Training in progress, step 600, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b1a741aef12c15963ba453b05ab5db82600bc551f2b0abdba0db986515581e
+oid sha256:14547ac515d48222d4a0714565b7f0ff43cdfe7e3433bc78e49e6b09b8981c81
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7904bad979c288a95b5544959e8198018d6b678ccb1bbd085c8a3715877659
+oid sha256:f3c489693ca786f69cce194ed047018280eb4f135c47799cb9c8c1a94a80a83a
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7197d140fd83963b935a376f4d10c9844e833c8ece7825e56a537cd1f8c644af
+oid sha256:7c3ab0f03d59ab2cacfa7684c6582db19c8faa2f71f12a0c59dcdb7658989a9f
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ceaa8f446e2f8dcda19c36d8e6153becc6476783cafdca7111122aee2ef02e4
+oid sha256:062db20f34ebc5332783844c03fac1617134d15c0ad9339a332184848e989644
 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:dc2db39bbffdd11bfa5291372b42f5e65728cd913b180ab1985ed1b3a40873fe
+oid sha256:fd64dd21576e02e753ec94ea95a93f198f48328a88aba4a0b14eb1c5b099960f
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3cc4c894c659d664488312db7958b2b28c1cb0b69e1b193236f71117586abc
+oid sha256:9147e0041db4b2f1bbe193ca483881fc7504c7fffc9a467e0d3c27f4f6362c06
 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:c1da01c95902e73134a96dda0be8f77798bec60a53a1f2dbb08b7e4384991650
+oid sha256:6476c01f704d06b7eca9adfe435dd9017de711e4ab1edb0533a8d4b92ea37f25
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56970e8db017cc28abe4f30ae5ecc2b1b0ca78752e49befac2699bb6e88ee3b2
+oid sha256:52461b7b55cf2eee72b6e10a42c3da62ee93fab77b4586e9e99529192d3b8dbe
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6628c12a9e847bd7b0ae41ef60b5411f45368fdb1098e87b82df12733ebc90
+oid sha256:63667f41da56d7b37e81a5ed39a2827a59d961a10f3db5d65d53c52bf140063c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7006e35aa389f7a9da3b0441e6946d07bdfe96c931f880353af9a6540dbecc
+oid sha256:60adab32009df101fecc7f478362117663e337a78ba4017ca403697239a831b2
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc8516280fb996848d161272211cec6b2fbaff18bd368f409c7ee2bb47862ee
+oid sha256:48eb373b7a317259acb89e88151da10b0d07ea04d20c599909c5968bfc9819c1
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22954ae1098f61d594e688048b08108dec1af0a05949920062dae9026ee41d19
+oid sha256:91aaac2801488334362c66999f6efe4f2ff3e9efee52c3fbb9472e6a04ca6a75
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f74cf2d94199da6c0c744e0a8fc5b249258fbfd3cbeeaf0782f20c5de466ce1
+oid sha256:53f1cd88f5f16fe0f959344eb591cfcac8cc96050715460be2e56f3c4370f019
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23702299123014933,
+  "epoch": 0.2844275894761792,
   "eval_steps": 20,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3819,6 +3819,766 @@
       "eval_samples_per_second": 5.415,
       "eval_steps_per_second": 0.18,
       "step": 500
+    },
+    {
+      "epoch": 0.23749703721260962,
+      "grad_norm": 5.681730270385742,
+      "learning_rate": 1.886989601909744e-05,
+      "loss": 0.1176,
+      "step": 501
+    },
+    {
+      "epoch": 0.23797108319506993,
+      "grad_norm": 5.455805778503418,
+      "learning_rate": 1.8862240277872587e-05,
+      "loss": 0.1556,
+      "step": 502
+    },
+    {
+      "epoch": 0.23844512917753022,
