{
  "best_metric": 11.928146362304688,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4192872117400419,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008385744234800839,
      "grad_norm": 0.028302129358053207,
      "learning_rate": 5e-05,
      "loss": 11.9244,
      "step": 1
    },
    {
      "epoch": 0.008385744234800839,
      "eval_loss": 11.931392669677734,
      "eval_runtime": 1.7366,
      "eval_samples_per_second": 462.968,
      "eval_steps_per_second": 58.159,
      "step": 1
    },
    {
      "epoch": 0.016771488469601678,
      "grad_norm": 0.025225507095456123,
      "learning_rate": 0.0001,
      "loss": 11.9287,
      "step": 2
    },
    {
      "epoch": 0.025157232704402517,
      "grad_norm": 0.025965744629502296,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9274,
      "step": 3
    },
    {
      "epoch": 0.033542976939203356,
      "grad_norm": 0.025864940136671066,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9299,
      "step": 4
    },
    {
      "epoch": 0.041928721174004195,
      "grad_norm": 0.0286379586905241,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9299,
      "step": 5
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 0.028485065326094627,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.931,
      "step": 6
    },
    {
      "epoch": 0.05870020964360587,
      "grad_norm": 0.027851169928908348,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9301,
      "step": 7
    },
    {
      "epoch": 0.06708595387840671,
      "grad_norm": 0.02716955542564392,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9305,
      "step": 8
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 0.03554312884807587,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9322,
      "step": 9
    },
    {
      "epoch": 0.08385744234800839,
      "grad_norm": 0.025717342272400856,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9337,
      "step": 10
    },
    {
      "epoch": 0.09224318658280922,
      "grad_norm": 0.04107967019081116,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.932,
      "step": 11
    },
    {
      "epoch": 0.10062893081761007,
      "grad_norm": 0.033041615039110184,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9331,
      "step": 12
    },
    {
      "epoch": 0.1090146750524109,
      "grad_norm": 0.03018532134592533,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9233,
      "step": 13
    },
    {
      "epoch": 0.11740041928721175,
      "grad_norm": 0.030003391206264496,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9242,
      "step": 14
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 0.027340294793248177,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9269,
      "step": 15
    },
    {
      "epoch": 0.13417190775681342,
      "grad_norm": 0.03445419296622276,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.9269,
      "step": 16
    },
    {
      "epoch": 0.14255765199161424,
      "grad_norm": 0.033826183527708054,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9288,
      "step": 17
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.04148228466510773,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9278,
      "step": 18
    },
    {
      "epoch": 0.15932914046121593,
      "grad_norm": 0.04665839672088623,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9292,
      "step": 19
    },
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 0.04396500810980797,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9288,
      "step": 20
    },
    {
      "epoch": 0.1761006289308176,
      "grad_norm": 0.04329974576830864,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9283,
      "step": 21
    },
    {
      "epoch": 0.18448637316561844,
      "grad_norm": 0.04438428208231926,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9338,
      "step": 22
    },
    {
      "epoch": 0.1928721174004193,
      "grad_norm": 0.052561450749635696,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9309,
      "step": 23
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": 0.048290323466062546,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9308,
      "step": 24
    },
    {
      "epoch": 0.20964360587002095,
      "grad_norm": 0.04853208363056183,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9345,
      "step": 25
    },
    {
      "epoch": 0.20964360587002095,
      "eval_loss": 11.929275512695312,
      "eval_runtime": 1.7367,
      "eval_samples_per_second": 462.955,
      "eval_steps_per_second": 58.157,
      "step": 25
    },
    {
      "epoch": 0.2180293501048218,
      "grad_norm": 0.0470016710460186,
      "learning_rate": 5e-05,
      "loss": 11.9248,
      "step": 26
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 0.047832075506448746,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 11.9269,
      "step": 27
    },
    {
      "epoch": 0.2348008385744235,
      "grad_norm": 0.054423995316028595,
      "learning_rate": 4.347369038899744e-05,
      "loss": 11.9269,
      "step": 28
    },
    {
      "epoch": 0.2431865828092243,
      "grad_norm": 0.059153150767087936,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 11.9256,
      "step": 29
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 0.05590154230594635,
      "learning_rate": 3.705904774487396e-05,
      "loss": 11.927,
      "step": 30
    },
    {
      "epoch": 0.259958071278826,
      "grad_norm": 0.058628544211387634,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.9266,
      "step": 31
    },
    {
      "epoch": 0.26834381551362685,
      "grad_norm": 0.06399206817150116,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9272,
      "step": 32
    },
    {
      "epoch": 0.27672955974842767,
      "grad_norm": 0.06347686797380447,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 11.9286,
      "step": 33
    },
    {
      "epoch": 0.2851153039832285,
      "grad_norm": 0.06550882756710052,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.9276,
      "step": 34
    },
    {
      "epoch": 0.29350104821802936,
      "grad_norm": 0.059900153428316116,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 11.9315,
      "step": 35
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 0.07278956472873688,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 11.9284,
      "step": 36
    },
    {
      "epoch": 0.31027253668763105,
      "grad_norm": 0.0694255456328392,
      "learning_rate": 1.703270924499656e-05,
      "loss": 11.9324,
      "step": 37
    },
    {
      "epoch": 0.31865828092243187,
      "grad_norm": 0.053817711770534515,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9236,
      "step": 38
    },
    {
      "epoch": 0.3270440251572327,
      "grad_norm": 0.066506028175354,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 11.9231,
      "step": 39
    },
    {
      "epoch": 0.33542976939203356,
      "grad_norm": 0.06306684017181396,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 11.9245,
      "step": 40
    },
    {
      "epoch": 0.3438155136268344,
      "grad_norm": 0.06684385240077972,
      "learning_rate": 8.426519384872733e-06,
      "loss": 11.9263,
      "step": 41
    },
    {
      "epoch": 0.3522012578616352,
      "grad_norm": 0.06455033272504807,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.9278,
      "step": 42
    },
    {
      "epoch": 0.36058700209643607,
      "grad_norm": 0.06546949595212936,
      "learning_rate": 5.156362923365588e-06,
      "loss": 11.9259,
      "step": 43
    },
    {
      "epoch": 0.3689727463312369,
      "grad_norm": 0.07471216470003128,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9258,
      "step": 44
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.0686088502407074,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.9275,
      "step": 45
    },
    {
      "epoch": 0.3857442348008386,
      "grad_norm": 0.07394406944513321,
      "learning_rate": 1.70370868554659e-06,
      "loss": 11.929,
      "step": 46
    },
    {
      "epoch": 0.3941299790356394,
      "grad_norm": 0.06964340806007385,
      "learning_rate": 9.607359798384785e-07,
      "loss": 11.9301,
      "step": 47
    },
    {
      "epoch": 0.4025157232704403,
      "grad_norm": 0.06854347884654999,
      "learning_rate": 4.277569313094809e-07,
      "loss": 11.9288,
      "step": 48
    },
    {
      "epoch": 0.4109014675052411,
      "grad_norm": 0.07059460133314133,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.929,
      "step": 49
    },
    {
      "epoch": 0.4192872117400419,
      "grad_norm": 0.07417823374271393,
      "learning_rate": 0.0,
      "loss": 11.9308,
      "step": 50
    },
    {
      "epoch": 0.4192872117400419,
      "eval_loss": 11.928146362304688,
      "eval_runtime": 1.7255,
      "eval_samples_per_second": 465.963,
      "eval_steps_per_second": 58.535,
      "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}