{
  "best_metric": 0.005342242307960987,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.08090614886731391,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004045307443365696,
      "eval_loss": 0.49801015853881836,
      "eval_runtime": 43.3011,
      "eval_samples_per_second": 18.037,
      "eval_steps_per_second": 4.526,
      "step": 1
    },
    {
      "epoch": 0.0040453074433656954,
      "grad_norm": 1.0355167388916016,
      "learning_rate": 5.05e-06,
      "loss": 0.2311,
      "step": 10
    },
    {
      "epoch": 0.008090614886731391,
      "grad_norm": 1.5257176160812378,
      "learning_rate": 1.01e-05,
      "loss": 0.199,
      "step": 20
    },
    {
      "epoch": 0.012135922330097087,
      "grad_norm": 0.5611529350280762,
      "learning_rate": 9.538888888888889e-06,
      "loss": 0.0588,
      "step": 30
    },
    {
      "epoch": 0.016181229773462782,
      "grad_norm": 0.027493484318256378,
      "learning_rate": 8.977777777777778e-06,
      "loss": 0.0085,
      "step": 40
    },
    {
      "epoch": 0.020226537216828478,
      "grad_norm": 8.812362670898438,
      "learning_rate": 8.416666666666667e-06,
      "loss": 0.0486,
      "step": 50
    },
    {
      "epoch": 0.020226537216828478,
      "eval_loss": 0.008491799235343933,
      "eval_runtime": 43.3298,
      "eval_samples_per_second": 18.025,
      "eval_steps_per_second": 4.523,
      "step": 50
    },
    {
      "epoch": 0.024271844660194174,
      "grad_norm": 0.9959584474563599,
      "learning_rate": 7.855555555555556e-06,
      "loss": 0.0005,
      "step": 60
    },
    {
      "epoch": 0.02831715210355987,
      "grad_norm": 0.14248639345169067,
      "learning_rate": 7.294444444444444e-06,
      "loss": 0.0035,
      "step": 70
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 0.0067140571773052216,
      "learning_rate": 6.733333333333333e-06,
      "loss": 0.001,
      "step": 80
    },
    {
      "epoch": 0.03640776699029126,
      "grad_norm": 0.009364698082208633,
      "learning_rate": 6.172222222222223e-06,
      "loss": 0.0003,
      "step": 90
    },
    {
      "epoch": 0.040453074433656956,
      "grad_norm": 0.013642555102705956,
      "learning_rate": 5.611111111111111e-06,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 0.040453074433656956,
      "eval_loss": 0.005722765810787678,
      "eval_runtime": 43.3568,
      "eval_samples_per_second": 18.013,
      "eval_steps_per_second": 4.521,
      "step": 100
    },
    {
      "epoch": 0.04449838187702265,
      "grad_norm": 0.04571974277496338,
      "learning_rate": 5.05e-06,
      "loss": 0.0002,
      "step": 110
    },
    {
      "epoch": 0.04854368932038835,
      "grad_norm": 0.01307100709527731,
      "learning_rate": 4.488888888888889e-06,
      "loss": 0.0007,
      "step": 120
    },
    {
      "epoch": 0.052588996763754045,
      "grad_norm": 0.43846479058265686,
      "learning_rate": 3.927777777777778e-06,
      "loss": 0.0027,
      "step": 130
    },
    {
      "epoch": 0.05663430420711974,
      "grad_norm": 0.002617649268358946,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 0.0006,
      "step": 140
    },
    {
      "epoch": 0.06067961165048544,
      "grad_norm": 1.0591951608657837,
      "learning_rate": 2.8055555555555555e-06,
      "loss": 0.0014,
      "step": 150
    },
    {
      "epoch": 0.06067961165048544,
      "eval_loss": 0.005342242307960987,
      "eval_runtime": 43.2869,
      "eval_samples_per_second": 18.042,
      "eval_steps_per_second": 4.528,
      "step": 150
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 0.0019265917362645268,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 0.0011,
      "step": 160
    },
    {
      "epoch": 0.06877022653721683,
      "grad_norm": 0.004902382381260395,
      "learning_rate": 1.6833333333333332e-06,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.07281553398058252,
      "grad_norm": 0.012828897684812546,
      "learning_rate": 1.1222222222222222e-06,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 0.07686084142394822,
      "grad_norm": 0.03425660356879234,
      "learning_rate": 5.611111111111111e-07,
      "loss": 0.0035,
      "step": 190
    },
    {
      "epoch": 0.08090614886731391,
      "grad_norm": 0.12202399224042892,
      "learning_rate": 0.0,
      "loss": 0.0148,
      "step": 200
    },
    {
      "epoch": 0.08090614886731391,
      "eval_loss": 0.005512339062988758,
      "eval_runtime": 43.2377,
      "eval_samples_per_second": 18.063,
      "eval_steps_per_second": 4.533,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.685210549898445e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}