{
  "best_metric": 2.2345645427703857,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7155635062611807,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 5.1959147453308105,
      "learning_rate": 5e-05,
      "loss": 3.6868,
      "step": 1
    },
    {
      "epoch": 0.028622540250447227,
      "eval_loss": 4.301292896270752,
      "eval_runtime": 3.1258,
      "eval_samples_per_second": 15.996,
      "eval_steps_per_second": 4.159,
      "step": 1
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 5.988410472869873,
      "learning_rate": 0.0001,
      "loss": 4.0639,
      "step": 2
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 6.287829875946045,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.0714,
      "step": 3
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 4.875919342041016,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.9675,
      "step": 4
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 5.528495788574219,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.9406,
      "step": 5
    },
    {
      "epoch": 0.17173524150268335,
      "grad_norm": 5.681136131286621,
      "learning_rate": 9.846666218300807e-05,
      "loss": 3.7416,
      "step": 6
    },
    {
      "epoch": 0.2003577817531306,
      "grad_norm": 3.5005509853363037,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.696,
      "step": 7
    },
    {
      "epoch": 0.22898032200357782,
      "grad_norm": 3.4585726261138916,
      "learning_rate": 9.657457896300791e-05,
      "loss": 3.2387,
      "step": 8
    },
    {
      "epoch": 0.25760286225402507,
      "grad_norm": 3.782135486602783,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.5966,
      "step": 9
    },
    {
      "epoch": 0.28622540250447226,
      "grad_norm": 4.032910346984863,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.7517,
      "step": 10
    },
    {
      "epoch": 0.3148479427549195,
      "grad_norm": 3.0664560794830322,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.5558,
      "step": 11
    },
    {
      "epoch": 0.3434704830053667,
      "grad_norm": 2.541337490081787,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.6952,
      "step": 12
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 3.1225051879882812,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.5049,
      "step": 13
    },
    {
      "epoch": 0.4007155635062612,
      "grad_norm": 4.351744174957275,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.6004,
      "step": 14
    },
    {
      "epoch": 0.4293381037567084,
      "grad_norm": 2.7151081562042236,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.28,
      "step": 15
    },
    {
      "epoch": 0.45796064400715564,
      "grad_norm": 2.72318696975708,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.9666,
      "step": 16
    },
    {
      "epoch": 0.4865831842576029,
      "grad_norm": 2.636446952819824,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.8992,
      "step": 17
    },
    {
      "epoch": 0.5152057245080501,
      "grad_norm": 2.799785852432251,
      "learning_rate": 7.75e-05,
      "loss": 2.0822,
      "step": 18
    },
    {
      "epoch": 0.5438282647584973,
      "grad_norm": 2.2449307441711426,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.3713,
      "step": 19
    },
    {
      "epoch": 0.5724508050089445,
      "grad_norm": 1.7994107007980347,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.2375,
      "step": 20
    },
    {
      "epoch": 0.6010733452593918,
      "grad_norm": 2.2747550010681152,
      "learning_rate": 6.946477593864228e-05,
      "loss": 2.0141,
      "step": 21
    },
    {
      "epoch": 0.629695885509839,
      "grad_norm": 3.4918453693389893,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.0491,
      "step": 22
    },
    {
      "epoch": 0.6583184257602862,
      "grad_norm": 2.9565210342407227,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.1609,
      "step": 23
    },
    {
      "epoch": 0.6869409660107334,
      "grad_norm": 2.646497964859009,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.3189,
      "step": 24
    },
    {
      "epoch": 0.7155635062611807,
      "grad_norm": 2.3935790061950684,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.8598,
      "step": 25
    },
    {
      "epoch": 0.7155635062611807,
      "eval_loss": 2.2345645427703857,
      "eval_runtime": 2.1726,
      "eval_samples_per_second": 23.014,
      "eval_steps_per_second": 5.984,
      "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": 2.4703766989111296e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}