{
  "best_metric": 0.5091546773910522,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.6329113924050633,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012658227848101266,
      "grad_norm": 42.028053283691406,
      "learning_rate": 2e-05,
      "loss": 6.0199,
      "step": 1
    },
    {
      "epoch": 0.012658227848101266,
      "eval_loss": 1.7844791412353516,
      "eval_runtime": 8.9481,
      "eval_samples_per_second": 14.975,
      "eval_steps_per_second": 1.9,
      "step": 1
    },
    {
      "epoch": 0.02531645569620253,
      "grad_norm": 45.79191970825195,
      "learning_rate": 4e-05,
      "loss": 6.0986,
      "step": 2
    },
    {
      "epoch": 0.0379746835443038,
      "grad_norm": 26.50522804260254,
      "learning_rate": 6e-05,
      "loss": 4.7016,
      "step": 3
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 13.651175498962402,
      "learning_rate": 8e-05,
      "loss": 4.4423,
      "step": 4
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 10.82734489440918,
      "learning_rate": 0.0001,
      "loss": 3.682,
      "step": 5
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 9.763678550720215,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.6171,
      "step": 6
    },
    {
      "epoch": 0.08860759493670886,
      "grad_norm": 10.851454734802246,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.2633,
      "step": 7
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 9.515451431274414,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9692,
      "step": 8
    },
    {
      "epoch": 0.11392405063291139,
      "grad_norm": 8.546252250671387,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.0759,
      "step": 9
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 8.0128173828125,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.4095,
      "step": 10
    },
    {
      "epoch": 0.13924050632911392,
      "grad_norm": 8.757233619689941,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.8278,
      "step": 11
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 8.649038314819336,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.829,
      "step": 12
    },
    {
      "epoch": 0.16455696202531644,
      "grad_norm": 8.026497840881348,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.7128,
      "step": 13
    },
    {
      "epoch": 0.17721518987341772,
      "grad_norm": 7.095391273498535,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.5395,
      "step": 14
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 6.5727715492248535,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.5782,
      "step": 15
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 9.417537689208984,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.5226,
      "step": 16
    },
    {
      "epoch": 0.21518987341772153,
      "grad_norm": 6.655349254608154,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.5861,
      "step": 17
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 6.458268165588379,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0705,
      "step": 18
    },
    {
      "epoch": 0.24050632911392406,
      "grad_norm": 7.291686058044434,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.4741,
      "step": 19
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 6.116868019104004,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.6819,
      "step": 20
    },
    {
      "epoch": 0.26582278481012656,
      "grad_norm": 5.806187152862549,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.836,
      "step": 21
    },
    {
      "epoch": 0.27848101265822783,
      "grad_norm": 5.537196159362793,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.5114,
      "step": 22
    },
    {
      "epoch": 0.2911392405063291,
      "grad_norm": 5.313586235046387,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.25,
      "step": 23
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 10.902448654174805,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.1196,
      "step": 24
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 6.734158992767334,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.5926,
      "step": 25
    },
    {
      "epoch": 0.31645569620253167,
      "eval_loss": 0.5596538186073303,
      "eval_runtime": 8.8918,
      "eval_samples_per_second": 15.07,
      "eval_steps_per_second": 1.912,
      "step": 25
    },
    {
      "epoch": 0.3291139240506329,
      "grad_norm": 7.093173503875732,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.3286,
      "step": 26
    },
    {
      "epoch": 0.34177215189873417,
      "grad_norm": 5.931855201721191,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.9256,
      "step": 27
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 7.020291328430176,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.2209,
      "step": 28
    },
    {
      "epoch": 0.3670886075949367,
      "grad_norm": 6.310258388519287,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.231,
      "step": 29
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 6.792581081390381,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.2158,
      "step": 30
    },
    {
      "epoch": 0.3924050632911392,
      "grad_norm": 6.202337265014648,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.0049,
      "step": 31
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 5.8156914710998535,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.069,
      "step": 32
    },
    {
      "epoch": 0.4177215189873418,
      "grad_norm": 5.831786155700684,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.1343,
      "step": 33
    },
    {
      "epoch": 0.43037974683544306,
      "grad_norm": 6.260862827301025,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.3229,
      "step": 34
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 5.3327202796936035,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.0672,
      "step": 35
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 4.9809417724609375,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9,
      "step": 36
    },
    {
      "epoch": 0.46835443037974683,
      "grad_norm": 6.4525909423828125,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.0248,
      "step": 37
    },
    {
      "epoch": 0.4810126582278481,
      "grad_norm": 6.171474933624268,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.9821,
      "step": 38
    },
    {
      "epoch": 0.4936708860759494,
      "grad_norm": 4.337746620178223,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.9903,
      "step": 39
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 4.888207912445068,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.0018,
      "step": 40
    },
    {
      "epoch": 0.5189873417721519,
      "grad_norm": 5.527780532836914,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.0755,
      "step": 41
    },
    {
      "epoch": 0.5316455696202531,
      "grad_norm": 5.051205158233643,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.979,
      "step": 42
    },
    {
      "epoch": 0.5443037974683544,
      "grad_norm": 5.09185266494751,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.0654,
      "step": 43
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 4.7769694328308105,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.7859,
      "step": 44
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 6.080770969390869,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8062,
      "step": 45
    },
    {
      "epoch": 0.5822784810126582,
      "grad_norm": 6.04468297958374,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.0148,
      "step": 46
    },
    {
      "epoch": 0.5949367088607594,
      "grad_norm": 6.175866603851318,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.8943,
      "step": 47
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 6.0562615394592285,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.9837,
      "step": 48
    },
    {
      "epoch": 0.620253164556962,
      "grad_norm": 7.458826541900635,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.5447,
      "step": 49
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 6.869083881378174,
      "learning_rate": 0.0,
      "loss": 2.0644,
      "step": 50
    },
    {
      "epoch": 0.6329113924050633,
      "eval_loss": 0.5091546773910522,
      "eval_runtime": 9.1468,
      "eval_samples_per_second": 14.65,
      "eval_steps_per_second": 1.859,
      "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": 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": 6.475265990669107e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}