{
  "best_metric": 1.2204139232635498,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.6069802731411229,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024279210925644917,
      "grad_norm": 1.7722647190093994,
      "learning_rate": 5e-05,
      "loss": 1.6302,
      "step": 1
    },
    {
      "epoch": 0.024279210925644917,
      "eval_loss": 1.7623697519302368,
      "eval_runtime": 13.4424,
      "eval_samples_per_second": 20.681,
      "eval_steps_per_second": 2.604,
      "step": 1
    },
    {
      "epoch": 0.048558421851289835,
      "grad_norm": 1.8735610246658325,
      "learning_rate": 0.0001,
      "loss": 1.7639,
      "step": 2
    },
    {
      "epoch": 0.07283763277693475,
      "grad_norm": 1.242928147315979,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6338,
      "step": 3
    },
    {
      "epoch": 0.09711684370257967,
      "grad_norm": 0.7185656428337097,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.4464,
      "step": 4
    },
    {
      "epoch": 0.12139605462822459,
      "grad_norm": 0.8275676965713501,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.409,
      "step": 5
    },
    {
      "epoch": 0.1456752655538695,
      "grad_norm": 0.7798041105270386,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.3467,
      "step": 6
    },
    {
      "epoch": 0.16995447647951442,
      "grad_norm": 0.7611581683158875,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.3044,
      "step": 7
    },
    {
      "epoch": 0.19423368740515934,
      "grad_norm": 0.5567551255226135,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.4015,
      "step": 8
    },
    {
      "epoch": 0.21851289833080426,
      "grad_norm": 0.580046534538269,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.4482,
      "step": 9
    },
    {
      "epoch": 0.24279210925644917,
      "grad_norm": 0.6574867367744446,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4606,
      "step": 10
    },
    {
      "epoch": 0.26707132018209406,
      "grad_norm": 0.7613857984542847,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.3532,
      "step": 11
    },
    {
      "epoch": 0.291350531107739,
      "grad_norm": 0.5821555852890015,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3331,
      "step": 12
    },
    {
      "epoch": 0.3156297420333839,
      "grad_norm": 0.4268592894077301,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.2977,
      "step": 13
    },
    {
      "epoch": 0.33990895295902884,
      "grad_norm": 0.4200943112373352,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2504,
      "step": 14
    },
    {
      "epoch": 0.36418816388467373,
      "grad_norm": 0.42564937472343445,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2022,
      "step": 15
    },
    {
      "epoch": 0.3884673748103187,
      "grad_norm": 0.4572436213493347,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.2242,
      "step": 16
    },
    {
      "epoch": 0.41274658573596357,
      "grad_norm": 0.49105581641197205,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.2034,
      "step": 17
    },
    {
      "epoch": 0.4370257966616085,
      "grad_norm": 0.4518444836139679,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2124,
      "step": 18
    },
    {
      "epoch": 0.4613050075872534,
      "grad_norm": 0.3952445983886719,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2795,
      "step": 19
    },
    {
      "epoch": 0.48558421851289835,
      "grad_norm": 0.4598488509654999,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3569,
      "step": 20
    },
    {
      "epoch": 0.5098634294385432,
      "grad_norm": 0.4049881398677826,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2496,
      "step": 21
    },
    {
      "epoch": 0.5341426403641881,
      "grad_norm": 0.4265231788158417,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.3095,
      "step": 22
    },
    {
      "epoch": 0.5584218512898331,
      "grad_norm": 0.4079309105873108,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.2289,
      "step": 23
    },
    {
      "epoch": 0.582701062215478,
      "grad_norm": 0.33031976222991943,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2246,
      "step": 24
    },
    {
      "epoch": 0.6069802731411229,
      "grad_norm": 0.32245883345603943,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.1406,
      "step": 25
    },
    {
      "epoch": 0.6069802731411229,
      "eval_loss": 1.2204139232635498,
      "eval_runtime": 13.4561,
      "eval_samples_per_second": 20.66,
      "eval_steps_per_second": 2.601,
      "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": 1.62480894509056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}