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:e2685cd63188a12b6e51a5f87202565fae64cf192dedbad3017d3d9a00011716
+oid sha256:ee6fb7682ac2960073f7f7f514a487e812e315d44419de7236d03c8ab15aadb0
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a564ea22e8120a98d07382ac39eaaeaf5ddb197a900e74e310ad7f4d8286fb1e
+oid sha256:88e008363e8993235e6eb2af6c9a5ff56f447d8bdc2cf16eca2f0422b1ede8c6
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc676c0cbe36a418bebb6a770754ec6e6b4550ec6cc2173fee8f8473cfd8acb2
+oid sha256:44b477d5172b476bbf9b578ef9878ce39658de519ce36fd3743830da1d68fefd
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0189f4aacb249403224b0e30e9c8aa2b90c60a248a90d9f5fdee546b7c9452
+oid sha256:145633610b9b152b0d2cfc8f1f6615f8471936dfa77ce591ae7e2e811ac751bb
 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:edae67eb4587445733f88b71e1245cfb3f5164c085e6d89fa55d75c346a20afb
+oid sha256:265e64cfbd04131bffb2a5617a8c2c4c2ea31a7fad0d26e752c26ca24a5c050c
 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:ee7eeca1e6b6ba7221886609291f76f4c0ee14fdab353839097d8c6fbf7ee572
+oid sha256:a960df6918c81f11623085f85ea94df1837af4b8f4267a1629fb6bab5c469523
 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:daabfcc6e1a3483f4db21790ddb98974904e8bc9e77135d80c25a77935fcb7db
+oid sha256:5862dd9e056331bb039021a6505bb7a3f1fa98b8a9f5c3fda8a0888d65d5b053
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c434609d68ad98f7889ff98e8f1dc2f6ac56615be0728c4c1a08a0e95e8e983
+oid sha256:dc9bd789414240ee2b44965c46a333328df7f9fce29ffffe29646f97e82894b8
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672bc765d367d7d4ffae64a9a7720cba4580c54ee7b0c79f366c5fcfec50f7ae
+oid sha256:2c60c3492b6f46efa4d46f08722f1ca59fb0c21715cf617886bb5ba859c7d9d5
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9b6f6648a3802b1d7df894c5bbd13bfaaff3cdef6fb263aaa54636226f2ff6
+oid sha256:c8b3388ef358d7f5f11e1879a04d7711953bb9f05b7b304558dfcff8e1df0bd0
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742fcffc6aba3ef3530cc33f6ad6b89ccb93cdf34124275e474711f05d532257
+oid sha256:e7c4655d165a45ceaebd2333d540d7ca911eb47056d42042ac402dbf7a3b1875
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b41b47676e62b604b32ae1968e1fffa4fc215a0c59a21338a7a142638b146f
+oid sha256:076dbf8750dbf683323b1e43171b411204fb0c6b72da57c223dae871c8d1c08e
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e3dd1bae2a933732e2e6fffe805496ee2173debbdafb8e9682fed9cdf6cd22a
+oid sha256:d5b83b9e4abe0e439076bc90dc25d49fcd5d4c81c9c012e6730d7f022accf132
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37105751391465674,
+  "epoch": 0.46382189239332094,
   "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": 5.761,
       "eval_steps_per_second": 0.188,
       "step": 400
+    },
+    {
+      "epoch": 0.3719851576994434,
+      "grad_norm": 4.4434332847595215,
+      "learning_rate": 1.582532541615122e-05,
+      "loss": 0.1563,
+      "step": 401
+    },
+    {
+      "epoch": 0.37291280148423006,
+      "grad_norm": 2.928924083709717,
+      "learning_rate": 1.57989700674967e-05,
+      "loss": 0.1211,
+      "step": 402
+    },
+    {
+      "epoch": 0.3738404452690167,
+      "grad_norm": 3.329848527908325,
+      "learning_rate": 1.5772553890390196e-05,
