{
  "best_metric": 1.7318332195281982,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.028585040495474036,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009528346831824678,
      "eval_loss": 2.0283005237579346,
      "eval_runtime": 91.3281,
      "eval_samples_per_second": 9.679,
      "eval_steps_per_second": 2.42,
      "step": 1
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 0.8241713047027588,
      "learning_rate": 0.00012,
      "loss": 1.9742,
      "step": 3
    },
    {
      "epoch": 0.004764173415912339,
      "eval_loss": 1.8770804405212402,
      "eval_runtime": 90.3623,
      "eval_samples_per_second": 9.783,
      "eval_steps_per_second": 2.446,
      "step": 5
    },
    {
      "epoch": 0.005717008099094807,
      "grad_norm": 0.419120192527771,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.9951,
      "step": 6
    },
    {
      "epoch": 0.00857551214864221,
      "grad_norm": 0.9354789853096008,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.9576,
      "step": 9
    },
    {
      "epoch": 0.009528346831824679,
      "eval_loss": 1.8005465269088745,
      "eval_runtime": 90.6074,
      "eval_samples_per_second": 9.756,
      "eval_steps_per_second": 2.439,
      "step": 10
    },
    {
      "epoch": 0.011434016198189614,
      "grad_norm": 0.4588392376899719,
      "learning_rate": 0.000163742398974869,
      "loss": 1.8324,
      "step": 12
    },
    {
      "epoch": 0.014292520247737018,
      "grad_norm": 0.4373359978199005,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7323,
      "step": 15
    },
    {
      "epoch": 0.014292520247737018,
      "eval_loss": 1.7643545866012573,
      "eval_runtime": 90.4049,
      "eval_samples_per_second": 9.778,
      "eval_steps_per_second": 2.445,
      "step": 15
    },
    {
      "epoch": 0.01715102429728442,
      "grad_norm": 0.3728502690792084,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.7233,
      "step": 18
    },
    {
      "epoch": 0.019056693663649357,
      "eval_loss": 1.7411246299743652,
      "eval_runtime": 90.5791,
      "eval_samples_per_second": 9.759,
      "eval_steps_per_second": 2.44,
      "step": 20
    },
    {
      "epoch": 0.020009528346831826,
      "grad_norm": 0.34966373443603516,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.8199,
      "step": 21
    },
    {
      "epoch": 0.022868032396379228,
      "grad_norm": 0.39327874779701233,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.7785,
      "step": 24
    },
    {
      "epoch": 0.023820867079561697,
      "eval_loss": 1.733565330505371,
      "eval_runtime": 90.5193,
      "eval_samples_per_second": 9.766,
      "eval_steps_per_second": 2.441,
      "step": 25
    },
    {
      "epoch": 0.02572653644592663,
      "grad_norm": 0.32263967394828796,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.7819,
      "step": 27
    },
    {
      "epoch": 0.028585040495474036,
      "grad_norm": 0.2795114517211914,
      "learning_rate": 0.0,
      "loss": 1.7779,
      "step": 30
    },
    {
      "epoch": 0.028585040495474036,
      "eval_loss": 1.7318332195281982,
      "eval_runtime": 90.187,
      "eval_samples_per_second": 9.802,
      "eval_steps_per_second": 2.45,
      "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": 4.451323701362688e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}