{
  "best_metric": 1.2769535779953003,
  "best_model_checkpoint": "mental-roberta-base-CD_baseline/checkpoint-1000",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 4.378986358642578,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 2.389,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.568194389343262,
      "learning_rate": 1.98e-05,
      "loss": 2.1424,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 15.351970672607422,
      "learning_rate": 1.97e-05,
      "loss": 1.978,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.168962478637695,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 1.8678,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.635171413421631,
      "learning_rate": 1.95e-05,
      "loss": 1.7668,
      "step": 50
    },
    {
      "epoch": 0.24,
      "grad_norm": 3.921550989151001,
      "learning_rate": 1.94e-05,
      "loss": 1.6985,
      "step": 60
    },
    {
      "epoch": 0.28,
      "grad_norm": 21.30545425415039,
      "learning_rate": 1.93e-05,
      "loss": 1.7725,
      "step": 70
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.5897629261016846,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.9746,
      "step": 80
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.9138140678405762,
      "learning_rate": 1.91e-05,
      "loss": 1.4866,
      "step": 90
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.1776585578918457,
      "learning_rate": 1.9e-05,
      "loss": 1.737,
      "step": 100
    },
    {
      "epoch": 0.44,
      "grad_norm": 7.035165309906006,
      "learning_rate": 1.8900000000000002e-05,
      "loss": 1.98,
      "step": 110
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.098265647888184,
      "learning_rate": 1.88e-05,
      "loss": 1.6998,
      "step": 120
    },
    {
      "epoch": 0.52,
      "grad_norm": 4.009236812591553,
      "learning_rate": 1.8700000000000004e-05,
      "loss": 1.6323,
      "step": 130
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.8470473289489746,
      "learning_rate": 1.86e-05,
      "loss": 1.8226,
      "step": 140
    },
    {
      "epoch": 0.6,
      "grad_norm": 49.7083740234375,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 1.7309,
      "step": 150
    },
    {
      "epoch": 0.64,
      "grad_norm": 4.127583980560303,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.7606,
      "step": 160
    },
    {
      "epoch": 0.68,
      "grad_norm": 2.7759668827056885,
      "learning_rate": 1.83e-05,
      "loss": 1.4,
      "step": 170
    },
    {
      "epoch": 0.72,
      "grad_norm": 6.541387557983398,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 1.647,
      "step": 180
    },
    {
      "epoch": 0.76,
      "grad_norm": 5.6331706047058105,
      "learning_rate": 1.8100000000000003e-05,
      "loss": 1.5166,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.045393466949463,
      "learning_rate": 1.8e-05,
      "loss": 1.7162,
      "step": 200
    },
    {
      "epoch": 0.84,
      "grad_norm": 6.527945041656494,
      "learning_rate": 1.79e-05,
      "loss": 1.6117,
      "step": 210
    },
    {
      "epoch": 0.88,
      "grad_norm": 3.565760374069214,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 1.7464,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 4.898312568664551,
      "learning_rate": 1.77e-05,
      "loss": 1.561,
      "step": 230
    },
    {
      "epoch": 0.96,
      "grad_norm": 5.3700103759765625,
      "learning_rate": 1.76e-05,
      "loss": 1.5109,
      "step": 240
    },
    {
      "epoch": 1.0,
      "grad_norm": 15.15703010559082,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.7629,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47391304347826085,
      "eval_f1": 0.38428281400288544,
      "eval_loss": 1.5328094959259033,
      "eval_precision": 0.3534519719474924,
      "eval_recall": 0.47391304347826085,
      "eval_runtime": 1.0211,
      "eval_samples_per_second": 225.243,
      "eval_steps_per_second": 28.4,
      "step": 250
    },
    {
      "epoch": 1.04,
