{
  "best_metric": 1.5221261978149414,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.3029315960912053,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05211726384364821,
      "grad_norm": 0.2591265141963959,
      "learning_rate": 5e-05,
      "loss": 1.5446,
      "step": 1
    },
    {
      "epoch": 0.05211726384364821,
      "eval_loss": 1.7352440357208252,
      "eval_runtime": 1.5465,
      "eval_samples_per_second": 84.06,
      "eval_steps_per_second": 10.992,
      "step": 1
    },
    {
      "epoch": 0.10423452768729642,
      "grad_norm": 0.3195701241493225,
      "learning_rate": 0.0001,
      "loss": 1.67,
      "step": 2
    },
    {
      "epoch": 0.1563517915309446,
      "grad_norm": 0.37172287702560425,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.7673,
      "step": 3
    },
    {
      "epoch": 0.20846905537459284,
      "grad_norm": 0.4107956886291504,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.7723,
      "step": 4
    },
    {
      "epoch": 0.26058631921824105,
      "grad_norm": 0.305014431476593,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.6542,
      "step": 5
    },
    {
      "epoch": 0.3127035830618892,
      "grad_norm": 0.23137179017066956,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.519,
      "step": 6
    },
    {
      "epoch": 0.36482084690553745,
      "grad_norm": 0.27529802918434143,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.5625,
      "step": 7
    },
    {
      "epoch": 0.4169381107491857,
      "grad_norm": 0.29970821738243103,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6496,
      "step": 8
    },
    {
      "epoch": 0.46905537459283386,
      "grad_norm": 0.3417079448699951,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6382,
      "step": 9
    },
    {
      "epoch": 0.5211726384364821,
      "grad_norm": 0.23188437521457672,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5449,
      "step": 10
    },
    {
      "epoch": 0.5732899022801303,
      "grad_norm": 0.22860518097877502,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.4941,
      "step": 11
    },
    {
      "epoch": 0.6254071661237784,
      "grad_norm": 0.23443861305713654,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5574,
      "step": 12
    },
    {
      "epoch": 0.6775244299674267,
      "grad_norm": 0.2669665217399597,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.6183,
      "step": 13
    },
    {
      "epoch": 0.7296416938110749,
      "grad_norm": 0.3732811510562897,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6219,
      "step": 14
    },
    {
      "epoch": 0.7817589576547231,
      "grad_norm": 0.19876886904239655,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.5135,
      "step": 15
    },
    {
      "epoch": 0.8338762214983714,
      "grad_norm": 0.1795257329940796,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5132,
      "step": 16
    },
    {
      "epoch": 0.8859934853420195,
      "grad_norm": 0.17552366852760315,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.5645,
      "step": 17
    },
    {
      "epoch": 0.9381107491856677,
      "grad_norm": 0.20799390971660614,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5952,
      "step": 18
    },
    {
      "epoch": 0.990228013029316,
      "grad_norm": 0.2864566445350647,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.5729,
      "step": 19
    },
    {
      "epoch": 1.0423452768729642,
      "grad_norm": 0.37049034237861633,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.7564,
      "step": 20
    },
    {
      "epoch": 1.0944625407166124,
      "grad_norm": 0.16121427714824677,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.4912,
      "step": 21
    },
    {
      "epoch": 1.1465798045602607,
      "grad_norm": 0.17705480754375458,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.5317,
      "step": 22
    },
    {
      "epoch": 1.1986970684039089,
      "grad_norm": 0.20234566926956177,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5432,
      "step": 23
    },
    {
      "epoch": 1.2508143322475571,
      "grad_norm": 0.1751578152179718,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.1263,
      "step": 24
    },
    {
      "epoch": 1.3029315960912053,
      "grad_norm": 0.18956966698169708,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.8535,
      "step": 25
    },
    {
      "epoch": 1.3029315960912053,
      "eval_loss": 1.5221261978149414,
      "eval_runtime": 1.5434,
      "eval_samples_per_second": 84.228,
      "eval_steps_per_second": 11.014,
      "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": 5.29768176943104e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}