+      "loss": 0.2248,
+      "step": 403
+    },
+    {
+      "epoch": 0.3747680890538033,
+      "grad_norm": 4.852266311645508,
+      "learning_rate": 1.5746077161924905e-05,
+      "loss": 0.2121,
+      "step": 404
+    },
+    {
+      "epoch": 0.37569573283859,
+      "grad_norm": 8.039565086364746,
+      "learning_rate": 1.5719540159829185e-05,
+      "loss": 0.1864,
+      "step": 405
+    },
+    {
+      "epoch": 0.37662337662337664,
+      "grad_norm": 4.178286552429199,
+      "learning_rate": 1.5692943162463628e-05,
+      "loss": 0.1164,
+      "step": 406
+    },
+    {
+      "epoch": 0.37755102040816324,
+      "grad_norm": 4.181092739105225,
+      "learning_rate": 1.5666286448818152e-05,
+      "loss": 0.136,
+      "step": 407
+    },
+    {
+      "epoch": 0.3784786641929499,
+      "grad_norm": 4.847424030303955,
+      "learning_rate": 1.5639570298509067e-05,
+      "loss": 0.1692,
+      "step": 408
+    },
+    {
+      "epoch": 0.37940630797773656,
+      "grad_norm": 5.589816570281982,
+      "learning_rate": 1.5612794991776147e-05,
+      "loss": 0.1375,
+      "step": 409
+    },
+    {
+      "epoch": 0.3803339517625232,
+      "grad_norm": 3.174445629119873,
+      "learning_rate": 1.5585960809479698e-05,
+      "loss": 0.1683,
+      "step": 410
+    },
+    {
+      "epoch": 0.3812615955473098,
+      "grad_norm": 7.2739739418029785,
+      "learning_rate": 1.5559068033097583e-05,
+      "loss": 0.2135,
+      "step": 411
+    },
+    {
+      "epoch": 0.3821892393320965,
+      "grad_norm": 5.514982223510742,
+      "learning_rate": 1.5532116944722308e-05,
+      "loss": 0.2366,
+      "step": 412
+    },
+    {
+      "epoch": 0.38311688311688313,
+      "grad_norm": 4.4258036613464355,
+      "learning_rate": 1.5505107827058038e-05,
+      "loss": 0.1667,
+      "step": 413
+    },
+    {
+      "epoch": 0.38404452690166974,
+      "grad_norm": 4.089566230773926,
+      "learning_rate": 1.547804096341763e-05,
+      "loss": 0.1647,
+      "step": 414
+    },
+    {
+      "epoch": 0.3849721706864564,
+      "grad_norm": 3.6559548377990723,
+      "learning_rate": 1.5450916637719683e-05,
+      "loss": 0.1705,
+      "step": 415
+    },
+    {
+      "epoch": 0.38589981447124305,
+      "grad_norm": 4.045246124267578,
+      "learning_rate": 1.5423735134485537e-05,
+      "loss": 0.1915,
+      "step": 416
+    },
+    {
+      "epoch": 0.3868274582560297,
+      "grad_norm": 3.6718714237213135,
+      "learning_rate": 1.5396496738836292e-05,
+      "loss": 0.1532,
+      "step": 417
+    },
+    {
+      "epoch": 0.3877551020408163,
+      "grad_norm": 4.593350887298584,
+      "learning_rate": 1.536920173648984e-05,
+      "loss": 0.1815,
+      "step": 418
+    },
+    {
+      "epoch": 0.38868274582560297,
+      "grad_norm": 3.913667917251587,
+      "learning_rate": 1.5341850413757834e-05,
+      "loss": 0.1448,
+      "step": 419
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "grad_norm": 4.148723125457764,
+      "learning_rate": 1.5314443057542703e-05,
+      "loss": 0.2082,
+      "step": 420
+    },
+    {
+      "epoch": 0.38961038961038963,
+      "eval_accuracy": 0.8603104212860311,
+      "eval_f1": 0.7136363636363636,
+      "eval_loss": 0.31429344415664673,