+      "grad_norm": 6.3678879737854,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.2133,
+      "step": 503
+    },
+    {
+      "epoch": 0.23891917515999053,
+      "grad_norm": 8.105287551879883,
+      "learning_rate": 1.8846855976117137e-05,
+      "loss": 0.1864,
+      "step": 504
+    },
+    {
+      "epoch": 0.23939322114245082,
+      "grad_norm": 12.376128196716309,
+      "learning_rate": 1.8839127457735325e-05,
+      "loss": 0.2301,
+      "step": 505
+    },
+    {
+      "epoch": 0.2398672671249111,
+      "grad_norm": 4.791072368621826,
+      "learning_rate": 1.8831374722560686e-05,
+      "loss": 0.1711,
+      "step": 506
+    },
+    {
+      "epoch": 0.24034131310737142,
+      "grad_norm": 7.560359001159668,
+      "learning_rate": 1.8823597791833595e-05,
+      "loss": 0.2847,
+      "step": 507
+    },
+    {
+      "epoch": 0.2408153590898317,
+      "grad_norm": 4.705785751342773,
+      "learning_rate": 1.8815796686860717e-05,
+      "loss": 0.1704,
+      "step": 508
+    },
+    {
+      "epoch": 0.24128940507229202,
+      "grad_norm": 4.360641002655029,
+      "learning_rate": 1.880797142901495e-05,
+      "loss": 0.171,
+      "step": 509
+    },
+    {
+      "epoch": 0.2417634510547523,
+      "grad_norm": 2.9732701778411865,
+      "learning_rate": 1.880012203973536e-05,
+      "loss": 0.1867,
+      "step": 510
+    },
+    {
+      "epoch": 0.24223749703721262,
+      "grad_norm": 5.549304008483887,
+      "learning_rate": 1.8792248540527124e-05,
+      "loss": 0.1999,
+      "step": 511
+    },
+    {
+      "epoch": 0.2427115430196729,
+      "grad_norm": 4.155362129211426,
+      "learning_rate": 1.878435095296148e-05,
+      "loss": 0.0973,
+      "step": 512
+    },
+    {
+      "epoch": 0.24318558900213322,
+      "grad_norm": 2.743211030960083,
+      "learning_rate": 1.877642929867566e-05,
+      "loss": 0.0951,
+      "step": 513
+    },
+    {
+      "epoch": 0.2436596349845935,
+      "grad_norm": 5.166907787322998,
+      "learning_rate": 1.876848359937283e-05,
+      "loss": 0.2062,
+      "step": 514
+    },
+    {
+      "epoch": 0.24413368096705382,
+      "grad_norm": 8.175763130187988,
+      "learning_rate": 1.876051387682204e-05,
+      "loss": 0.3424,
+      "step": 515
+    },
+    {
+      "epoch": 0.2446077269495141,
+      "grad_norm": 7.783774375915527,
+      "learning_rate": 1.8752520152858136e-05,
+      "loss": 0.1457,
+      "step": 516
+    },
+    {
+      "epoch": 0.2450817729319744,
+      "grad_norm": 3.428746461868286,
+      "learning_rate": 1.8744502449381748e-05,
+      "loss": 0.1067,
+      "step": 517
+    },
+    {
+      "epoch": 0.2455558189144347,
+      "grad_norm": 5.763442039489746,
+      "learning_rate": 1.8736460788359195e-05,
+      "loss": 0.1122,
+      "step": 518
+    },
+    {
+      "epoch": 0.246029864896895,
+      "grad_norm": 4.418912887573242,
+      "learning_rate": 1.872839519182242e-05,
+      "loss": 0.1818,
+      "step": 519
+    },
+    {
+      "epoch": 0.2465039108793553,
+      "grad_norm": 12.567361831665039,
+      "learning_rate": 1.8720305681868954e-05,
+      "loss": 0.2092,
+      "step": 520
+    },
+    {
+      "epoch": 0.2465039108793553,
+      "eval_accuracy": 0.9895330112721417,
+      "eval_f1": 0.8849557522123894,