      "grad_norm": 11.55996322631836,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 1.5392,
      "step": 260
    },
    {
      "epoch": 1.08,
      "grad_norm": 9.391329765319824,
      "learning_rate": 1.73e-05,
      "loss": 1.5147,
      "step": 270
    },
    {
      "epoch": 1.12,
      "grad_norm": 7.441842079162598,
      "learning_rate": 1.72e-05,
      "loss": 1.5203,
      "step": 280
    },
    {
      "epoch": 1.16,
      "grad_norm": 9.423290252685547,
      "learning_rate": 1.7100000000000002e-05,
      "loss": 1.34,
      "step": 290
    },
    {
      "epoch": 1.2,
      "grad_norm": 6.1367573738098145,
      "learning_rate": 1.7e-05,
      "loss": 1.368,
      "step": 300
    },
    {
      "epoch": 1.24,
      "grad_norm": 8.754669189453125,
      "learning_rate": 1.69e-05,
      "loss": 1.4532,
      "step": 310
    },
    {
      "epoch": 1.28,
      "grad_norm": 12.048688888549805,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.5626,
      "step": 320
    },
    {
      "epoch": 1.32,
      "grad_norm": 8.47139835357666,
      "learning_rate": 1.67e-05,
      "loss": 1.4029,
      "step": 330
    },
    {
      "epoch": 1.36,
      "grad_norm": 13.538434982299805,
      "learning_rate": 1.66e-05,
      "loss": 1.2561,
      "step": 340
    },
    {
      "epoch": 1.4,
      "grad_norm": 11.475522994995117,
      "learning_rate": 1.65e-05,
      "loss": 1.5971,
      "step": 350
    },
    {
      "epoch": 1.44,
      "grad_norm": 14.821061134338379,
      "learning_rate": 1.64e-05,
      "loss": 1.6198,
      "step": 360
    },
    {
      "epoch": 1.48,
      "grad_norm": 12.751998901367188,
      "learning_rate": 1.63e-05,
      "loss": 1.28,
      "step": 370
    },
    {
      "epoch": 1.52,
      "grad_norm": 10.061027526855469,
      "learning_rate": 1.62e-05,
      "loss": 1.226,
      "step": 380
    },
    {
      "epoch": 1.56,
      "grad_norm": 21.2222900390625,
      "learning_rate": 1.6100000000000002e-05,
      "loss": 1.1642,
      "step": 390
    },
    {
      "epoch": 1.6,
      "grad_norm": 15.691130638122559,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.4167,
      "step": 400
    },
    {
      "epoch": 1.64,
      "grad_norm": 17.03270721435547,
      "learning_rate": 1.5900000000000004e-05,
      "loss": 1.3666,
      "step": 410
    },
    {
      "epoch": 1.68,
      "grad_norm": 8.01834487915039,
      "learning_rate": 1.58e-05,
      "loss": 1.237,
      "step": 420
    },
    {
      "epoch": 1.72,
      "grad_norm": 18.645164489746094,
      "learning_rate": 1.5700000000000002e-05,
      "loss": 1.4502,
      "step": 430
    },
    {
      "epoch": 1.76,
      "grad_norm": 12.169353485107422,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 1.5965,
      "step": 440
    },
    {
      "epoch": 1.8,
      "grad_norm": 13.11835765838623,
      "learning_rate": 1.55e-05,
      "loss": 1.1895,
      "step": 450
    },
    {
      "epoch": 1.84,
      "grad_norm": 29.902376174926758,
      "learning_rate": 1.54e-05,
      "loss": 1.4158,
      "step": 460
    },
    {
      "epoch": 1.88,
      "grad_norm": 8.317435264587402,
      "learning_rate": 1.5300000000000003e-05,
      "loss": 1.2013,
      "step": 470
    },
    {
      "epoch": 1.92,
      "grad_norm": 10.2247314453125,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.3446,
      "step": 480
    },
    {
      "epoch": 1.96,
      "grad_norm": 11.59114933013916,
      "learning_rate": 1.5100000000000001e-05,
      "loss": 1.2326,
      "step": 490
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.2176513671875,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.4033,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5260869565217391,
      "eval_f1": 0.5009687691265158,
      "eval_loss": 1.3281586170196533,
      "eval_precision": 0.5395269845664888,
      "eval_recall": 0.5260869565217391,
      "eval_runtime": 1.0114,
      "eval_samples_per_second": 227.398,
      "eval_steps_per_second": 28.672,
      "step": 500
    },
    {
      "epoch": 2.04,
      "grad_norm": 11.444624900817871,
      "learning_rate": 1.4900000000000001e-05,
