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:f1b6729e5ec442a789c5534de429bbdd6ad74a54d5ab148d14bedb4c23a8a93c
+oid sha256:4f4e1f5f1b463bbf7a2ef4d4af3eb26c728852abec7c6787de609ac33d09a95c
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3904e43332132ff406e596c21aff0aea66547b88a808d0b93bd70992806b298f
+oid sha256:90a4eef445695e00c0448191c471e20fc90fac55088f64ebc374faeb67378993
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f709b6b535d116a4c507da712164b2a513083e086ddbad328209690c3c4d840f
+oid sha256:c69c54a9cccf4257b34f1b979d5d539b31b5218794be3960611b7d2d897e994a
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8558d307d1f88b1327b3b2f17ea6c2f66defc8bd2c42208a49d3340fa5c0ff3d
+oid sha256:3ed25b5e3653278282ac873c3af5310841446a9e13773d544889afce31024bcb
 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:a5bbd86757f6d90709e53c4bee410c64f46e1e00a7b69516495436b3b19fa4bc
+oid sha256:39de24dbe6f2f3a1b4e34daf6b8e7473a3a38ea40a91769099a82e8f4ebd1d0b
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927e5715a176e36583234bf60605473a6e6ee212a6ae9002c13b90bbdbfa2413
+oid sha256:98fb28188ad6ed7eb480ef9e981c73e6e5e156423f75a203ab35ebe4c0ee7122
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803c82bb739590694cf28b3c107b771168530366a9df3d0d35a186cd19f75ac8
+oid sha256:a8f0f9b2d5716e1b93fa3c48662c835a10bad645dcd88050a14008f0e7777a56
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d742b4fad568eaa03fc2dc329d88c7eed505e69160db904dc9c312d372f1582
+oid sha256:3a1a3d5f6e07161b2ee73578e4b8d161f40891058e3f83f813289b5c369f350a
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b534588f047199495c247b01b639a4ec3dd05f1cd5d046f973172fb1baf268d
+oid sha256:9c0996004e3280ba2b8c5308142e245e93b9a3d5870de383914360145085a647
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a128bd654cc64f4756f3ca659f2e594694372fb259352d497e7af42c47bdf834
+oid sha256:5b99dae60d08ae089466b878474ef297a0b281547cd1097ea214ecee77244b16
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7e301223140cc7be084a97964d668a32053ebf50ebcb22fe5f6447769a9865
+oid sha256:7c3acfb47638e30fe1106672a6fd0db74c9187c94c19467e9d22bd366fbb5472
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f114cbbab4db7dbcae3790f915ff92c38c1bdffe548e2426dc312a0c4340440f
+oid sha256:9723827a668573edbd596a65e0f225b208491adf853284b8da3f11b792077fdc
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88a4ccf03a33f28d34c318afb486939b571f6edba4a67537bf973b4e8c4ed91
+oid sha256:9a124d1e9d8a7b4a76d7294be394802bfec19da05b0209e12c8dc6b8ab250293
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5154639175257731,
+  "epoch": 0.6443298969072165,
   "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": 5.398,
       "eval_steps_per_second": 0.178,
       "step": 400
+    },
+    {
+      "epoch": 0.5167525773195877,
+      "grad_norm": 1.0079818964004517,
+      "learning_rate": 1.1167551721113435e-05,
+      "loss": 0.0049,
+      "step": 401
+    },
+    {
+      "epoch": 0.5180412371134021,
+      "grad_norm": 0.5026824474334717,
+      "learning_rate": 1.1122839380745738e-05,
+      "loss": 0.0034,
+      "step": 402
+    },
+    {
+      "epoch": 0.5193298969072165,
+      "grad_norm": 0.251522421836853,
+      "learning_rate": 1.1078104294337806e-05,
+      "loss": 0.0016,
+      "step": 403
+    },
+    {
+      "epoch": 0.520618556701031,
+      "grad_norm": 0.2365703135728836,
+      "learning_rate": 1.1033347368115494e-05,
+      "loss": 0.0008,
+      "step": 404
+    },
+    {
+      "epoch": 0.5219072164948454,
+      "grad_norm": 0.3773232400417328,
+      "learning_rate": 1.0988569508747075e-05,
+      "loss": 0.0018,
+      "step": 405
+    },
+    {
+      "epoch": 0.5231958762886598,
+      "grad_norm": 1.486518383026123,
+      "learning_rate": 1.0943771623324884e-05,
