{
  "best_metric": 10.356481552124023,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.30143180105501133,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012057272042200452,
      "grad_norm": 0.29372695088386536,
      "learning_rate": 5e-05,
      "loss": 10.3802,
      "step": 1
    },
    {
      "epoch": 0.012057272042200452,
      "eval_loss": 10.380714416503906,
      "eval_runtime": 1.6845,
      "eval_samples_per_second": 331.845,
      "eval_steps_per_second": 41.555,
      "step": 1
    },
    {
      "epoch": 0.024114544084400905,
      "grad_norm": 0.29436203837394714,
      "learning_rate": 0.0001,
      "loss": 10.3815,
      "step": 2
    },
    {
      "epoch": 0.03617181612660136,
      "grad_norm": 0.2924072742462158,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3808,
      "step": 3
    },
    {
      "epoch": 0.04822908816880181,
      "grad_norm": 0.29187890887260437,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.06028636021100226,
      "grad_norm": 0.28935664892196655,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3794,
      "step": 5
    },
    {
      "epoch": 0.07234363225320271,
      "grad_norm": 0.29046961665153503,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.378,
      "step": 6
    },
    {
      "epoch": 0.08440090429540316,
      "grad_norm": 0.29813316464424133,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3756,
      "step": 7
    },
    {
      "epoch": 0.09645817633760362,
      "grad_norm": 0.30296024680137634,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3749,
      "step": 8
    },
    {
      "epoch": 0.10851544837980406,
      "grad_norm": 0.3060512840747833,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3743,
      "step": 9
    },
    {
      "epoch": 0.12057272042200452,
      "grad_norm": 0.3108205199241638,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.373,
      "step": 10
    },
    {
      "epoch": 0.13262999246420498,
      "grad_norm": 0.3159935474395752,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.372,
      "step": 11
    },
    {
      "epoch": 0.14468726450640543,
      "grad_norm": 0.3171635568141937,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3688,
      "step": 12
    },
    {
      "epoch": 0.15674453654860587,
      "grad_norm": 0.3182453513145447,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3699,
      "step": 13
    },
    {
      "epoch": 0.16880180859080632,
      "grad_norm": 0.3205792307853699,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3683,
      "step": 14
    },
    {
      "epoch": 0.1808590806330068,
      "grad_norm": 0.3250167965888977,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3673,
      "step": 15
    },
    {
      "epoch": 0.19291635267520724,
      "grad_norm": 0.33457398414611816,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.367,
      "step": 16
    },
    {
      "epoch": 0.20497362471740768,
      "grad_norm": 0.334460973739624,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3666,
      "step": 17
    },
    {
      "epoch": 0.21703089675960813,
      "grad_norm": 0.33570876717567444,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3642,
      "step": 18
    },
    {
      "epoch": 0.2290881688018086,
      "grad_norm": 0.34196099638938904,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.363,
      "step": 19
    },
    {
      "epoch": 0.24114544084400905,
      "grad_norm": 0.3495764136314392,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3616,
      "step": 20
    },
    {
      "epoch": 0.2532027128862095,
      "grad_norm": 0.35669052600860596,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3619,
      "step": 21
    },
    {
      "epoch": 0.26525998492840996,
      "grad_norm": 0.3679502010345459,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3591,
      "step": 22
    },
    {
      "epoch": 0.2773172569706104,
      "grad_norm": 0.36417484283447266,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3582,
      "step": 23
    },
    {
      "epoch": 0.28937452901281085,
      "grad_norm": 0.3735411465167999,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3577,
      "step": 24
    },
    {
      "epoch": 0.30143180105501133,
      "grad_norm": 0.37289372086524963,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3567,
      "step": 25
    },
    {
      "epoch": 0.30143180105501133,
      "eval_loss": 10.356481552124023,
      "eval_runtime": 1.6961,
      "eval_samples_per_second": 329.576,
      "eval_steps_per_second": 41.271,
      "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": 33492736671744.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}