{
  "best_metric": 1.0678768157958984,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 84,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 1.699779748916626,
      "learning_rate": 1e-05,
      "loss": 1.4503,
      "step": 1
    },
    {
      "epoch": 0.03571428571428571,
      "eval_loss": 1.6286729574203491,
      "eval_runtime": 3.8315,
      "eval_samples_per_second": 12.267,
      "eval_steps_per_second": 3.132,
      "step": 1
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.9459228515625,
      "learning_rate": 2e-05,
      "loss": 1.5431,
      "step": 2
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 1.5444223880767822,
      "learning_rate": 3e-05,
      "loss": 1.485,
      "step": 3
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.828545331954956,
      "learning_rate": 4e-05,
      "loss": 1.5345,
      "step": 4
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.6014165878295898,
      "learning_rate": 5e-05,
      "loss": 1.6242,
      "step": 5
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.756152629852295,
      "learning_rate": 6e-05,
      "loss": 1.6398,
      "step": 6
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0617715120315552,
      "learning_rate": 7e-05,
      "loss": 1.2802,
      "step": 7
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.2845737934112549,
      "learning_rate": 8e-05,
      "loss": 1.4341,
      "step": 8
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 1.1846259832382202,
      "learning_rate": 9e-05,
      "loss": 1.3764,
      "step": 9
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.9985613822937012,
      "learning_rate": 0.0001,
      "loss": 1.1661,
      "step": 10
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.181240200996399,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.4043,
      "step": 11
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.2978146076202393,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.2975,
      "step": 12
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.8944197297096252,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.2176,
      "step": 13
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.7838349342346191,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.1616,
      "step": 14
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.667181670665741,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.139,
      "step": 15
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.715985894203186,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.175,
      "step": 16
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.8861929774284363,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.2037,
      "step": 17
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.0346869230270386,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.2577,
      "step": 18
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.6048142910003662,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.2117,
      "step": 19
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.6575442552566528,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.1469,
      "step": 20
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5992381572723389,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.1609,
      "step": 21
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.8459616303443909,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.0932,
      "step": 22
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.8620023727416992,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.2146,
      "step": 23
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.9809871315956116,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.1341,
      "step": 24
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.4556620121002197,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.0431,
      "step": 25
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.6410847902297974,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.145,
      "step": 26
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.6918867826461792,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.0548,
      "step": 27
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.03254234790802,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.0624,
      "step": 28
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.4657690227031708,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.0837,
      "step": 29
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.5787471532821655,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.993,
      "step": 30
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.6005241274833679,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.9823,
      "step": 31
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.6915076375007629,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.9212,
      "step": 32
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.7980732321739197,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.8616,
      "step": 33
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.8493084907531738,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.7512,
      "step": 34
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.5029008388519287,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.9363,
      "step": 35
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.6272581219673157,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.9813,
      "step": 36
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.7248469591140747,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.8941,
      "step": 37
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.7229782342910767,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.8525,
      "step": 38
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.8697368502616882,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.8085,
      "step": 39
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.9230009317398071,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.8435,
      "step": 40
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.47812873125076294,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.9226,
      "step": 41
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5833685994148254,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.9486,
      "step": 42
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.5935266613960266,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.8815,
      "step": 43
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.7497686743736267,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.8752,
      "step": 44
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.8591090440750122,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.9177,
      "step": 45
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.8800234198570251,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.7726,
      "step": 46
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.5047954320907593,
      "learning_rate": 5e-05,
      "loss": 0.9669,
      "step": 47
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.6673800945281982,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.9553,
      "step": 48
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.6023098230361938,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.8924,
      "step": 49
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.7557825446128845,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.7967,
      "step": 50
    },
    {
      "epoch": 1.7857142857142856,
      "eval_loss": 1.0678768157958984,
      "eval_runtime": 3.9244,
      "eval_samples_per_second": 11.976,
      "eval_steps_per_second": 3.058,
      "step": 50
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.9605938792228699,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.8505,
      "step": 51
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.9948092103004456,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.8254,
      "step": 52
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.5172920823097229,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.997,
      "step": 53
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.618449866771698,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.8848,
      "step": 54
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.7257911562919617,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.8151,
      "step": 55
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9913805723190308,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.6593,
      "step": 56
    },
    {
      "epoch": 2.0357142857142856,
      "grad_norm": 0.509917140007019,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.9468,
      "step": 57
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.5384827852249146,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.8333,
      "step": 58
    },
    {
      "epoch": 2.107142857142857,
      "grad_norm": 0.6404847502708435,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.7695,
      "step": 59
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.7586694359779358,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.7043,
      "step": 60
    },
    {
      "epoch": 2.1785714285714284,
      "grad_norm": 0.886222779750824,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.5816,
      "step": 61
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.9940441846847534,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.5794,
      "step": 62
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.5342968702316284,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.8532,
      "step": 63
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.6643630266189575,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.8265,
      "step": 64
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.6381016373634338,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.7252,
      "step": 65
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.6933656334877014,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.6327,
      "step": 66
    },
    {
      "epoch": 2.392857142857143,
      "grad_norm": 0.8817493915557861,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.5871,
      "step": 67
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.0448442697525024,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.6083,
      "step": 68
    },
    {
      "epoch": 2.4642857142857144,
      "grad_norm": 0.6664843559265137,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.8117,
      "step": 69
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.8378458023071289,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.8003,
      "step": 70
    },
    {
      "epoch": 2.5357142857142856,
      "grad_norm": 0.7771973013877869,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.7034,
      "step": 71
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.8301295638084412,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.6515,
      "step": 72
    },
    {
      "epoch": 2.607142857142857,
      "grad_norm": 0.9299514293670654,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.4939,
      "step": 73
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 1.0564358234405518,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.4689,
      "step": 74
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.6848633885383606,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.83,
      "step": 75
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.7416503429412842,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.7841,
      "step": 76
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.7347410917282104,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.741,
      "step": 77
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.7589361667633057,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.5824,
      "step": 78
    },
    {
      "epoch": 2.821428571428571,
      "grad_norm": 0.964680016040802,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.6366,
      "step": 79
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.945676863193512,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.4343,
      "step": 80
    },
    {
      "epoch": 2.892857142857143,
      "grad_norm": 0.6502677202224731,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.8532,
      "step": 81
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.7305717468261719,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.7416,
      "step": 82
    },
    {
      "epoch": 2.9642857142857144,
      "grad_norm": 0.7641732692718506,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.5735,
      "step": 83
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0511471033096313,
      "learning_rate": 0.0,
      "loss": 0.5306,
      "step": 84
    }
  ],
  "logging_steps": 1,
  "max_steps": 84,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.3114639925221786e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}