{
  "best_metric": 1.2476589679718018,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.01697792869269949,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016977928692699492,
      "eval_loss": 1.4329637289047241,
      "eval_runtime": 234.0581,
      "eval_samples_per_second": 5.298,
      "eval_steps_per_second": 1.324,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": 1.311955213546753,
      "learning_rate": 4.1400000000000003e-05,
      "loss": 1.4203,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": 0.7833012342453003,
      "learning_rate": 8.280000000000001e-05,
      "loss": 1.338,
      "step": 20
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": 0.7402932047843933,
      "learning_rate": 0.00012419999999999998,
      "loss": 1.2575,
      "step": 30
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": 0.7024871110916138,
      "learning_rate": 0.00016560000000000001,
      "loss": 1.2019,
      "step": 40
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": 0.804834246635437,
      "learning_rate": 0.000207,
      "loss": 1.2279,
      "step": 50
    },
    {
      "epoch": 0.008488964346349746,
      "eval_loss": 1.2476589679718018,
      "eval_runtime": 235.3963,
      "eval_samples_per_second": 5.268,
      "eval_steps_per_second": 1.317,
      "step": 50
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": 0.7924010753631592,
      "learning_rate": 0.00020674787920189178,
      "loss": 1.222,
      "step": 60
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": 0.8740193247795105,
      "learning_rate": 0.00020599274511475253,
      "loss": 1.2045,
      "step": 70
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": 0.8409563899040222,
      "learning_rate": 0.00020473827667594888,
      "loss": 1.2077,
      "step": 80
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": 1.0255435705184937,
      "learning_rate": 0.00020299058552961598,
      "loss": 1.2556,
      "step": 90
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": 1.3903775215148926,
      "learning_rate": 0.00020075818625134152,
      "loss": 1.303,
      "step": 100
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": 1.3105939626693726,
      "eval_runtime": 235.3286,
      "eval_samples_per_second": 5.269,
      "eval_steps_per_second": 1.317,
      "step": 100
    }
  ],
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.193703014544179e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}