{
  "best_metric": 1.8876161575317383,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06796941376380629,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027187765505522514,
      "grad_norm": 1.8446872234344482,
      "learning_rate": 5e-05,
      "loss": 3.1005,
      "step": 1
    },
    {
      "epoch": 0.0027187765505522514,
      "eval_loss": 3.4761812686920166,
      "eval_runtime": 3.86,
      "eval_samples_per_second": 12.953,
      "eval_steps_per_second": 3.368,
      "step": 1
    },
    {
      "epoch": 0.005437553101104503,
      "grad_norm": 1.8384300470352173,
      "learning_rate": 0.0001,
      "loss": 3.1166,
      "step": 2
    },
    {
      "epoch": 0.008156329651656755,
      "grad_norm": 1.742788553237915,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.1483,
      "step": 3
    },
    {
      "epoch": 0.010875106202209005,
      "grad_norm": 1.6164594888687134,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.7983,
      "step": 4
    },
    {
      "epoch": 0.013593882752761258,
      "grad_norm": 1.7915750741958618,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.5768,
      "step": 5
    },
    {
      "epoch": 0.01631265930331351,
      "grad_norm": 1.8303508758544922,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.3811,
      "step": 6
    },
    {
      "epoch": 0.019031435853865762,
      "grad_norm": 1.5399417877197266,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.3666,
      "step": 7
    },
    {
      "epoch": 0.02175021240441801,
      "grad_norm": 1.2493640184402466,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.2269,
      "step": 8
    },
    {
      "epoch": 0.024468988954970263,
      "grad_norm": 1.1250720024108887,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.2005,
      "step": 9
    },
    {
      "epoch": 0.027187765505522515,
      "grad_norm": 1.0368432998657227,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.1366,
      "step": 10
    },
    {
      "epoch": 0.029906542056074768,
      "grad_norm": 0.9859645366668701,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.9241,
      "step": 11
    },
    {
      "epoch": 0.03262531860662702,
      "grad_norm": 0.9766353368759155,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.9443,
      "step": 12
    },
    {
      "epoch": 0.03534409515717927,
      "grad_norm": 0.8744819760322571,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.0566,
      "step": 13
    },
    {
      "epoch": 0.038062871707731524,
      "grad_norm": 0.8641797304153442,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.115,
      "step": 14
    },
    {
      "epoch": 0.04078164825828377,
      "grad_norm": 0.7743111252784729,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.1498,
      "step": 15
    },
    {
      "epoch": 0.04350042480883602,
      "grad_norm": 0.8845915198326111,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.15,
      "step": 16
    },
    {
      "epoch": 0.04621920135938828,
      "grad_norm": 0.783896267414093,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.9129,
      "step": 17
    },
    {
      "epoch": 0.048937977909940526,
      "grad_norm": 0.7092758417129517,
      "learning_rate": 7.75e-05,
      "loss": 1.9772,
      "step": 18
    },
    {
      "epoch": 0.051656754460492775,
      "grad_norm": 0.7224475741386414,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.0502,
      "step": 19
    },
    {
      "epoch": 0.05437553101104503,
      "grad_norm": 0.7935304641723633,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.0447,
      "step": 20
    },
    {
      "epoch": 0.05709430756159728,
      "grad_norm": 0.7622972726821899,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.9269,
      "step": 21
    },
    {
      "epoch": 0.059813084112149535,
      "grad_norm": 0.731041669845581,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.9865,
      "step": 22
    },
    {
      "epoch": 0.06253186066270179,
      "grad_norm": 0.7223778963088989,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.8974,
      "step": 23
    },
    {
      "epoch": 0.06525063721325404,
      "grad_norm": 0.7909101247787476,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.8845,
      "step": 24
    },
    {
      "epoch": 0.06796941376380629,
      "grad_norm": 0.876282274723053,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.7724,
      "step": 25
    },
    {
      "epoch": 0.06796941376380629,
      "eval_loss": 1.8876161575317383,
      "eval_runtime": 3.5153,
      "eval_samples_per_second": 14.224,
      "eval_steps_per_second": 3.698,
      "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": 2.987771858905989e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}