+      "loss": 0.0276,
+      "step": 406
+    },
+    {
+      "epoch": 0.5244845360824743,
+      "grad_norm": 0.07446420192718506,
+      "learning_rate": 1.0898954619346924e-05,
+      "loss": 0.0008,
+      "step": 407
+    },
+    {
+      "epoch": 0.5257731958762887,
+      "grad_norm": 0.12031542509794235,
+      "learning_rate": 1.085411940469851e-05,
+      "loss": 0.0012,
+      "step": 408
+    },
+    {
+      "epoch": 0.5270618556701031,
+      "grad_norm": 0.2832430601119995,
+      "learning_rate": 1.0809266887633849e-05,
+      "loss": 0.0009,
+      "step": 409
+    },
+    {
+      "epoch": 0.5283505154639175,
+      "grad_norm": 0.21104812622070312,
+      "learning_rate": 1.0764397976757658e-05,
+      "loss": 0.0028,
+      "step": 410
+    },
+    {
+      "epoch": 0.529639175257732,
+      "grad_norm": 2.558060884475708,
+      "learning_rate": 1.0719513581006751e-05,
+      "loss": 0.018,
+      "step": 411
+    },
+    {
+      "epoch": 0.5309278350515464,
+      "grad_norm": 0.1067991852760315,
+      "learning_rate": 1.0674614609631634e-05,
+      "loss": 0.0004,
+      "step": 412
+    },
+    {
+      "epoch": 0.5322164948453608,
+      "grad_norm": 1.812943935394287,
+      "learning_rate": 1.062970197217808e-05,
+      "loss": 0.0152,
+      "step": 413
+    },
+    {
+      "epoch": 0.5335051546391752,
+      "grad_norm": 1.7201879024505615,
+      "learning_rate": 1.0584776578468698e-05,
+      "loss": 0.0071,
+      "step": 414
+    },
+    {
+      "epoch": 0.5347938144329897,
+      "grad_norm": 0.17433598637580872,
+      "learning_rate": 1.0539839338584509e-05,
+      "loss": 0.0017,
+      "step": 415
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 1.8511940240859985,
+      "learning_rate": 1.0494891162846515e-05,
+      "loss": 0.0036,
+      "step": 416
+    },
+    {
+      "epoch": 0.5373711340206185,
+      "grad_norm": 0.22043751180171967,
+      "learning_rate": 1.0449932961797249e-05,
+      "loss": 0.0014,
+      "step": 417
+    },
+    {
+      "epoch": 0.538659793814433,
+      "grad_norm": 4.1709370613098145,
+      "learning_rate": 1.040496564618233e-05,
+      "loss": 0.0426,
+      "step": 418
+    },
+    {
+      "epoch": 0.5399484536082474,
+      "grad_norm": 2.242624282836914,
+      "learning_rate": 1.0359990126932022e-05,
+      "loss": 0.0141,
+      "step": 419
+    },
+    {
+      "epoch": 0.5412371134020618,
+      "grad_norm": 0.7744148969650269,
+      "learning_rate": 1.0315007315142772e-05,
+      "loss": 0.0028,
+      "step": 420
+    },
+    {
+      "epoch": 0.5412371134020618,
+      "eval_accuracy": 0.9965243296921549,
+      "eval_f1": 0.9391304347826087,
+      "eval_loss": 0.01408898364752531,
+      "eval_precision": 0.9310344827586207,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.4124,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.18,
+      "step": 420
+    },
+    {
+      "epoch": 0.5425257731958762,
+      "grad_norm": 2.3163211345672607,
+      "learning_rate": 1.0270018122058753e-05,
+      "loss": 0.0163,
+      "step": 421
+    },
+    {
+      "epoch": 0.5438144329896907,
+      "grad_norm": 0.7905238270759583,
+      "learning_rate": 1.0225023459053416e-05,
+      "loss": 0.0029,
+      "step": 422
+    },
+    {
+      "epoch": 0.5451030927835051,
+      "grad_norm": 1.9856590032577515,
+      "learning_rate": 1.018002423761101e-05,
+      "loss": 0.0499,
+      "step": 423
+    },
+    {
+      "epoch": 0.5463917525773195,
+      "grad_norm": 0.17007720470428467,
+      "learning_rate": 1.0135021369308138e-05,
+      "loss": 0.0009,
+      "step": 424
+    },
+    {
+      "epoch": 0.5476804123711341,
+      "grad_norm": 0.5280592441558838,
+      "learning_rate": 1.0090015765795265e-05,