      "loss": 1.1357,
      "step": 510
    },
    {
      "epoch": 2.08,
      "grad_norm": 13.202922821044922,
      "learning_rate": 1.48e-05,
      "loss": 1.154,
      "step": 520
    },
    {
      "epoch": 2.12,
      "grad_norm": 16.034732818603516,
      "learning_rate": 1.4700000000000002e-05,
      "loss": 1.0562,
      "step": 530
    },
    {
      "epoch": 2.16,
      "grad_norm": 7.477020263671875,
      "learning_rate": 1.46e-05,
      "loss": 1.0975,
      "step": 540
    },
    {
      "epoch": 2.2,
      "grad_norm": 12.851716995239258,
      "learning_rate": 1.45e-05,
      "loss": 1.1655,
      "step": 550
    },
    {
      "epoch": 2.24,
      "grad_norm": 13.109989166259766,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.0101,
      "step": 560
    },
    {
      "epoch": 2.28,
      "grad_norm": 14.998272895812988,
      "learning_rate": 1.43e-05,
      "loss": 0.9762,
      "step": 570
    },
    {
      "epoch": 2.32,
      "grad_norm": 22.052188873291016,
      "learning_rate": 1.4200000000000001e-05,
      "loss": 1.0931,
      "step": 580
    },
    {
      "epoch": 2.36,
      "grad_norm": 20.38056182861328,
      "learning_rate": 1.41e-05,
      "loss": 1.0295,
      "step": 590
    },
    {
      "epoch": 2.4,
      "grad_norm": 14.597001075744629,
      "learning_rate": 1.4e-05,
      "loss": 1.0001,
      "step": 600
    },
    {
      "epoch": 2.44,
      "grad_norm": 18.28936195373535,
      "learning_rate": 1.39e-05,
      "loss": 1.1457,
      "step": 610
    },
    {
      "epoch": 2.48,
      "grad_norm": 4.188849925994873,
      "learning_rate": 1.38e-05,
      "loss": 1.1505,
      "step": 620
    },
    {
      "epoch": 2.52,
      "grad_norm": 19.210851669311523,
      "learning_rate": 1.3700000000000003e-05,
      "loss": 0.9443,
      "step": 630
    },
    {
      "epoch": 2.56,
      "grad_norm": 14.057235717773438,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.1828,
      "step": 640
    },
    {
      "epoch": 2.6,
      "grad_norm": 18.877193450927734,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.2169,
      "step": 650
    },
    {
      "epoch": 2.64,
      "grad_norm": 11.197978019714355,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 1.0629,
      "step": 660
    },
    {
      "epoch": 2.68,
      "grad_norm": 34.57655715942383,
      "learning_rate": 1.3300000000000001e-05,
      "loss": 1.183,
      "step": 670
    },
    {
      "epoch": 2.72,
      "grad_norm": 15.682902336120605,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 0.9974,
      "step": 680
    },
    {
      "epoch": 2.76,
      "grad_norm": 12.469610214233398,
      "learning_rate": 1.3100000000000002e-05,
      "loss": 1.1861,
      "step": 690
    },
    {
      "epoch": 2.8,
      "grad_norm": 19.878341674804688,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.0039,
      "step": 700
    },
    {
      "epoch": 2.84,
      "grad_norm": 18.73297691345215,
      "learning_rate": 1.2900000000000002e-05,
      "loss": 1.0106,
      "step": 710
    },
    {
      "epoch": 2.88,
      "grad_norm": 23.088468551635742,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.0126,
      "step": 720
    },
    {
      "epoch": 2.92,
      "grad_norm": 16.777488708496094,
      "learning_rate": 1.27e-05,
      "loss": 0.8662,
      "step": 730
    },
    {
      "epoch": 2.96,
      "grad_norm": 16.595956802368164,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 1.0424,
      "step": 740
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.72782039642334,
      "learning_rate": 1.25e-05,
      "loss": 0.7635,
      "step": 750
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5608695652173913,
      "eval_f1": 0.5336963494705901,
      "eval_loss": 1.3101598024368286,
      "eval_precision": 0.537211136181388,
      "eval_recall": 0.5608695652173913,
      "eval_runtime": 1.0439,
      "eval_samples_per_second": 220.326,
      "eval_steps_per_second": 27.78,
      "step": 750
    },
    {
      "epoch": 3.04,
      "grad_norm": 8.257983207702637,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 0.7983,
