{
  "best_metric": 2.6227145195007324,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3510311540149188,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014041246160596753,
      "grad_norm": 0.8327537775039673,
      "learning_rate": 2e-05,
      "loss": 1.9615,
      "step": 1
    },
    {
      "epoch": 0.014041246160596753,
      "eval_loss": 3.3978569507598877,
      "eval_runtime": 0.5068,
      "eval_samples_per_second": 98.667,
      "eval_steps_per_second": 25.654,
      "step": 1
    },
    {
      "epoch": 0.028082492321193506,
      "grad_norm": 1.332243800163269,
      "learning_rate": 4e-05,
      "loss": 1.824,
      "step": 2
    },
    {
      "epoch": 0.04212373848179026,
      "grad_norm": 1.4095451831817627,
      "learning_rate": 6e-05,
      "loss": 2.211,
      "step": 3
    },
    {
      "epoch": 0.05616498464238701,
      "grad_norm": 2.0809977054595947,
      "learning_rate": 8e-05,
      "loss": 2.3834,
      "step": 4
    },
    {
      "epoch": 0.07020623080298377,
      "grad_norm": 2.163429021835327,
      "learning_rate": 0.0001,
      "loss": 2.7688,
      "step": 5
    },
    {
      "epoch": 0.08424747696358052,
      "grad_norm": 2.884552001953125,
      "learning_rate": 9.997539658034168e-05,
      "loss": 2.8267,
      "step": 6
    },
    {
      "epoch": 0.09828872312417727,
      "grad_norm": 3.912673234939575,
      "learning_rate": 9.990161322484486e-05,
      "loss": 3.3231,
      "step": 7
    },
    {
      "epoch": 0.11232996928477403,
      "grad_norm": 5.349924564361572,
      "learning_rate": 9.977873061452552e-05,
      "loss": 3.5412,
      "step": 8
    },
    {
      "epoch": 0.12637121544537078,
      "grad_norm": 6.738022327423096,
      "learning_rate": 9.96068831197139e-05,
      "loss": 3.6021,
      "step": 9
    },
    {
      "epoch": 0.14041246160596754,
      "grad_norm": 8.926319122314453,
      "learning_rate": 9.938625865312251e-05,
      "loss": 3.5968,
      "step": 10
    },
    {
      "epoch": 0.15445370776656428,
      "grad_norm": 8.15119743347168,
      "learning_rate": 9.911709846436641e-05,
      "loss": 3.9218,
      "step": 11
    },
    {
      "epoch": 0.16849495392716105,
      "grad_norm": 12.402828216552734,
      "learning_rate": 9.879969687616027e-05,
      "loss": 4.5223,
      "step": 12
    },
    {
      "epoch": 0.18253620008775778,
      "grad_norm": 2.7531869411468506,
      "learning_rate": 9.84344009624807e-05,
      "loss": 2.1757,
      "step": 13
    },
    {
      "epoch": 0.19657744624835455,
      "grad_norm": 5.453584671020508,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.8657,
      "step": 14
    },
    {
      "epoch": 0.21061869240895129,
      "grad_norm": 6.201056003570557,
      "learning_rate": 9.756177587652856e-05,
      "loss": 2.0874,
      "step": 15
    },
    {
      "epoch": 0.22465993856954805,
      "grad_norm": 6.548382759094238,
      "learning_rate": 9.705540090697575e-05,
      "loss": 2.5228,
      "step": 16
    },
    {
      "epoch": 0.2387011847301448,
      "grad_norm": 4.07675313949585,
      "learning_rate": 9.650303897398232e-05,
      "loss": 2.5761,
      "step": 17
    },
    {
      "epoch": 0.25274243089074155,
      "grad_norm": 2.8793468475341797,
      "learning_rate": 9.590529407721231e-05,
      "loss": 2.6513,
      "step": 18
    },
    {
      "epoch": 0.2667836770513383,
      "grad_norm": 5.506067276000977,
      "learning_rate": 9.526281984193436e-05,
      "loss": 3.0722,
      "step": 19
    },
    {
      "epoch": 0.2808249232119351,
      "grad_norm": 10.677892684936523,
      "learning_rate": 9.4576318804292e-05,
      "loss": 3.2006,
      "step": 20
    },
    {
      "epoch": 0.2948661693725318,
      "grad_norm": 9.370729446411133,
      "learning_rate": 9.384654164309083e-05,
      "loss": 3.1187,
      "step": 21
    },
    {
      "epoch": 0.30890741553312856,
      "grad_norm": 7.775137901306152,
      "learning_rate": 9.30742863589421e-05,
      "loss": 3.2763,
      "step": 22
    },
    {
      "epoch": 0.3229486616937253,
      "grad_norm": 6.3419623374938965,
      "learning_rate": 9.226039740166091e-05,
      "loss": 3.7332,
      "step": 23
    },
    {
      "epoch": 0.3369899078543221,
      "grad_norm": 8.918274879455566,
      "learning_rate": 9.140576474687264e-05,
      "loss": 3.8572,
      "step": 24
    },
    {
      "epoch": 0.3510311540149188,
      "grad_norm": 15.176338195800781,
      "learning_rate": 9.051132292283771e-05,
      "loss": 5.0712,
      "step": 25
    },
    {
      "epoch": 0.3510311540149188,
      "eval_loss": 2.6227145195007324,
      "eval_runtime": 0.5047,
      "eval_samples_per_second": 99.066,
      "eval_steps_per_second": 25.757,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.47650456322048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}