+      "loss": 0.0031,
+      "step": 425
+    },
+    {
+      "epoch": 0.5489690721649485,
+      "grad_norm": 1.507529616355896,
+      "learning_rate": 1.004500833877828e-05,
+      "loss": 0.0333,
+      "step": 426
+    },
+    {
+      "epoch": 0.5502577319587629,
+      "grad_norm": 3.355781316757202,
+      "learning_rate": 1e-05,
+      "loss": 0.0136,
+      "step": 427
+    },
+    {
+      "epoch": 0.5515463917525774,
+      "grad_norm": 2.624476909637451,
+      "learning_rate": 9.954991661221724e-06,
+      "loss": 0.0115,
+      "step": 428
+    },
+    {
+      "epoch": 0.5528350515463918,
+      "grad_norm": 1.1731654405593872,
+      "learning_rate": 9.909984234204738e-06,
+      "loss": 0.0029,
+      "step": 429
+    },
+    {
+      "epoch": 0.5541237113402062,
+      "grad_norm": 0.35924506187438965,
+      "learning_rate": 9.864978630691865e-06,
+      "loss": 0.0023,
+      "step": 430
+    },
+    {
+      "epoch": 0.5554123711340206,
+      "grad_norm": 0.4166584610939026,
+      "learning_rate": 9.819975762388993e-06,
+      "loss": 0.0023,
+      "step": 431
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 1.3430147171020508,
+      "learning_rate": 9.774976540946589e-06,
+      "loss": 0.022,
+      "step": 432
+    },
+    {
+      "epoch": 0.5579896907216495,
+      "grad_norm": 1.9612890481948853,
+      "learning_rate": 9.729981877941249e-06,
+      "loss": 0.0268,
+      "step": 433
+    },
+    {
+      "epoch": 0.5592783505154639,
+      "grad_norm": 1.5633459091186523,
+      "learning_rate": 9.684992684857232e-06,
+      "loss": 0.0058,
+      "step": 434
+    },
+    {
+      "epoch": 0.5605670103092784,
+      "grad_norm": 1.8824856281280518,
+      "learning_rate": 9.640009873067981e-06,
+      "loss": 0.0161,
+      "step": 435
+    },
+    {
+      "epoch": 0.5618556701030928,
+      "grad_norm": 0.3390294015407562,
+      "learning_rate": 9.595034353817673e-06,
+      "loss": 0.0011,
+      "step": 436
+    },
+    {
+      "epoch": 0.5631443298969072,
+      "grad_norm": 1.143394947052002,
+      "learning_rate": 9.550067038202756e-06,
+      "loss": 0.0032,
+      "step": 437
+    },
+    {
+      "epoch": 0.5644329896907216,
+      "grad_norm": 1.6857935190200806,
+      "learning_rate": 9.505108837153489e-06,
+      "loss": 0.0161,
+      "step": 438
+    },
+    {
+      "epoch": 0.5657216494845361,
+      "grad_norm": 0.44908684492111206,
+      "learning_rate": 9.460160661415496e-06,
+      "loss": 0.0027,
+      "step": 439
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 0.46384885907173157,
+      "learning_rate": 9.415223421531308e-06,
+      "loss": 0.0035,
+      "step": 440
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "eval_accuracy": 0.9960278053624627,
+      "eval_f1": 0.9272727272727272,
+      "eval_loss": 0.014668312855064869,
+      "eval_precision": 0.9622641509433962,
+      "eval_recall": 0.8947368421052632,
+      "eval_runtime": 85.42,
+      "eval_samples_per_second": 5.327,
+      "eval_steps_per_second": 0.176,
+      "step": 440
+    },
+    {
+      "epoch": 0.5682989690721649,
+      "grad_norm": 0.303989052772522,
+      "learning_rate": 9.370298027821924e-06,
+      "loss": 0.0011,
+      "step": 441
+    },
+    {
+      "epoch": 0.5695876288659794,
+      "grad_norm": 1.179250717163086,
+      "learning_rate": 9.325385390368367e-06,
+      "loss": 0.0108,
+      "step": 442
+    },
+    {
+      "epoch": 0.5708762886597938,
+      "grad_norm": 0.0955902561545372,
+      "learning_rate": 9.280486418993254e-06,
+      "loss": 0.0008,
+      "step": 443
+    },
+    {
+      "epoch": 0.5721649484536082,
+      "grad_norm": 4.412278175354004,
+      "learning_rate": 9.23560202324235e-06,
+      "loss": 0.0331,
