{
  "best_metric": 0.35316547751426697,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.2188183807439825,
  "eval_steps": 50,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00087527352297593,
      "eval_loss": 0.5409302115440369,
      "eval_runtime": 48.1638,
      "eval_samples_per_second": 9.987,
      "eval_steps_per_second": 2.512,
      "step": 1
    },
    {
      "epoch": 0.0087527352297593,
      "grad_norm": 0.6199236512184143,
      "learning_rate": 4.22e-05,
      "loss": 1.1012,
      "step": 10
    },
    {
      "epoch": 0.0175054704595186,
      "grad_norm": 0.603871762752533,
      "learning_rate": 8.44e-05,
      "loss": 0.7497,
      "step": 20
    },
    {
      "epoch": 0.0262582056892779,
      "grad_norm": 0.17278185486793518,
      "learning_rate": 0.0001266,
      "loss": 0.2424,
      "step": 30
    },
    {
      "epoch": 0.0350109409190372,
      "grad_norm": 0.2742425203323364,
      "learning_rate": 0.0001688,
      "loss": 0.0084,
      "step": 40
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 0.21153666079044342,
      "learning_rate": 0.000211,
      "loss": 0.0076,
      "step": 50
    },
    {
      "epoch": 0.0437636761487965,
      "eval_loss": 0.4160047173500061,
      "eval_runtime": 48.0642,
      "eval_samples_per_second": 10.007,
      "eval_steps_per_second": 2.517,
      "step": 50
    },
    {
      "epoch": 0.0525164113785558,
      "grad_norm": 0.5463985204696655,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.6921,
      "step": 60
    },
    {
      "epoch": 0.061269146608315096,
      "grad_norm": 0.8098825812339783,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.5244,
      "step": 70
    },
    {
      "epoch": 0.0700218818380744,
      "grad_norm": 0.38064104318618774,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.2607,
      "step": 80
    },
    {
      "epoch": 0.0787746170678337,
      "grad_norm": 0.050267886370420456,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.0061,
      "step": 90
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 0.3279358148574829,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.0024,
      "step": 100
    },
    {
      "epoch": 0.087527352297593,
      "eval_loss": 0.35316547751426697,
      "eval_runtime": 48.4486,
      "eval_samples_per_second": 9.928,
      "eval_steps_per_second": 2.497,
      "step": 100
    },
    {
      "epoch": 0.0962800875273523,
      "grad_norm": 0.5827049612998962,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.8235,
      "step": 110
    },
    {
      "epoch": 0.1050328227571116,
      "grad_norm": 0.36756134033203125,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.6406,
      "step": 120
    },
    {
      "epoch": 0.1137855579868709,
      "grad_norm": 0.10399194061756134,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.1631,
      "step": 130
    },
    {
      "epoch": 0.12253829321663019,
      "grad_norm": 0.05342819169163704,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.0033,
      "step": 140
    },
    {
      "epoch": 0.13129102844638948,
      "grad_norm": 0.01769879087805748,
      "learning_rate": 0.00018631768874905217,
      "loss": 0.001,
      "step": 150
    },
    {
      "epoch": 0.13129102844638948,
      "eval_loss": 0.3601878583431244,
      "eval_runtime": 48.1446,
      "eval_samples_per_second": 9.991,
      "eval_steps_per_second": 2.513,
      "step": 150
    },
    {
      "epoch": 0.1400437636761488,
      "grad_norm": 0.5799025893211365,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.9458,
      "step": 160
    },
    {
      "epoch": 0.1487964989059081,
      "grad_norm": 0.33210673928260803,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.4653,
      "step": 170
    },
    {
      "epoch": 0.1575492341356674,
      "grad_norm": 0.07417658716440201,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.101,
      "step": 180
    },
    {
      "epoch": 0.16630196936542668,
      "grad_norm": 0.005981265101581812,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.0118,
      "step": 190
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 0.0026285904459655285,
      "learning_rate": 0.00015825,
      "loss": 0.001,
      "step": 200
    },
    {
      "epoch": 0.175054704595186,
      "eval_loss": 0.3552694618701935,
      "eval_runtime": 47.8669,
      "eval_samples_per_second": 10.049,
      "eval_steps_per_second": 2.528,
      "step": 200
    },
    {
      "epoch": 0.1838074398249453,
      "grad_norm": 0.5865310430526733,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.7926,
      "step": 210
    },
    {
      "epoch": 0.1925601750547046,
      "grad_norm": 0.6336154341697693,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.7418,
      "step": 220
    },
    {
      "epoch": 0.2013129102844639,
      "grad_norm": 0.0030132222454994917,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.1631,
      "step": 230
    },
    {
      "epoch": 0.2100656455142232,
      "grad_norm": 0.004187281243503094,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.001,
      "step": 240
    },
    {
      "epoch": 0.2188183807439825,
      "grad_norm": 0.03684316575527191,
      "learning_rate": 0.00012381988274386116,
      "loss": 0.0009,
      "step": 250
    },
    {
      "epoch": 0.2188183807439825,
      "eval_loss": 0.3651936948299408,
      "eval_runtime": 48.1017,
      "eval_samples_per_second": 10.0,
      "eval_steps_per_second": 2.516,
      "step": 250
    }
  ],
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.17585994072064e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}