{
  "best_metric": 10.351482391357422,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0846740050804403,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001693480101608806,
      "grad_norm": 0.05767215043306351,
      "learning_rate": 7e-06,
      "loss": 10.3761,
      "step": 1
    },
    {
      "epoch": 0.001693480101608806,
      "eval_loss": 10.376470565795898,
      "eval_runtime": 2.2633,
      "eval_samples_per_second": 439.62,
      "eval_steps_per_second": 110.016,
      "step": 1
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 0.05682261288166046,
      "learning_rate": 1.4e-05,
      "loss": 10.3756,
      "step": 2
    },
    {
      "epoch": 0.005080440304826418,
      "grad_norm": 0.05533347651362419,
      "learning_rate": 2.1e-05,
      "loss": 10.3759,
      "step": 3
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 0.06400913745164871,
      "learning_rate": 2.8e-05,
      "loss": 10.3753,
      "step": 4
    },
    {
      "epoch": 0.00846740050804403,
      "grad_norm": 0.06217538192868233,
      "learning_rate": 3.5e-05,
      "loss": 10.3766,
      "step": 5
    },
    {
      "epoch": 0.010160880609652836,
      "grad_norm": 0.059953831136226654,
      "learning_rate": 4.2e-05,
      "loss": 10.3753,
      "step": 6
    },
    {
      "epoch": 0.011854360711261643,
      "grad_norm": 0.06322812288999557,
      "learning_rate": 4.899999999999999e-05,
      "loss": 10.3751,
      "step": 7
    },
    {
      "epoch": 0.013547840812870448,
      "grad_norm": 0.06448973715305328,
      "learning_rate": 5.6e-05,
      "loss": 10.3755,
      "step": 8
    },
    {
      "epoch": 0.015241320914479255,
      "grad_norm": 0.06553128361701965,
      "learning_rate": 6.3e-05,
      "loss": 10.3754,
      "step": 9
    },
    {
      "epoch": 0.01693480101608806,
      "grad_norm": 0.06717841327190399,
      "learning_rate": 7e-05,
      "loss": 10.3749,
      "step": 10
    },
    {
      "epoch": 0.018628281117696866,
      "grad_norm": 0.06435838341712952,
      "learning_rate": 6.999521567473641e-05,
      "loss": 10.3753,
      "step": 11
    },
    {
      "epoch": 0.02032176121930567,
      "grad_norm": 0.06390493363142014,
      "learning_rate": 6.998086400693241e-05,
      "loss": 10.3744,
      "step": 12
    },
    {
      "epoch": 0.02201524132091448,
      "grad_norm": 0.06731149554252625,
      "learning_rate": 6.995694892019065e-05,
      "loss": 10.3745,
      "step": 13
    },
    {
      "epoch": 0.023708721422523286,
      "grad_norm": 0.08515335619449615,
      "learning_rate": 6.99234769526571e-05,
      "loss": 10.3737,
      "step": 14
    },
    {
      "epoch": 0.02540220152413209,
      "grad_norm": 0.08068357408046722,
      "learning_rate": 6.988045725523343e-05,
      "loss": 10.3727,
      "step": 15
    },
    {
      "epoch": 0.027095681625740897,
      "grad_norm": 0.08304785192012787,
      "learning_rate": 6.982790158907539e-05,
      "loss": 10.3722,
      "step": 16
    },
    {
      "epoch": 0.028789161727349702,
      "grad_norm": 0.08605454862117767,
      "learning_rate": 6.976582432237733e-05,
      "loss": 10.3725,
      "step": 17
    },
    {
      "epoch": 0.03048264182895851,
      "grad_norm": 0.0890476256608963,
      "learning_rate": 6.969424242644413e-05,
      "loss": 10.3728,
      "step": 18
    },
    {
      "epoch": 0.03217612193056731,
      "grad_norm": 0.09603014588356018,
      "learning_rate": 6.961317547105138e-05,
      "loss": 10.3707,
      "step": 19
    },
    {
      "epoch": 0.03386960203217612,
      "grad_norm": 0.09333094954490662,
      "learning_rate": 6.952264561909527e-05,
      "loss": 10.3714,
      "step": 20
    },
    {
      "epoch": 0.03556308213378493,
      "grad_norm": 0.11809182167053223,
      "learning_rate": 6.942267762053337e-05,
      "loss": 10.3699,
      "step": 21
    },
    {
      "epoch": 0.03725656223539373,
      "grad_norm": 0.12310867756605148,
      "learning_rate": 6.931329880561832e-05,
      "loss": 10.3696,
      "step": 22
    },
    {
      "epoch": 0.03895004233700254,
      "grad_norm": 0.12797869741916656,
      "learning_rate": 6.919453907742597e-05,
      "loss": 10.3694,
      "step": 23
    },
    {
      "epoch": 0.04064352243861134,
      "grad_norm": 0.14211532473564148,
      "learning_rate": 6.90664309036802e-05,
      "loss": 10.3684,
      "step": 24
    },
    {
      "epoch": 0.04233700254022015,
      "grad_norm": 0.13544224202632904,
      "learning_rate": 6.892900930787656e-05,
      "loss": 10.3687,
      "step": 25
    },
    {
      "epoch": 0.04403048264182896,
