{
  "best_metric": 2.5114123821258545,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7843137254901961,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01568627450980392,
      "grad_norm": 0.9195303320884705,
      "learning_rate": 1e-05,
      "loss": 2.8736,
      "step": 1
    },
    {
      "epoch": 0.01568627450980392,
      "eval_loss": 3.324666738510132,
      "eval_runtime": 7.9726,
      "eval_samples_per_second": 13.546,
      "eval_steps_per_second": 3.387,
      "step": 1
    },
    {
      "epoch": 0.03137254901960784,
      "grad_norm": 1.0334582328796387,
      "learning_rate": 2e-05,
      "loss": 2.8739,
      "step": 2
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 1.0187386274337769,
      "learning_rate": 3e-05,
      "loss": 2.9073,
      "step": 3
    },
    {
      "epoch": 0.06274509803921569,
      "grad_norm": 0.9314672946929932,
      "learning_rate": 4e-05,
      "loss": 2.9041,
      "step": 4
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.9586840867996216,
      "learning_rate": 5e-05,
      "loss": 2.807,
      "step": 5
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.9514013528823853,
      "learning_rate": 6e-05,
      "loss": 2.996,
      "step": 6
    },
    {
      "epoch": 0.10980392156862745,
      "grad_norm": 0.8477784395217896,
      "learning_rate": 7e-05,
      "loss": 2.9011,
      "step": 7
    },
    {
      "epoch": 0.12549019607843137,
      "grad_norm": 0.898993968963623,
      "learning_rate": 8e-05,
      "loss": 2.7146,
      "step": 8
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 0.8038886785507202,
      "learning_rate": 9e-05,
      "loss": 2.7318,
      "step": 9
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.8036936521530151,
      "learning_rate": 0.0001,
      "loss": 2.6728,
      "step": 10
    },
    {
      "epoch": 0.17254901960784313,
      "grad_norm": 0.9414847493171692,
      "learning_rate": 9.999255120204248e-05,
      "loss": 2.6703,
      "step": 11
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 1.016950249671936,
      "learning_rate": 9.997020702755353e-05,
      "loss": 2.7351,
      "step": 12
    },
    {
      "epoch": 0.20392156862745098,
      "grad_norm": 1.0459362268447876,
      "learning_rate": 9.99329741340228e-05,
      "loss": 2.6783,
      "step": 13
    },
    {
      "epoch": 0.2196078431372549,
      "grad_norm": 1.2477803230285645,
      "learning_rate": 9.98808636150624e-05,
      "loss": 2.6327,
      "step": 14
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.4739620685577393,
      "learning_rate": 9.981389099710132e-05,
      "loss": 3.0748,
      "step": 15
    },
    {
      "epoch": 0.25098039215686274,
      "grad_norm": 0.5202563405036926,
      "learning_rate": 9.973207623475965e-05,
      "loss": 2.41,
      "step": 16
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.6118998527526855,
      "learning_rate": 9.96354437049027e-05,
      "loss": 2.5087,
      "step": 17
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.5753269791603088,
      "learning_rate": 9.952402219937816e-05,
      "loss": 2.5023,
      "step": 18
    },
    {
      "epoch": 0.2980392156862745,
      "grad_norm": 0.548793613910675,
      "learning_rate": 9.939784491643734e-05,
      "loss": 2.4598,
      "step": 19
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.5158197283744812,
      "learning_rate": 9.92569494508437e-05,
      "loss": 2.626,
      "step": 20
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 0.4742230474948883,
      "learning_rate": 9.910137778267152e-05,
      "loss": 2.539,
      "step": 21
    },
    {
      "epoch": 0.34509803921568627,
      "grad_norm": 0.4577326774597168,
      "learning_rate": 9.893117626479777e-05,
      "loss": 2.5212,
      "step": 22
    },
    {
      "epoch": 0.3607843137254902,
      "grad_norm": 0.469974547624588,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.4532,
      "step": 23
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.6523585915565491,
      "learning_rate": 9.85470908713026e-05,
      "loss": 2.4785,
      "step": 24
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.6335188746452332,
      "learning_rate": 9.833332143466099e-05,
      "loss": 2.5327,
      "step": 25
    },
    {
      "epoch": 0.40784313725490196,
      "grad_norm": 0.5561938881874084,
