{
  "best_metric": 2.955871820449829,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0638620579548176,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001277241159096352,
      "grad_norm": 5.397294998168945,
      "learning_rate": 5e-05,
      "loss": 3.9107,
      "step": 1
    },
    {
      "epoch": 0.001277241159096352,
      "eval_loss": 6.961343765258789,
      "eval_runtime": 2.9789,
      "eval_samples_per_second": 16.785,
      "eval_steps_per_second": 4.364,
      "step": 1
    },
    {
      "epoch": 0.002554482318192704,
      "grad_norm": 6.115942478179932,
      "learning_rate": 0.0001,
      "loss": 4.4455,
      "step": 2
    },
    {
      "epoch": 0.0038317234772890555,
      "grad_norm": 6.432067394256592,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.9182,
      "step": 3
    },
    {
      "epoch": 0.005108964636385408,
      "grad_norm": 4.971473693847656,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.37,
      "step": 4
    },
    {
      "epoch": 0.006386205795481759,
      "grad_norm": 7.451247692108154,
      "learning_rate": 9.913533761814537e-05,
      "loss": 5.2423,
      "step": 5
    },
    {
      "epoch": 0.007663446954578111,
      "grad_norm": 5.390747547149658,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.8583,
      "step": 6
    },
    {
      "epoch": 0.008940688113674463,
      "grad_norm": 6.206498146057129,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.1828,
      "step": 7
    },
    {
      "epoch": 0.010217929272770815,
      "grad_norm": 4.19208288192749,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.1756,
      "step": 8
    },
    {
      "epoch": 0.011495170431867168,
      "grad_norm": 3.817302942276001,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.1623,
      "step": 9
    },
    {
      "epoch": 0.012772411590963519,
      "grad_norm": 5.364481449127197,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.5353,
      "step": 10
    },
    {
      "epoch": 0.014049652750059871,
      "grad_norm": 5.762411117553711,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5802,
      "step": 11
    },
    {
      "epoch": 0.015326893909156222,
      "grad_norm": 6.493536949157715,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.3552,
      "step": 12
    },
    {
      "epoch": 0.016604135068252573,
      "grad_norm": 8.597394943237305,
      "learning_rate": 8.883279133655399e-05,
      "loss": 3.6321,
      "step": 13
    },
    {
      "epoch": 0.017881376227348925,
      "grad_norm": 8.784098625183105,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.4948,
      "step": 14
    },
    {
      "epoch": 0.019158617386445278,
      "grad_norm": 3.6853532791137695,
      "learning_rate": 8.467056167950311e-05,
      "loss": 3.5728,
      "step": 15
    },
    {
      "epoch": 0.02043585854554163,
      "grad_norm": 3.2291996479034424,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.652,
      "step": 16
    },
    {
      "epoch": 0.021713099704637983,
      "grad_norm": 6.095546245574951,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.161,
      "step": 17
    },
    {
      "epoch": 0.022990340863734336,
      "grad_norm": 3.977355480194092,
      "learning_rate": 7.75e-05,
      "loss": 3.299,
      "step": 18
    },
    {
      "epoch": 0.024267582022830685,
      "grad_norm": 4.840251922607422,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.9087,
      "step": 19
    },
    {
      "epoch": 0.025544823181927037,
      "grad_norm": 2.9431254863739014,
      "learning_rate": 7.222075445642904e-05,
      "loss": 3.768,
      "step": 20
    },
    {
      "epoch": 0.02682206434102339,
      "grad_norm": 5.682262420654297,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.2159,
      "step": 21
    },
    {
      "epoch": 0.028099305500119742,
      "grad_norm": 8.014816284179688,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.0127,
      "step": 22
    },
    {
      "epoch": 0.029376546659216095,
      "grad_norm": 8.57851505279541,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.0431,
      "step": 23
    },
    {
      "epoch": 0.030653787818312444,
      "grad_norm": 7.359556674957275,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.9599,
      "step": 24
    },
    {
      "epoch": 0.0319310289774088,
      "grad_norm": 4.628635883331299,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.8194,
      "step": 25
    },
    {
      "epoch": 0.0319310289774088,
      "eval_loss": 3.4176676273345947,
      "eval_runtime": 2.3384,