+      "eval_loss": 0.03357277810573578,
+      "eval_precision": 0.819672131147541,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 50.2265,
+      "eval_samples_per_second": 5.396,
+      "eval_steps_per_second": 0.179,
+      "step": 520
+    },
+    {
+      "epoch": 0.2469779568618156,
+      "grad_norm": 4.847149848937988,
+      "learning_rate": 1.871219228066185e-05,
+      "loss": 0.1458,
+      "step": 521
+    },
+    {
+      "epoch": 0.2474520028442759,
+      "grad_norm": 14.294929504394531,
+      "learning_rate": 1.8704055010429604e-05,
+      "loss": 0.2378,
+      "step": 522
+    },
+    {
+      "epoch": 0.2479260488267362,
+      "grad_norm": 8.848465919494629,
+      "learning_rate": 1.869589389346611e-05,
+      "loss": 0.1957,
+      "step": 523
+    },
+    {
+      "epoch": 0.2484000948091965,
+      "grad_norm": 7.963865280151367,
+      "learning_rate": 1.8687708952130602e-05,
+      "loss": 0.2389,
+      "step": 524
+    },
+    {
+      "epoch": 0.2488741407916568,
+      "grad_norm": 6.276052951812744,
+      "learning_rate": 1.867950020884758e-05,
+      "loss": 0.1899,
+      "step": 525
+    },
+    {
+      "epoch": 0.2493481867741171,
+      "grad_norm": 4.264331340789795,
+      "learning_rate": 1.867126768610676e-05,
+      "loss": 0.1336,
+      "step": 526
+    },
+    {
+      "epoch": 0.2498222327565774,
+      "grad_norm": 5.881321907043457,
+      "learning_rate": 1.866301140646299e-05,
+      "loss": 0.1832,
+      "step": 527
+    },
+    {
+      "epoch": 0.2502962787390377,
+      "grad_norm": 6.979321002960205,
+      "learning_rate": 1.8654731392536238e-05,
+      "loss": 0.2483,
+      "step": 528
+    },
+    {
+      "epoch": 0.25077032472149796,
+      "grad_norm": 6.509945392608643,
+      "learning_rate": 1.8646427667011465e-05,
+      "loss": 0.1578,
+      "step": 529
+    },
+    {
+      "epoch": 0.2512443707039583,
+      "grad_norm": 9.517057418823242,
+      "learning_rate": 1.863810025263862e-05,
+      "loss": 0.2089,
+      "step": 530
+    },
+    {
+      "epoch": 0.2517184166864186,
+      "grad_norm": 6.159739017486572,
+      "learning_rate": 1.8629749172232528e-05,
+      "loss": 0.1491,
+      "step": 531
+    },
+    {
+      "epoch": 0.2521924626688789,
+      "grad_norm": 7.890002727508545,
+      "learning_rate": 1.8621374448672878e-05,
+      "loss": 0.2089,
+      "step": 532
+    },
+    {
+      "epoch": 0.25266650865133916,
+      "grad_norm": 5.750835418701172,
+      "learning_rate": 1.861297610490412e-05,
+      "loss": 0.1672,
+      "step": 533
+    },
+    {
+      "epoch": 0.2531405546337995,
+      "grad_norm": 8.991978645324707,
+      "learning_rate": 1.8604554163935416e-05,
+      "loss": 0.2807,
+      "step": 534
+    },
+    {
+      "epoch": 0.2536146006162598,
+      "grad_norm": 8.729525566101074,
+      "learning_rate": 1.859610864884059e-05,
+      "loss": 0.1845,
+      "step": 535
+    },
+    {
+      "epoch": 0.2540886465987201,
+      "grad_norm": 5.400993824005127,
+      "learning_rate": 1.8587639582758032e-05,
+      "loss": 0.1581,
+      "step": 536
+    },
+    {
+      "epoch": 0.25456269258118036,
+      "grad_norm": 3.7591798305511475,
+      "learning_rate": 1.8579146988890677e-05,
+      "loss": 0.151,
