cec6b2fbaff18bd368f409c7ee2bb47862ee
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e846eaa578475e925de0df482a62461453c06206473a7bc362a5197d2f618af6
+oid sha256:22954ae1098f61d594e688048b08108dec1af0a05949920062dae9026ee41d19
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4313ca58a9a7e33eef3592d48644eb528c3538f041f445f8bd3e6ef60654dc2
+oid sha256:3f74cf2d94199da6c0c744e0a8fc5b249258fbfd3cbeeaf0782f20c5de466ce1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18961839298411945,
+  "epoch": 0.23702299123014933,
   "eval_steps": 20,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3059,6 +3059,766 @@
       "eval_samples_per_second": 5.399,
       "eval_steps_per_second": 0.179,
       "step": 400
+    },
+    {
+      "epoch": 0.19009243896657976,
+      "grad_norm": 4.189998626708984,
+      "learning_rate": 1.950954166447816e-05,
+      "loss": 0.2315,
+      "step": 401
+    },
+    {
+      "epoch": 0.19056648494904005,
+      "grad_norm": 7.759528636932373,
+      "learning_rate": 1.950440854222844e-05,
+      "loss": 0.1772,
+      "step": 402
+    },
+    {
+      "epoch": 0.19104053093150036,
+      "grad_norm": 3.0708417892456055,
+      "learning_rate": 1.9499249380497597e-05,
+      "loss": 0.1683,
+      "step": 403
+    },
+    {
+      "epoch": 0.19151457691396065,
+      "grad_norm": 6.50071907043457,
+      "learning_rate": 1.949406419342032e-05,
+      "loss": 0.2347,
+      "step": 404
+    },
+    {
+      "epoch": 0.19198862289642096,
+      "grad_norm": 7.221626281738281,
+      "learning_rate": 1.948885299520261e-05,
+      "loss": 0.2549,
+      "step": 405
+    },
+    {
+      "epoch": 0.19246266887888125,
+      "grad_norm": 2.5001566410064697,
+      "learning_rate": 1.9483615800121717e-05,
+      "loss": 0.099,
+      "step": 406
+    },
+    {
+      "epoch": 0.19293671486134156,
+      "grad_norm": 6.132114410400391,
+      "learning_rate": 1.947835262252613e-05,
+      "loss": 0.1272,
+      "step": 407
+    },
+    {
+      "epoch": 0.19341076084380185,
+      "grad_norm": 7.621204376220703,
+      "learning_rate": 1.9473063476835518e-05,
+      "loss": 0.1659,
+      "step": 408
+    },
+    {
+      "epoch": 0.19388480682626213,
+      "grad_norm": 5.252957820892334,
+      "learning_rate": 1.946774837754069e-05,
+      "loss": 0.1525,
+      "step": 409
+    },
+    {
+      "epoch": 0.19435885280872245,
+      "grad_norm": 6.265228271484375,
+      "learning_rate": 1.946240733920356e-05,
+      "loss": 0.304,
+      "step": 410
+    },
+    {
+      "epoch": 0.19483289879118273,
+      "grad_norm": 6.704779624938965,
+      "learning_rate": 1.945704037645713e-05,
+      "loss": 0.1892,
+      "step": 411
+    },
+    {
+      "epoch": 0.19530694477364305,
+      "grad_norm": 6.787877559661865,
+      "learning_rate": 1.9451647504005394e-05,
+      "loss": 0.2538,
+      "step": 412
+    },
+    {
+      "epoch": 0.19578099075610333,
+      "grad_norm": 3.9719345569610596,
+      "learning_rate": 1.9446228736623355e-05,
+      "loss": 0.1344,
+      "step": 413
+    },
+    {
+      "epoch": 0.19625503673856365,
+      "grad_norm": 5.928083896636963,
+      "learning_rate": 1.9440784089156955e-05,
+      "loss": 0.2413,
+      "step": 414
+    },
+    {
+      "epoch": 0.19672908272102393,
+      "grad_norm": 3.9046196937561035,
+      "learning_rate": 1.9435313576523037e-05,
+      "loss": 0.2113,
+      "step": 415
+    },
+    {
+      "epoch": 0.19720312870348425,
