{
  "best_metric": 4.142909526824951,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.6546644844517185,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02618657937806874,
      "grad_norm": 0.8365817070007324,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 4.3524,
      "step": 1
    },
    {
      "epoch": 0.02618657937806874,
      "eval_loss": 4.789937496185303,
      "eval_runtime": 0.2765,
      "eval_samples_per_second": 180.833,
      "eval_steps_per_second": 47.017,
      "step": 1
    },
    {
      "epoch": 0.05237315875613748,
      "grad_norm": 1.151999831199646,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.528,
      "step": 2
    },
    {
      "epoch": 0.07855973813420622,
      "grad_norm": 1.1144686937332153,
      "learning_rate": 0.0001,
      "loss": 4.5486,
      "step": 3
    },
    {
      "epoch": 0.10474631751227496,
      "grad_norm": 0.9449473023414612,
      "learning_rate": 9.997376600647783e-05,
      "loss": 4.6597,
      "step": 4
    },
    {
      "epoch": 0.1309328968903437,
      "grad_norm": 0.8100228905677795,
      "learning_rate": 9.989509461357426e-05,
      "loss": 4.6623,
      "step": 5
    },
    {
      "epoch": 0.15711947626841244,
      "grad_norm": 0.8471514582633972,
      "learning_rate": 9.976407754861426e-05,
      "loss": 4.6003,
      "step": 6
    },
    {
      "epoch": 0.18330605564648117,
      "grad_norm": 0.9861735701560974,
      "learning_rate": 9.958086757163489e-05,
      "loss": 4.5851,
      "step": 7
    },
    {
      "epoch": 0.20949263502454993,
      "grad_norm": 1.1125617027282715,
      "learning_rate": 9.934567829727386e-05,
      "loss": 4.5956,
      "step": 8
    },
    {
      "epoch": 0.23567921440261866,
      "grad_norm": 1.0278071165084839,
      "learning_rate": 9.905878394570453e-05,
      "loss": 4.7214,
      "step": 9
    },
    {
      "epoch": 0.2618657937806874,
      "grad_norm": 2.4233837127685547,
      "learning_rate": 9.872051902290737e-05,
      "loss": 4.0809,
      "step": 10
    },
    {
      "epoch": 0.28805237315875615,
      "grad_norm": 0.6828261613845825,
      "learning_rate": 9.833127793065098e-05,
      "loss": 4.1133,
      "step": 11
    },
    {
      "epoch": 0.3142389525368249,
      "grad_norm": 1.080686330795288,
      "learning_rate": 9.789151450663723e-05,
      "loss": 4.1603,
      "step": 12
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.7597512602806091,
      "learning_rate": 9.740174149534693e-05,
      "loss": 4.2075,
      "step": 13
    },
    {
      "epoch": 0.36661211129296234,
      "grad_norm": 0.6978819370269775,
      "learning_rate": 9.686252995020249e-05,
      "loss": 4.155,
      "step": 14
    },
    {
      "epoch": 0.39279869067103107,
      "grad_norm": 0.5029189586639404,
      "learning_rate": 9.627450856774539e-05,
      "loss": 4.2456,
      "step": 15
    },
    {
      "epoch": 0.41898527004909986,
      "grad_norm": 0.49850398302078247,
      "learning_rate": 9.563836295460398e-05,
      "loss": 4.375,
      "step": 16
    },
    {
      "epoch": 0.4451718494271686,
      "grad_norm": 0.6559662222862244,
      "learning_rate": 9.495483482810688e-05,
      "loss": 4.3,
      "step": 17
    },
    {
      "epoch": 0.4713584288052373,
      "grad_norm": 1.1999343633651733,
      "learning_rate": 9.422472115147382e-05,
      "loss": 4.4429,
      "step": 18
    },
    {
      "epoch": 0.49754500818330605,
      "grad_norm": 1.2498600482940674,
      "learning_rate": 9.3448873204592e-05,
      "loss": 4.5719,
      "step": 19
    },
    {
      "epoch": 0.5237315875613748,
      "grad_norm": 0.8708962798118591,
      "learning_rate": 9.2628195591462e-05,
      "loss": 3.7549,
      "step": 20
    },
    {
      "epoch": 0.5499181669394435,
      "grad_norm": 0.6062394380569458,
      "learning_rate": 9.176364518546989e-05,
      "loss": 3.9636,
      "step": 21
    },
    {
      "epoch": 0.5761047463175123,
      "grad_norm": 0.46776407957077026,
      "learning_rate": 9.08562300137157e-05,
      "loss": 4.0005,
      "step": 22
    },
    {
      "epoch": 0.602291325695581,
      "grad_norm": 0.41210252046585083,
      "learning_rate": 8.990700808169889e-05,
      "loss": 3.9414,
      "step": 23
    },
    {
      "epoch": 0.6284779050736498,
      "grad_norm": 0.4796847701072693,
      "learning_rate": 8.891708613973126e-05,
      "loss": 4.0629,
      "step": 24
    },
    {
      "epoch": 0.6546644844517185,
      "grad_norm": 0.42416390776634216,
      "learning_rate": 8.788761839251559e-05,
      "loss": 4.0834,
      "step": 25
    },
    {
      "epoch": 0.6546644844517185,
      "eval_loss": 4.142909526824951,
      "eval_runtime": 0.2882,
      "eval_samples_per_second": 173.488,
      "eval_steps_per_second": 45.107,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 5686862177894400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}