+      "step": 537
+    },
+    {
+      "epoch": 0.2550367385636407,
+      "grad_norm": 4.554786682128906,
+      "learning_rate": 1.857063089050591e-05,
+      "loss": 0.1672,
+      "step": 538
+    },
+    {
+      "epoch": 0.255510784546101,
+      "grad_norm": 5.148488998413086,
+      "learning_rate": 1.8562091310935514e-05,
+      "loss": 0.1258,
+      "step": 539
+    },
+    {
+      "epoch": 0.25598483052856125,
+      "grad_norm": 7.819247245788574,
+      "learning_rate": 1.8553528273575597e-05,
+      "loss": 0.2247,
+      "step": 540
+    },
+    {
+      "epoch": 0.25598483052856125,
+      "eval_accuracy": 0.9927536231884058,
+      "eval_f1": 0.9158878504672897,
+      "eval_loss": 0.02866183966398239,
+      "eval_precision": 0.8909090909090909,
+      "eval_recall": 0.9423076923076923,
+      "eval_runtime": 50.5721,
+      "eval_samples_per_second": 5.359,
+      "eval_steps_per_second": 0.178,
+      "step": 540
+    },
+    {
+      "epoch": 0.25645887651102156,
+      "grad_norm": 5.182741641998291,
+      "learning_rate": 1.8544941801886543e-05,
+      "loss": 0.1985,
+      "step": 541
+    },
+    {
+      "epoch": 0.2569329224934819,
+      "grad_norm": 10.451058387756348,
+      "learning_rate": 1.8536331919392938e-05,
+      "loss": 0.2074,
+      "step": 542
+    },
+    {
+      "epoch": 0.2574069684759422,
+      "grad_norm": 4.122173309326172,
+      "learning_rate": 1.8527698649683507e-05,
+      "loss": 0.1409,
+      "step": 543
+    },
+    {
+      "epoch": 0.25788101445840245,
+      "grad_norm": 4.434998989105225,
+      "learning_rate": 1.8519042016411045e-05,
+      "loss": 0.1919,
+      "step": 544
+    },
+    {
+      "epoch": 0.25835506044086276,
+      "grad_norm": 4.652968406677246,
+      "learning_rate": 1.8510362043292363e-05,
+      "loss": 0.2015,
+      "step": 545
+    },
+    {
+      "epoch": 0.2588291064233231,
+      "grad_norm": 2.667080879211426,
+      "learning_rate": 1.850165875410822e-05,
+      "loss": 0.1196,
+      "step": 546
+    },
+    {
+      "epoch": 0.2593031524057834,
+      "grad_norm": 4.295355796813965,
+      "learning_rate": 1.8492932172703236e-05,
+      "loss": 0.1693,
+      "step": 547
+    },
+    {
+      "epoch": 0.25977719838824365,
+      "grad_norm": 7.52603006362915,
+      "learning_rate": 1.848418232298587e-05,
+      "loss": 0.1776,
+      "step": 548
+    },
+    {
+      "epoch": 0.26025124437070396,
+      "grad_norm": 12.561964988708496,
+      "learning_rate": 1.8475409228928314e-05,
+      "loss": 0.2784,
+      "step": 549
+    },
+    {
+      "epoch": 0.2607252903531643,
+      "grad_norm": 3.891218423843384,
+      "learning_rate": 1.8466612914566447e-05,
+      "loss": 0.1314,
+      "step": 550
+    },
+    {
+      "epoch": 0.26119933633562453,
+      "grad_norm": 4.668924331665039,
+      "learning_rate": 1.8457793403999766e-05,
+      "loss": 0.1323,
+      "step": 551
+    },
+    {
+      "epoch": 0.26167338231808485,
+      "grad_norm": 4.252039432525635,
+      "learning_rate": 1.844895072139132e-05,
+      "loss": 0.1404,
+      "step": 552
+    },
+    {
+      "epoch": 0.26214742830054516,
+      "grad_norm": 13.645633697509766,
+      "learning_rate": 1.844008489096764e-05,
+      "loss": 0.2463,
