{
  "best_metric": 0.7666683197021484,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.4652014652014653,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 42.63615417480469,
      "learning_rate": 5e-05,
      "loss": 10.8108,
      "step": 1
    },
    {
      "epoch": 0.029304029304029304,
      "eval_loss": 11.66943359375,
      "eval_runtime": 12.0274,
      "eval_samples_per_second": 19.123,
      "eval_steps_per_second": 2.411,
      "step": 1
    },
    {
      "epoch": 0.05860805860805861,
      "grad_norm": 43.70536804199219,
      "learning_rate": 0.0001,
      "loss": 11.4368,
      "step": 2
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 30.874406814575195,
      "learning_rate": 9.989294616193017e-05,
      "loss": 8.1072,
      "step": 3
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 17.766359329223633,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.914,
      "step": 4
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 10.942605972290039,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.2661,
      "step": 5
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 4.077508926391602,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1809,
      "step": 6
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 4.200634479522705,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.0111,
      "step": 7
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 2.5703258514404297,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9798,
      "step": 8
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 1.4646650552749634,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.8646,
      "step": 9
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 1.0245696306228638,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7594,
      "step": 10
    },
    {
      "epoch": 0.32234432234432236,
      "grad_norm": 0.7607440948486328,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.7369,
      "step": 11
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 1.600371241569519,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.8084,
      "step": 12
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.577329397201538,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.7607,
      "step": 13
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 1.0018422603607178,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8165,
      "step": 14
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.8424701690673828,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8129,
      "step": 15
    },
    {
      "epoch": 0.46886446886446886,
      "grad_norm": 0.5086039900779724,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8195,
      "step": 16
    },
    {
      "epoch": 0.4981684981684982,
      "grad_norm": 0.6842309236526489,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8075,
      "step": 17
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.6705095767974854,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7247,
      "step": 18
    },
    {
      "epoch": 0.5567765567765568,
      "grad_norm": 0.24981459975242615,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.741,
      "step": 19
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.3129333257675171,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7393,
      "step": 20
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.7338513135910034,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7904,
      "step": 21
    },
    {
      "epoch": 0.6446886446886447,
      "grad_norm": 1.3784418106079102,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8909,
      "step": 22
    },
    {
      "epoch": 0.673992673992674,
      "grad_norm": 0.8394548296928406,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8305,
      "step": 23
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.29354768991470337,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8116,
      "step": 24
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 0.3640207350254059,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.8095,
      "step": 25
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 0.789313018321991,
      "eval_runtime": 12.0233,
      "eval_samples_per_second": 19.13,
      "eval_steps_per_second": 2.412,
      "step": 25
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.6007457375526428,
      "learning_rate": 5e-05,
      "loss": 0.8029,
      "step": 26
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 1.0814050436019897,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.7535,
      "step": 27
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.8970361351966858,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7552,
      "step": 28
    },
    {
      "epoch": 0.8498168498168498,
      "grad_norm": 0.5584169030189514,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.772,
      "step": 29
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.19214436411857605,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7811,
      "step": 30
    },
    {
      "epoch": 0.9084249084249084,
      "grad_norm": 0.4855462312698364,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.8256,
      "step": 31
    },
    {
      "epoch": 0.9377289377289377,
      "grad_norm": 0.5026677250862122,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8139,
      "step": 32
    },
    {
      "epoch": 0.967032967032967,
      "grad_norm": 1.100959062576294,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.8822,
      "step": 33
    },
    {
      "epoch": 0.9963369963369964,
      "grad_norm": 0.678441047668457,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8372,
      "step": 34
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 1.023532748222351,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.4417,
      "step": 35
    },
    {
      "epoch": 1.054945054945055,
      "grad_norm": 0.5481376647949219,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.7156,
      "step": 36
    },
    {
      "epoch": 1.0842490842490842,
      "grad_norm": 0.5916444659233093,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.7388,
      "step": 37
    },
    {
      "epoch": 1.1135531135531136,
      "grad_norm": 0.48780718445777893,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7178,
      "step": 38
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.8632380366325378,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.8168,
      "step": 39
    },
    {
      "epoch": 1.1721611721611722,
      "grad_norm": 0.6176807284355164,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.8144,
      "step": 40
    },
    {
      "epoch": 1.2014652014652014,
      "grad_norm": 0.3913164436817169,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.7581,
      "step": 41
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.5620902180671692,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8182,
      "step": 42
    },
    {
      "epoch": 1.26007326007326,
      "grad_norm": 0.5761415362358093,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.793,
      "step": 43
    },
    {
      "epoch": 1.2893772893772895,
      "grad_norm": 0.623988926410675,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7259,
      "step": 44
    },
    {
      "epoch": 1.3186813186813187,
      "grad_norm": 0.6083937287330627,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.7406,
      "step": 45
    },
    {
      "epoch": 1.347985347985348,
      "grad_norm": 0.6067966818809509,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.7433,
      "step": 46
    },
    {
      "epoch": 1.3772893772893773,
      "grad_norm": 0.5738537311553955,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.7611,
      "step": 47
    },
    {
      "epoch": 1.4065934065934065,
      "grad_norm": 0.5093715190887451,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.7872,
      "step": 48
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.4598458707332611,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.804,
      "step": 49
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 0.6957669258117676,
      "learning_rate": 0.0,
      "loss": 0.8004,
      "step": 50
    },
    {
      "epoch": 1.4652014652014653,
      "eval_loss": 0.7666683197021484,
      "eval_runtime": 12.0189,
      "eval_samples_per_second": 19.137,
      "eval_steps_per_second": 2.413,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.631381723512832e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}