{
  "best_metric": 11.014021873474121,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.10351966873706005,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002070393374741201,
      "grad_norm": 5.711524963378906,
      "learning_rate": 5e-05,
      "loss": 177.6369,
      "step": 1
    },
    {
      "epoch": 0.002070393374741201,
      "eval_loss": 11.103752136230469,
      "eval_runtime": 0.4223,
      "eval_samples_per_second": 118.396,
      "eval_steps_per_second": 30.783,
      "step": 1
    },
    {
      "epoch": 0.004140786749482402,
      "grad_norm": 4.117014408111572,
      "learning_rate": 0.0001,
      "loss": 177.8271,
      "step": 2
    },
    {
      "epoch": 0.006211180124223602,
      "grad_norm": 3.66237211227417,
      "learning_rate": 9.990365154573717e-05,
      "loss": 177.7256,
      "step": 3
    },
    {
      "epoch": 0.008281573498964804,
      "grad_norm": 3.668341875076294,
      "learning_rate": 9.961501876182148e-05,
      "loss": 177.6245,
      "step": 4
    },
    {
      "epoch": 0.010351966873706004,
      "grad_norm": 3.676244020462036,
      "learning_rate": 9.913533761814537e-05,
      "loss": 177.7081,
      "step": 5
    },
    {
      "epoch": 0.012422360248447204,
      "grad_norm": 3.8247900009155273,
      "learning_rate": 9.846666218300807e-05,
      "loss": 177.6291,
      "step": 6
    },
    {
      "epoch": 0.014492753623188406,
      "grad_norm": 3.936617851257324,
      "learning_rate": 9.761185582727977e-05,
      "loss": 177.5606,
      "step": 7
    },
    {
      "epoch": 0.016563146997929608,
      "grad_norm": 4.178831100463867,
      "learning_rate": 9.657457896300791e-05,
      "loss": 177.5936,
      "step": 8
    },
    {
      "epoch": 0.018633540372670808,
      "grad_norm": 4.82990026473999,
      "learning_rate": 9.535927336897098e-05,
      "loss": 177.5515,
      "step": 9
    },
    {
      "epoch": 0.020703933747412008,
      "grad_norm": 5.298854827880859,
      "learning_rate": 9.397114317029975e-05,
      "loss": 177.395,
      "step": 10
    },
    {
      "epoch": 0.022774327122153208,
      "grad_norm": 5.932757377624512,
      "learning_rate": 9.241613255361455e-05,
      "loss": 177.2761,
      "step": 11
    },
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 7.25010347366333,
      "learning_rate": 9.070090031310558e-05,
      "loss": 177.3037,
      "step": 12
    },
    {
      "epoch": 0.026915113871635612,
      "grad_norm": 7.97006893157959,
      "learning_rate": 8.883279133655399e-05,
      "loss": 176.9708,
      "step": 13
    },
    {
      "epoch": 0.028985507246376812,
      "grad_norm": 5.248260498046875,
      "learning_rate": 8.681980515339464e-05,
      "loss": 177.044,
      "step": 14
    },
    {
      "epoch": 0.031055900621118012,
      "grad_norm": 4.100940227508545,
      "learning_rate": 8.467056167950311e-05,
      "loss": 177.2155,
      "step": 15
    },
    {
      "epoch": 0.033126293995859216,
      "grad_norm": 4.038162708282471,
      "learning_rate": 8.239426430539243e-05,
      "loss": 177.2178,
      "step": 16
    },
    {
      "epoch": 0.035196687370600416,
      "grad_norm": 3.8790948390960693,
      "learning_rate": 8.000066048588211e-05,
      "loss": 177.1103,
      "step": 17
    },
    {
      "epoch": 0.037267080745341616,
      "grad_norm": 3.8974990844726562,
      "learning_rate": 7.75e-05,
      "loss": 177.1824,
      "step": 18
    },
    {
      "epoch": 0.039337474120082816,
      "grad_norm": 4.2685723304748535,
      "learning_rate": 7.490299105985507e-05,
      "loss": 177.0003,
      "step": 19
    },
    {
      "epoch": 0.041407867494824016,
      "grad_norm": 4.329255104064941,
      "learning_rate": 7.222075445642904e-05,
      "loss": 177.041,
      "step": 20
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 4.323456287384033,
      "learning_rate": 6.946477593864228e-05,
      "loss": 177.0872,
      "step": 21
    },
    {
      "epoch": 0.045548654244306416,
      "grad_norm": 5.143335342407227,
      "learning_rate": 6.664685702961344e-05,
      "loss": 176.9813,
      "step": 22
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 5.269317626953125,
      "learning_rate": 6.377906449072578e-05,
      "loss": 176.8138,
      "step": 23
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 6.120867729187012,
      "learning_rate": 6.087367864990233e-05,
      "loss": 176.5913,
      "step": 24
    },
    {
      "epoch": 0.051759834368530024,
      "grad_norm": 8.52836799621582,
      "learning_rate": 5.794314081535644e-05,
      "loss": 176.5033,
      "step": 25
    },
    {
      "epoch": 0.051759834368530024,
