{
  "best_metric": 1.7814539670944214,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0016735001255125093,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.578333751708365e-05,
      "eval_loss": 2.590552806854248,
      "eval_runtime": 1918.3314,
      "eval_samples_per_second": 7.87,
      "eval_steps_per_second": 1.968,
      "step": 1
    },
    {
      "epoch": 0.00016735001255125095,
      "grad_norm": 0.9075861573219299,
      "learning_rate": 0.00012,
      "loss": 2.3936,
      "step": 3
    },
    {
      "epoch": 0.0002789166875854182,
      "eval_loss": 2.2584927082061768,
      "eval_runtime": 1927.8168,
      "eval_samples_per_second": 7.831,
      "eval_steps_per_second": 1.958,
      "step": 5
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": 1.1849775314331055,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4006,
      "step": 6
    },
    {
      "epoch": 0.0005020500376537528,
      "grad_norm": 0.6381310224533081,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.123,
      "step": 9
    },
    {
      "epoch": 0.0005578333751708364,
      "eval_loss": 2.008568286895752,
      "eval_runtime": 1926.5033,
      "eval_samples_per_second": 7.836,
      "eval_steps_per_second": 1.96,
      "step": 10
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": 0.6661816239356995,
      "learning_rate": 0.000163742398974869,
      "loss": 2.0581,
      "step": 12
    },
    {
      "epoch": 0.0008367500627562547,
      "grad_norm": 0.5966145396232605,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9456,
      "step": 15
    },
    {
      "epoch": 0.0008367500627562547,
      "eval_loss": 1.8909106254577637,
      "eval_runtime": 1926.6899,
      "eval_samples_per_second": 7.836,
      "eval_steps_per_second": 1.959,
      "step": 15
    },
    {
      "epoch": 0.0010041000753075056,
      "grad_norm": 0.5314346551895142,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.8832,
      "step": 18
    },
    {
      "epoch": 0.0011156667503416729,
      "eval_loss": 1.8154946565628052,
      "eval_runtime": 1927.6089,
      "eval_samples_per_second": 7.832,
      "eval_steps_per_second": 1.958,
      "step": 20
    },
    {
      "epoch": 0.0011714500878587566,
      "grad_norm": 0.5717261433601379,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.7195,
      "step": 21
    },
    {
      "epoch": 0.0013388001004100076,
      "grad_norm": 0.6992154121398926,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.8193,
      "step": 24
    },
    {
      "epoch": 0.001394583437927091,
      "eval_loss": 1.7873667478561401,
      "eval_runtime": 1926.2101,
      "eval_samples_per_second": 7.838,
      "eval_steps_per_second": 1.96,
      "step": 25
    },
    {
      "epoch": 0.0015061501129612586,
      "grad_norm": 0.6408898234367371,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.7178,
      "step": 27
    },
    {
      "epoch": 0.0016735001255125093,
      "grad_norm": 0.7179284691810608,
      "learning_rate": 0.0,
      "loss": 1.8085,
      "step": 30
    },
    {
      "epoch": 0.0016735001255125093,
      "eval_loss": 1.7814539670944214,
      "eval_runtime": 1926.588,
      "eval_samples_per_second": 7.836,
      "eval_steps_per_second": 1.959,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3183977611264e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}