{
  "best_metric": 1.6505544185638428,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2768166089965398,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011072664359861591,
      "grad_norm": 3.085151433944702,
      "learning_rate": 5e-05,
      "loss": 2.0965,
      "step": 1
    },
    {
      "epoch": 0.011072664359861591,
      "eval_loss": 2.226940631866455,
      "eval_runtime": 7.9021,
      "eval_samples_per_second": 77.068,
      "eval_steps_per_second": 9.744,
      "step": 1
    },
    {
      "epoch": 0.022145328719723183,
      "grad_norm": 2.4434478282928467,
      "learning_rate": 0.0001,
      "loss": 2.1067,
      "step": 2
    },
    {
      "epoch": 0.03321799307958478,
      "grad_norm": 1.3165335655212402,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.1499,
      "step": 3
    },
    {
      "epoch": 0.044290657439446365,
      "grad_norm": 0.9989780187606812,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1183,
      "step": 4
    },
    {
      "epoch": 0.05536332179930796,
      "grad_norm": 0.7292075753211975,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.0738,
      "step": 5
    },
    {
      "epoch": 0.06643598615916955,
      "grad_norm": 1.1118435859680176,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.1048,
      "step": 6
    },
    {
      "epoch": 0.07750865051903114,
      "grad_norm": 2.3716795444488525,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0179,
      "step": 7
    },
    {
      "epoch": 0.08858131487889273,
      "grad_norm": 1.524487853050232,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0181,
      "step": 8
    },
    {
      "epoch": 0.09965397923875433,
      "grad_norm": 1.016344428062439,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9666,
      "step": 9
    },
    {
      "epoch": 0.11072664359861592,
      "grad_norm": 1.953541874885559,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7658,
      "step": 10
    },
    {
      "epoch": 0.12179930795847752,
      "grad_norm": 2.0307700634002686,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.7502,
      "step": 11
    },
    {
      "epoch": 0.1328719723183391,
      "grad_norm": 2.3972978591918945,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8412,
      "step": 12
    },
    {
      "epoch": 0.1439446366782007,
      "grad_norm": 1.575653076171875,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.8075,
      "step": 13
    },
    {
      "epoch": 0.15501730103806227,
      "grad_norm": 0.6672093272209167,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8219,
      "step": 14
    },
    {
      "epoch": 0.16608996539792387,
      "grad_norm": 0.5373260378837585,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.8665,
      "step": 15
    },
    {
      "epoch": 0.17716262975778546,
      "grad_norm": 0.5511289238929749,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.8291,
      "step": 16
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.4291207194328308,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8075,
      "step": 17
    },
    {
      "epoch": 0.19930795847750865,
      "grad_norm": 0.457125186920166,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7697,
      "step": 18
    },
    {
      "epoch": 0.21038062283737025,
      "grad_norm": 0.4102403223514557,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.7076,
      "step": 19
    },
    {
      "epoch": 0.22145328719723184,
      "grad_norm": 0.3947022557258606,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6706,
      "step": 20
    },
    {
      "epoch": 0.23252595155709344,
      "grad_norm": 0.4045722186565399,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.694,
      "step": 21
    },
    {
      "epoch": 0.24359861591695503,
      "grad_norm": 0.5666907429695129,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5357,
      "step": 22
    },
    {
      "epoch": 0.2546712802768166,
      "grad_norm": 0.8208253383636475,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5144,
      "step": 23
    },
    {
      "epoch": 0.2657439446366782,
      "grad_norm": 0.9341422319412231,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.5001,
      "step": 24
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 1.0937079191207886,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.6608,
      "step": 25
    },
    {
      "epoch": 0.2768166089965398,
      "eval_loss": 1.6505544185638428,
      "eval_runtime": 7.8911,
      "eval_samples_per_second": 77.176,
      "eval_steps_per_second": 9.758,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.4758308929536e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}