+      "grad_norm": 11.968066215515137,
+      "learning_rate": 1.942981721370931e-05,
+      "loss": 0.1943,
+      "step": 416
+    },
+    {
+      "epoch": 0.19767717468594453,
+      "grad_norm": 6.351183891296387,
+      "learning_rate": 1.942429501577431e-05,
+      "loss": 0.1533,
+      "step": 417
+    },
+    {
+      "epoch": 0.19815122066840485,
+      "grad_norm": 5.750969886779785,
+      "learning_rate": 1.9418746997847347e-05,
+      "loss": 0.2765,
+      "step": 418
+    },
+    {
+      "epoch": 0.19862526665086513,
+      "grad_norm": 5.9713850021362305,
+      "learning_rate": 1.9413173175128472e-05,
+      "loss": 0.1987,
+      "step": 419
+    },
+    {
+      "epoch": 0.19909931263332542,
+      "grad_norm": 4.042611122131348,
+      "learning_rate": 1.9407573562888437e-05,
+      "loss": 0.1442,
+      "step": 420
+    },
+    {
+      "epoch": 0.19909931263332542,
+      "eval_accuracy": 0.9855072463768116,
+      "eval_f1": 0.8448275862068966,
+      "eval_loss": 0.039507586508989334,
+      "eval_precision": 0.765625,
+      "eval_recall": 0.9423076923076923,
+      "eval_runtime": 48.9137,
+      "eval_samples_per_second": 5.54,
+      "eval_steps_per_second": 0.184,
+      "step": 420
+    },
+    {
+      "epoch": 0.19957335861578573,
+      "grad_norm": 5.3435282707214355,
+      "learning_rate": 1.9401948176468645e-05,
+      "loss": 0.2182,
+      "step": 421
+    },
+    {
+      "epoch": 0.20004740459824602,
+      "grad_norm": 7.2359747886657715,
+      "learning_rate": 1.9396297031281124e-05,
+      "loss": 0.2538,
+      "step": 422
+    },
+    {
+      "epoch": 0.20052145058070633,
+      "grad_norm": 4.870368480682373,
+      "learning_rate": 1.9390620142808462e-05,
+      "loss": 0.2151,
+      "step": 423
+    },
+    {
+      "epoch": 0.20099549656316662,
+      "grad_norm": 4.006406307220459,
+      "learning_rate": 1.9384917526603783e-05,
+      "loss": 0.254,
+      "step": 424
+    },
+    {
+      "epoch": 0.20146954254562693,
+      "grad_norm": 5.7069244384765625,
+      "learning_rate": 1.9379189198290697e-05,
+      "loss": 0.2183,
+      "step": 425
+    },
+    {
+      "epoch": 0.20194358852808722,
+      "grad_norm": 6.024723529815674,
+      "learning_rate": 1.9373435173563257e-05,
+      "loss": 0.2386,
+      "step": 426
+    },
+    {
+      "epoch": 0.20241763451054753,
+      "grad_norm": 9.129636764526367,
+      "learning_rate": 1.9367655468185913e-05,
+      "loss": 0.2554,
+      "step": 427
+    },
+    {
+      "epoch": 0.20289168049300782,
+      "grad_norm": 6.194615364074707,
+      "learning_rate": 1.9361850097993487e-05,
+      "loss": 0.2658,
+      "step": 428
+    },
+    {
+      "epoch": 0.20336572647546813,
+      "grad_norm": 8.10988712310791,
+      "learning_rate": 1.9356019078891098e-05,
+      "loss": 0.2046,
+      "step": 429
+    },
+    {
+      "epoch": 0.20383977245792842,
+      "grad_norm": 3.277400493621826,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.191,
+      "step": 430
+    },
+    {
+      "epoch": 0.2043138184403887,
+      "grad_norm": 4.1480278968811035,
+      "learning_rate": 1.9344280157928265e-05,
+      "loss": 0.1775,
+      "step": 431
+    },
+    {
+      "epoch": 0.20478786442284902,
+      "grad_norm": 5.914576530456543,
+      "learning_rate": 1.9338372288229253e-05,
+      "loss": 0.2799,
+      "step": 432
+    },
+    {
+      "epoch": 0.2052619104053093,
+      "grad_norm": 4.470582008361816,
