{
  "best_metric": 0.47236114740371704,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.057085771371485655,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022834308548594262,
      "grad_norm": 0.22559398412704468,
      "learning_rate": 5e-05,
      "loss": 0.3501,
      "step": 1
    },
    {
      "epoch": 0.0022834308548594262,
      "eval_loss": 0.6596930623054504,
      "eval_runtime": 200.1881,
      "eval_samples_per_second": 14.741,
      "eval_steps_per_second": 1.843,
      "step": 1
    },
    {
      "epoch": 0.0045668617097188524,
      "grad_norm": 0.22919631004333496,
      "learning_rate": 0.0001,
      "loss": 0.3151,
      "step": 2
    },
    {
      "epoch": 0.006850292564578279,
      "grad_norm": 0.2545759975910187,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.4304,
      "step": 3
    },
    {
      "epoch": 0.009133723419437705,
      "grad_norm": 0.23282743990421295,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.3648,
      "step": 4
    },
    {
      "epoch": 0.01141715427429713,
      "grad_norm": 0.22734428942203522,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.3844,
      "step": 5
    },
    {
      "epoch": 0.013700585129156558,
      "grad_norm": 0.32344239950180054,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4446,
      "step": 6
    },
    {
      "epoch": 0.015984015984015984,
      "grad_norm": 0.25610044598579407,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.4174,
      "step": 7
    },
    {
      "epoch": 0.01826744683887541,
      "grad_norm": 0.19879823923110962,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5232,
      "step": 8
    },
    {
      "epoch": 0.020550877693734836,
      "grad_norm": 0.2444503903388977,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.596,
      "step": 9
    },
    {
      "epoch": 0.02283430854859426,
      "grad_norm": 0.2801436185836792,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7173,
      "step": 10
    },
    {
      "epoch": 0.02511773940345369,
      "grad_norm": 0.29815584421157837,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.7865,
      "step": 11
    },
    {
      "epoch": 0.027401170258313116,
      "grad_norm": 0.3620450794696808,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.9747,
      "step": 12
    },
    {
      "epoch": 0.029684601113172542,
      "grad_norm": 0.18315419554710388,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.4203,
      "step": 13
    },
    {
      "epoch": 0.03196803196803197,
      "grad_norm": 0.17548008263111115,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2471,
      "step": 14
    },
    {
      "epoch": 0.0342514628228914,
      "grad_norm": 0.220022052526474,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.3949,
      "step": 15
    },
    {
      "epoch": 0.03653489367775082,
      "grad_norm": 0.17819145321846008,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.3722,
      "step": 16
    },
    {
      "epoch": 0.03881832453261025,
      "grad_norm": 0.19627267122268677,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4137,
      "step": 17
    },
    {
      "epoch": 0.04110175538746967,
      "grad_norm": 0.15671569108963013,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4389,
      "step": 18
    },
    {
      "epoch": 0.0433851862423291,
      "grad_norm": 0.16053399443626404,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.4783,
      "step": 19
    },
    {
      "epoch": 0.04566861709718852,
      "grad_norm": 0.16855283081531525,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5583,
      "step": 20
    },
    {
      "epoch": 0.04795204795204795,
      "grad_norm": 0.19199872016906738,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.5753,
      "step": 21
    },
    {
      "epoch": 0.05023547880690738,
      "grad_norm": 0.22297468781471252,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6232,
      "step": 22
    },
    {
      "epoch": 0.052518909661766804,
      "grad_norm": 0.25045719742774963,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.6832,
      "step": 23
    },
    {
      "epoch": 0.05480234051662623,
      "grad_norm": 0.31544703245162964,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8324,
      "step": 24
    },
    {
      "epoch": 0.057085771371485655,
      "grad_norm": 0.4587164521217346,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.0082,
      "step": 25
    },
    {
      "epoch": 0.057085771371485655,
      "eval_loss": 0.47236114740371704,
      "eval_runtime": 200.2165,
      "eval_samples_per_second": 14.739,
      "eval_steps_per_second": 1.843,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}