+      "step": 444
+    },
+    {
+      "epoch": 0.5734536082474226,
+      "grad_norm": 0.4738692045211792,
+      "learning_rate": 9.190733112366158e-06,
+      "loss": 0.0024,
+      "step": 445
+    },
+    {
+      "epoch": 0.5747422680412371,
+      "grad_norm": 1.4232240915298462,
+      "learning_rate": 9.145880595301495e-06,
+      "loss": 0.0095,
+      "step": 446
+    },
+    {
+      "epoch": 0.5760309278350515,
+      "grad_norm": 1.06927490234375,
+      "learning_rate": 9.101045380653076e-06,
+      "loss": 0.0038,
+      "step": 447
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 1.7943761348724365,
+      "learning_rate": 9.056228376675118e-06,
+      "loss": 0.0181,
+      "step": 448
+    },
+    {
+      "epoch": 0.5786082474226805,
+      "grad_norm": 0.47978296875953674,
+      "learning_rate": 9.011430491252924e-06,
+      "loss": 0.0019,
+      "step": 449
+    },
+    {
+      "epoch": 0.5798969072164949,
+      "grad_norm": 2.006948947906494,
+      "learning_rate": 8.966652631884506e-06,
+      "loss": 0.0152,
+      "step": 450
+    },
+    {
+      "epoch": 0.5811855670103093,
+      "grad_norm": 0.14350372552871704,
+      "learning_rate": 8.921895705662194e-06,
+      "loss": 0.0009,
+      "step": 451
+    },
+    {
+      "epoch": 0.5824742268041238,
+      "grad_norm": 1.1150081157684326,
+      "learning_rate": 8.877160619254264e-06,
+      "loss": 0.0036,
+      "step": 452
+    },
+    {
+      "epoch": 0.5837628865979382,
+      "grad_norm": 0.7745972275733948,
+      "learning_rate": 8.832448278886567e-06,
+      "loss": 0.0061,
+      "step": 453
+    },
+    {
+      "epoch": 0.5850515463917526,
+      "grad_norm": 0.15023173391819,
+      "learning_rate": 8.787759590324177e-06,
+      "loss": 0.0008,
+      "step": 454
+    },
+    {
+      "epoch": 0.586340206185567,
+      "grad_norm": 0.15638376772403717,
+      "learning_rate": 8.743095458853034e-06,
+      "loss": 0.0015,
+      "step": 455
+    },
+    {
+      "epoch": 0.5876288659793815,
+      "grad_norm": 0.8829141855239868,
+      "learning_rate": 8.698456789261617e-06,
+      "loss": 0.0047,
+      "step": 456
+    },
+    {
+      "epoch": 0.5889175257731959,
+      "grad_norm": 0.13397619128227234,
+      "learning_rate": 8.653844485822603e-06,
+      "loss": 0.0008,
+      "step": 457
+    },
+    {
+      "epoch": 0.5902061855670103,
+      "grad_norm": 0.54257732629776,
+      "learning_rate": 8.609259452274559e-06,
+      "loss": 0.0015,
+      "step": 458
+    },
+    {
+      "epoch": 0.5914948453608248,
+      "grad_norm": 3.111884832382202,
+      "learning_rate": 8.56470259180362e-06,
+      "loss": 0.0354,
+      "step": 459
+    },
+    {
+      "epoch": 0.5927835051546392,
+      "grad_norm": 0.41738268733024597,
+      "learning_rate": 8.52017480702521e-06,
+      "loss": 0.0016,
+      "step": 460
+    },
+    {
+      "epoch": 0.5927835051546392,
+      "eval_accuracy": 0.9965243296921549,
+      "eval_f1": 0.9357798165137615,
+      "eval_loss": 0.01587463542819023,
+      "eval_precision": 0.9807692307692307,
+      "eval_recall": 0.8947368421052632,
+      "eval_runtime": 84.0121,
+      "eval_samples_per_second": 5.416,
+      "eval_steps_per_second": 0.179,
+      "step": 460
+    },
+    {
+      "epoch": 0.5940721649484536,
+      "grad_norm": 1.6076654195785522,
+      "learning_rate": 8.475676999965747e-06,
+      "loss": 0.0089,
+      "step": 461
+    },
+    {
+      "epoch": 0.595360824742268,
+      "grad_norm": 0.16697372496128082,
+      "learning_rate": 8.431210072044371e-06,
+      "loss": 0.0007,
+      "step": 462
+    },
+    {
+      "epoch": 0.5966494845360825,
+      "grad_norm": 1.6268433332443237,
+      "learning_rate": 8.386774924054686e-06,
+      "loss": 0.0048,