+      "learning_rate": 1.9332438833943065e-05,
+      "loss": 0.144,
+      "step": 433
+    },
+    {
+      "epoch": 0.20573595638776962,
+      "grad_norm": 5.149271488189697,
+      "learning_rate": 1.9326479811325736e-05,
+      "loss": 0.1882,
+      "step": 434
+    },
+    {
+      "epoch": 0.2062100023702299,
+      "grad_norm": 5.199272632598877,
+      "learning_rate": 1.9320495236703366e-05,
+      "loss": 0.2096,
+      "step": 435
+    },
+    {
+      "epoch": 0.20668404835269022,
+      "grad_norm": 4.065655708312988,
+      "learning_rate": 1.931448512647205e-05,
+      "loss": 0.1786,
+      "step": 436
+    },
+    {
+      "epoch": 0.2071580943351505,
+      "grad_norm": 3.961599111557007,
+      "learning_rate": 1.9308449497097847e-05,
+      "loss": 0.1615,
+      "step": 437
+    },
+    {
+      "epoch": 0.20763214031761082,
+      "grad_norm": 3.985469341278076,
+      "learning_rate": 1.9302388365116734e-05,
+      "loss": 0.1311,
+      "step": 438
+    },
+    {
+      "epoch": 0.2081061863000711,
+      "grad_norm": 3.8260138034820557,
+      "learning_rate": 1.9296301747134555e-05,
+      "loss": 0.1956,
+      "step": 439
+    },
+    {
+      "epoch": 0.20858023228253142,
+      "grad_norm": 4.328072547912598,
+      "learning_rate": 1.9290189659826974e-05,
+      "loss": 0.1957,
+      "step": 440
+    },
+    {
+      "epoch": 0.20858023228253142,
+      "eval_accuracy": 0.9903381642512077,
+      "eval_f1": 0.8928571428571429,
+      "eval_loss": 0.03430945798754692,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 48.6442,
+      "eval_samples_per_second": 5.571,
+      "eval_steps_per_second": 0.185,
+      "step": 440
+    },
+    {
+      "epoch": 0.2090542782649917,
+      "grad_norm": 3.6678905487060547,
+      "learning_rate": 1.9284052119939448e-05,
+      "loss": 0.1329,
+      "step": 441
+    },
+    {
+      "epoch": 0.209528324247452,
+      "grad_norm": 3.7596359252929688,
+      "learning_rate": 1.927788914428715e-05,
+      "loss": 0.1907,
+      "step": 442
+    },
+    {
+      "epoch": 0.2100023702299123,
+      "grad_norm": 4.306353569030762,
+      "learning_rate": 1.9271700749754954e-05,
+      "loss": 0.1437,
+      "step": 443
+    },
+    {
+      "epoch": 0.2104764162123726,
+      "grad_norm": 6.4847636222839355,
+      "learning_rate": 1.9265486953297373e-05,
+      "loss": 0.1889,
+      "step": 444
+    },
+    {
+      "epoch": 0.2109504621948329,
+      "grad_norm": 7.348166465759277,
+      "learning_rate": 1.92592477719385e-05,
+      "loss": 0.1978,
+      "step": 445
+    },
+    {
+      "epoch": 0.2114245081772932,
+      "grad_norm": 7.6974873542785645,
+      "learning_rate": 1.9252983222771996e-05,
+      "loss": 0.296,
+      "step": 446
+    },
+    {
+      "epoch": 0.2118985541597535,
+      "grad_norm": 5.88078498840332,
+      "learning_rate": 1.9246693322961002e-05,
+      "loss": 0.1981,
+      "step": 447
+    },
+    {
+      "epoch": 0.2123726001422138,
+      "grad_norm": 6.422124862670898,
+      "learning_rate": 1.9240378089738136e-05,
+      "loss": 0.1393,
+      "step": 448
+    },
+    {
+      "epoch": 0.2128466461246741,
+      "grad_norm": 6.030878067016602,
+      "learning_rate": 1.9234037540405405e-05,
+      "loss": 0.1384,
+      "step": 449
+    },
+    {
+      "epoch": 0.2133206921071344,
+      "grad_norm": 7.562985897064209,
+      "learning_rate": 1.922767169233418e-05,
+      "loss": 0.1907,
