{
  "best_metric": 1.312924861907959,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.1475644699140402,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 120.85951232910156,
      "learning_rate": 5e-05,
      "loss": 32.286,
      "step": 1
    },
    {
      "epoch": 0.022922636103151862,
      "eval_loss": 2.5055336952209473,
      "eval_runtime": 4.6657,
      "eval_samples_per_second": 10.716,
      "eval_steps_per_second": 2.786,
      "step": 1
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 161.19876098632812,
      "learning_rate": 0.0001,
      "loss": 33.7871,
      "step": 2
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 104.41687774658203,
      "learning_rate": 9.990365154573717e-05,
      "loss": 28.9507,
      "step": 3
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 54.25310134887695,
      "learning_rate": 9.961501876182148e-05,
      "loss": 26.8732,
      "step": 4
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 50.378841400146484,
      "learning_rate": 9.913533761814537e-05,
      "loss": 26.9191,
      "step": 5
    },
    {
      "epoch": 0.13753581661891118,
      "grad_norm": 40.16834259033203,
      "learning_rate": 9.846666218300807e-05,
      "loss": 26.0473,
      "step": 6
    },
    {
      "epoch": 0.16045845272206305,
      "grad_norm": 36.23431396484375,
      "learning_rate": 9.761185582727977e-05,
      "loss": 26.2807,
      "step": 7
    },
    {
      "epoch": 0.1833810888252149,
      "grad_norm": 35.77769470214844,
      "learning_rate": 9.657457896300791e-05,
      "loss": 23.7471,
      "step": 8
    },
    {
      "epoch": 0.20630372492836677,
      "grad_norm": 36.986839294433594,
      "learning_rate": 9.535927336897098e-05,
      "loss": 23.9079,
      "step": 9
    },
    {
      "epoch": 0.22922636103151864,
      "grad_norm": 37.075111389160156,
      "learning_rate": 9.397114317029975e-05,
      "loss": 23.1041,
      "step": 10
    },
    {
      "epoch": 0.2521489971346705,
      "grad_norm": 100.97027587890625,
      "learning_rate": 9.241613255361455e-05,
      "loss": 21.5802,
      "step": 11
    },
    {
      "epoch": 0.27507163323782235,
      "grad_norm": 34.042057037353516,
      "learning_rate": 9.070090031310558e-05,
      "loss": 25.2909,
      "step": 12
    },
    {
      "epoch": 0.2979942693409742,
      "grad_norm": 30.627338409423828,
      "learning_rate": 8.883279133655399e-05,
      "loss": 24.6656,
      "step": 13
    },
    {
      "epoch": 0.3209169054441261,
      "grad_norm": 27.973888397216797,
      "learning_rate": 8.681980515339464e-05,
      "loss": 24.4171,
      "step": 14
    },
    {
      "epoch": 0.3438395415472779,
      "grad_norm": 27.664453506469727,
      "learning_rate": 8.467056167950311e-05,
      "loss": 23.8782,
      "step": 15
    },
    {
      "epoch": 0.3667621776504298,
      "grad_norm": 29.356807708740234,
      "learning_rate": 8.239426430539243e-05,
      "loss": 22.3149,
      "step": 16
    },
    {
      "epoch": 0.38968481375358166,
      "grad_norm": 29.775989532470703,
      "learning_rate": 8.000066048588211e-05,
      "loss": 23.9977,
      "step": 17
    },
    {
      "epoch": 0.41260744985673353,
      "grad_norm": 30.343734741210938,
      "learning_rate": 7.75e-05,
      "loss": 22.3011,
      "step": 18
    },
    {
      "epoch": 0.4355300859598854,
      "grad_norm": 33.033485412597656,
      "learning_rate": 7.490299105985507e-05,
      "loss": 23.2546,
      "step": 19
    },
    {
      "epoch": 0.4584527220630373,
      "grad_norm": 34.381256103515625,
      "learning_rate": 7.222075445642904e-05,
      "loss": 23.6353,
      "step": 20
    },
    {
      "epoch": 0.4813753581661891,
      "grad_norm": 35.273128509521484,
      "learning_rate": 6.946477593864228e-05,
      "loss": 22.0287,
      "step": 21
    },
    {
      "epoch": 0.504297994269341,
      "grad_norm": 30.15144157409668,
      "learning_rate": 6.664685702961344e-05,
      "loss": 21.7471,
      "step": 22
    },
    {
      "epoch": 0.5272206303724928,
      "grad_norm": 28.10733985900879,
      "learning_rate": 6.377906449072578e-05,
      "loss": 23.9749,
      "step": 23
    },
    {
      "epoch": 0.5501432664756447,
      "grad_norm": 25.103281021118164,
      "learning_rate": 6.087367864990233e-05,
      "loss": 23.3658,
      "step": 24
    },
    {
      "epoch": 0.5730659025787965,
      "grad_norm": 26.523576736450195,
      "learning_rate": 5.794314081535644e-05,
      "loss": 24.1702,
      "step": 25
    },
    {
      "epoch": 0.5730659025787965,
      "eval_loss": 1.3627617359161377,
      "eval_runtime": 4.7389,