+      "eval_precision": 0.839572192513369,
+      "eval_recall": 0.6205533596837944,
+      "eval_runtime": 48.5179,
+      "eval_samples_per_second": 5.689,
+      "eval_steps_per_second": 0.185,
+      "step": 420
+    },
+    {
+      "epoch": 0.39053803339517623,
+      "grad_norm": 4.14030122756958,
+      "learning_rate": 1.5286979955334655e-05,
+      "loss": 0.1749,
+      "step": 421
+    },
+    {
+      "epoch": 0.3914656771799629,
+      "grad_norm": 3.4345805644989014,
+      "learning_rate": 1.5259461395208628e-05,
+      "loss": 0.1712,
+      "step": 422
+    },
+    {
+      "epoch": 0.39239332096474955,
+      "grad_norm": 3.9379382133483887,
+      "learning_rate": 1.52318876658213e-05,
+      "loss": 0.1658,
+      "step": 423
+    },
+    {
+      "epoch": 0.39332096474953615,
+      "grad_norm": 3.1555135250091553,
+      "learning_rate": 1.5204259056408046e-05,
+      "loss": 0.1537,
+      "step": 424
+    },
+    {
+      "epoch": 0.3942486085343228,
+      "grad_norm": 3.893655776977539,
+      "learning_rate": 1.5176575856779904e-05,
+      "loss": 0.1509,
+      "step": 425
+    },
+    {
+      "epoch": 0.39517625231910947,
+      "grad_norm": 4.423066139221191,
+      "learning_rate": 1.5148838357320537e-05,
+      "loss": 0.1501,
+      "step": 426
+    },
+    {
+      "epoch": 0.3961038961038961,
+      "grad_norm": 5.078852653503418,
+      "learning_rate": 1.512104684898319e-05,
+      "loss": 0.2835,
+      "step": 427
+    },
+    {
+      "epoch": 0.3970315398886827,
+      "grad_norm": 3.377333164215088,
+      "learning_rate": 1.5093201623287631e-05,
+      "loss": 0.1393,
+      "step": 428
+    },
+    {
+      "epoch": 0.3979591836734694,
+      "grad_norm": 4.0545196533203125,
+      "learning_rate": 1.5065302972317108e-05,
+      "loss": 0.1567,
+      "step": 429
+    },
+    {
+      "epoch": 0.39888682745825604,
+      "grad_norm": 6.253279685974121,
+      "learning_rate": 1.5037351188715265e-05,
+      "loss": 0.2155,
+      "step": 430
+    },
+    {
+      "epoch": 0.39981447124304265,
+      "grad_norm": 2.698172092437744,
+      "learning_rate": 1.5009346565683088e-05,
+      "loss": 0.1102,
+      "step": 431
+    },
+    {
+      "epoch": 0.4007421150278293,
+      "grad_norm": 4.845376014709473,
+      "learning_rate": 1.4981289396975818e-05,
+      "loss": 0.2186,
+      "step": 432
+    },
+    {
+      "epoch": 0.40166975881261596,
+      "grad_norm": 2.9927968978881836,
+      "learning_rate": 1.4953179976899878e-05,
+      "loss": 0.1365,
+      "step": 433
+    },
+    {
+      "epoch": 0.4025974025974026,
+      "grad_norm": 3.484133720397949,
+      "learning_rate": 1.4925018600309784e-05,
+      "loss": 0.18,
+      "step": 434
+    },
+    {
+      "epoch": 0.4035250463821892,
+      "grad_norm": 2.8350846767425537,
+      "learning_rate": 1.4896805562605052e-05,
+      "loss": 0.1644,
+      "step": 435
+    },
+    {
+      "epoch": 0.4044526901669759,
+      "grad_norm": 3.7044577598571777,
+      "learning_rate": 1.4868541159727097e-05,
+      "loss": 0.1758,
+      "step": 436
+    },
+    {
+      "epoch": 0.40538033395176254,
+      "grad_norm": 3.7919528484344482,
+      "learning_rate": 1.4840225688156132e-05,
