{
  "best_metric": 0.6369848251342773,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.221884498480243,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0486322188449848,
      "grad_norm": 9.046380996704102,
      "learning_rate": 5e-05,
      "loss": 3.3931,
      "step": 1
    },
    {
      "epoch": 0.0486322188449848,
      "eval_loss": 4.781421184539795,
      "eval_runtime": 3.3191,
      "eval_samples_per_second": 41.879,
      "eval_steps_per_second": 5.423,
      "step": 1
    },
    {
      "epoch": 0.0972644376899696,
      "grad_norm": 7.5731329917907715,
      "learning_rate": 0.0001,
      "loss": 4.2615,
      "step": 2
    },
    {
      "epoch": 0.1458966565349544,
      "grad_norm": 7.320644378662109,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.4261,
      "step": 3
    },
    {
      "epoch": 0.1945288753799392,
      "grad_norm": 8.42262077331543,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.7952,
      "step": 4
    },
    {
      "epoch": 0.24316109422492402,
      "grad_norm": 9.451285362243652,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.9032,
      "step": 5
    },
    {
      "epoch": 0.2917933130699088,
      "grad_norm": 8.28438949584961,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7165,
      "step": 6
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 5.48672342300415,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6377,
      "step": 7
    },
    {
      "epoch": 0.3890577507598784,
      "grad_norm": 3.8141331672668457,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5142,
      "step": 8
    },
    {
      "epoch": 0.4376899696048632,
      "grad_norm": 3.9788246154785156,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.3652,
      "step": 9
    },
    {
      "epoch": 0.48632218844984804,
      "grad_norm": 4.899479389190674,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8154,
      "step": 10
    },
    {
      "epoch": 0.5349544072948328,
      "grad_norm": 4.353118896484375,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.9319,
      "step": 11
    },
    {
      "epoch": 0.5835866261398176,
      "grad_norm": 5.567763328552246,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1158,
      "step": 12
    },
    {
      "epoch": 0.6322188449848024,
      "grad_norm": 4.067556858062744,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.8698,
      "step": 13
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 2.3221864700317383,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.777,
      "step": 14
    },
    {
      "epoch": 0.729483282674772,
      "grad_norm": 4.185751914978027,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2234,
      "step": 15
    },
    {
      "epoch": 0.7781155015197568,
      "grad_norm": 2.2419371604919434,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.5877,
      "step": 16
    },
    {
      "epoch": 0.8267477203647416,
      "grad_norm": 1.3619014024734497,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5595,
      "step": 17
    },
    {
      "epoch": 0.8753799392097265,
      "grad_norm": 2.139798879623413,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.672,
      "step": 18
    },
    {
      "epoch": 0.9240121580547113,
      "grad_norm": 2.716907024383545,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7699,
      "step": 19
    },
    {
      "epoch": 0.9726443768996961,
      "grad_norm": 3.265707492828369,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8743,
      "step": 20
    },
    {
      "epoch": 1.027355623100304,
      "grad_norm": 3.6474814414978027,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7644,
      "step": 21
    },
    {
      "epoch": 1.0759878419452888,
      "grad_norm": 2.879976272583008,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.479,
      "step": 22
    },
    {
      "epoch": 1.1246200607902737,
      "grad_norm": 3.007579803466797,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5571,
      "step": 23
    },
    {
      "epoch": 1.1732522796352582,
      "grad_norm": 2.000781297683716,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.5527,
      "step": 24
    },
    {
      "epoch": 1.221884498480243,
      "grad_norm": 3.722931146621704,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.7381,
      "step": 25
    },
    {
      "epoch": 1.221884498480243,
      "eval_loss": 0.6369848251342773,
      "eval_runtime": 3.3108,
      "eval_samples_per_second": 41.984,
      "eval_steps_per_second": 5.437,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.327074698592256e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}