{
  "best_metric": 2.4111673831939697,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.024466328215793014,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009786531286317206,
      "grad_norm": 0.9052294492721558,
      "learning_rate": 5e-05,
      "loss": 2.4264,
      "step": 1
    },
    {
      "epoch": 0.0009786531286317206,
      "eval_loss": 2.863002061843872,
      "eval_runtime": 2.6894,
      "eval_samples_per_second": 18.591,
      "eval_steps_per_second": 4.834,
      "step": 1
    },
    {
      "epoch": 0.0019573062572634413,
      "grad_norm": 1.0080630779266357,
      "learning_rate": 0.0001,
      "loss": 2.5587,
      "step": 2
    },
    {
      "epoch": 0.002935959385895162,
      "grad_norm": 0.9608753323554993,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.6122,
      "step": 3
    },
    {
      "epoch": 0.0039146125145268825,
      "grad_norm": 0.6398207545280457,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.4608,
      "step": 4
    },
    {
      "epoch": 0.004893265643158603,
      "grad_norm": 0.5527761578559875,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.5155,
      "step": 5
    },
    {
      "epoch": 0.005871918771790324,
      "grad_norm": 0.893443763256073,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.4791,
      "step": 6
    },
    {
      "epoch": 0.006850571900422044,
      "grad_norm": 0.6713712215423584,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.4671,
      "step": 7
    },
    {
      "epoch": 0.007829225029053765,
      "grad_norm": 0.49785712361335754,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.4463,
      "step": 8
    },
    {
      "epoch": 0.008807878157685486,
      "grad_norm": 0.4845285713672638,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.4611,
      "step": 9
    },
    {
      "epoch": 0.009786531286317205,
      "grad_norm": 0.5214321613311768,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.4473,
      "step": 10
    },
    {
      "epoch": 0.010765184414948926,
      "grad_norm": 0.53846275806427,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.3884,
      "step": 11
    },
    {
      "epoch": 0.011743837543580648,
      "grad_norm": 0.6865140795707703,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.3446,
      "step": 12
    },
    {
      "epoch": 0.012722490672212369,
      "grad_norm": 0.5346219539642334,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.198,
      "step": 13
    },
    {
      "epoch": 0.013701143800844088,
      "grad_norm": 0.6182193756103516,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.3342,
      "step": 14
    },
    {
      "epoch": 0.014679796929475809,
      "grad_norm": 0.46032652258872986,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.298,
      "step": 15
    },
    {
      "epoch": 0.01565845005810753,
      "grad_norm": 0.3307320475578308,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.2378,
      "step": 16
    },
    {
      "epoch": 0.01663710318673925,
      "grad_norm": 0.26941177248954773,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.3683,
      "step": 17
    },
    {
      "epoch": 0.017615756315370972,
      "grad_norm": 0.2807510793209076,
      "learning_rate": 7.75e-05,
      "loss": 2.3843,
      "step": 18
    },
    {
      "epoch": 0.01859440944400269,
      "grad_norm": 0.33372122049331665,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.3049,
      "step": 19
    },
    {
      "epoch": 0.01957306257263441,
      "grad_norm": 0.3496776521205902,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.3267,
      "step": 20
    },
    {
      "epoch": 0.020551715701266134,
      "grad_norm": 0.38420557975769043,
      "learning_rate": 6.946477593864228e-05,
      "loss": 2.3582,
      "step": 21
    },
    {
      "epoch": 0.021530368829897853,
      "grad_norm": 0.4269815683364868,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.3467,
      "step": 22
    },
    {
      "epoch": 0.022509021958529572,
      "grad_norm": 0.45104503631591797,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.3472,
      "step": 23
    },
    {
      "epoch": 0.023487675087161295,
      "grad_norm": 0.44177213311195374,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.3087,
      "step": 24
    },
    {
      "epoch": 0.024466328215793014,
      "grad_norm": 0.565604567527771,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.4263,
      "step": 25
    },
    {
      "epoch": 0.024466328215793014,
      "eval_loss": 2.4111673831939697,
      "eval_runtime": 2.0329,
      "eval_samples_per_second": 24.595,
      "eval_steps_per_second": 6.395,
      "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": 2.9859068337822106e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}