{
  "best_metric": 1.648253321647644,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9803921568627451,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 0.24988579750061035,
      "learning_rate": 5e-05,
      "loss": 1.8407,
      "step": 1
    },
    {
      "epoch": 0.0392156862745098,
      "eval_loss": 1.9764854907989502,
      "eval_runtime": 4.5291,
      "eval_samples_per_second": 37.976,
      "eval_steps_per_second": 4.857,
      "step": 1
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.25837182998657227,
      "learning_rate": 0.0001,
      "loss": 1.883,
      "step": 2
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.2485896646976471,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.8896,
      "step": 3
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.25695013999938965,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.9502,
      "step": 4
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.2187684327363968,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9433,
      "step": 5
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.21632742881774902,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9729,
      "step": 6
    },
    {
      "epoch": 0.27450980392156865,
      "grad_norm": 0.16930197179317474,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6653,
      "step": 7
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.22359579801559448,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7018,
      "step": 8
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.2660350203514099,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7458,
      "step": 9
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.2784881293773651,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7523,
      "step": 10
    },
    {
      "epoch": 0.43137254901960786,
      "grad_norm": 0.23793818056583405,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8239,
      "step": 11
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.22583788633346558,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9176,
      "step": 12
    },
    {
      "epoch": 0.5098039215686274,
      "grad_norm": 0.14187447726726532,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.6413,
      "step": 13
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.1522621512413025,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6188,
      "step": 14
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.16769146919250488,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6939,
      "step": 15
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.18174070119857788,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6399,
      "step": 16
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.19126224517822266,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.7498,
      "step": 17
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.19128768146038055,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7815,
      "step": 18
    },
    {
      "epoch": 0.7450980392156863,
      "grad_norm": 0.17445573210716248,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6568,
      "step": 19
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.16562898457050323,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5288,
      "step": 20
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.16586856544017792,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6014,
      "step": 21
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.16047951579093933,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6202,
      "step": 22
    },
    {
      "epoch": 0.9019607843137255,
      "grad_norm": 0.17289896309375763,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.7032,
      "step": 23
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.19855345785617828,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.771,
      "step": 24
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.25787705183029175,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7947,
      "step": 25
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 1.648253321647644,
      "eval_runtime": 4.5219,
      "eval_samples_per_second": 38.037,
      "eval_steps_per_second": 4.865,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8190589936939827e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}