+      "loss": 0.1609,
+      "step": 437
+    },
+    {
+      "epoch": 0.40630797773654914,
+      "grad_norm": 3.7263407707214355,
+      "learning_rate": 1.4811859444908053e-05,
+      "loss": 0.1674,
+      "step": 438
+    },
+    {
+      "epoch": 0.4072356215213358,
+      "grad_norm": 3.5427684783935547,
+      "learning_rate": 1.4783442727531328e-05,
+      "loss": 0.212,
+      "step": 439
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 5.29186487197876,
+      "learning_rate": 1.4754975834103877e-05,
+      "loss": 0.2051,
+      "step": 440
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "eval_accuracy": 0.8569844789356984,
+      "eval_f1": 0.6978922716627635,
+      "eval_loss": 0.3138832747936249,
+      "eval_precision": 0.8563218390804598,
+      "eval_recall": 0.5889328063241107,
+      "eval_runtime": 48.1239,
+      "eval_samples_per_second": 5.735,
+      "eval_steps_per_second": 0.187,
+      "step": 440
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 6.476135730743408,
+      "learning_rate": 1.4726459063229946e-05,
+      "loss": 0.1586,
+      "step": 441
+    },
+    {
+      "epoch": 0.4100185528756957,
+      "grad_norm": 4.70169734954834,
+      "learning_rate": 1.4697892714036959e-05,
+      "loss": 0.1604,
+      "step": 442
+    },
+    {
+      "epoch": 0.4109461966604824,
+      "grad_norm": 3.1262881755828857,
+      "learning_rate": 1.4669277086172406e-05,
+      "loss": 0.1282,
+      "step": 443
+    },
+    {
+      "epoch": 0.41187384044526903,
+      "grad_norm": 3.5137503147125244,
+      "learning_rate": 1.4640612479800686e-05,
+      "loss": 0.179,
+      "step": 444
+    },
+    {
+      "epoch": 0.41280148423005564,
+      "grad_norm": 5.388190269470215,
+      "learning_rate": 1.4611899195599952e-05,
+      "loss": 0.2404,
+      "step": 445
+    },
+    {
+      "epoch": 0.4137291280148423,
+      "grad_norm": 4.668002128601074,
+      "learning_rate": 1.4583137534758968e-05,
+      "loss": 0.1781,
+      "step": 446
+    },
+    {
+      "epoch": 0.41465677179962895,
+      "grad_norm": 4.363613128662109,
+      "learning_rate": 1.455432779897395e-05,
+      "loss": 0.1636,
+      "step": 447
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 3.608628749847412,
+      "learning_rate": 1.4525470290445392e-05,
+      "loss": 0.1604,
+      "step": 448
+    },
+    {
+      "epoch": 0.4165120593692022,
+      "grad_norm": 4.1195387840271,
+      "learning_rate": 1.4496565311874902e-05,
+      "loss": 0.1752,
+      "step": 449
+    },
+    {
+      "epoch": 0.4174397031539889,
+      "grad_norm": 2.9940760135650635,
+      "learning_rate": 1.4467613166462024e-05,
+      "loss": 0.1579,
+      "step": 450
+    },
+    {
+      "epoch": 0.41836734693877553,
+      "grad_norm": 3.3826465606689453,
+      "learning_rate": 1.4438614157901073e-05,
+      "loss": 0.1529,
+      "step": 451
+    },
+    {
+      "epoch": 0.41929499072356213,
+      "grad_norm": 2.9892001152038574,
+      "learning_rate": 1.4409568590377918e-05,
+      "loss": 0.1435,
+      "step": 452
+    },
+    {
+      "epoch": 0.4202226345083488,
+      "grad_norm": 3.4909090995788574,
+      "learning_rate": 1.4380476768566825e-05,
+      "loss": 0.1879,
+      "step": 453