      "eval_loss": 11.040526390075684,
      "eval_runtime": 0.1039,
      "eval_samples_per_second": 481.058,
      "eval_steps_per_second": 125.075,
      "step": 25
    },
    {
      "epoch": 0.053830227743271224,
      "grad_norm": 6.273050785064697,
      "learning_rate": 5.500000000000001e-05,
      "loss": 176.543,
      "step": 26
    },
    {
      "epoch": 0.055900621118012424,
      "grad_norm": 4.564478874206543,
      "learning_rate": 5.205685918464356e-05,
      "loss": 176.7715,
      "step": 27
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 4.060601234436035,
      "learning_rate": 4.912632135009769e-05,
      "loss": 176.7596,
      "step": 28
    },
    {
      "epoch": 0.060041407867494824,
      "grad_norm": 4.104419231414795,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 176.7908,
      "step": 29
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 4.079372406005859,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 176.8614,
      "step": 30
    },
    {
      "epoch": 0.06418219461697723,
      "grad_norm": 3.9627532958984375,
      "learning_rate": 4.053522406135775e-05,
      "loss": 176.7196,
      "step": 31
    },
    {
      "epoch": 0.06625258799171843,
      "grad_norm": 4.171489238739014,
      "learning_rate": 3.777924554357096e-05,
      "loss": 176.7438,
      "step": 32
    },
    {
      "epoch": 0.06832298136645963,
      "grad_norm": 4.367033958435059,
      "learning_rate": 3.509700894014496e-05,
      "loss": 176.5595,
      "step": 33
    },
    {
      "epoch": 0.07039337474120083,
      "grad_norm": 4.644000053405762,
      "learning_rate": 3.250000000000001e-05,
      "loss": 176.4825,
      "step": 34
    },
    {
      "epoch": 0.07246376811594203,
      "grad_norm": 4.799984455108643,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 176.5039,
      "step": 35
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 5.801799297332764,
      "learning_rate": 2.760573569460757e-05,
      "loss": 176.2772,
      "step": 36
    },
    {
      "epoch": 0.07660455486542443,
      "grad_norm": 6.784635543823242,
      "learning_rate": 2.53294383204969e-05,
      "loss": 176.0369,
      "step": 37
    },
    {
      "epoch": 0.07867494824016563,
      "grad_norm": 7.3659515380859375,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 175.6978,
      "step": 38
    },
    {
      "epoch": 0.08074534161490683,
      "grad_norm": 6.215569972991943,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 176.2542,
      "step": 39
    },
    {
      "epoch": 0.08281573498964803,
      "grad_norm": 4.460636615753174,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 176.5287,
      "step": 40
    },
    {
      "epoch": 0.08488612836438923,
      "grad_norm": 4.100980281829834,
      "learning_rate": 1.758386744638546e-05,
      "loss": 176.6485,
      "step": 41
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 4.223078727722168,
      "learning_rate": 1.602885682970026e-05,
      "loss": 176.5936,
      "step": 42
    },
    {
      "epoch": 0.08902691511387163,
      "grad_norm": 4.136197090148926,
      "learning_rate": 1.464072663102903e-05,
      "loss": 176.5854,
      "step": 43
    },
    {
      "epoch": 0.09109730848861283,
      "grad_norm": 4.319904804229736,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 176.4969,
      "step": 44
    },
    {
      "epoch": 0.09316770186335403,
      "grad_norm": 4.2462158203125,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 176.4756,
      "step": 45
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 4.513911247253418,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 176.411,
      "step": 46
    },
    {
      "epoch": 0.09730848861283643,
      "grad_norm": 4.598360538482666,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 176.2859,
      "step": 47
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 5.463926792144775,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 176.1009,
      "step": 48
    },
    {
      "epoch": 0.10144927536231885,
      "grad_norm": 5.886993408203125,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 175.9742,
      "step": 49
    },
    {
      "epoch": 0.10351966873706005,
      "grad_norm": 8.994738578796387,
      "learning_rate": 1e-05,
      "loss": 175.2022,
      "step": 50
    },
    {
      "epoch": 0.10351966873706005,
      "eval_loss": 11.014021873474121,
      "eval_runtime": 0.1074,
      "eval_samples_per_second": 465.736,
      "eval_steps_per_second": 121.091,
      "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": 38111123865600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}