      "step": 760
    },
    {
      "epoch": 3.08,
      "grad_norm": 17.17106056213379,
      "learning_rate": 1.23e-05,
      "loss": 0.8106,
      "step": 770
    },
    {
      "epoch": 3.12,
      "grad_norm": 6.935492515563965,
      "learning_rate": 1.22e-05,
      "loss": 0.5296,
      "step": 780
    },
    {
      "epoch": 3.16,
      "grad_norm": 26.85825538635254,
      "learning_rate": 1.2100000000000001e-05,
      "loss": 0.9861,
      "step": 790
    },
    {
      "epoch": 3.2,
      "grad_norm": 10.665637016296387,
      "learning_rate": 1.2e-05,
      "loss": 0.9043,
      "step": 800
    },
    {
      "epoch": 3.24,
      "grad_norm": 34.452388763427734,
      "learning_rate": 1.1900000000000001e-05,
      "loss": 0.8038,
      "step": 810
    },
    {
      "epoch": 3.28,
      "grad_norm": 18.837228775024414,
      "learning_rate": 1.18e-05,
      "loss": 0.8004,
      "step": 820
    },
    {
      "epoch": 3.32,
      "grad_norm": 13.866151809692383,
      "learning_rate": 1.17e-05,
      "loss": 0.6666,
      "step": 830
    },
    {
      "epoch": 3.36,
      "grad_norm": 12.578895568847656,
      "learning_rate": 1.16e-05,
      "loss": 0.6488,
      "step": 840
    },
    {
      "epoch": 3.4,
      "grad_norm": 2.9693028926849365,
      "learning_rate": 1.15e-05,
      "loss": 0.9074,
      "step": 850
    },
    {
      "epoch": 3.44,
      "grad_norm": 11.259392738342285,
      "learning_rate": 1.14e-05,
      "loss": 0.7097,
      "step": 860
    },
    {
      "epoch": 3.48,
      "grad_norm": 8.34443187713623,
      "learning_rate": 1.13e-05,
      "loss": 0.7404,
      "step": 870
    },
    {
      "epoch": 3.52,
      "grad_norm": 22.02679443359375,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.7031,
      "step": 880
    },
    {
      "epoch": 3.56,
      "grad_norm": 18.178070068359375,
      "learning_rate": 1.1100000000000002e-05,
      "loss": 0.7763,
      "step": 890
    },
    {
      "epoch": 3.6,
      "grad_norm": 38.39835739135742,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.8073,
      "step": 900
    },
    {
      "epoch": 3.64,
      "grad_norm": 27.14322280883789,
      "learning_rate": 1.0900000000000002e-05,
      "loss": 0.745,
      "step": 910
    },
    {
      "epoch": 3.68,
      "grad_norm": 14.671334266662598,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 0.7552,
      "step": 920
    },
    {
      "epoch": 3.72,
      "grad_norm": 6.039632320404053,
      "learning_rate": 1.0700000000000001e-05,
      "loss": 0.6619,
      "step": 930
    },
    {
      "epoch": 3.76,
      "grad_norm": 20.04022979736328,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 0.7781,
      "step": 940
    },
    {
      "epoch": 3.8,
      "grad_norm": 20.994312286376953,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 0.8624,
      "step": 950
    },
    {
      "epoch": 3.84,
      "grad_norm": 27.07198143005371,
      "learning_rate": 1.04e-05,
      "loss": 0.728,
      "step": 960
    },
    {
      "epoch": 3.88,
      "grad_norm": 17.27962875366211,
      "learning_rate": 1.0300000000000001e-05,
      "loss": 0.6684,
      "step": 970
    },
    {
      "epoch": 3.92,
      "grad_norm": 20.02420997619629,
      "learning_rate": 1.02e-05,
      "loss": 0.6107,
      "step": 980
    },
    {
      "epoch": 3.96,
      "grad_norm": 4.354977607727051,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 0.6526,
      "step": 990
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.899433135986328,
      "learning_rate": 1e-05,
      "loss": 0.8688,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5956521739130435,
      "eval_f1": 0.5794783047946798,
      "eval_loss": 1.2769535779953003,
      "eval_precision": 0.580110231445542,
      "eval_recall": 0.5956521739130435,
      "eval_runtime": 1.0338,
      "eval_samples_per_second": 222.477,
      "eval_steps_per_second": 28.051,
      "step": 1000
    },
    {
      "epoch": 4.04,
      "grad_norm": 13.660650253295898,
      "learning_rate": 9.9e-06,
      "loss": 0.5165,