+      "step": 553
+    },
+    {
+      "epoch": 0.2626214742830055,
+      "grad_norm": 8.817793846130371,
+      "learning_rate": 1.843119593701868e-05,
+      "loss": 0.2191,
+      "step": 554
+    },
+    {
+      "epoch": 0.26309552026546573,
+      "grad_norm": 3.518982410430908,
+      "learning_rate": 1.8422283883897744e-05,
+      "loss": 0.1856,
+      "step": 555
+    },
+    {
+      "epoch": 0.26356956624792605,
+      "grad_norm": 4.6413044929504395,
+      "learning_rate": 1.8413348756021415e-05,
+      "loss": 0.2101,
+      "step": 556
+    },
+    {
+      "epoch": 0.26404361223038636,
+      "grad_norm": 3.4393184185028076,
+      "learning_rate": 1.8404390577869508e-05,
+      "loss": 0.0917,
+      "step": 557
+    },
+    {
+      "epoch": 0.2645176582128467,
+      "grad_norm": 7.83014440536499,
+      "learning_rate": 1.839540937398498e-05,
+      "loss": 0.1848,
+      "step": 558
+    },
+    {
+      "epoch": 0.26499170419530693,
+      "grad_norm": 5.448614597320557,
+      "learning_rate": 1.8386405168973875e-05,
+      "loss": 0.201,
+      "step": 559
+    },
+    {
+      "epoch": 0.26546575017776725,
+      "grad_norm": 9.165091514587402,
+      "learning_rate": 1.8377377987505252e-05,
+      "loss": 0.2684,
+      "step": 560
+    },
+    {
+      "epoch": 0.26546575017776725,
+      "eval_accuracy": 0.9919484702093397,
+      "eval_f1": 0.9090909090909091,
+      "eval_loss": 0.028601787984371185,
+      "eval_precision": 0.8620689655172413,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 49.8418,
+      "eval_samples_per_second": 5.437,
+      "eval_steps_per_second": 0.181,
+      "step": 560
+    },
+    {
+      "epoch": 0.26593979616022756,
+      "grad_norm": 4.3900065422058105,
+      "learning_rate": 1.836832785431112e-05,
+      "loss": 0.1651,
+      "step": 561
+    },
+    {
+      "epoch": 0.2664138421426878,
+      "grad_norm": 6.591796398162842,
+      "learning_rate": 1.8359254794186368e-05,
+      "loss": 0.2222,
+      "step": 562
+    },
+    {
+      "epoch": 0.26688788812514813,
+      "grad_norm": 4.408583641052246,
+      "learning_rate": 1.8350158831988708e-05,
+      "loss": 0.1636,
+      "step": 563
+    },
+    {
+      "epoch": 0.26736193410760845,
+      "grad_norm": 4.501555442810059,
+      "learning_rate": 1.8341039992638585e-05,
+      "loss": 0.1883,
+      "step": 564
+    },
+    {
+      "epoch": 0.26783598009006876,
+      "grad_norm": 3.782682418823242,
+      "learning_rate": 1.8331898301119123e-05,
+      "loss": 0.1582,
+      "step": 565
+    },
+    {
+      "epoch": 0.268310026072529,
+      "grad_norm": 3.5062944889068604,
+      "learning_rate": 1.832273378247606e-05,
+      "loss": 0.1352,
+      "step": 566
+    },
+    {
+      "epoch": 0.26878407205498933,
+      "grad_norm": 3.86049747467041,
+      "learning_rate": 1.831354646181767e-05,
+      "loss": 0.106,
+      "step": 567
+    },
+    {
+      "epoch": 0.26925811803744965,
+      "grad_norm": 3.148836374282837,
+      "learning_rate": 1.8304336364314707e-05,
+      "loss": 0.1623,
+      "step": 568
+    },
+    {
+      "epoch": 0.2697321640199099,
+      "grad_norm": 6.754387855529785,
+      "learning_rate": 1.829510351520031e-05,
+      "loss": 0.2434,
+      "step": 569
