{
  "best_metric": 1.0937927961349487,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.02839094328909078,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011356377315636312,
      "grad_norm": 0.44248098134994507,
      "learning_rate": 5e-05,
      "loss": 0.9817,
      "step": 1
    },
    {
      "epoch": 0.0011356377315636312,
      "eval_loss": 1.2888797521591187,
      "eval_runtime": 43.0895,
      "eval_samples_per_second": 137.69,
      "eval_steps_per_second": 17.22,
      "step": 1
    },
    {
      "epoch": 0.0022712754631272624,
      "grad_norm": 0.4765216112136841,
      "learning_rate": 0.0001,
      "loss": 1.0479,
      "step": 2
    },
    {
      "epoch": 0.0034069131946908937,
      "grad_norm": 0.4120439887046814,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.0244,
      "step": 3
    },
    {
      "epoch": 0.004542550926254525,
      "grad_norm": 0.45249271392822266,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.1028,
      "step": 4
    },
    {
      "epoch": 0.005678188657818156,
      "grad_norm": 0.493412584066391,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.0797,
      "step": 5
    },
    {
      "epoch": 0.0068138263893817875,
      "grad_norm": 0.5234484076499939,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0833,
      "step": 6
    },
    {
      "epoch": 0.007949464120945418,
      "grad_norm": 0.4893084168434143,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.0104,
      "step": 7
    },
    {
      "epoch": 0.00908510185250905,
      "grad_norm": 0.44374406337738037,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0527,
      "step": 8
    },
    {
      "epoch": 0.01022073958407268,
      "grad_norm": 0.5221227407455444,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.077,
      "step": 9
    },
    {
      "epoch": 0.011356377315636311,
      "grad_norm": 0.6887457966804504,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.275,
      "step": 10
    },
    {
      "epoch": 0.012492015047199944,
      "grad_norm": 0.8918617367744446,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.2428,
      "step": 11
    },
    {
      "epoch": 0.013627652778763575,
      "grad_norm": 1.2448235750198364,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3729,
      "step": 12
    },
    {
      "epoch": 0.014763290510327206,
      "grad_norm": 0.4785754680633545,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8452,
      "step": 13
    },
    {
      "epoch": 0.015898928241890837,
      "grad_norm": 0.37022310495376587,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.899,
      "step": 14
    },
    {
      "epoch": 0.017034565973454468,
      "grad_norm": 0.45012906193733215,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.0393,
      "step": 15
    },
    {
      "epoch": 0.0181702037050181,
      "grad_norm": 0.42740723490715027,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.0453,
      "step": 16
    },
    {
      "epoch": 0.01930584143658173,
      "grad_norm": 0.4445900321006775,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.0891,
      "step": 17
    },
    {
      "epoch": 0.02044147916814536,
      "grad_norm": 0.42049741744995117,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1098,
      "step": 18
    },
    {
      "epoch": 0.02157711689970899,
      "grad_norm": 0.4503211975097656,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.1623,
      "step": 19
    },
    {
      "epoch": 0.022712754631272623,
      "grad_norm": 0.41351017355918884,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.1624,
      "step": 20
    },
    {
      "epoch": 0.023848392362836254,
      "grad_norm": 0.42763012647628784,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.0766,
      "step": 21
    },
    {
      "epoch": 0.024984030094399888,
      "grad_norm": 0.5273652672767639,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.202,
      "step": 22
    },
    {
      "epoch": 0.02611966782596352,
      "grad_norm": 0.6357163786888123,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.2158,
      "step": 23
    },
    {
      "epoch": 0.02725530555752715,
      "grad_norm": 0.9283555150032043,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.3415,
      "step": 24
    },
    {
      "epoch": 0.02839094328909078,
      "grad_norm": 1.512017846107483,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.3185,
      "step": 25
    },
    {
      "epoch": 0.02839094328909078,
      "eval_loss": 1.0937927961349487,
      "eval_runtime": 42.7702,
      "eval_samples_per_second": 138.718,
      "eval_steps_per_second": 17.349,
      "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": 1.4875783445086208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}