      "step": 1010
    },
    {
      "epoch": 4.08,
      "grad_norm": 6.362195014953613,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.3606,
      "step": 1020
    },
    {
      "epoch": 4.12,
      "grad_norm": 4.183453559875488,
      "learning_rate": 9.7e-06,
      "loss": 0.4387,
      "step": 1030
    },
    {
      "epoch": 4.16,
      "grad_norm": 26.112573623657227,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.586,
      "step": 1040
    },
    {
      "epoch": 4.2,
      "grad_norm": 19.786802291870117,
      "learning_rate": 9.5e-06,
      "loss": 0.5322,
      "step": 1050
    },
    {
      "epoch": 4.24,
      "grad_norm": 8.961174011230469,
      "learning_rate": 9.4e-06,
      "loss": 0.6079,
      "step": 1060
    },
    {
      "epoch": 4.28,
      "grad_norm": 15.39157772064209,
      "learning_rate": 9.3e-06,
      "loss": 0.4597,
      "step": 1070
    },
    {
      "epoch": 4.32,
      "grad_norm": 24.373172760009766,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.6407,
      "step": 1080
    },
    {
      "epoch": 4.36,
      "grad_norm": 20.961610794067383,
      "learning_rate": 9.100000000000001e-06,
      "loss": 0.4461,
      "step": 1090
    },
    {
      "epoch": 4.4,
      "grad_norm": 16.351242065429688,
      "learning_rate": 9e-06,
      "loss": 0.5012,
      "step": 1100
    },
    {
      "epoch": 4.44,
      "grad_norm": 10.587532043457031,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.6065,
      "step": 1110
    },
    {
      "epoch": 4.48,
      "grad_norm": 4.534018516540527,
      "learning_rate": 8.8e-06,
      "loss": 0.2906,
      "step": 1120
    },
    {
      "epoch": 4.52,
      "grad_norm": 1.747666597366333,
      "learning_rate": 8.700000000000001e-06,
      "loss": 0.4286,
      "step": 1130
    },
    {
      "epoch": 4.56,
      "grad_norm": 17.067201614379883,
      "learning_rate": 8.6e-06,
      "loss": 0.4721,
      "step": 1140
    },
    {
      "epoch": 4.6,
      "grad_norm": 15.651820182800293,
      "learning_rate": 8.5e-06,
      "loss": 0.5677,
      "step": 1150
    },
    {
      "epoch": 4.64,
      "grad_norm": 20.833948135375977,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.4825,
      "step": 1160
    },
    {
      "epoch": 4.68,
      "grad_norm": 1.568106770515442,
      "learning_rate": 8.3e-06,
      "loss": 0.5056,
      "step": 1170
    },
    {
      "epoch": 4.72,
      "grad_norm": 21.512529373168945,
      "learning_rate": 8.2e-06,
      "loss": 0.4923,
      "step": 1180
    },
    {
      "epoch": 4.76,
      "grad_norm": 11.180012702941895,
      "learning_rate": 8.1e-06,
      "loss": 0.6553,
      "step": 1190
    },
    {
      "epoch": 4.8,
      "grad_norm": 17.37482452392578,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.3976,
      "step": 1200
    },
    {
      "epoch": 4.84,
      "grad_norm": 15.096935272216797,
      "learning_rate": 7.9e-06,
      "loss": 0.6105,
      "step": 1210
    },
    {
      "epoch": 4.88,
      "grad_norm": 8.122323036193848,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.4211,
      "step": 1220
    },
    {
      "epoch": 4.92,
      "grad_norm": 15.952132225036621,
      "learning_rate": 7.7e-06,
      "loss": 0.6625,
      "step": 1230
    },
    {
      "epoch": 4.96,
      "grad_norm": 18.230487823486328,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.5536,
      "step": 1240
    },
    {
      "epoch": 5.0,
      "grad_norm": 43.71910095214844,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4432,
      "step": 1250
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6086956521739131,
      "eval_f1": 0.594058293120158,
      "eval_loss": 1.4374070167541504,
      "eval_precision": 0.6038115384886801,
      "eval_recall": 0.6086956521739131,
      "eval_runtime": 1.0253,
      "eval_samples_per_second": 224.32,
      "eval_steps_per_second": 28.284,
      "step": 1250
    },
    {
      "epoch": 5.04,
      "grad_norm": 16.41998863220215,
      "learning_rate": 7.4e-06,
      "loss": 0.3491,
      "step": 1260
    },
    {
      "epoch": 5.08,
