{
  "best_metric": 0.0411064513027668,
  "best_model_checkpoint": "./TransparentBagClassifier/checkpoint-316",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 790,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 1.8177610635757446,
      "learning_rate": 1.974683544303798e-05,
      "loss": 0.6502,
      "step": 10
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 1.735235333442688,
      "learning_rate": 1.949367088607595e-05,
      "loss": 0.5886,
      "step": 20
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 1.5866175889968872,
      "learning_rate": 1.9240506329113926e-05,
      "loss": 0.5145,
      "step": 30
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 2.1754307746887207,
      "learning_rate": 1.89873417721519e-05,
      "loss": 0.4214,
      "step": 40
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 1.926560401916504,
      "learning_rate": 1.8734177215189874e-05,
      "loss": 0.303,
      "step": 50
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 1.284515619277954,
      "learning_rate": 1.848101265822785e-05,
      "loss": 0.2735,
      "step": 60
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 1.0484488010406494,
      "learning_rate": 1.8227848101265824e-05,
      "loss": 0.2382,
      "step": 70
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.6332635879516602,
      "learning_rate": 1.7974683544303798e-05,
      "loss": 0.1651,
      "step": 80
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 0.7192436456680298,
      "learning_rate": 1.7721518987341772e-05,
      "loss": 0.1691,
      "step": 90
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 0.5396292209625244,
      "learning_rate": 1.746835443037975e-05,
      "loss": 0.1371,
      "step": 100
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 1.0010855197906494,
      "learning_rate": 1.7215189873417723e-05,
      "loss": 0.1054,
      "step": 110
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 2.316347360610962,
      "learning_rate": 1.6962025316455696e-05,
      "loss": 0.1485,
      "step": 120
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 4.399435043334961,
      "learning_rate": 1.6708860759493674e-05,
      "loss": 0.0898,
      "step": 130
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 0.6504904627799988,
      "learning_rate": 1.6455696202531647e-05,
      "loss": 0.1151,
      "step": 140
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 0.26793766021728516,
      "learning_rate": 1.620253164556962e-05,
      "loss": 0.0694,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9820627802690582,
      "eval_loss": 0.0719464123249054,
      "eval_runtime": 29.347,
      "eval_samples_per_second": 7.599,
      "eval_steps_per_second": 0.954,
      "step": 158
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.31842896342277527,
      "learning_rate": 1.5949367088607598e-05,
      "loss": 0.0743,
      "step": 160
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 4.0135979652404785,
      "learning_rate": 1.5696202531645572e-05,
      "loss": 0.0614,
      "step": 170
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 0.2785925567150116,
      "learning_rate": 1.5443037974683546e-05,
      "loss": 0.0635,
      "step": 180
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 0.21624621748924255,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 0.0524,
      "step": 190
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.35363027453422546,
      "learning_rate": 1.4936708860759495e-05,
      "loss": 0.0342,
      "step": 200
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 1.0792415142059326,
      "learning_rate": 1.468354430379747e-05,
      "loss": 0.0497,
      "step": 210
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 0.19490359723567963,
      "learning_rate": 1.4430379746835444e-05,
      "loss": 0.0591,
      "step": 220
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 0.16427624225616455,
      "learning_rate": 1.417721518987342e-05,
      "loss": 0.037,
      "step": 230
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 7.667697429656982,
      "learning_rate": 1.3924050632911395e-05,
      "loss": 0.089,
      "step": 240
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 0.15142761170864105,
      "learning_rate": 1.3670886075949368e-05,
      "loss": 0.1013,
      "step": 250
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 3.7054553031921387,
      "learning_rate": 1.3417721518987344e-05,
      "loss": 0.077,
      "step": 260
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 0.13252966105937958,
      "learning_rate": 1.3164556962025317e-05,
      "loss": 0.0528,
      "step": 270
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 0.14607028663158417,
      "learning_rate": 1.2911392405063293e-05,
      "loss": 0.1078,
      "step": 280
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 0.17516593635082245,