+      "step": 450
+    },
+    {
+      "epoch": 0.21379473808959468,
+      "grad_norm": 6.239231586456299,
+      "learning_rate": 1.9221280562965145e-05,
+      "loss": 0.1804,
+      "step": 451
+    },
+    {
+      "epoch": 0.214268784072055,
+      "grad_norm": 6.161927223205566,
+      "learning_rate": 1.9214864169808252e-05,
+      "loss": 0.1156,
+      "step": 452
+    },
+    {
+      "epoch": 0.21474283005451528,
+      "grad_norm": 10.836844444274902,
+      "learning_rate": 1.9208422530442658e-05,
+      "loss": 0.3175,
+      "step": 453
+    },
+    {
+      "epoch": 0.2152168760369756,
+      "grad_norm": 6.956441402435303,
+      "learning_rate": 1.9201955662516693e-05,
+      "loss": 0.1713,
+      "step": 454
+    },
+    {
+      "epoch": 0.21569092201943588,
+      "grad_norm": 5.461636543273926,
+      "learning_rate": 1.9195463583747814e-05,
+      "loss": 0.1354,
+      "step": 455
+    },
+    {
+      "epoch": 0.2161649680018962,
+      "grad_norm": 5.017518997192383,
+      "learning_rate": 1.9188946311922537e-05,
+      "loss": 0.2034,
+      "step": 456
+    },
+    {
+      "epoch": 0.21663901398435648,
+      "grad_norm": 4.602156162261963,
+      "learning_rate": 1.9182403864896407e-05,
+      "loss": 0.1813,
+      "step": 457
+    },
+    {
+      "epoch": 0.2171130599668168,
+      "grad_norm": 5.34616231918335,
+      "learning_rate": 1.9175836260593937e-05,
+      "loss": 0.1929,
+      "step": 458
+    },
+    {
+      "epoch": 0.21758710594927708,
+      "grad_norm": 6.494266986846924,
+      "learning_rate": 1.9169243517008572e-05,
+      "loss": 0.2436,
+      "step": 459
+    },
+    {
+      "epoch": 0.2180611519317374,
+      "grad_norm": 10.610939979553223,
+      "learning_rate": 1.916262565220263e-05,
+      "loss": 0.2593,
+      "step": 460
+    },
+    {
+      "epoch": 0.2180611519317374,
+      "eval_accuracy": 0.9919484702093397,
+      "eval_f1": 0.9074074074074074,
+      "eval_loss": 0.03075222112238407,
+      "eval_precision": 0.875,
+      "eval_recall": 0.9423076923076923,
+      "eval_runtime": 47.9054,
+      "eval_samples_per_second": 5.657,
+      "eval_steps_per_second": 0.188,
+      "step": 460
+    },
+    {
+      "epoch": 0.21853519791419768,
+      "grad_norm": 5.9074788093566895,
+      "learning_rate": 1.915598268430724e-05,
+      "loss": 0.153,
+      "step": 461
+    },
+    {
+      "epoch": 0.21900924389665796,
+      "grad_norm": 3.602909803390503,
+      "learning_rate": 1.9149314631522325e-05,
+      "loss": 0.1545,
+      "step": 462
+    },
+    {
+      "epoch": 0.21948328987911828,
+      "grad_norm": 4.433838844299316,
+      "learning_rate": 1.914262151211653e-05,
+      "loss": 0.1526,
+      "step": 463
+    },
+    {
+      "epoch": 0.21995733586157856,
+      "grad_norm": 8.290746688842773,
+      "learning_rate": 1.9135903344427163e-05,
+      "loss": 0.1552,
+      "step": 464
+    },
+    {
+      "epoch": 0.22043138184403888,
+      "grad_norm": 13.321844100952148,
+      "learning_rate": 1.912916014686018e-05,
+      "loss": 0.2367,
+      "step": 465
+    },
+    {
+      "epoch": 0.22090542782649916,
+      "grad_norm": 6.072572708129883,
+      "learning_rate": 1.912239193789009e-05,
+      "loss": 0.2007,
+      "step": 466
+    },
+    {
+      "epoch": 0.22137947380895948,
+      "grad_norm": 3.8708927631378174,
+      "learning_rate": 1.9115598736059934e-05,
+      "loss": 0.1375,
+      "step": 467