      "grad_norm": 16.400732040405273,
      "learning_rate": 7.3e-06,
      "loss": 0.3177,
      "step": 1270
    },
    {
      "epoch": 5.12,
      "grad_norm": 21.35452651977539,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.3004,
      "step": 1280
    },
    {
      "epoch": 5.16,
      "grad_norm": 9.482089042663574,
      "learning_rate": 7.100000000000001e-06,
      "loss": 0.2588,
      "step": 1290
    },
    {
      "epoch": 5.2,
      "grad_norm": 14.700976371765137,
      "learning_rate": 7e-06,
      "loss": 0.3262,
      "step": 1300
    },
    {
      "epoch": 5.24,
      "grad_norm": 11.437019348144531,
      "learning_rate": 6.9e-06,
      "loss": 0.3954,
      "step": 1310
    },
    {
      "epoch": 5.28,
      "grad_norm": 10.643627166748047,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.1852,
      "step": 1320
    },
    {
      "epoch": 5.32,
      "grad_norm": 33.29022216796875,
      "learning_rate": 6.700000000000001e-06,
      "loss": 0.5024,
      "step": 1330
    },
    {
      "epoch": 5.36,
      "grad_norm": 27.292346954345703,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.2858,
      "step": 1340
    },
    {
      "epoch": 5.4,
      "grad_norm": 34.4414176940918,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.2465,
      "step": 1350
    },
    {
      "epoch": 5.44,
      "grad_norm": 19.40508270263672,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.3818,
      "step": 1360
    },
    {
      "epoch": 5.48,
      "grad_norm": 30.40248680114746,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.3123,
      "step": 1370
    },
    {
      "epoch": 5.52,
      "grad_norm": 16.111865997314453,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.2661,
      "step": 1380
    },
    {
      "epoch": 5.56,
      "grad_norm": 11.861916542053223,
      "learning_rate": 6.1e-06,
      "loss": 0.4043,
      "step": 1390
    },
    {
      "epoch": 5.6,
      "grad_norm": 39.95186996459961,
      "learning_rate": 6e-06,
      "loss": 0.3573,
      "step": 1400
    },
    {
      "epoch": 5.64,
      "grad_norm": 12.199712753295898,
      "learning_rate": 5.9e-06,
      "loss": 0.2876,
      "step": 1410
    },
    {
      "epoch": 5.68,
      "grad_norm": 37.9615364074707,
      "learning_rate": 5.8e-06,
      "loss": 0.3462,
      "step": 1420
    },
    {
      "epoch": 5.72,
      "grad_norm": 60.29270553588867,
      "learning_rate": 5.7e-06,
      "loss": 0.4482,
      "step": 1430
    },
    {
      "epoch": 5.76,
      "grad_norm": 10.729787826538086,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.3709,
      "step": 1440
    },
    {
      "epoch": 5.8,
      "grad_norm": 28.756450653076172,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.4185,
      "step": 1450
    },
    {
      "epoch": 5.84,
      "grad_norm": 12.605400085449219,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.3089,
      "step": 1460
    },
    {
      "epoch": 5.88,
      "grad_norm": 1.9020392894744873,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.1827,
      "step": 1470
    },
    {
      "epoch": 5.92,
      "grad_norm": 4.700870513916016,
      "learning_rate": 5.2e-06,
      "loss": 0.3849,
      "step": 1480
    },
    {
      "epoch": 5.96,
      "grad_norm": 8.93205451965332,
      "learning_rate": 5.1e-06,
      "loss": 0.3077,
      "step": 1490
    },
    {
      "epoch": 6.0,
      "grad_norm": 32.244083404541016,
      "learning_rate": 5e-06,
      "loss": 0.3489,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_f1": 0.5901467318357858,
      "eval_loss": 1.481338620185852,
      "eval_precision": 0.6123818572731616,
      "eval_recall": 0.5869565217391305,
      "eval_runtime": 1.0437,
      "eval_samples_per_second": 220.36,
      "eval_steps_per_second": 27.784,
      "step": 1500
    },
    {
      "epoch": 6.04,
      "grad_norm": 10.3549165725708,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.2758,
      "step": 1510
    },
    {
      "epoch": 6.08,
      "grad_norm": 12.63352108001709,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.205,
