{
  "best_metric": 1.4687479734420776,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1784121320249777,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 0.6175674796104431,
      "learning_rate": 5e-05,
      "loss": 1.8728,
      "step": 1
    },
    {
      "epoch": 0.007136485280999108,
      "eval_loss": 2.002394437789917,
      "eval_runtime": 30.7215,
      "eval_samples_per_second": 30.728,
      "eval_steps_per_second": 3.841,
      "step": 1
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 0.5661294460296631,
      "learning_rate": 0.0001,
      "loss": 1.9178,
      "step": 2
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 0.5823862552642822,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.844,
      "step": 3
    },
    {
      "epoch": 0.028545941123996433,
      "grad_norm": 0.5266484618186951,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.7699,
      "step": 4
    },
    {
      "epoch": 0.03568242640499554,
      "grad_norm": 0.6617392897605896,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.6637,
      "step": 5
    },
    {
      "epoch": 0.042818911685994644,
      "grad_norm": 0.5150014162063599,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.6131,
      "step": 6
    },
    {
      "epoch": 0.049955396966993755,
      "grad_norm": 0.48592281341552734,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6481,
      "step": 7
    },
    {
      "epoch": 0.057091882247992866,
      "grad_norm": 0.6050815582275391,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6882,
      "step": 8
    },
    {
      "epoch": 0.06422836752899197,
      "grad_norm": 0.6173608303070068,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.666,
      "step": 9
    },
    {
      "epoch": 0.07136485280999108,
      "grad_norm": 0.6555174589157104,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6982,
      "step": 10
    },
    {
      "epoch": 0.07850133809099019,
      "grad_norm": 0.7624517679214478,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.7869,
      "step": 11
    },
    {
      "epoch": 0.08563782337198929,
      "grad_norm": 0.9466533064842224,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8974,
      "step": 12
    },
    {
      "epoch": 0.0927743086529884,
      "grad_norm": 0.6618228554725647,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.7405,
      "step": 13
    },
    {
      "epoch": 0.09991079393398751,
      "grad_norm": 0.4013254642486572,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6472,
      "step": 14
    },
    {
      "epoch": 0.10704727921498662,
      "grad_norm": 0.41740894317626953,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6267,
      "step": 15
    },
    {
      "epoch": 0.11418376449598573,
      "grad_norm": 0.4490373730659485,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.587,
      "step": 16
    },
    {
      "epoch": 0.12132024977698483,
      "grad_norm": 0.45013779401779175,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5025,
      "step": 17
    },
    {
      "epoch": 0.12845673505798394,
      "grad_norm": 0.40676969289779663,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4488,
      "step": 18
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.3980136811733246,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.3683,
      "step": 19
    },
    {
      "epoch": 0.14272970561998216,
      "grad_norm": 0.36879634857177734,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3982,
      "step": 20
    },
    {
      "epoch": 0.14986619090098127,
      "grad_norm": 0.37536928057670593,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.4288,
      "step": 21
    },
    {
      "epoch": 0.15700267618198038,
      "grad_norm": 0.4245150685310364,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5434,
      "step": 22
    },
    {
      "epoch": 0.1641391614629795,
      "grad_norm": 0.494149774312973,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5239,
      "step": 23
    },
    {
      "epoch": 0.17127564674397858,
      "grad_norm": 0.5720580816268921,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.6833,
      "step": 24
    },
    {
      "epoch": 0.1784121320249777,
      "grad_norm": 0.9948855042457581,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.8018,
      "step": 25
    },
    {
      "epoch": 0.1784121320249777,
      "eval_loss": 1.4687479734420776,
      "eval_runtime": 30.7545,
      "eval_samples_per_second": 30.695,
      "eval_steps_per_second": 3.837,
      "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": 2.7465491653695898e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}