{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.119815668202765,
  "eval_steps": 25,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07373271889400922,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.07373271889400922,
      "eval_loss": NaN,
      "eval_runtime": 1.6547,
      "eval_samples_per_second": 55.6,
      "eval_steps_per_second": 7.252,
      "step": 1
    },
    {
      "epoch": 0.14746543778801843,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.22119815668202766,
      "grad_norm": NaN,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.29493087557603687,
      "grad_norm": NaN,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.3686635944700461,
      "grad_norm": NaN,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.4423963133640553,
      "grad_norm": NaN,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": NaN,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5898617511520737,
      "grad_norm": NaN,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.663594470046083,
      "grad_norm": NaN,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7373271889400922,
      "grad_norm": NaN,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.8110599078341014,
      "grad_norm": NaN,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8847926267281107,
      "grad_norm": NaN,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.9585253456221198,
      "grad_norm": NaN,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": NaN,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.1382488479262673,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.2119815668202765,
      "grad_norm": NaN,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": NaN,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.359447004608295,
      "grad_norm": NaN,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.4331797235023043,
      "grad_norm": NaN,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.5069124423963134,
      "grad_norm": NaN,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": NaN,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.6543778801843319,
      "grad_norm": NaN,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.728110599078341,
      "grad_norm": NaN,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.80184331797235,
      "grad_norm": NaN,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.8755760368663594,
      "grad_norm": NaN,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.8755760368663594,
      "eval_loss": NaN,
      "eval_runtime": 1.6571,
      "eval_samples_per_second": 55.52,
      "eval_steps_per_second": 7.242,
      "step": 25
    },
    {
      "epoch": 1.9493087557603688,
      "grad_norm": NaN,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 2.055299539170507,
      "grad_norm": NaN,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 2.129032258064516,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 2.2027649769585254,
      "grad_norm": NaN,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 2.2764976958525347,
      "grad_norm": NaN,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 2.3502304147465436,
      "grad_norm": NaN,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 2.423963133640553,
      "grad_norm": NaN,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 2.4976958525345623,
      "grad_norm": NaN,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": NaN,
      "learning_rate": 7.740495722810271e-06,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 2.6451612903225805,
      "grad_norm": NaN,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 2.71889400921659,
      "grad_norm": NaN,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 2.792626728110599,
      "grad_norm": NaN,
      "learning_rate": 2.573177902642726e-06,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 2.8663594470046085,
      "grad_norm": NaN,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 2.9400921658986174,
      "grad_norm": NaN,
      "learning_rate": 6.474868681043578e-07,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 3.046082949308756,
      "grad_norm": NaN,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 3.119815668202765,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 41
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "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": 1.827986893480919e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}