{
  "best_metric": 0.25602078437805176,
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
  "epoch": 0.22172949002217296,
  "eval_steps": 50,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008869179600886918,
      "eval_loss": 2.8770248889923096,
      "eval_runtime": 38.1113,
      "eval_samples_per_second": 12.463,
      "eval_steps_per_second": 3.122,
      "step": 1
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 2.364651918411255,
      "learning_rate": 4.02e-05,
      "loss": 1.7045,
      "step": 10
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 5.935655117034912,
      "learning_rate": 8.04e-05,
      "loss": 1.2618,
      "step": 20
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 2.099881172180176,
      "learning_rate": 0.0001206,
      "loss": 0.6453,
      "step": 30
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 1.2235733270645142,
      "learning_rate": 0.0001608,
      "loss": 0.3949,
      "step": 40
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 2.9881107807159424,
      "learning_rate": 0.000201,
      "loss": 0.4097,
      "step": 50
    },
    {
      "epoch": 0.04434589800443459,
      "eval_loss": 0.5164891481399536,
      "eval_runtime": 38.3505,
      "eval_samples_per_second": 12.386,
      "eval_steps_per_second": 3.103,
      "step": 50
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 1.0847694873809814,
      "learning_rate": 0.00020075518705111234,
      "loss": 0.412,
      "step": 60
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 2.6469056606292725,
      "learning_rate": 0.00020002194090852784,
      "loss": 0.4117,
      "step": 70
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 1.295844554901123,
      "learning_rate": 0.00019880383387374748,
      "loss": 0.4179,
      "step": 80
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 1.5523910522460938,
      "learning_rate": 0.00019710680044180106,
      "loss": 0.3102,
      "step": 90
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.0117522478103638,
      "learning_rate": 0.0001949391083889838,
      "loss": 0.2715,
      "step": 100
    },
    {
      "epoch": 0.08869179600886919,
      "eval_loss": 0.38211727142333984,
      "eval_runtime": 38.181,
      "eval_samples_per_second": 12.441,
      "eval_steps_per_second": 3.117,
      "step": 100
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.8537772297859192,
      "learning_rate": 0.00019231131849308138,
      "loss": 0.3774,
      "step": 110
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 2.790709972381592,
      "learning_rate": 0.00018923623308232218,
      "loss": 0.3956,
      "step": 120
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 1.3601632118225098,
      "learning_rate": 0.00018572883366372081,
      "loss": 0.4427,
      "step": 130
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 1.0446776151657104,
      "learning_rate": 0.00018180620793468224,
      "loss": 0.2675,
      "step": 140
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 2.1166090965270996,
      "learning_rate": 0.00017748746653345728,
      "loss": 0.2237,
      "step": 150
    },
    {
      "epoch": 0.13303769401330376,
      "eval_loss": 0.31679707765579224,
      "eval_runtime": 38.1684,
      "eval_samples_per_second": 12.445,
      "eval_steps_per_second": 3.118,
      "step": 150
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.9246871471405029,
      "learning_rate": 0.00017279364993403443,
      "loss": 0.312,
      "step": 160
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": 2.4459915161132812,
      "learning_rate": 0.00016774762593906525,
      "loss": 0.3171,
      "step": 170
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 1.1200841665267944,
      "learning_rate": 0.00016237397827022866,
      "loss": 0.2871,
      "step": 180
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": 1.3566011190414429,
      "learning_rate": 0.00015669888679881007,
      "loss": 0.171,
      "step": 190
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 1.6793667078018188,
      "learning_rate": 0.00015075,
      "loss": 0.1994,
      "step": 200
    },
    {
      "epoch": 0.17738359201773837,
      "eval_loss": 0.3108082711696625,
      "eval_runtime": 38.1848,
      "eval_samples_per_second": 12.44,
      "eval_steps_per_second": 3.116,
      "step": 200
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": 0.7012319564819336,
      "learning_rate": 0.00014455630025230227,
      "loss": 0.3329,
      "step": 210
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 1.5228286981582642,
      "learning_rate": 0.00013814796263829918,
      "loss": 0.3096,
      "step": 220
    },
    {
      "epoch": 0.2039911308203991,
      "grad_norm": 0.6246249079704285,
      "learning_rate": 0.00013155620793468223,
      "loss": 0.2082,
      "step": 230
    },
    {
      "epoch": 0.21286031042128603,
      "grad_norm": 1.0557504892349243,
      "learning_rate": 0.0001248131505077666,
      "loss": 0.2378,
      "step": 240
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 1.1284499168395996,
      "learning_rate": 0.00011795164185552652,
      "loss": 0.1585,
      "step": 250
    },
    {
      "epoch": 0.22172949002217296,
      "eval_loss": 0.25602078437805176,
      "eval_runtime": 38.5281,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 3.089,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 6.257264513620378e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}