+    },
+    {
+      "epoch": 0.2702062100023702,
+      "grad_norm": 5.247784614562988,
+      "learning_rate": 1.828584793976997e-05,
+      "loss": 0.1331,
+      "step": 570
+    },
+    {
+      "epoch": 0.27068025598483053,
+      "grad_norm": 5.818985939025879,
+      "learning_rate": 1.827656966338143e-05,
+      "loss": 0.1737,
+      "step": 571
+    },
+    {
+      "epoch": 0.27115430196729084,
+      "grad_norm": 6.568758487701416,
+      "learning_rate": 1.8267268711454634e-05,
+      "loss": 0.1579,
+      "step": 572
+    },
+    {
+      "epoch": 0.2716283479497511,
+      "grad_norm": 3.268862009048462,
+      "learning_rate": 1.825794510947164e-05,
+      "loss": 0.1111,
+      "step": 573
+    },
+    {
+      "epoch": 0.2721023939322114,
+      "grad_norm": 6.984981060028076,
+      "learning_rate": 1.8248598882976575e-05,
+      "loss": 0.0992,
+      "step": 574
+    },
+    {
+      "epoch": 0.27257643991467173,
+      "grad_norm": 7.59507942199707,
+      "learning_rate": 1.8239230057575542e-05,
+      "loss": 0.214,
+      "step": 575
+    },
+    {
+      "epoch": 0.27305048589713204,
+      "grad_norm": 5.1507768630981445,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.2327,
+      "step": 576
+    },
+    {
+      "epoch": 0.2735245318795923,
+      "grad_norm": 5.358564853668213,
+      "learning_rate": 1.8220424712789502e-05,
+      "loss": 0.1408,
+      "step": 577
+    },
+    {
+      "epoch": 0.2739985778620526,
+      "grad_norm": 4.9489054679870605,
+      "learning_rate": 1.8210988244926003e-05,
+      "loss": 0.1331,
+      "step": 578
+    },
+    {
+      "epoch": 0.27447262384451293,
+      "grad_norm": 3.4182543754577637,
+      "learning_rate": 1.8201529281199398e-05,
+      "loss": 0.1632,
+      "step": 579
+    },
+    {
+      "epoch": 0.2749466698269732,
+      "grad_norm": 4.689789772033691,
+      "learning_rate": 1.8192047847524667e-05,
+      "loss": 0.1485,
+      "step": 580
+    },
+    {
+      "epoch": 0.2749466698269732,
+      "eval_accuracy": 0.9895330112721417,
+      "eval_f1": 0.8849557522123894,
+      "eval_loss": 0.035417672246694565,
+      "eval_precision": 0.819672131147541,
+      "eval_recall": 0.9615384615384616,
+      "eval_runtime": 50.3007,
+      "eval_samples_per_second": 5.388,
+      "eval_steps_per_second": 0.179,
+      "step": 580
+    },
+    {
+      "epoch": 0.2754207158094335,
+      "grad_norm": 10.920886039733887,
+      "learning_rate": 1.818254396987835e-05,
+      "loss": 0.1957,
+      "step": 581
+    },
+    {
+      "epoch": 0.2758947617918938,
+      "grad_norm": 5.822461128234863,
+      "learning_rate": 1.8173017674298467e-05,
+      "loss": 0.2047,
+      "step": 582
+    },
+    {
+      "epoch": 0.27636880777435413,
+      "grad_norm": 3.932877540588379,
+      "learning_rate": 1.8163468986884466e-05,
+      "loss": 0.1519,
+      "step": 583
+    },
+    {
+      "epoch": 0.2768428537568144,
+      "grad_norm": 4.026641368865967,
+      "learning_rate": 1.8153897933797145e-05,
+      "loss": 0.1476,
+      "step": 584
+    },
+    {
+      "epoch": 0.2773168997392747,
+      "grad_norm": 7.63388204574585,
+      "learning_rate": 1.8144304541258562e-05,
+      "loss": 0.1801,
+      "step": 585
+    },
+    {