+    },
+    {
+      "epoch": 0.42115027829313545,
+      "grad_norm": 3.8178699016571045,
+      "learning_rate": 1.4351338997627233e-05,
+      "loss": 0.1693,
+      "step": 454
+    },
+    {
+      "epoch": 0.42207792207792205,
+      "grad_norm": 3.101930618286133,
+      "learning_rate": 1.4322155583200577e-05,
+      "loss": 0.1315,
+      "step": 455
+    },
+    {
+      "epoch": 0.4230055658627087,
+      "grad_norm": 3.344278335571289,
+      "learning_rate": 1.429292683140706e-05,
+      "loss": 0.1539,
+      "step": 456
+    },
+    {
+      "epoch": 0.42393320964749537,
+      "grad_norm": 2.970942497253418,
+      "learning_rate": 1.4263653048842461e-05,
+      "loss": 0.1374,
+      "step": 457
+    },
+    {
+      "epoch": 0.424860853432282,
+      "grad_norm": 3.1692464351654053,
+      "learning_rate": 1.4234334542574906e-05,
+      "loss": 0.2035,
+      "step": 458
+    },
+    {
+      "epoch": 0.42578849721706863,
+      "grad_norm": 2.829171895980835,
+      "learning_rate": 1.4204971620141648e-05,
+      "loss": 0.1483,
+      "step": 459
+    },
+    {
+      "epoch": 0.4267161410018553,
+      "grad_norm": 3.1080052852630615,
+      "learning_rate": 1.4175564589545853e-05,
+      "loss": 0.0959,
+      "step": 460
+    },
+    {
+      "epoch": 0.4267161410018553,
+      "eval_accuracy": 0.8569844789356984,
+      "eval_f1": 0.6993006993006993,
+      "eval_loss": 0.3129526674747467,
+      "eval_precision": 0.8522727272727273,
+      "eval_recall": 0.5928853754940712,
+      "eval_runtime": 48.0013,
+      "eval_samples_per_second": 5.75,
+      "eval_steps_per_second": 0.187,
+      "step": 460
+    },
+    {
+      "epoch": 0.42764378478664195,
+      "grad_norm": 4.785598278045654,
+      "learning_rate": 1.4146113759253362e-05,
+      "loss": 0.1891,
+      "step": 461
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 4.229030609130859,
+      "learning_rate": 1.411661943818944e-05,
+      "loss": 0.1546,
+      "step": 462
+    },
+    {
+      "epoch": 0.4294990723562152,
+      "grad_norm": 4.43852424621582,
+      "learning_rate": 1.4087081935735565e-05,
+      "loss": 0.1769,
+      "step": 463
+    },
+    {
+      "epoch": 0.43042671614100186,
+      "grad_norm": 4.6244049072265625,
+      "learning_rate": 1.4057501561726157e-05,
+      "loss": 0.2404,
+      "step": 464
+    },
+    {
+      "epoch": 0.4313543599257885,
+      "grad_norm": 4.3941168785095215,
+      "learning_rate": 1.4027878626445339e-05,
+      "loss": 0.1781,
+      "step": 465
+    },
+    {
+      "epoch": 0.4322820037105751,
+      "grad_norm": 6.995157718658447,
+      "learning_rate": 1.3998213440623691e-05,
+      "loss": 0.2318,
+      "step": 466
+    },
+    {
+      "epoch": 0.4332096474953618,
+      "grad_norm": 2.781472682952881,
+      "learning_rate": 1.3968506315434973e-05,
+      "loss": 0.0949,
+      "step": 467
+    },
+    {
+      "epoch": 0.43413729128014844,
+      "grad_norm": 2.9485185146331787,
+      "learning_rate": 1.3938757562492873e-05,
+      "loss": 0.1268,
+      "step": 468
+    },
+    {
+      "epoch": 0.43506493506493504,
+      "grad_norm": 6.8653130531311035,
+      "learning_rate": 1.390896749384773e-05,
+      "loss": 0.2818,
+      "step": 469