      "grad_norm": 0.15587803721427917,
      "learning_rate": 6.87823118597072e-05,
      "loss": 10.3667,
      "step": 26
    },
    {
      "epoch": 0.04572396274343776,
      "grad_norm": 0.15392404794692993,
      "learning_rate": 6.862637866478969e-05,
      "loss": 10.3679,
      "step": 27
    },
    {
      "epoch": 0.04741744284504657,
      "grad_norm": 0.15195734798908234,
      "learning_rate": 6.846125235370252e-05,
      "loss": 10.3674,
      "step": 28
    },
    {
      "epoch": 0.04911092294665537,
      "grad_norm": 0.1591203212738037,
      "learning_rate": 6.828697807033038e-05,
      "loss": 10.3646,
      "step": 29
    },
    {
      "epoch": 0.05080440304826418,
      "grad_norm": 0.17264410853385925,
      "learning_rate": 6.81036034595222e-05,
      "loss": 10.3642,
      "step": 30
    },
    {
      "epoch": 0.05249788314987299,
      "grad_norm": 0.1709284484386444,
      "learning_rate": 6.791117865406564e-05,
      "loss": 10.3635,
      "step": 31
    },
    {
      "epoch": 0.05419136325148179,
      "grad_norm": 0.17630036175251007,
      "learning_rate": 6.770975626098112e-05,
      "loss": 10.365,
      "step": 32
    },
    {
      "epoch": 0.0558848433530906,
      "grad_norm": 0.1866825520992279,
      "learning_rate": 6.749939134713974e-05,
      "loss": 10.3628,
      "step": 33
    },
    {
      "epoch": 0.057578323454699404,
      "grad_norm": 0.17809787392616272,
      "learning_rate": 6.728014142420846e-05,
      "loss": 10.3629,
      "step": 34
    },
    {
      "epoch": 0.05927180355630821,
      "grad_norm": 0.20281663537025452,
      "learning_rate": 6.7052066432927e-05,
      "loss": 10.3578,
      "step": 35
    },
    {
      "epoch": 0.06096528365791702,
      "grad_norm": 0.19204723834991455,
      "learning_rate": 6.681522872672069e-05,
      "loss": 10.3585,
      "step": 36
    },
    {
      "epoch": 0.06265876375952582,
      "grad_norm": 0.1810905933380127,
      "learning_rate": 6.656969305465356e-05,
      "loss": 10.3592,
      "step": 37
    },
    {
      "epoch": 0.06435224386113463,
      "grad_norm": 0.19030340015888214,
      "learning_rate": 6.631552654372672e-05,
      "loss": 10.3601,
      "step": 38
    },
    {
      "epoch": 0.06604572396274344,
      "grad_norm": 0.16998638212680817,
      "learning_rate": 6.60527986805264e-05,
      "loss": 10.3573,
      "step": 39
    },
    {
      "epoch": 0.06773920406435224,
      "grad_norm": 0.1517295241355896,
      "learning_rate": 6.578158129222711e-05,
      "loss": 10.3549,
      "step": 40
    },
    {
      "epoch": 0.06943268416596104,
      "grad_norm": 0.15249769389629364,
      "learning_rate": 6.550194852695469e-05,
      "loss": 10.3559,
      "step": 41
    },
    {
      "epoch": 0.07112616426756986,
      "grad_norm": 0.15435636043548584,
      "learning_rate": 6.521397683351509e-05,
      "loss": 10.354,
      "step": 42
    },
    {
      "epoch": 0.07281964436917866,
      "grad_norm": 0.14684386551380157,
      "learning_rate": 6.491774494049386e-05,
      "loss": 10.355,
      "step": 43
    },
    {
      "epoch": 0.07451312447078746,
      "grad_norm": 0.15682685375213623,
      "learning_rate": 6.461333383473272e-05,
      "loss": 10.3522,
      "step": 44
    },
    {
      "epoch": 0.07620660457239628,
      "grad_norm": 0.14739371836185455,
      "learning_rate": 6.430082673918849e-05,
      "loss": 10.3518,
      "step": 45
    },
    {
      "epoch": 0.07790008467400508,
      "grad_norm": 0.14083759486675262,
      "learning_rate": 6.398030909018069e-05,
      "loss": 10.3527,
      "step": 46
    },
    {
      "epoch": 0.07959356477561388,
      "grad_norm": 0.11909397691488266,
      "learning_rate": 6.365186851403423e-05,
      "loss": 10.3539,
      "step": 47
    },
    {
      "epoch": 0.08128704487722269,
      "grad_norm": 0.11432235687971115,
      "learning_rate": 6.331559480312315e-05,
      "loss": 10.3531,
      "step": 48
    },
    {
      "epoch": 0.0829805249788315,
      "grad_norm": 0.13134874403476715,
      "learning_rate": 6.297157989132236e-05,
      "loss": 10.3544,
      "step": 49
    },
    {
      "epoch": 0.0846740050804403,
      "grad_norm": 0.19639384746551514,
      "learning_rate": 6.261991782887377e-05,
      "loss": 10.3542,
      "step": 50
    },
    {
      "epoch": 0.0846740050804403,
      "eval_loss": 10.351482391357422,
      "eval_runtime": 2.2614,
      "eval_samples_per_second": 439.995,
      "eval_steps_per_second": 110.109,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5744859021312.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}