+      "step": 463
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 1.5314583778381348,
+      "learning_rate": 8.342372456146512e-06,
+      "loss": 0.0074,
+      "step": 464
+    },
+    {
+      "epoch": 0.5992268041237113,
+      "grad_norm": 2.308037519454956,
+      "learning_rate": 8.29800356780764e-06,
+      "loss": 0.0105,
+      "step": 465
+    },
+    {
+      "epoch": 0.6005154639175257,
+      "grad_norm": 0.43206554651260376,
+      "learning_rate": 8.253669157845632e-06,
+      "loss": 0.0025,
+      "step": 466
+    },
+    {
+      "epoch": 0.6018041237113402,
+      "grad_norm": 2.582341194152832,
+      "learning_rate": 8.20937012436959e-06,
+      "loss": 0.0118,
+      "step": 467
+    },
+    {
+      "epoch": 0.6030927835051546,
+      "grad_norm": 0.5174412727355957,
+      "learning_rate": 8.165107364771979e-06,
+      "loss": 0.0015,
+      "step": 468
+    },
+    {
+      "epoch": 0.604381443298969,
+      "grad_norm": 1.751904845237732,
+      "learning_rate": 8.12088177571044e-06,
+      "loss": 0.0129,
+      "step": 469
+    },
+    {
+      "epoch": 0.6056701030927835,
+      "grad_norm": 0.601997435092926,
+      "learning_rate": 8.076694253089632e-06,
+      "loss": 0.0025,
+      "step": 470
+    },
+    {
+      "epoch": 0.6069587628865979,
+      "grad_norm": 0.21518899500370026,
+      "learning_rate": 8.032545692043068e-06,
+      "loss": 0.0007,
+      "step": 471
+    },
+    {
+      "epoch": 0.6082474226804123,
+      "grad_norm": 0.23358668386936188,
+      "learning_rate": 7.988436986915005e-06,
+      "loss": 0.0016,
+      "step": 472
+    },
+    {
+      "epoch": 0.6095360824742269,
+      "grad_norm": 1.7518439292907715,
+      "learning_rate": 7.944369031242307e-06,
+      "loss": 0.0363,
+      "step": 473
+    },
+    {
+      "epoch": 0.6108247422680413,
+      "grad_norm": 0.2232217937707901,
+      "learning_rate": 7.900342717736354e-06,
+      "loss": 0.0022,
+      "step": 474
+    },
+    {
+      "epoch": 0.6121134020618557,
+      "grad_norm": 0.07207631319761276,
+      "learning_rate": 7.856358938264953e-06,
+      "loss": 0.0004,
+      "step": 475
+    },
+    {
+      "epoch": 0.6134020618556701,
+      "grad_norm": 3.338632822036743,
+      "learning_rate": 7.812418583834282e-06,
+      "loss": 0.0105,
+      "step": 476
+    },
+    {
+      "epoch": 0.6146907216494846,
+      "grad_norm": 0.6013636589050293,
+      "learning_rate": 7.768522544570818e-06,
+      "loss": 0.0021,
+      "step": 477
+    },
+    {
+      "epoch": 0.615979381443299,
+      "grad_norm": 1.2868963479995728,
+      "learning_rate": 7.724671709703328e-06,
+      "loss": 0.0131,
+      "step": 478
+    },
+    {
+      "epoch": 0.6172680412371134,
+      "grad_norm": 1.118053913116455,
+      "learning_rate": 7.680866967544841e-06,
+      "loss": 0.0023,
+      "step": 479
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 3.8270020484924316,
+      "learning_rate": 7.637109205474665e-06,
+      "loss": 0.0262,
+      "step": 480
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "eval_accuracy": 0.997020854021847,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.01405768096446991,
+      "eval_precision": 0.9473684210526315,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 83.4682,
+      "eval_samples_per_second": 5.451,
+      "eval_steps_per_second": 0.18,
+      "step": 480
+    },
+    {
+      "epoch": 0.6198453608247423,
+      "grad_norm": 4.576198577880859,
+      "learning_rate": 7.5933993099203936e-06,
+      "loss": 0.0198,
+      "step": 481
+    },
+    {
+      "epoch": 0.6211340206185567,
+      "grad_norm": 1.4137742519378662,
+      "learning_rate": 7.5497381663399716e-06,
+      "loss": 0.012,
+      "step": 482
+    },
+    {