+    },
+    {
+      "epoch": 0.4359925788497217,
+      "grad_norm": 5.269331932067871,
+      "learning_rate": 1.3879136421983265e-05,
+      "loss": 0.1386,
+      "step": 470
+    },
+    {
+      "epoch": 0.43692022263450836,
+      "grad_norm": 5.839674472808838,
+      "learning_rate": 1.3849264659813314e-05,
+      "loss": 0.1739,
+      "step": 471
+    },
+    {
+      "epoch": 0.437847866419295,
+      "grad_norm": 4.306594371795654,
+      "learning_rate": 1.3819352520678519e-05,
+      "loss": 0.1562,
+      "step": 472
+    },
+    {
+      "epoch": 0.4387755102040816,
+      "grad_norm": 4.80615234375,
+      "learning_rate": 1.378940031834307e-05,
+      "loss": 0.2049,
+      "step": 473
+    },
+    {
+      "epoch": 0.4397031539888683,
+      "grad_norm": 4.824836730957031,
+      "learning_rate": 1.3759408366991391e-05,
+      "loss": 0.1667,
+      "step": 474
+    },
+    {
+      "epoch": 0.44063079777365494,
+      "grad_norm": 4.227314472198486,
+      "learning_rate": 1.3729376981224869e-05,
+      "loss": 0.1783,
+      "step": 475
+    },
+    {
+      "epoch": 0.44155844155844154,
+      "grad_norm": 4.170743942260742,
+      "learning_rate": 1.3699306476058523e-05,
+      "loss": 0.1724,
+      "step": 476
+    },
+    {
+      "epoch": 0.4424860853432282,
+      "grad_norm": 6.098860263824463,
+      "learning_rate": 1.3669197166917723e-05,
+      "loss": 0.2301,
+      "step": 477
+    },
+    {
+      "epoch": 0.44341372912801486,
+      "grad_norm": 3.2894742488861084,
+      "learning_rate": 1.3639049369634878e-05,
+      "loss": 0.1636,
+      "step": 478
+    },
+    {
+      "epoch": 0.44434137291280146,
+      "grad_norm": 3.913362503051758,
+      "learning_rate": 1.3608863400446113e-05,
+      "loss": 0.1762,
+      "step": 479
+    },
+    {
+      "epoch": 0.4452690166975881,
+      "grad_norm": 4.007498741149902,
+      "learning_rate": 1.357863957598796e-05,
+      "loss": 0.1955,
+      "step": 480
+    },
+    {
+      "epoch": 0.4452690166975881,
+      "eval_accuracy": 0.8592017738359202,
+      "eval_f1": 0.7080459770114943,
+      "eval_loss": 0.3043546974658966,
+      "eval_precision": 0.8461538461538461,
+      "eval_recall": 0.6086956521739131,
+      "eval_runtime": 48.2191,
+      "eval_samples_per_second": 5.724,
+      "eval_steps_per_second": 0.187,
+      "step": 480
+    },
+    {
+      "epoch": 0.4461966604823748,
+      "grad_norm": 4.113521575927734,
+      "learning_rate": 1.3548378213294042e-05,
+      "loss": 0.1875,
+      "step": 481
+    },
+    {
+      "epoch": 0.44712430426716143,
+      "grad_norm": 4.532953262329102,
+      "learning_rate": 1.3518079629791725e-05,
+      "loss": 0.1425,
+      "step": 482
+    },
+    {
+      "epoch": 0.44805194805194803,
+      "grad_norm": 2.7280144691467285,
+      "learning_rate": 1.3487744143298822e-05,
+      "loss": 0.0783,
+      "step": 483
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 3.562812566757202,
+      "learning_rate": 1.345737207202023e-05,
+      "loss": 0.1569,
+      "step": 484
+    },
+    {
+      "epoch": 0.44990723562152135,
+      "grad_norm": 5.523044109344482,
+      "learning_rate": 1.3426963734544601e-05,
+      "loss": 0.2227,
+      "step": 485
+    },