      "eval_samples_per_second": 10.551,
      "eval_steps_per_second": 2.743,
      "step": 25
    },
    {
      "epoch": 0.5959885386819485,
      "grad_norm": 27.527820587158203,
      "learning_rate": 5.500000000000001e-05,
      "loss": 23.6761,
      "step": 26
    },
    {
      "epoch": 0.6189111747851003,
      "grad_norm": 27.30636215209961,
      "learning_rate": 5.205685918464356e-05,
      "loss": 22.9558,
      "step": 27
    },
    {
      "epoch": 0.6418338108882522,
      "grad_norm": 29.87013053894043,
      "learning_rate": 4.912632135009769e-05,
      "loss": 23.2196,
      "step": 28
    },
    {
      "epoch": 0.664756446991404,
      "grad_norm": 29.727075576782227,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 21.3986,
      "step": 29
    },
    {
      "epoch": 0.6876790830945558,
      "grad_norm": 29.525386810302734,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 21.6861,
      "step": 30
    },
    {
      "epoch": 0.7106017191977078,
      "grad_norm": 29.010095596313477,
      "learning_rate": 4.053522406135775e-05,
      "loss": 22.7758,
      "step": 31
    },
    {
      "epoch": 0.7335243553008596,
      "grad_norm": 32.525333404541016,
      "learning_rate": 3.777924554357096e-05,
      "loss": 19.9094,
      "step": 32
    },
    {
      "epoch": 0.7564469914040115,
      "grad_norm": 35.969703674316406,
      "learning_rate": 3.509700894014496e-05,
      "loss": 21.9237,
      "step": 33
    },
    {
      "epoch": 0.7793696275071633,
      "grad_norm": 24.25885009765625,
      "learning_rate": 3.250000000000001e-05,
      "loss": 23.5966,
      "step": 34
    },
    {
      "epoch": 0.8022922636103151,
      "grad_norm": 24.96795082092285,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 22.0095,
      "step": 35
    },
    {
      "epoch": 0.8252148997134671,
      "grad_norm": 24.220693588256836,
      "learning_rate": 2.760573569460757e-05,
      "loss": 22.4496,
      "step": 36
    },
    {
      "epoch": 0.8481375358166189,
      "grad_norm": 23.359615325927734,
      "learning_rate": 2.53294383204969e-05,
      "loss": 20.1796,
      "step": 37
    },
    {
      "epoch": 0.8710601719197708,
      "grad_norm": 24.08407211303711,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 21.778,
      "step": 38
    },
    {
      "epoch": 0.8939828080229226,
      "grad_norm": 27.159765243530273,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 22.5282,
      "step": 39
    },
    {
      "epoch": 0.9169054441260746,
      "grad_norm": 25.686376571655273,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 20.8734,
      "step": 40
    },
    {
      "epoch": 0.9398280802292264,
      "grad_norm": 27.449390411376953,
      "learning_rate": 1.758386744638546e-05,
      "loss": 21.2547,
      "step": 41
    },
    {
      "epoch": 0.9627507163323782,
      "grad_norm": 30.158475875854492,
      "learning_rate": 1.602885682970026e-05,
      "loss": 20.4989,
      "step": 42
    },
    {
      "epoch": 0.9856733524355301,
      "grad_norm": 33.0136604309082,
      "learning_rate": 1.464072663102903e-05,
      "loss": 20.1556,
      "step": 43
    },
    {
      "epoch": 1.010028653295129,
      "grad_norm": 21.4853572845459,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 21.4587,
      "step": 44
    },
    {
      "epoch": 1.0329512893982808,
      "grad_norm": 19.242902755737305,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 20.5628,
      "step": 45
    },
    {
      "epoch": 1.0558739255014327,
      "grad_norm": 19.76910400390625,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 19.7431,
      "step": 46
    },
    {
      "epoch": 1.0787965616045845,
      "grad_norm": 20.58301544189453,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 20.1779,
      "step": 47
    },
    {
      "epoch": 1.1017191977077363,
      "grad_norm": 21.95994758605957,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 19.1627,
      "step": 48
    },
    {
      "epoch": 1.1246418338108883,
      "grad_norm": 22.073286056518555,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 17.5031,
      "step": 49
    },
    {
      "epoch": 1.1475644699140402,
      "grad_norm": 21.839536666870117,
      "learning_rate": 1e-05,
      "loss": 18.7401,
      "step": 50
    },
    {
      "epoch": 1.1475644699140402,
      "eval_loss": 1.312924861907959,
      "eval_runtime": 4.7394,
      "eval_samples_per_second": 10.55,
      "eval_steps_per_second": 2.743,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.658021338284032e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}