      "step": 1520
    },
    {
      "epoch": 6.12,
      "grad_norm": 9.606993675231934,
      "learning_rate": 4.7e-06,
      "loss": 0.2557,
      "step": 1530
    },
    {
      "epoch": 6.16,
      "grad_norm": 1.3631489276885986,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.255,
      "step": 1540
    },
    {
      "epoch": 6.2,
      "grad_norm": 22.932092666625977,
      "learning_rate": 4.5e-06,
      "loss": 0.3251,
      "step": 1550
    },
    {
      "epoch": 6.24,
      "grad_norm": 15.687180519104004,
      "learning_rate": 4.4e-06,
      "loss": 0.1323,
      "step": 1560
    },
    {
      "epoch": 6.28,
      "grad_norm": 0.9915614128112793,
      "learning_rate": 4.3e-06,
      "loss": 0.1807,
      "step": 1570
    },
    {
      "epoch": 6.32,
      "grad_norm": 1.9621161222457886,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.2397,
      "step": 1580
    },
    {
      "epoch": 6.36,
      "grad_norm": 1.7371257543563843,
      "learning_rate": 4.1e-06,
      "loss": 0.2391,
      "step": 1590
    },
    {
      "epoch": 6.4,
      "grad_norm": 3.6397323608398438,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2326,
      "step": 1600
    },
    {
      "epoch": 6.44,
      "grad_norm": 19.90898323059082,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.1249,
      "step": 1610
    },
    {
      "epoch": 6.48,
      "grad_norm": 24.969144821166992,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.2336,
      "step": 1620
    },
    {
      "epoch": 6.52,
      "grad_norm": 8.904400825500488,
      "learning_rate": 3.7e-06,
      "loss": 0.244,
      "step": 1630
    },
    {
      "epoch": 6.56,
      "grad_norm": 18.82139778137207,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.2858,
      "step": 1640
    },
    {
      "epoch": 6.6,
      "grad_norm": 24.00533676147461,
      "learning_rate": 3.5e-06,
      "loss": 0.3073,
      "step": 1650
    },
    {
      "epoch": 6.64,
      "grad_norm": 7.122366905212402,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.1949,
      "step": 1660
    },
    {
      "epoch": 6.68,
      "grad_norm": 3.693237781524658,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.1558,
      "step": 1670
    },
    {
      "epoch": 6.72,
      "grad_norm": 16.943511962890625,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.3307,
      "step": 1680
    },
    {
      "epoch": 6.76,
      "grad_norm": 1.202619194984436,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.1836,
      "step": 1690
    },
    {
      "epoch": 6.8,
      "grad_norm": 2.2889859676361084,
      "learning_rate": 3e-06,
      "loss": 0.1612,
      "step": 1700
    },
    {
      "epoch": 6.84,
      "grad_norm": 24.393550872802734,
      "learning_rate": 2.9e-06,
      "loss": 0.2287,
      "step": 1710
    },
    {
      "epoch": 6.88,
      "grad_norm": 15.723957061767578,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.1942,
      "step": 1720
    },
    {
      "epoch": 6.92,
      "grad_norm": 11.214823722839355,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.2522,
      "step": 1730
    },
    {
      "epoch": 6.96,
      "grad_norm": 37.70159149169922,
      "learning_rate": 2.6e-06,
      "loss": 0.1987,
      "step": 1740
    },
    {
      "epoch": 7.0,
      "grad_norm": 19.29395866394043,
      "learning_rate": 2.5e-06,
      "loss": 0.3154,
      "step": 1750
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.591304347826087,
      "eval_f1": 0.59225954110776,
      "eval_loss": 1.561277151107788,
      "eval_precision": 0.6051404726650386,
      "eval_recall": 0.591304347826087,
      "eval_runtime": 1.0235,
      "eval_samples_per_second": 224.722,
      "eval_steps_per_second": 28.334,
      "step": 1750
    },
    {
      "epoch": 7.04,
      "grad_norm": 8.514004707336426,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.141,
      "step": 1760
    },
    {
      "epoch": 7.08,
      "grad_norm": 14.699041366577148,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1434,
      "step": 1770
    },
    {