+    },
+    {
+      "epoch": 0.22185351979141976,
+      "grad_norm": 4.0472092628479,
+      "learning_rate": 1.910878055998123e-05,
+      "loss": 0.1327,
+      "step": 468
+    },
+    {
+      "epoch": 0.22232756577388008,
+      "grad_norm": 4.479143142700195,
+      "learning_rate": 1.9101937428333918e-05,
+      "loss": 0.1913,
+      "step": 469
+    },
+    {
+      "epoch": 0.22280161175634036,
+      "grad_norm": 4.356966495513916,
+      "learning_rate": 1.909506935986631e-05,
+      "loss": 0.1698,
+      "step": 470
+    },
+    {
+      "epoch": 0.22327565773880068,
+      "grad_norm": 7.67513370513916,
+      "learning_rate": 1.908817637339503e-05,
+      "loss": 0.2444,
+      "step": 471
+    },
+    {
+      "epoch": 0.22374970372126096,
+      "grad_norm": 6.602683067321777,
+      "learning_rate": 1.908125848780498e-05,
+      "loss": 0.2005,
+      "step": 472
+    },
+    {
+      "epoch": 0.22422374970372125,
+      "grad_norm": 10.097046852111816,
+      "learning_rate": 1.9074315722049278e-05,
+      "loss": 0.2625,
+      "step": 473
+    },
+    {
+      "epoch": 0.22469779568618156,
+      "grad_norm": 9.88956069946289,
+      "learning_rate": 1.90673480951492e-05,
+      "loss": 0.2045,
+      "step": 474
+    },
+    {
+      "epoch": 0.22517184166864185,
+      "grad_norm": 6.545369625091553,
+      "learning_rate": 1.906035562619414e-05,
+      "loss": 0.1933,
+      "step": 475
+    },
+    {
+      "epoch": 0.22564588765110216,
+      "grad_norm": 5.960228443145752,
+      "learning_rate": 1.9053338334341553e-05,
+      "loss": 0.1812,
+      "step": 476
+    },
+    {
+      "epoch": 0.22611993363356245,
+      "grad_norm": 6.84769868850708,
+      "learning_rate": 1.90462962388169e-05,
+      "loss": 0.2436,
+      "step": 477
+    },
+    {
+      "epoch": 0.22659397961602276,
+      "grad_norm": 5.503833770751953,
+      "learning_rate": 1.9039229358913594e-05,
+      "loss": 0.192,
+      "step": 478
+    },
+    {
+      "epoch": 0.22706802559848305,
+      "grad_norm": 4.82657527923584,
+      "learning_rate": 1.9032137713992957e-05,
+      "loss": 0.1775,
+      "step": 479
+    },
+    {
+      "epoch": 0.22754207158094336,
+      "grad_norm": 3.190770387649536,
+      "learning_rate": 1.9025021323484155e-05,
+      "loss": 0.1137,
+      "step": 480
+    },
+    {
+      "epoch": 0.22754207158094336,
+      "eval_accuracy": 0.9935587761674718,
+      "eval_f1": 0.9259259259259259,
+      "eval_loss": 0.023625820875167847,
+      "eval_precision": 0.8928571428571429,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 48.7682,
+      "eval_samples_per_second": 5.557,
+      "eval_steps_per_second": 0.185,
+      "step": 480
+    },
+    {
+      "epoch": 0.22801611756340365,
+      "grad_norm": 5.586182594299316,
+      "learning_rate": 1.9017880206884157e-05,
+      "loss": 0.257,
+      "step": 481
+    },
+    {
+      "epoch": 0.22849016354586396,
+      "grad_norm": 13.091703414916992,
+      "learning_rate": 1.9010714383757668e-05,
+      "loss": 0.2785,
+      "step": 482
+    },
+    {
+      "epoch": 0.22896420952832425,
+      "grad_norm": 5.211515426635742,
+      "learning_rate": 1.9003523873737082e-05,
+      "loss": 0.1478,
+      "step": 483
+    },
+    {
+      "epoch": 0.22943825551078453,
+      "grad_norm": 3.8805530071258545,
+      "learning_rate": 1.8996308696522435e-05,
+      "loss": 0.1164,
+      "step": 484
+    },
+    {
