{
  "best_metric": 11.92774772644043,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.11477761836441894,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022955523672883787,
      "grad_norm": 0.011360950767993927,
      "learning_rate": 5e-05,
      "loss": 11.9322,
      "step": 1
    },
    {
      "epoch": 0.0022955523672883787,
      "eval_loss": 11.929409980773926,
      "eval_runtime": 0.128,
      "eval_samples_per_second": 390.554,
      "eval_steps_per_second": 101.544,
      "step": 1
    },
    {
      "epoch": 0.004591104734576757,
      "grad_norm": 0.009733411483466625,
      "learning_rate": 0.0001,
      "loss": 11.9318,
      "step": 2
    },
    {
      "epoch": 0.006886657101865136,
      "grad_norm": 0.011101752519607544,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.009182209469153515,
      "grad_norm": 0.011169670149683952,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9327,
      "step": 4
    },
    {
      "epoch": 0.011477761836441894,
      "grad_norm": 0.010796564631164074,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.931,
      "step": 5
    },
    {
      "epoch": 0.013773314203730272,
      "grad_norm": 0.010938778519630432,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9318,
      "step": 6
    },
    {
      "epoch": 0.01606886657101865,
      "grad_norm": 0.011996432207524776,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9327,
      "step": 7
    },
    {
      "epoch": 0.01836441893830703,
      "grad_norm": 0.012821040116250515,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9311,
      "step": 8
    },
    {
      "epoch": 0.02065997130559541,
      "grad_norm": 0.012357225641608238,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9317,
      "step": 9
    },
    {
      "epoch": 0.02295552367288379,
      "grad_norm": 0.01354469358921051,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9313,
      "step": 10
    },
    {
      "epoch": 0.025251076040172165,
      "grad_norm": 0.01358281634747982,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9313,
      "step": 11
    },
    {
      "epoch": 0.027546628407460545,
      "grad_norm": 0.012229177169501781,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9321,
      "step": 12
    },
    {
      "epoch": 0.029842180774748924,
      "grad_norm": 0.015538652427494526,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9316,
      "step": 13
    },
    {
      "epoch": 0.0321377331420373,
      "grad_norm": 0.01976892724633217,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9319,
      "step": 14
    },
    {
      "epoch": 0.03443328550932568,
      "grad_norm": 0.019717110320925713,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9321,
      "step": 15
    },
    {
      "epoch": 0.03672883787661406,
      "grad_norm": 0.022157777100801468,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9309,
      "step": 16
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.01957789622247219,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9314,
      "step": 17
    },
    {
      "epoch": 0.04131994261119082,
      "grad_norm": 0.021483201533555984,
      "learning_rate": 7.75e-05,
      "loss": 11.9308,
      "step": 18
    },
    {
      "epoch": 0.0436154949784792,
      "grad_norm": 0.02299327775835991,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9309,
      "step": 19
    },
    {
      "epoch": 0.04591104734576758,
      "grad_norm": 0.019226081669330597,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9317,
      "step": 20
    },
    {
      "epoch": 0.04820659971305596,
      "grad_norm": 0.021830759942531586,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9311,
      "step": 21
    },
    {
      "epoch": 0.05050215208034433,
      "grad_norm": 0.015856323763728142,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9316,
      "step": 22
    },
    {
      "epoch": 0.05279770444763271,
      "grad_norm": 0.018046198412775993,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9301,
      "step": 23
    },
    {
      "epoch": 0.05509325681492109,
      "grad_norm": 0.018557066097855568,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9308,
      "step": 24
    },
    {
      "epoch": 0.05738880918220947,
      "grad_norm": 0.01523104403167963,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9307,
      "step": 25
    },
    {
      "epoch": 0.05738880918220947,
      "eval_loss": 11.928428649902344,
      "eval_runtime": 0.1344,
      "eval_samples_per_second": 371.984,
      "eval_steps_per_second": 96.716,
      "step": 25
    },
    {
      "epoch": 0.05968436154949785,
      "grad_norm": 0.030939413234591484,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9311,
      "step": 26
    },
    {
      "epoch": 0.06197991391678623,
      "grad_norm": 0.030720077455043793,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9305,
      "step": 27
    },
    {
      "epoch": 0.0642754662840746,
      "grad_norm": 0.029229579493403435,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9319,
      "step": 28
    },
    {
      "epoch": 0.06657101865136299,
      "grad_norm": 0.02834383025765419,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9316,
      "step": 29
    },
    {
      "epoch": 0.06886657101865136,
      "grad_norm": 0.03144960105419159,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9308,
      "step": 30
    },
    {
      "epoch": 0.07116212338593975,
      "grad_norm": 0.03125367313623428,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9311,
      "step": 31
    },
    {
      "epoch": 0.07345767575322812,
      "grad_norm": 0.030726848170161247,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9302,
      "step": 32
    },
    {
      "epoch": 0.0757532281205165,
      "grad_norm": 0.029451433569192886,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9302,
      "step": 33
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.028316278010606766,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9303,
      "step": 34
    },
    {
      "epoch": 0.08034433285509325,
      "grad_norm": 0.023046843707561493,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9309,
      "step": 35
    },
    {
      "epoch": 0.08263988522238164,
      "grad_norm": 0.018658028915524483,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9302,
      "step": 36
    },
    {
      "epoch": 0.08493543758967001,
      "grad_norm": 0.021122856065630913,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9311,
      "step": 37
    },
    {
      "epoch": 0.0872309899569584,
      "grad_norm": 0.03167968988418579,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9314,
      "step": 38
    },
    {
      "epoch": 0.08952654232424677,
      "grad_norm": 0.041138049215078354,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9303,
      "step": 39
    },
    {
      "epoch": 0.09182209469153516,
      "grad_norm": 0.03652139753103256,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.9302,
      "step": 40
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.032850828021764755,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9304,
      "step": 41
    },
    {
      "epoch": 0.09641319942611191,
      "grad_norm": 0.03657353296875954,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9312,
      "step": 42
    },
    {
      "epoch": 0.09870875179340029,
      "grad_norm": 0.03682245686650276,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.931,
      "step": 43
    },
    {
      "epoch": 0.10100430416068866,
      "grad_norm": 0.03354611247777939,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9306,
      "step": 44
    },
    {
      "epoch": 0.10329985652797705,
      "grad_norm": 0.0355108417570591,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9296,
      "step": 45
    },
    {
      "epoch": 0.10559540889526542,
      "grad_norm": 0.02785145863890648,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9298,
      "step": 46
    },
    {
      "epoch": 0.1078909612625538,
      "grad_norm": 0.02927231416106224,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9309,
      "step": 47
    },
    {
      "epoch": 0.11018651362984218,
      "grad_norm": 0.027248775586485863,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9298,
      "step": 48
    },
    {
      "epoch": 0.11248206599713056,
      "grad_norm": 0.019637739285826683,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.9318,
      "step": 49
    },
    {
      "epoch": 0.11477761836441894,
      "grad_norm": 0.027051644399762154,
      "learning_rate": 1e-05,
      "loss": 11.9307,
      "step": 50
    },
    {
      "epoch": 0.11477761836441894,
      "eval_loss": 11.92774772644043,
      "eval_runtime": 0.1326,
      "eval_samples_per_second": 377.161,
      "eval_steps_per_second": 98.062,
      "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": 1044448935936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}