      "learning_rate": 1.2658227848101268e-05,
      "loss": 0.0872,
      "step": 290
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.4909473955631256,
      "learning_rate": 1.240506329113924e-05,
      "loss": 0.1023,
      "step": 300
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 17.056110382080078,
      "learning_rate": 1.2151898734177216e-05,
      "loss": 0.0871,
      "step": 310
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9955156950672646,
      "eval_loss": 0.0411064513027668,
      "eval_runtime": 30.7571,
      "eval_samples_per_second": 7.25,
      "eval_steps_per_second": 0.91,
      "step": 316
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 0.14253969490528107,
      "learning_rate": 1.189873417721519e-05,
      "loss": 0.0258,
      "step": 320
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 0.1595589965581894,
      "learning_rate": 1.1645569620253165e-05,
      "loss": 0.0181,
      "step": 330
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 0.11532098799943924,
      "learning_rate": 1.139240506329114e-05,
      "loss": 0.0369,
      "step": 340
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 0.10694638639688492,
      "learning_rate": 1.1139240506329114e-05,
      "loss": 0.055,
      "step": 350
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 0.11190392822027206,
      "learning_rate": 1.088607594936709e-05,
      "loss": 0.0981,
      "step": 360
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 0.11986145377159119,
      "learning_rate": 1.0632911392405063e-05,
      "loss": 0.1199,
      "step": 370
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 0.8623329401016235,
      "learning_rate": 1.0379746835443039e-05,
      "loss": 0.076,
      "step": 380
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 0.34745362401008606,
      "learning_rate": 1.0126582278481014e-05,
      "loss": 0.0396,
      "step": 390
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 2.8758838176727295,
      "learning_rate": 9.87341772151899e-06,
      "loss": 0.0168,
      "step": 400
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 0.15997739136219025,
      "learning_rate": 9.620253164556963e-06,
      "loss": 0.0848,
      "step": 410
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 0.1280534863471985,
      "learning_rate": 9.367088607594937e-06,
      "loss": 0.0895,
      "step": 420
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 0.09299108386039734,
      "learning_rate": 9.113924050632912e-06,
      "loss": 0.0217,
      "step": 430
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 0.09745831787586212,
      "learning_rate": 8.860759493670886e-06,
      "loss": 0.0136,
      "step": 440
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 0.3660314977169037,
      "learning_rate": 8.607594936708861e-06,
      "loss": 0.066,
      "step": 450
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 0.10188435018062592,
      "learning_rate": 8.354430379746837e-06,
      "loss": 0.0337,
      "step": 460
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 0.08400288224220276,
      "learning_rate": 8.10126582278481e-06,
      "loss": 0.0561,
      "step": 470
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9910313901345291,
      "eval_loss": 0.041871435940265656,
      "eval_runtime": 28.742,
      "eval_samples_per_second": 7.759,
      "eval_steps_per_second": 0.974,
      "step": 474
    },
    {
      "epoch": 3.037974683544304,
      "grad_norm": 0.08712360262870789,
      "learning_rate": 7.848101265822786e-06,
      "loss": 0.0165,
      "step": 480
    },
    {
      "epoch": 3.1012658227848102,
      "grad_norm": 0.08917823433876038,
      "learning_rate": 7.5949367088607605e-06,
      "loss": 0.0788,
      "step": 490
    },
    {
      "epoch": 3.1645569620253164,
      "grad_norm": 12.753520965576172,
      "learning_rate": 7.341772151898735e-06,
      "loss": 0.0523,
      "step": 500
    },
    {
      "epoch": 3.2278481012658227,
      "grad_norm": 0.1649811565876007,
      "learning_rate": 7.08860759493671e-06,
      "loss": 0.0119,
      "step": 510
    },
    {
      "epoch": 3.291139240506329,
      "grad_norm": 0.08447328209877014,
      "learning_rate": 6.835443037974684e-06,
      "loss": 0.0114,
      "step": 520
    },
    {
      "epoch": 3.3544303797468356,
      "grad_norm": 0.48710471391677856,
      "learning_rate": 6.582278481012659e-06,
      "loss": 0.0506,
      "step": 530
    },
    {
      "epoch": 3.4177215189873418,
      "grad_norm": 0.10614439100027084,
      "learning_rate": 6.329113924050634e-06,
      "loss": 0.0155,
      "step": 540
    },
    {
      "epoch": 3.481012658227848,
      "grad_norm": 0.08778823167085648,
      "learning_rate": 6.075949367088608e-06,
      "loss": 0.0118,
      "step": 550
    },
    {
      "epoch": 3.5443037974683547,
      "grad_norm": 0.08901780843734741,
