{
  "best_metric": 0.4723750054836273,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.04856726566294318,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001942690626517727,
      "grad_norm": 0.6803475618362427,
      "learning_rate": 1e-05,
      "loss": 2.2766,
      "step": 1
    },
    {
      "epoch": 0.001942690626517727,
      "eval_loss": 0.6704726219177246,
      "eval_runtime": 42.8729,
      "eval_samples_per_second": 5.061,
      "eval_steps_per_second": 2.542,
      "step": 1
    },
    {
      "epoch": 0.003885381253035454,
      "grad_norm": 0.60342937707901,
      "learning_rate": 2e-05,
      "loss": 2.507,
      "step": 2
    },
    {
      "epoch": 0.005828071879553181,
      "grad_norm": 0.5822948217391968,
      "learning_rate": 3e-05,
      "loss": 1.8993,
      "step": 3
    },
    {
      "epoch": 0.007770762506070908,
      "grad_norm": 0.707507848739624,
      "learning_rate": 4e-05,
      "loss": 2.534,
      "step": 4
    },
    {
      "epoch": 0.009713453132588635,
      "grad_norm": 0.4827619791030884,
      "learning_rate": 5e-05,
      "loss": 2.3013,
      "step": 5
    },
    {
      "epoch": 0.009713453132588635,
      "eval_loss": 0.6683055758476257,
      "eval_runtime": 43.1261,
      "eval_samples_per_second": 5.032,
      "eval_steps_per_second": 2.527,
      "step": 5
    },
    {
      "epoch": 0.011656143759106362,
      "grad_norm": 0.7720835208892822,
      "learning_rate": 6e-05,
      "loss": 2.1516,
      "step": 6
    },
    {
      "epoch": 0.013598834385624089,
      "grad_norm": 0.6448253393173218,
      "learning_rate": 7e-05,
      "loss": 1.9544,
      "step": 7
    },
    {
      "epoch": 0.015541525012141816,
      "grad_norm": 0.7023385763168335,
      "learning_rate": 8e-05,
      "loss": 2.2042,
      "step": 8
    },
    {
      "epoch": 0.017484215638659543,
      "grad_norm": 1.196603775024414,
      "learning_rate": 9e-05,
      "loss": 2.7489,
      "step": 9
    },
    {
      "epoch": 0.01942690626517727,
      "grad_norm": 0.9811630845069885,
      "learning_rate": 0.0001,
      "loss": 2.2584,
      "step": 10
    },
    {
      "epoch": 0.01942690626517727,
      "eval_loss": 0.6306657195091248,
      "eval_runtime": 43.2127,
      "eval_samples_per_second": 5.022,
      "eval_steps_per_second": 2.522,
      "step": 10
    },
    {
      "epoch": 0.021369596891694997,
      "grad_norm": 1.3569114208221436,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.1272,
      "step": 11
    },
    {
      "epoch": 0.023312287518212724,
      "grad_norm": 1.2888952493667603,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.7706,
      "step": 12
    },
    {
      "epoch": 0.02525497814473045,
      "grad_norm": 1.3824020624160767,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.378,
      "step": 13
    },
    {
      "epoch": 0.027197668771248178,
      "grad_norm": 0.6680025458335876,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.563,
      "step": 14
    },
    {
      "epoch": 0.029140359397765905,
      "grad_norm": 1.1097849607467651,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6712,
      "step": 15
    },
    {
      "epoch": 0.029140359397765905,
      "eval_loss": 0.5315653085708618,
      "eval_runtime": 43.447,
      "eval_samples_per_second": 4.995,
      "eval_steps_per_second": 2.509,
      "step": 15
    },
    {
      "epoch": 0.03108305002428363,
      "grad_norm": 1.1700183153152466,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.3199,
      "step": 16
    },
    {
      "epoch": 0.03302574065080136,
      "grad_norm": 1.2776918411254883,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.6961,
      "step": 17
    },
    {
      "epoch": 0.034968431277319086,
      "grad_norm": 1.0217623710632324,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.1827,
      "step": 18
    },
    {
      "epoch": 0.036911121903836816,
      "grad_norm": 1.0589659214019775,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3891,
      "step": 19
    },
    {
      "epoch": 0.03885381253035454,
      "grad_norm": 2.043240785598755,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.0682,
      "step": 20
    },
    {
      "epoch": 0.03885381253035454,
      "eval_loss": 0.48243945837020874,
      "eval_runtime": 43.5062,
      "eval_samples_per_second": 4.988,
      "eval_steps_per_second": 2.505,
      "step": 20
    },
    {
      "epoch": 0.04079650315687227,
      "grad_norm": 1.2976908683776855,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.2973,
      "step": 21
    },
    {
      "epoch": 0.042739193783389993,
      "grad_norm": 2.772876501083374,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1802,
      "step": 22
    },
    {
      "epoch": 0.044681884409907724,
      "grad_norm": 1.1275978088378906,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.5172,
      "step": 23
    },
    {
      "epoch": 0.04662457503642545,
      "grad_norm": 2.216585159301758,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.9489,
      "step": 24
    },
    {
      "epoch": 0.04856726566294318,
      "grad_norm": 1.3420172929763794,
      "learning_rate": 0.0,
      "loss": 1.4192,
      "step": 25
    },
    {
      "epoch": 0.04856726566294318,
      "eval_loss": 0.4723750054836273,
      "eval_runtime": 43.4128,
      "eval_samples_per_second": 4.999,
      "eval_steps_per_second": 2.511,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 7915560763392000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}