      "epoch": 7.12,
      "grad_norm": 3.5710041522979736,
      "learning_rate": 2.2e-06,
      "loss": 0.111,
      "step": 1780
    },
    {
      "epoch": 7.16,
      "grad_norm": 6.2862043380737305,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.1849,
      "step": 1790
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.646734356880188,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1165,
      "step": 1800
    },
    {
      "epoch": 7.24,
      "grad_norm": 11.804097175598145,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.1244,
      "step": 1810
    },
    {
      "epoch": 7.28,
      "grad_norm": 0.8081532716751099,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.1073,
      "step": 1820
    },
    {
      "epoch": 7.32,
      "grad_norm": 11.27471923828125,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.1358,
      "step": 1830
    },
    {
      "epoch": 7.36,
      "grad_norm": 5.462678909301758,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.2306,
      "step": 1840
    },
    {
      "epoch": 7.4,
      "grad_norm": 12.020944595336914,
      "learning_rate": 1.5e-06,
      "loss": 0.1748,
      "step": 1850
    },
    {
      "epoch": 7.44,
      "grad_norm": 1.7447506189346313,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.1637,
      "step": 1860
    },
    {
      "epoch": 7.48,
      "grad_norm": 0.5202816724777222,
      "learning_rate": 1.3e-06,
      "loss": 0.2389,
      "step": 1870
    },
    {
      "epoch": 7.52,
      "grad_norm": 2.9551496505737305,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.1258,
      "step": 1880
    },
    {
      "epoch": 7.56,
      "grad_norm": 23.559301376342773,
      "learning_rate": 1.1e-06,
      "loss": 0.2493,
      "step": 1890
    },
    {
      "epoch": 7.6,
      "grad_norm": 41.33919906616211,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.3827,
      "step": 1900
    },
    {
      "epoch": 7.64,
      "grad_norm": 0.6776648759841919,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.2181,
      "step": 1910
    },
    {
      "epoch": 7.68,
      "grad_norm": 22.915781021118164,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.1071,
      "step": 1920
    },
    {
      "epoch": 7.72,
      "grad_norm": 2.265955686569214,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.1141,
      "step": 1930
    },
    {
      "epoch": 7.76,
      "grad_norm": 12.892213821411133,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.2067,
      "step": 1940
    },
    {
      "epoch": 7.8,
      "grad_norm": 9.663905143737793,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.1923,
      "step": 1950
    },
    {
      "epoch": 7.84,
      "grad_norm": 1.7676267623901367,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.1594,
      "step": 1960
    },
    {
      "epoch": 7.88,
      "grad_norm": 10.767372131347656,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.2527,
      "step": 1970
    },
    {
      "epoch": 7.92,
      "grad_norm": 0.9327512979507446,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.1834,
      "step": 1980
    },
    {
      "epoch": 7.96,
      "grad_norm": 5.60221004486084,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 0.1309,
      "step": 1990
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.293955326080322,
      "learning_rate": 0.0,
      "loss": 0.1553,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5956521739130435,
      "eval_f1": 0.5930584359493084,
      "eval_loss": 1.61259126663208,
      "eval_precision": 0.5985692492099816,
      "eval_recall": 0.5956521739130435,
      "eval_runtime": 1.0349,
      "eval_samples_per_second": 222.237,
      "eval_steps_per_second": 28.021,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "step": 2000,
      "total_flos": 1768238889429720.0,
      "train_loss": 0.7754807794690132,
      "train_runtime": 287.3312,
      "train_samples_per_second": 55.573,
      "train_steps_per_second": 6.961
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 1768238889429720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}