+    {
+      "epoch": 0.45083487940630795,
+      "grad_norm": 4.155531883239746,
+      "learning_rate": 1.3396519449841006e-05,
+      "loss": 0.2297,
+      "step": 486
+    },
+    {
+      "epoch": 0.4517625231910946,
+      "grad_norm": 2.8421530723571777,
+      "learning_rate": 1.3366039537255589e-05,
+      "loss": 0.1699,
+      "step": 487
+    },
+    {
+      "epoch": 0.45269016697588127,
+      "grad_norm": 3.845489263534546,
+      "learning_rate": 1.3335524316508208e-05,
+      "loss": 0.1773,
+      "step": 488
+    },
+    {
+      "epoch": 0.4536178107606679,
+      "grad_norm": 3.0157673358917236,
+      "learning_rate": 1.3304974107689088e-05,
+      "loss": 0.1379,
+      "step": 489
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.74364972114563,
+      "learning_rate": 1.3274389231255466e-05,
+      "loss": 0.1265,
+      "step": 490
+    },
+    {
+      "epoch": 0.4554730983302412,
+      "grad_norm": 6.820478439331055,
+      "learning_rate": 1.3243770008028225e-05,
+      "loss": 0.1849,
+      "step": 491
+    },
+    {
+      "epoch": 0.45640074211502785,
+      "grad_norm": 2.741809368133545,
+      "learning_rate": 1.3213116759188525e-05,
+      "loss": 0.1295,
+      "step": 492
+    },
+    {
+      "epoch": 0.45732838589981445,
+      "grad_norm": 3.473961353302002,
+      "learning_rate": 1.3182429806274442e-05,
+      "loss": 0.099,
+      "step": 493
+    },
+    {
+      "epoch": 0.4582560296846011,
+      "grad_norm": 5.271576881408691,
+      "learning_rate": 1.3151709471177589e-05,
+      "loss": 0.1753,
+      "step": 494
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 6.4196577072143555,
+      "learning_rate": 1.3120956076139746e-05,
+      "loss": 0.2568,
+      "step": 495
+    },
+    {
+      "epoch": 0.4601113172541744,
+      "grad_norm": 5.339606761932373,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.1535,
+      "step": 496
+    },
+    {
+      "epoch": 0.461038961038961,
+      "grad_norm": 4.3615593910217285,
+      "learning_rate": 1.305935139693874e-05,
+      "loss": 0.1362,
+      "step": 497
+    },
+    {
+      "epoch": 0.4619666048237477,
+      "grad_norm": 4.690557956695557,
+      "learning_rate": 1.3028500758979507e-05,
+      "loss": 0.1776,
+      "step": 498
+    },
+    {
+      "epoch": 0.46289424860853434,
+      "grad_norm": 4.32938814163208,
+      "learning_rate": 1.299761835348038e-05,
+      "loss": 0.1429,
+      "step": 499
+    },
+    {
+      "epoch": 0.46382189239332094,
+      "grad_norm": 3.8397958278656006,
+      "learning_rate": 1.296670450438317e-05,
+      "loss": 0.1904,
+      "step": 500
+    },
+    {
+      "epoch": 0.46382189239332094,
+      "eval_accuracy": 0.8403547671840355,
+      "eval_f1": 0.6381909547738693,
+      "eval_loss": 0.3388740122318268,
+      "eval_precision": 0.8758620689655172,
+      "eval_recall": 0.5019762845849802,
+      "eval_runtime": 48.3395,
+      "eval_samples_per_second": 5.71,
+      "eval_steps_per_second": 0.186,
+      "step": 500
     }
   ],
   "logging_steps": 1,
@@ -3078,7 +3838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2786427319078093e+17,
+  "total_flos": 1.5957678843389542e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null