+      "epoch": 0.277790945721735,
+      "grad_norm": 6.409342288970947,
+      "learning_rate": 1.8134688835552003e-05,
+      "loss": 0.1739,
+      "step": 586
+    },
+    {
+      "epoch": 0.27826499170419533,
+      "grad_norm": 6.363264560699463,
+      "learning_rate": 1.8125050843021864e-05,
+      "loss": 0.1361,
+      "step": 587
+    },
+    {
+      "epoch": 0.2787390376866556,
+      "grad_norm": 4.324347972869873,
+      "learning_rate": 1.8115390590073612e-05,
+      "loss": 0.1366,
+      "step": 588
+    },
+    {
+      "epoch": 0.2792130836691159,
+      "grad_norm": 4.929332256317139,
+      "learning_rate": 1.81057081031737e-05,
+      "loss": 0.1702,
+      "step": 589
+    },
+    {
+      "epoch": 0.2796871296515762,
+      "grad_norm": 9.115571022033691,
+      "learning_rate": 1.8096003408849494e-05,
+      "loss": 0.2041,
+      "step": 590
+    },
+    {
+      "epoch": 0.2801611756340365,
+      "grad_norm": 3.8357152938842773,
+      "learning_rate": 1.8086276533689203e-05,
+      "loss": 0.1817,
+      "step": 591
+    },
+    {
+      "epoch": 0.2806352216164968,
+      "grad_norm": 6.761523723602295,
+      "learning_rate": 1.807652750434181e-05,
+      "loss": 0.1802,
+      "step": 592
+    },
+    {
+      "epoch": 0.2811092675989571,
+      "grad_norm": 4.541932106018066,
+      "learning_rate": 1.8066756347516985e-05,
+      "loss": 0.19,
+      "step": 593
+    },
+    {
+      "epoch": 0.2815833135814174,
+      "grad_norm": 4.590600967407227,
+      "learning_rate": 1.805696308998503e-05,
+      "loss": 0.2543,
+      "step": 594
+    },
+    {
+      "epoch": 0.2820573595638777,
+      "grad_norm": 5.389986038208008,
+      "learning_rate": 1.804714775857679e-05,
+      "loss": 0.167,
+      "step": 595
+    },
+    {
+      "epoch": 0.282531405546338,
+      "grad_norm": 4.69621467590332,
+      "learning_rate": 1.803731038018359e-05,
+      "loss": 0.1495,
+      "step": 596
+    },
+    {
+      "epoch": 0.2830054515287983,
+      "grad_norm": 4.559863090515137,
+      "learning_rate": 1.8027450981757162e-05,
+      "loss": 0.1929,
+      "step": 597
+    },
+    {
+      "epoch": 0.2834794975112586,
+      "grad_norm": 7.2930216789245605,
+      "learning_rate": 1.8017569590309564e-05,
+      "loss": 0.1402,
+      "step": 598
+    },
+    {
+      "epoch": 0.2839535434937189,
+      "grad_norm": 5.581624507904053,
+      "learning_rate": 1.8007666232913095e-05,
+      "loss": 0.1774,
+      "step": 599
+    },
+    {
+      "epoch": 0.2844275894761792,
+      "grad_norm": 6.207181930541992,
+      "learning_rate": 1.799774093670026e-05,
+      "loss": 0.1168,
+      "step": 600
+    },
+    {
+      "epoch": 0.2844275894761792,
+      "eval_accuracy": 0.9927536231884058,
+      "eval_f1": 0.9158878504672897,
+      "eval_loss": 0.02737443894147873,
+      "eval_precision": 0.8909090909090909,
+      "eval_recall": 0.9423076923076923,
+      "eval_runtime": 50.6456,
+      "eval_samples_per_second": 5.351,
+      "eval_steps_per_second": 0.178,
+      "step": 600
     }
   ],
   "logging_steps": 1,
@@ -3838,7 +4598,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3338310337993114e+17,
+  "total_flos": 1.599781785955205e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null