+      "epoch": 0.22991230149324485,
+      "grad_norm": 5.7906293869018555,
+      "learning_rate": 1.8989068871881336e-05,
+      "loss": 0.1905,
+      "step": 485
+    },
+    {
+      "epoch": 0.23038634747570513,
+      "grad_norm": 3.8140764236450195,
+      "learning_rate": 1.898180441964893e-05,
+      "loss": 0.2113,
+      "step": 486
+    },
+    {
+      "epoch": 0.23086039345816545,
+      "grad_norm": 2.9873130321502686,
+      "learning_rate": 1.897451535972783e-05,
+      "loss": 0.1156,
+      "step": 487
+    },
+    {
+      "epoch": 0.23133443944062573,
+      "grad_norm": 4.1001505851745605,
+      "learning_rate": 1.8967201712088056e-05,
+      "loss": 0.1476,
+      "step": 488
+    },
+    {
+      "epoch": 0.23180848542308605,
+      "grad_norm": 4.187485694885254,
+      "learning_rate": 1.8959863496767022e-05,
+      "loss": 0.1837,
+      "step": 489
+    },
+    {
+      "epoch": 0.23228253140554633,
+      "grad_norm": 7.173356533050537,
+      "learning_rate": 1.8952500733869415e-05,
+      "loss": 0.2964,
+      "step": 490
+    },
+    {
+      "epoch": 0.23275657738800665,
+      "grad_norm": 7.43308162689209,
+      "learning_rate": 1.8945113443567202e-05,
+      "loss": 0.2136,
+      "step": 491
+    },
+    {
+      "epoch": 0.23323062337046693,
+      "grad_norm": 4.697380542755127,
+      "learning_rate": 1.8937701646099537e-05,
+      "loss": 0.1953,
+      "step": 492
+    },
+    {
+      "epoch": 0.23370466935292725,
+      "grad_norm": 2.4572548866271973,
+      "learning_rate": 1.893026536177272e-05,
+      "loss": 0.1506,
+      "step": 493
+    },
+    {
+      "epoch": 0.23417871533538753,
+      "grad_norm": 9.078280448913574,
+      "learning_rate": 1.8922804610960134e-05,
+      "loss": 0.2009,
+      "step": 494
+    },
+    {
+      "epoch": 0.23465276131784782,
+      "grad_norm": 3.59165620803833,
+      "learning_rate": 1.8915319414102197e-05,
+      "loss": 0.1611,
+      "step": 495
+    },
+    {
+      "epoch": 0.23512680730030813,
+      "grad_norm": 3.31412935256958,
+      "learning_rate": 1.8907809791706304e-05,
+      "loss": 0.1465,
+      "step": 496
+    },
+    {
+      "epoch": 0.23560085328276842,
+      "grad_norm": 4.140017986297607,
+      "learning_rate": 1.890027576434677e-05,
+      "loss": 0.1957,
+      "step": 497
+    },
+    {
+      "epoch": 0.23607489926522873,
+      "grad_norm": 7.067059516906738,
+      "learning_rate": 1.8892717352664762e-05,
+      "loss": 0.2505,
+      "step": 498
+    },
+    {
+      "epoch": 0.23654894524768902,
+      "grad_norm": 4.36193323135376,
+      "learning_rate": 1.8885134577368268e-05,
+      "loss": 0.1392,
+      "step": 499
+    },
+    {
+      "epoch": 0.23702299123014933,
+      "grad_norm": 5.218912124633789,
+      "learning_rate": 1.887752745923202e-05,
+      "loss": 0.2213,
+      "step": 500
+    },
+    {
+      "epoch": 0.23702299123014933,
+      "eval_accuracy": 0.9879227053140096,
+      "eval_f1": 0.8717948717948718,
+      "eval_loss": 0.02638288587331772,
+      "eval_precision": 0.7846153846153846,
+      "eval_recall": 0.9807692307692307,
+      "eval_runtime": 50.0425,
+      "eval_samples_per_second": 5.415,
+      "eval_steps_per_second": 0.18,
+      "step": 500
     }
   ],
   "logging_steps": 1,
@@ -3078,7 +3838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0657465288045363e+17,
+  "total_flos": 1.3338310337993114e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null