{
  "best_metric": 0.9442797303199768,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6294256490952006,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012588512981904013,
      "grad_norm": 21.16543960571289,
      "learning_rate": 5e-05,
      "loss": 2.3373,
      "step": 1
    },
    {
      "epoch": 0.012588512981904013,
      "eval_loss": 2.5010251998901367,
      "eval_runtime": 13.6534,
      "eval_samples_per_second": 39.258,
      "eval_steps_per_second": 4.907,
      "step": 1
    },
    {
      "epoch": 0.025177025963808025,
      "grad_norm": 23.64405059814453,
      "learning_rate": 0.0001,
      "loss": 2.3002,
      "step": 2
    },
    {
      "epoch": 0.03776553894571204,
      "grad_norm": 23.064193725585938,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.3989,
      "step": 3
    },
    {
      "epoch": 0.05035405192761605,
      "grad_norm": 20.119773864746094,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1218,
      "step": 4
    },
    {
      "epoch": 0.06294256490952006,
      "grad_norm": 21.986080169677734,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.1021,
      "step": 5
    },
    {
      "epoch": 0.07553107789142408,
      "grad_norm": 21.071178436279297,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.8549,
      "step": 6
    },
    {
      "epoch": 0.08811959087332809,
      "grad_norm": 23.8582706451416,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0362,
      "step": 7
    },
    {
      "epoch": 0.1007081038552321,
      "grad_norm": 26.81045150756836,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9506,
      "step": 8
    },
    {
      "epoch": 0.11329661683713611,
      "grad_norm": 31.266883850097656,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6144,
      "step": 9
    },
    {
      "epoch": 0.12588512981904013,
      "grad_norm": 34.45520782470703,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6564,
      "step": 10
    },
    {
      "epoch": 0.13847364280094415,
      "grad_norm": 36.80929183959961,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.5002,
      "step": 11
    },
    {
      "epoch": 0.15106215578284815,
      "grad_norm": 33.41875076293945,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.6248,
      "step": 12
    },
    {
      "epoch": 0.16365066876475218,
      "grad_norm": 53.04654312133789,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.7668,
      "step": 13
    },
    {
      "epoch": 0.17623918174665618,
      "grad_norm": 79.66429901123047,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9672,
      "step": 14
    },
    {
      "epoch": 0.1888276947285602,
      "grad_norm": 53.10544967651367,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5469,
      "step": 15
    },
    {
      "epoch": 0.2014162077104642,
      "grad_norm": 40.61369323730469,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6699,
      "step": 16
    },
    {
      "epoch": 0.21400472069236823,
      "grad_norm": 31.596616744995117,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.4594,
      "step": 17
    },
    {
      "epoch": 0.22659323367427223,
      "grad_norm": 34.025482177734375,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3662,
      "step": 18
    },
    {
      "epoch": 0.23918174665617625,
      "grad_norm": 32.110267639160156,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2301,
      "step": 19
    },
    {
      "epoch": 0.25177025963808025,
      "grad_norm": 38.80237579345703,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3337,
      "step": 20
    },
    {
      "epoch": 0.26435877261998425,
      "grad_norm": 32.85317611694336,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2655,
      "step": 21
    },
    {
      "epoch": 0.2769472856018883,
      "grad_norm": 28.820865631103516,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.171,
      "step": 22
    },
    {
      "epoch": 0.2895357985837923,
      "grad_norm": 32.6195182800293,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.1392,
      "step": 23
    },
    {
      "epoch": 0.3021243115656963,
      "grad_norm": 30.52219009399414,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1825,
      "step": 24
    },
    {
      "epoch": 0.3147128245476003,
      "grad_norm": 36.73969650268555,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.0942,
      "step": 25
    },
    {
      "epoch": 0.3147128245476003,
      "eval_loss": 1.1853362321853638,
      "eval_runtime": 13.6363,
      "eval_samples_per_second": 39.307,
      "eval_steps_per_second": 4.913,
      "step": 25
    },
    {
      "epoch": 0.32730133752950435,
      "grad_norm": 32.60086441040039,
      "learning_rate": 5e-05,
      "loss": 1.6508,
      "step": 26
    },
    {
      "epoch": 0.33988985051140835,
      "grad_norm": 29.659774780273438,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.3073,
      "step": 27
    },
    {
      "epoch": 0.35247836349331235,
      "grad_norm": 27.13357925415039,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.2718,
      "step": 28
    },
    {
      "epoch": 0.36506687647521635,
      "grad_norm": 24.87796401977539,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.2055,
      "step": 29
    },
    {
      "epoch": 0.3776553894571204,
      "grad_norm": 24.10536003112793,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.16,
      "step": 30
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 25.981910705566406,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.0399,
      "step": 31
    },
    {
      "epoch": 0.4028324154209284,
      "grad_norm": 36.10255813598633,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.135,
      "step": 32
    },
    {
      "epoch": 0.4154209284028324,
      "grad_norm": 40.39674758911133,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.1585,
      "step": 33
    },
    {
      "epoch": 0.42800944138473646,
      "grad_norm": 34.2160758972168,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8405,
      "step": 34
    },
    {
      "epoch": 0.44059795436664045,
      "grad_norm": 33.32962417602539,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.797,
      "step": 35
    },
    {
      "epoch": 0.45318646734854445,
      "grad_norm": 27.23453140258789,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.7851,
      "step": 36
    },
    {
      "epoch": 0.46577498033044845,
      "grad_norm": 31.11690330505371,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.9167,
      "step": 37
    },
    {
      "epoch": 0.4783634933123525,
      "grad_norm": 31.77367401123047,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.096,
      "step": 38
    },
    {
      "epoch": 0.4909520062942565,
      "grad_norm": 31.28978729248047,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.3097,
      "step": 39
    },
    {
      "epoch": 0.5035405192761605,
      "grad_norm": 24.03819465637207,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.0327,
      "step": 40
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 24.845369338989258,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.0824,
      "step": 41
    },
    {
      "epoch": 0.5287175452399685,
      "grad_norm": 24.798585891723633,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.058,
      "step": 42
    },
    {
      "epoch": 0.5413060582218725,
      "grad_norm": 24.77889633178711,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.9896,
      "step": 43
    },
    {
      "epoch": 0.5538945712037766,
      "grad_norm": 24.031038284301758,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.8687,
      "step": 44
    },
    {
      "epoch": 0.5664830841856806,
      "grad_norm": 24.104299545288086,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.9357,
      "step": 45
    },
    {
      "epoch": 0.5790715971675846,
      "grad_norm": 24.142581939697266,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.8889,
      "step": 46
    },
    {
      "epoch": 0.5916601101494886,
      "grad_norm": 23.086729049682617,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.6544,
      "step": 47
    },
    {
      "epoch": 0.6042486231313926,
      "grad_norm": 24.28306770324707,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.7109,
      "step": 48
    },
    {
      "epoch": 0.6168371361132966,
      "grad_norm": 25.321258544921875,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.7226,
      "step": 49
    },
    {
      "epoch": 0.6294256490952006,
      "grad_norm": 40.5628776550293,
      "learning_rate": 0.0,
      "loss": 0.7491,
      "step": 50
    },
    {
      "epoch": 0.6294256490952006,
      "eval_loss": 0.9442797303199768,
      "eval_runtime": 13.6356,
      "eval_samples_per_second": 39.309,
      "eval_steps_per_second": 4.914,
      "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": 9.70274988097536e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}