      "learning_rate": 9.810515099218003e-05,
      "loss": 2.7133,
      "step": 26
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 0.6505088210105896,
      "learning_rate": 9.78626475276808e-05,
      "loss": 2.5733,
      "step": 27
    },
    {
      "epoch": 0.4392156862745098,
      "grad_norm": 0.7462759613990784,
      "learning_rate": 9.760588329553571e-05,
      "loss": 2.6319,
      "step": 28
    },
    {
      "epoch": 0.4549019607843137,
      "grad_norm": 0.8369238376617432,
      "learning_rate": 9.73349347991403e-05,
      "loss": 2.5938,
      "step": 29
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.1839768886566162,
      "learning_rate": 9.704988276811883e-05,
      "loss": 2.9516,
      "step": 30
    },
    {
      "epoch": 0.48627450980392156,
      "grad_norm": 0.29538607597351074,
      "learning_rate": 9.675081213427076e-05,
      "loss": 2.3553,
      "step": 31
    },
    {
      "epoch": 0.5019607843137255,
      "grad_norm": 0.40422534942626953,
      "learning_rate": 9.643781200626511e-05,
      "loss": 2.426,
      "step": 32
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 0.41036108136177063,
      "learning_rate": 9.611097564309053e-05,
      "loss": 2.503,
      "step": 33
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.4156786799430847,
      "learning_rate": 9.577040042626833e-05,
      "loss": 2.3799,
      "step": 34
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.39962074160575867,
      "learning_rate": 9.54161878308377e-05,
      "loss": 2.4543,
      "step": 35
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.4289894998073578,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.4369,
      "step": 36
    },
    {
      "epoch": 0.5803921568627451,
      "grad_norm": 0.4545486271381378,
      "learning_rate": 9.466727668927816e-05,
      "loss": 2.5761,
      "step": 37
    },
    {
      "epoch": 0.596078431372549,
      "grad_norm": 0.431194931268692,
      "learning_rate": 9.42728012826605e-05,
      "loss": 2.4045,
      "step": 38
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.43016883730888367,
      "learning_rate": 9.38651347099721e-05,
      "loss": 2.3858,
      "step": 39
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.45133844017982483,
      "learning_rate": 9.344439843625034e-05,
      "loss": 2.4977,
      "step": 40
    },
    {
      "epoch": 0.6431372549019608,
      "grad_norm": 0.4912121295928955,
      "learning_rate": 9.301071782067504e-05,
      "loss": 2.4795,
      "step": 41
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.6027780175209045,
      "learning_rate": 9.256422207921757e-05,
      "loss": 2.5236,
      "step": 42
    },
    {
      "epoch": 0.6745098039215687,
      "grad_norm": 0.5655380487442017,
      "learning_rate": 9.210504424614059e-05,
      "loss": 2.4498,
      "step": 43
    },
    {
      "epoch": 0.6901960784313725,
      "grad_norm": 0.6778488755226135,
      "learning_rate": 9.163332113436032e-05,
      "loss": 2.5315,
      "step": 44
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.1361249685287476,
      "learning_rate": 9.114919329468282e-05,
      "loss": 2.8519,
      "step": 45
    },
    {
      "epoch": 0.7215686274509804,
      "grad_norm": 0.3818633258342743,
      "learning_rate": 9.065280497392663e-05,
      "loss": 2.4607,
      "step": 46
    },
    {
      "epoch": 0.7372549019607844,
      "grad_norm": 0.3662630319595337,
      "learning_rate": 9.014430407194413e-05,
      "loss": 2.4082,
      "step": 47
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.35173290967941284,
      "learning_rate": 8.962384209755452e-05,
      "loss": 2.5405,
      "step": 48
    },
    {
      "epoch": 0.7686274509803922,
      "grad_norm": 0.38660287857055664,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.4206,
      "step": 49
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.40245190262794495,
      "learning_rate": 8.854765873974898e-05,
      "loss": 2.5983,
      "step": 50
    },
    {
      "epoch": 0.7843137254901961,
      "eval_loss": 2.5114123821258545,
      "eval_runtime": 8.157,
      "eval_samples_per_second": 13.24,
      "eval_steps_per_second": 3.31,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.8297705914368e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}