{
  "best_metric": 2.9710018634796143,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.018481726193226446,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007392690477290579,
      "grad_norm": 0.6081264019012451,
      "learning_rate": 5e-05,
      "loss": 3.1577,
      "step": 1
    },
    {
      "epoch": 0.0007392690477290579,
      "eval_loss": 4.195895195007324,
      "eval_runtime": 969.06,
      "eval_samples_per_second": 9.404,
      "eval_steps_per_second": 1.176,
      "step": 1
    },
    {
      "epoch": 0.0014785380954581157,
      "grad_norm": 0.9309924840927124,
      "learning_rate": 0.0001,
      "loss": 3.4383,
      "step": 2
    },
    {
      "epoch": 0.0022178071431871735,
      "grad_norm": 0.5503907203674316,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.5455,
      "step": 3
    },
    {
      "epoch": 0.0029570761909162315,
      "grad_norm": 0.7579587697982788,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.5382,
      "step": 4
    },
    {
      "epoch": 0.0036963452386452895,
      "grad_norm": 1.0003035068511963,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.6219,
      "step": 5
    },
    {
      "epoch": 0.004435614286374347,
      "grad_norm": 1.165474772453308,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.6023,
      "step": 6
    },
    {
      "epoch": 0.0051748833341034054,
      "grad_norm": 1.2234491109848022,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.6794,
      "step": 7
    },
    {
      "epoch": 0.005914152381832463,
      "grad_norm": 1.4161816835403442,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.6668,
      "step": 8
    },
    {
      "epoch": 0.006653421429561521,
      "grad_norm": 1.5868772268295288,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.6169,
      "step": 9
    },
    {
      "epoch": 0.007392690477290579,
      "grad_norm": 1.3991680145263672,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.6064,
      "step": 10
    },
    {
      "epoch": 0.008131959525019637,
      "grad_norm": 1.551560401916504,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.844,
      "step": 11
    },
    {
      "epoch": 0.008871228572748694,
      "grad_norm": 2.185145616531372,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.8718,
      "step": 12
    },
    {
      "epoch": 0.009610497620477753,
      "grad_norm": 0.964591920375824,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.7685,
      "step": 13
    },
    {
      "epoch": 0.010349766668206811,
      "grad_norm": 1.0235710144042969,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.8684,
      "step": 14
    },
    {
      "epoch": 0.011089035715935868,
      "grad_norm": 0.9440206289291382,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.8124,
      "step": 15
    },
    {
      "epoch": 0.011828304763664926,
      "grad_norm": 0.5510419607162476,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.8748,
      "step": 16
    },
    {
      "epoch": 0.012567573811393984,
      "grad_norm": 0.4680745005607605,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.9763,
      "step": 17
    },
    {
      "epoch": 0.013306842859123043,
      "grad_norm": 0.6219832301139832,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.9339,
      "step": 18
    },
    {
      "epoch": 0.0140461119068521,
      "grad_norm": 1.7636165618896484,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.9163,
      "step": 19
    },
    {
      "epoch": 0.014785380954581158,
      "grad_norm": 2.6265430450439453,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.0557,
      "step": 20
    },
    {
      "epoch": 0.015524650002310215,
      "grad_norm": 4.389255523681641,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.1214,
      "step": 21
    },
    {
      "epoch": 0.016263919050039273,
      "grad_norm": 4.146439075469971,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.1418,
      "step": 22
    },
    {
      "epoch": 0.01700318809776833,
      "grad_norm": 3.0236587524414062,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.283,
      "step": 23
    },
    {
      "epoch": 0.017742457145497388,
      "grad_norm": 4.432220935821533,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.3437,
      "step": 24
    },
    {
      "epoch": 0.018481726193226446,
      "grad_norm": 9.338114738464355,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.4673,
      "step": 25
    },
    {
      "epoch": 0.018481726193226446,
      "eval_loss": 2.9710018634796143,
      "eval_runtime": 969.1531,
      "eval_samples_per_second": 9.403,
      "eval_steps_per_second": 1.176,
      "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": 5.114180768104448e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}