{
  "best_metric": 0.8028371334075928,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0016218232537018116,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.487293014807247e-05,
      "grad_norm": 9.75472354888916,
      "learning_rate": 2e-05,
      "loss": 8.1444,
      "step": 1
    },
    {
      "epoch": 6.487293014807247e-05,
      "eval_loss": 1.7887955904006958,
      "eval_runtime": 599.9067,
      "eval_samples_per_second": 10.82,
      "eval_steps_per_second": 5.411,
      "step": 1
    },
    {
      "epoch": 0.00012974586029614494,
      "grad_norm": 11.683684349060059,
      "learning_rate": 4e-05,
      "loss": 7.756,
      "step": 2
    },
    {
      "epoch": 0.00019461879044421738,
      "grad_norm": 10.239891052246094,
      "learning_rate": 6e-05,
      "loss": 7.3487,
      "step": 3
    },
    {
      "epoch": 0.00025949172059228987,
      "grad_norm": 5.831728458404541,
      "learning_rate": 8e-05,
      "loss": 6.5008,
      "step": 4
    },
    {
      "epoch": 0.0003243646507403623,
      "grad_norm": 8.679244041442871,
      "learning_rate": 0.0001,
      "loss": 7.6476,
      "step": 5
    },
    {
      "epoch": 0.0003243646507403623,
      "eval_loss": 1.6379072666168213,
      "eval_runtime": 587.2065,
      "eval_samples_per_second": 11.054,
      "eval_steps_per_second": 5.528,
      "step": 5
    },
    {
      "epoch": 0.00038923758088843475,
      "grad_norm": 6.1510725021362305,
      "learning_rate": 0.00012,
      "loss": 7.1118,
      "step": 6
    },
    {
      "epoch": 0.00045411051103650725,
      "grad_norm": 8.355069160461426,
      "learning_rate": 0.00014,
      "loss": 7.7826,
      "step": 7
    },
    {
      "epoch": 0.0005189834411845797,
      "grad_norm": 6.8486857414245605,
      "learning_rate": 0.00016,
      "loss": 5.4679,
      "step": 8
    },
    {
      "epoch": 0.0005838563713326521,
      "grad_norm": 10.025384902954102,
      "learning_rate": 0.00018,
      "loss": 5.6222,
      "step": 9
    },
    {
      "epoch": 0.0006487293014807246,
      "grad_norm": 7.206371307373047,
      "learning_rate": 0.0002,
      "loss": 5.6096,
      "step": 10
    },
    {
      "epoch": 0.0006487293014807246,
      "eval_loss": 1.2036751508712769,
      "eval_runtime": 593.239,
      "eval_samples_per_second": 10.942,
      "eval_steps_per_second": 5.472,
      "step": 10
    },
    {
      "epoch": 0.0007136022316287971,
      "grad_norm": 8.447565078735352,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.5169,
      "step": 11
    },
    {
      "epoch": 0.0007784751617768695,
      "grad_norm": 6.3583149909973145,
      "learning_rate": 0.0001913545457642601,
      "loss": 3.6096,
      "step": 12
    },
    {
      "epoch": 0.000843348091924942,
      "grad_norm": 7.392266273498535,
      "learning_rate": 0.00018090169943749476,
      "loss": 5.3685,
      "step": 13
    },
    {
      "epoch": 0.0009082210220730145,
      "grad_norm": 7.1356730461120605,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.5941,
      "step": 14
    },
    {
      "epoch": 0.000973093952221087,
      "grad_norm": 11.207259178161621,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.9803,
      "step": 15
    },
    {
      "epoch": 0.000973093952221087,
      "eval_loss": 0.9349899291992188,
      "eval_runtime": 594.6572,
      "eval_samples_per_second": 10.916,
      "eval_steps_per_second": 5.459,
      "step": 15
    },
    {
      "epoch": 0.0010379668823691595,
      "grad_norm": 8.692298889160156,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.5715,
      "step": 16
    },
    {
      "epoch": 0.0011028398125172319,
      "grad_norm": 7.856359481811523,
      "learning_rate": 0.00011045284632676536,
      "loss": 3.9533,
      "step": 17
    },
    {
      "epoch": 0.0011677127426653043,
      "grad_norm": 11.625333786010742,
      "learning_rate": 8.954715367323468e-05,
      "loss": 4.167,
      "step": 18
    },
    {
      "epoch": 0.0012325856728133769,
      "grad_norm": 11.39608097076416,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.4974,
      "step": 19
    },
    {
      "epoch": 0.0012974586029614492,
      "grad_norm": 8.31639289855957,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.2432,
      "step": 20
    },
    {
      "epoch": 0.0012974586029614492,
      "eval_loss": 0.8296452760696411,
      "eval_runtime": 610.928,
      "eval_samples_per_second": 10.625,
      "eval_steps_per_second": 5.313,
      "step": 20
    },
    {
      "epoch": 0.0013623315331095216,
      "grad_norm": 7.80236291885376,
      "learning_rate": 3.308693936411421e-05,
      "loss": 4.3949,
      "step": 21
    },
    {
      "epoch": 0.0014272044632575942,
      "grad_norm": 7.568052768707275,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 3.0615,
      "step": 22
    },
    {
      "epoch": 0.0014920773934056666,
      "grad_norm": 13.245499610900879,
      "learning_rate": 8.645454235739903e-06,
      "loss": 2.7618,
      "step": 23
    },
    {
      "epoch": 0.001556950323553739,
      "grad_norm": 9.530472755432129,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.1139,
      "step": 24
    },
    {
      "epoch": 0.0016218232537018116,
      "grad_norm": 7.105537414550781,
      "learning_rate": 0.0,
      "loss": 2.4744,
      "step": 25
    },
    {
      "epoch": 0.0016218232537018116,
      "eval_loss": 0.8028371334075928,
      "eval_runtime": 578.5339,
      "eval_samples_per_second": 11.22,
      "eval_steps_per_second": 5.611,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 956050056413184.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}