{
  "best_metric": 2.7589340209960938,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0004875646632634653,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9502586530538612e-05,
      "grad_norm": 10.661989212036133,
      "learning_rate": 2e-05,
      "loss": 17.5988,
      "step": 1
    },
    {
      "epoch": 1.9502586530538612e-05,
      "eval_loss": 3.740457773208618,
      "eval_runtime": 1365.6714,
      "eval_samples_per_second": 15.809,
      "eval_steps_per_second": 7.905,
      "step": 1
    },
    {
      "epoch": 3.9005173061077225e-05,
      "grad_norm": 10.52691650390625,
      "learning_rate": 4e-05,
      "loss": 16.048,
      "step": 2
    },
    {
      "epoch": 5.850775959161584e-05,
      "grad_norm": 11.181418418884277,
      "learning_rate": 6e-05,
      "loss": 16.6304,
      "step": 3
    },
    {
      "epoch": 7.801034612215445e-05,
      "grad_norm": 10.484938621520996,
      "learning_rate": 8e-05,
      "loss": 13.6512,
      "step": 4
    },
    {
      "epoch": 9.751293265269307e-05,
      "grad_norm": 9.14451789855957,
      "learning_rate": 0.0001,
      "loss": 13.9934,
      "step": 5
    },
    {
      "epoch": 9.751293265269307e-05,
      "eval_loss": 3.650926351547241,
      "eval_runtime": 1358.0436,
      "eval_samples_per_second": 15.898,
      "eval_steps_per_second": 7.949,
      "step": 5
    },
    {
      "epoch": 0.00011701551918323167,
      "grad_norm": 9.735679626464844,
      "learning_rate": 0.00012,
      "loss": 14.8166,
      "step": 6
    },
    {
      "epoch": 0.00013651810571377028,
      "grad_norm": 11.231522560119629,
      "learning_rate": 0.00014,
      "loss": 14.2715,
      "step": 7
    },
    {
      "epoch": 0.0001560206922443089,
      "grad_norm": 9.9983549118042,
      "learning_rate": 0.00016,
      "loss": 16.138,
      "step": 8
    },
    {
      "epoch": 0.00017552327877484752,
      "grad_norm": 11.767319679260254,
      "learning_rate": 0.00018,
      "loss": 14.2577,
      "step": 9
    },
    {
      "epoch": 0.00019502586530538614,
      "grad_norm": 10.551060676574707,
      "learning_rate": 0.0002,
      "loss": 12.2586,
      "step": 10
    },
    {
      "epoch": 0.00019502586530538614,
      "eval_loss": 3.241389274597168,
      "eval_runtime": 1337.3498,
      "eval_samples_per_second": 16.144,
      "eval_steps_per_second": 8.072,
      "step": 10
    },
    {
      "epoch": 0.00021452845183592473,
      "grad_norm": 11.396815299987793,
      "learning_rate": 0.00019781476007338058,
      "loss": 14.3918,
      "step": 11
    },
    {
      "epoch": 0.00023403103836646335,
      "grad_norm": 11.829697608947754,
      "learning_rate": 0.0001913545457642601,
      "loss": 12.4219,
      "step": 12
    },
    {
      "epoch": 0.00025353362489700194,
      "grad_norm": 10.012219429016113,
      "learning_rate": 0.00018090169943749476,
      "loss": 13.4621,
      "step": 13
    },
    {
      "epoch": 0.00027303621142754056,
      "grad_norm": 10.259438514709473,
      "learning_rate": 0.00016691306063588583,
      "loss": 12.6029,
      "step": 14
    },
    {
      "epoch": 0.0002925387979580792,
      "grad_norm": 10.923121452331543,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3155,
      "step": 15
    },
    {
      "epoch": 0.0002925387979580792,
      "eval_loss": 2.895463228225708,
      "eval_runtime": 1337.8698,
      "eval_samples_per_second": 16.138,
      "eval_steps_per_second": 8.069,
      "step": 15
    },
    {
      "epoch": 0.0003120413844886178,
      "grad_norm": 11.50796127319336,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.7577,
      "step": 16
    },
    {
      "epoch": 0.0003315439710191564,
      "grad_norm": 11.235647201538086,
      "learning_rate": 0.00011045284632676536,
      "loss": 11.9318,
      "step": 17
    },
    {
      "epoch": 0.00035104655754969504,
      "grad_norm": 12.540641784667969,
      "learning_rate": 8.954715367323468e-05,
      "loss": 9.7892,
      "step": 18
    },
    {
      "epoch": 0.00037054914408023366,
      "grad_norm": 14.46514892578125,
      "learning_rate": 6.909830056250527e-05,
      "loss": 11.772,
      "step": 19
    },
    {
      "epoch": 0.0003900517306107723,
      "grad_norm": 11.827276229858398,
      "learning_rate": 5.000000000000002e-05,
      "loss": 11.2938,
      "step": 20
    },
    {
      "epoch": 0.0003900517306107723,
      "eval_loss": 2.7899820804595947,
      "eval_runtime": 1360.8212,
      "eval_samples_per_second": 15.865,
      "eval_steps_per_second": 7.933,
      "step": 20
    },
    {
      "epoch": 0.00040955431714131084,
      "grad_norm": 12.596237182617188,
      "learning_rate": 3.308693936411421e-05,
      "loss": 11.2898,
      "step": 21
    },
    {
      "epoch": 0.00042905690367184946,
      "grad_norm": 12.902812004089355,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 12.0772,
      "step": 22
    },
    {
      "epoch": 0.0004485594902023881,
      "grad_norm": 11.842628479003906,
      "learning_rate": 8.645454235739903e-06,
      "loss": 10.7107,
      "step": 23
    },
    {
      "epoch": 0.0004680620767329267,
      "grad_norm": 12.775739669799805,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 11.206,
      "step": 24
    },
    {
      "epoch": 0.0004875646632634653,
      "grad_norm": 12.864251136779785,
      "learning_rate": 0.0,
      "loss": 10.6576,
      "step": 25
    },
    {
      "epoch": 0.0004875646632634653,
      "eval_loss": 2.7589340209960938,
      "eval_runtime": 1328.6073,
      "eval_samples_per_second": 16.25,
      "eval_steps_per_second": 8.125,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 187674132480000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}