      "eval_samples_per_second": 21.382,
      "eval_steps_per_second": 5.559,
      "step": 25
    },
    {
      "epoch": 0.033208270136505146,
      "grad_norm": 2.9280927181243896,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.5654,
      "step": 26
    },
    {
      "epoch": 0.0344855112956015,
      "grad_norm": 2.801668882369995,
      "learning_rate": 5.205685918464356e-05,
      "loss": 2.7446,
      "step": 27
    },
    {
      "epoch": 0.03576275245469785,
      "grad_norm": 3.4079697132110596,
      "learning_rate": 4.912632135009769e-05,
      "loss": 3.2324,
      "step": 28
    },
    {
      "epoch": 0.0370399936137942,
      "grad_norm": 4.457375526428223,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 3.2512,
      "step": 29
    },
    {
      "epoch": 0.038317234772890556,
      "grad_norm": 12.326119422912598,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 2.4725,
      "step": 30
    },
    {
      "epoch": 0.03959447593198691,
      "grad_norm": 6.261662006378174,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.2874,
      "step": 31
    },
    {
      "epoch": 0.04087171709108326,
      "grad_norm": 4.075770854949951,
      "learning_rate": 3.777924554357096e-05,
      "loss": 2.3201,
      "step": 32
    },
    {
      "epoch": 0.04214895825017961,
      "grad_norm": 2.7039589881896973,
      "learning_rate": 3.509700894014496e-05,
      "loss": 3.6826,
      "step": 33
    },
    {
      "epoch": 0.043426199409275966,
      "grad_norm": 2.4863486289978027,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.7119,
      "step": 34
    },
    {
      "epoch": 0.04470344056837232,
      "grad_norm": 3.140991687774658,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.5157,
      "step": 35
    },
    {
      "epoch": 0.04598068172746867,
      "grad_norm": 3.5709006786346436,
      "learning_rate": 2.760573569460757e-05,
      "loss": 3.8917,
      "step": 36
    },
    {
      "epoch": 0.04725792288656502,
      "grad_norm": 4.075592994689941,
      "learning_rate": 2.53294383204969e-05,
      "loss": 3.3369,
      "step": 37
    },
    {
      "epoch": 0.04853516404566137,
      "grad_norm": 3.7284469604492188,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.5284,
      "step": 38
    },
    {
      "epoch": 0.04981240520475772,
      "grad_norm": 3.799734354019165,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 2.1592,
      "step": 39
    },
    {
      "epoch": 0.051089646363854074,
      "grad_norm": 3.1631314754486084,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 2.7785,
      "step": 40
    },
    {
      "epoch": 0.05236688752295043,
      "grad_norm": 3.053359031677246,
      "learning_rate": 1.758386744638546e-05,
      "loss": 2.9911,
      "step": 41
    },
    {
      "epoch": 0.05364412868204678,
      "grad_norm": 3.8054542541503906,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.8448,
      "step": 42
    },
    {
      "epoch": 0.05492136984114313,
      "grad_norm": 2.217982530593872,
      "learning_rate": 1.464072663102903e-05,
      "loss": 2.7711,
      "step": 43
    },
    {
      "epoch": 0.056198611000239485,
      "grad_norm": 2.570152521133423,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 2.3292,
      "step": 44
    },
    {
      "epoch": 0.05747585215933584,
      "grad_norm": 2.582834482192993,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 3.452,
      "step": 45
    },
    {
      "epoch": 0.05875309331843219,
      "grad_norm": 4.0312957763671875,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.5707,
      "step": 46
    },
    {
      "epoch": 0.060030334477528535,
      "grad_norm": 2.474395513534546,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 3.4277,
      "step": 47
    },
    {
      "epoch": 0.06130757563662489,
      "grad_norm": 2.419994592666626,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.6311,
      "step": 48
    },
    {
      "epoch": 0.06258481679572124,
      "grad_norm": 4.7385430335998535,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 3.4403,
      "step": 49
    },
    {
      "epoch": 0.0638620579548176,
      "grad_norm": 4.351629257202148,
      "learning_rate": 1e-05,
      "loss": 3.6853,
      "step": 50
    },
    {
      "epoch": 0.0638620579548176,
      "eval_loss": 2.955871820449829,
      "eval_runtime": 2.355,
      "eval_samples_per_second": 21.232,
      "eval_steps_per_second": 5.52,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.968086838542336e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}