+      "epoch": 0.6224226804123711,
+      "grad_norm": 0.7309709787368774,
+      "learning_rate": 7.506126659203733e-06,
+      "loss": 0.0052,
+      "step": 483
+    },
+    {
+      "epoch": 0.6237113402061856,
+      "grad_norm": 1.414675235748291,
+      "learning_rate": 7.462565671976504e-06,
+      "loss": 0.005,
+      "step": 484
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.5044420957565308,
+      "learning_rate": 7.419056087099695e-06,
+      "loss": 0.0034,
+      "step": 485
+    },
+    {
+      "epoch": 0.6262886597938144,
+      "grad_norm": 0.4570430815219879,
+      "learning_rate": 7.375598785973429e-06,
+      "loss": 0.0022,
+      "step": 486
+    },
+    {
+      "epoch": 0.6275773195876289,
+      "grad_norm": 1.932029128074646,
+      "learning_rate": 7.332194648938689e-06,
+      "loss": 0.0102,
+      "step": 487
+    },
+    {
+      "epoch": 0.6288659793814433,
+      "grad_norm": 1.0421007871627808,
+      "learning_rate": 7.288844555259471e-06,
+      "loss": 0.0039,
+      "step": 488
+    },
+    {
+      "epoch": 0.6301546391752577,
+      "grad_norm": 0.5654887557029724,
+      "learning_rate": 7.245549383104993e-06,
+      "loss": 0.0022,
+      "step": 489
+    },
+    {
+      "epoch": 0.6314432989690721,
+      "grad_norm": 0.5495522022247314,
+      "learning_rate": 7.202310009531886e-06,
+      "loss": 0.0036,
+      "step": 490
+    },
+    {
+      "epoch": 0.6327319587628866,
+      "grad_norm": 2.5807251930236816,
+      "learning_rate": 7.159127310466441e-06,
+      "loss": 0.012,
+      "step": 491
+    },
+    {
+      "epoch": 0.634020618556701,
+      "grad_norm": 0.829201877117157,
+      "learning_rate": 7.116002160686851e-06,
+      "loss": 0.006,
+      "step": 492
+    },
+    {
+      "epoch": 0.6353092783505154,
+      "grad_norm": 0.9482012391090393,
+      "learning_rate": 7.072935433805508e-06,
+      "loss": 0.0089,
+      "step": 493
+    },
+    {
+      "epoch": 0.6365979381443299,
+      "grad_norm": 1.9564292430877686,
+      "learning_rate": 7.0299280022512875e-06,
+      "loss": 0.0109,
+      "step": 494
+    },
+    {
+      "epoch": 0.6378865979381443,
+      "grad_norm": 0.7540721297264099,
+      "learning_rate": 6.986980737251889e-06,
+      "loss": 0.0022,
+      "step": 495
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 0.34916985034942627,
+      "learning_rate": 6.944094508816182e-06,
+      "loss": 0.004,
+      "step": 496
+    },
+    {
+      "epoch": 0.6404639175257731,
+      "grad_norm": 0.06619101762771606,
+      "learning_rate": 6.9012701857165755e-06,
+      "loss": 0.0002,
+      "step": 497
+    },
+    {
+      "epoch": 0.6417525773195877,
+      "grad_norm": 1.7265164852142334,
+      "learning_rate": 6.858508635471428e-06,
+      "loss": 0.0038,
+      "step": 498
+    },
+    {
+      "epoch": 0.6430412371134021,
+      "grad_norm": 0.7744361758232117,
+      "learning_rate": 6.815810724327469e-06,
+      "loss": 0.0032,
+      "step": 499
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "grad_norm": 3.491551637649536,
+      "learning_rate": 6.773177317242257e-06,
+      "loss": 0.0294,
+      "step": 500
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "eval_accuracy": 0.997020854021847,
+      "eval_f1": 0.9454545454545454,
+      "eval_loss": 0.016488004475831985,
+      "eval_precision": 0.9811320754716981,
+      "eval_recall": 0.9122807017543859,
+      "eval_runtime": 83.472,
+      "eval_samples_per_second": 5.451,
+      "eval_steps_per_second": 0.18,
+      "step": 500
     }
   ],
   "logging_steps": 1,
@@ -3078,7 +3838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.336068185962578e+17,
+  "total_flos": 1.6687462625574912e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null