{
  "best_metric": 0.16538894176483154,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03388681802778719,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016943409013893597,
      "eval_loss": 0.2710127830505371,
      "eval_runtime": 202.1343,
      "eval_samples_per_second": 12.294,
      "eval_steps_per_second": 3.077,
      "step": 1
    },
    {
      "epoch": 0.0016943409013893595,
      "grad_norm": 1.9416357278823853,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 0.3603,
      "step": 10
    },
    {
      "epoch": 0.003388681802778719,
      "grad_norm": 2.084803581237793,
      "learning_rate": 8.120000000000001e-05,
      "loss": 0.2829,
      "step": 20
    },
    {
      "epoch": 0.005083022704168078,
      "grad_norm": 2.351337194442749,
      "learning_rate": 0.00012179999999999999,
      "loss": 0.2922,
      "step": 30
    },
    {
      "epoch": 0.006777363605557438,
      "grad_norm": 3.6437880992889404,
      "learning_rate": 0.00016240000000000002,
      "loss": 0.2862,
      "step": 40
    },
    {
      "epoch": 0.008471704506946797,
      "grad_norm": 10.51866340637207,
      "learning_rate": 0.000203,
      "loss": 0.3485,
      "step": 50
    },
    {
      "epoch": 0.008471704506946797,
      "eval_loss": 0.16538894176483154,
      "eval_runtime": 202.5859,
      "eval_samples_per_second": 12.266,
      "eval_steps_per_second": 3.07,
      "step": 50
    },
    {
      "epoch": 0.010166045408336157,
      "grad_norm": 1.790229082107544,
      "learning_rate": 0.00020275275110137215,
      "loss": 0.2842,
      "step": 60
    },
    {
      "epoch": 0.011860386309725517,
      "grad_norm": 1.7886559963226318,
      "learning_rate": 0.00020201220897726938,
      "loss": 0.3127,
      "step": 70
    },
    {
      "epoch": 0.013554727211114876,
      "grad_norm": 2.6341745853424072,
      "learning_rate": 0.00020078198147448128,
      "loss": 0.3139,
      "step": 80
    },
    {
      "epoch": 0.015249068112504236,
      "grad_norm": 3.013049364089966,
      "learning_rate": 0.00019906806213773937,
      "loss": 0.327,
      "step": 90
    },
    {
      "epoch": 0.016943409013893594,
      "grad_norm": 6.521936893463135,
      "learning_rate": 0.0001968788010097697,
      "loss": 0.3893,
      "step": 100
    },
    {
      "epoch": 0.016943409013893594,
      "eval_loss": 0.1979130208492279,
      "eval_runtime": 202.6819,
      "eval_samples_per_second": 12.261,
      "eval_steps_per_second": 3.069,
      "step": 100
    },
    {
      "epoch": 0.018637749915282956,
      "grad_norm": 1.9125583171844482,
      "learning_rate": 0.00019422486395072398,
      "loss": 0.3318,
      "step": 110
    },
    {
      "epoch": 0.020332090816672314,
      "grad_norm": 1.7610540390014648,
      "learning_rate": 0.0001911191806751811,
      "loss": 0.2976,
      "step": 120
    },
    {
      "epoch": 0.022026431718061675,
      "grad_norm": 2.0341711044311523,
      "learning_rate": 0.00018757688175987723,
      "loss": 0.3682,
      "step": 130
    },
    {
      "epoch": 0.023720772619451033,
      "grad_norm": 2.6553566455841064,
      "learning_rate": 0.00018361522492905716,
      "loss": 0.3767,
      "step": 140
    },
    {
      "epoch": 0.025415113520840395,
      "grad_norm": 7.6121907234191895,
      "learning_rate": 0.00017925351097657625,
      "loss": 0.398,
      "step": 150
    },
    {
      "epoch": 0.025415113520840395,
      "eval_loss": 0.19531093537807465,
      "eval_runtime": 202.675,
      "eval_samples_per_second": 12.261,
      "eval_steps_per_second": 3.069,
      "step": 150
    },
    {
      "epoch": 0.027109454422229753,
      "grad_norm": 1.6871684789657593,
      "learning_rate": 0.00017451298973437308,
      "loss": 0.3654,
      "step": 160
    },
    {
      "epoch": 0.02880379532361911,
      "grad_norm": 2.150817394256592,
      "learning_rate": 0.0001694167565454241,
      "loss": 0.3326,
      "step": 170
    },
    {
      "epoch": 0.030498136225008472,
      "grad_norm": 2.821345329284668,
      "learning_rate": 0.0001639896397455543,
      "loss": 0.3337,
      "step": 180
    },
    {
      "epoch": 0.032192477126397834,
      "grad_norm": 2.3680481910705566,
      "learning_rate": 0.0001582580797022808,
      "loss": 0.3199,
      "step": 190
    },
    {
      "epoch": 0.03388681802778719,
      "grad_norm": 6.9135589599609375,
      "learning_rate": 0.00015225,
      "loss": 0.3978,
      "step": 200
    },
    {
      "epoch": 0.03388681802778719,
      "eval_loss": 0.19054758548736572,
      "eval_runtime": 202.7026,
      "eval_samples_per_second": 12.259,
      "eval_steps_per_second": 3.069,
      "step": 200
    }
  ],
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.080119355480474e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}