      "learning_rate": 5.8227848101265824e-06,
      "loss": 0.0144,
      "step": 560
    },
    {
      "epoch": 3.607594936708861,
      "grad_norm": 3.638420581817627,
      "learning_rate": 5.569620253164557e-06,
      "loss": 0.0123,
      "step": 570
    },
    {
      "epoch": 3.670886075949367,
      "grad_norm": 0.07501719892024994,
      "learning_rate": 5.3164556962025316e-06,
      "loss": 0.0112,
      "step": 580
    },
    {
      "epoch": 3.7341772151898733,
      "grad_norm": 0.07867681980133057,
      "learning_rate": 5.063291139240507e-06,
      "loss": 0.0175,
      "step": 590
    },
    {
      "epoch": 3.7974683544303796,
      "grad_norm": 1.1297374963760376,
      "learning_rate": 4.8101265822784815e-06,
      "loss": 0.0109,
      "step": 600
    },
    {
      "epoch": 3.8607594936708862,
      "grad_norm": 0.27534130215644836,
      "learning_rate": 4.556962025316456e-06,
      "loss": 0.0386,
      "step": 610
    },
    {
      "epoch": 3.9240506329113924,
      "grad_norm": 0.07276225835084915,
      "learning_rate": 4.303797468354431e-06,
      "loss": 0.0186,
      "step": 620
    },
    {
      "epoch": 3.9873417721518987,
      "grad_norm": 0.07785341143608093,
      "learning_rate": 4.050632911392405e-06,
      "loss": 0.0673,
      "step": 630
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9865470852017937,
      "eval_loss": 0.04242047667503357,
      "eval_runtime": 41.253,
      "eval_samples_per_second": 5.406,
      "eval_steps_per_second": 0.679,
      "step": 632
    },
    {
      "epoch": 4.050632911392405,
      "grad_norm": 0.07723096013069153,
      "learning_rate": 3.7974683544303802e-06,
      "loss": 0.0101,
      "step": 640
    },
    {
      "epoch": 4.113924050632911,
      "grad_norm": 0.07696326822042465,
      "learning_rate": 3.544303797468355e-06,
      "loss": 0.0289,
      "step": 650
    },
    {
      "epoch": 4.177215189873418,
      "grad_norm": 0.07799258828163147,
      "learning_rate": 3.2911392405063294e-06,
      "loss": 0.0604,
      "step": 660
    },
    {
      "epoch": 4.2405063291139244,
      "grad_norm": 0.08302771300077438,
      "learning_rate": 3.037974683544304e-06,
      "loss": 0.0096,
      "step": 670
    },
    {
      "epoch": 4.30379746835443,
      "grad_norm": 0.0777091532945633,
      "learning_rate": 2.7848101265822785e-06,
      "loss": 0.0096,
      "step": 680
    },
    {
      "epoch": 4.367088607594937,
      "grad_norm": 0.1073741614818573,
      "learning_rate": 2.5316455696202535e-06,
      "loss": 0.0128,
      "step": 690
    },
    {
      "epoch": 4.430379746835443,
      "grad_norm": 0.06873705983161926,
      "learning_rate": 2.278481012658228e-06,
      "loss": 0.1127,
      "step": 700
    },
    {
      "epoch": 4.493670886075949,
      "grad_norm": 0.10447876155376434,
      "learning_rate": 2.0253164556962026e-06,
      "loss": 0.0099,
      "step": 710
    },
    {
      "epoch": 4.556962025316456,
      "grad_norm": 0.07418622821569443,
      "learning_rate": 1.7721518987341774e-06,
      "loss": 0.0138,
      "step": 720
    },
    {
      "epoch": 4.620253164556962,
      "grad_norm": 0.07888732105493546,
      "learning_rate": 1.518987341772152e-06,
      "loss": 0.0539,
      "step": 730
    },
    {
      "epoch": 4.6835443037974684,
      "grad_norm": 0.07641228288412094,
      "learning_rate": 1.2658227848101267e-06,
      "loss": 0.0095,
      "step": 740
    },
    {
      "epoch": 4.746835443037975,
      "grad_norm": 0.07773224264383316,
      "learning_rate": 1.0126582278481013e-06,
      "loss": 0.0501,
      "step": 750
    },
    {
      "epoch": 4.810126582278481,
      "grad_norm": 0.08096041530370712,
      "learning_rate": 7.59493670886076e-07,
      "loss": 0.0093,
      "step": 760
    },
    {
      "epoch": 4.8734177215189876,
      "grad_norm": 0.0873405709862709,
      "learning_rate": 5.063291139240507e-07,
      "loss": 0.0842,
      "step": 770
    },
    {
      "epoch": 4.936708860759493,
      "grad_norm": 0.788959264755249,
      "learning_rate": 2.5316455696202533e-07,
      "loss": 0.0162,
      "step": 780
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.11727602779865265,
      "learning_rate": 0.0,
      "loss": 0.0099,
      "step": 790
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9820627802690582,
      "eval_loss": 0.05168794468045235,
      "eval_runtime": 29.684,
      "eval_samples_per_second": 7.512,
      "eval_steps_per_second": 0.943,
      "step": 790
    },
    {
      "epoch": 5.0,
      "step": 790,
      "total_flos": 4.893619144161485e+17,
      "train_loss": 0.08755870511448836,
      "train_runtime": 2689.1935,
      "train_samples_per_second": 2.348,
      "train_steps_per_second": 0.294
    }
  ],
  "logging_steps": 10,
  "max_steps": 790,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.893619144161485e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}