{
  "best_metric": 1.9534236192703247,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06902502157031924,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027610008628127696,
      "grad_norm": 121.57788848876953,
      "learning_rate": 5e-05,
      "loss": 13.5104,
      "step": 1
    },
    {
      "epoch": 0.0027610008628127696,
      "eval_loss": 13.60006046295166,
      "eval_runtime": 22.1692,
      "eval_samples_per_second": 110.063,
      "eval_steps_per_second": 13.758,
      "step": 1
    },
    {
      "epoch": 0.005522001725625539,
      "grad_norm": 120.4114761352539,
      "learning_rate": 0.0001,
      "loss": 13.5466,
      "step": 2
    },
    {
      "epoch": 0.00828300258843831,
      "grad_norm": 189.47218322753906,
      "learning_rate": 9.989294616193017e-05,
      "loss": 13.0268,
      "step": 3
    },
    {
      "epoch": 0.011044003451251078,
      "grad_norm": 74.05614471435547,
      "learning_rate": 9.957224306869053e-05,
      "loss": 8.1214,
      "step": 4
    },
    {
      "epoch": 0.013805004314063849,
      "grad_norm": 65.40906524658203,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.8602,
      "step": 5
    },
    {
      "epoch": 0.01656600517687662,
      "grad_norm": 49.65504455566406,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.3736,
      "step": 6
    },
    {
      "epoch": 0.019327006039689388,
      "grad_norm": 75.54695892333984,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.7208,
      "step": 7
    },
    {
      "epoch": 0.022088006902502157,
      "grad_norm": 32.32862854003906,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.0733,
      "step": 8
    },
    {
      "epoch": 0.024849007765314925,
      "grad_norm": 13.67139720916748,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.6005,
      "step": 9
    },
    {
      "epoch": 0.027610008628127698,
      "grad_norm": 19.72774887084961,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.4848,
      "step": 10
    },
    {
      "epoch": 0.030371009490940466,
      "grad_norm": 26.92169952392578,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.2381,
      "step": 11
    },
    {
      "epoch": 0.03313201035375324,
      "grad_norm": 63.783424377441406,
      "learning_rate": 8.966766701456177e-05,
      "loss": 6.0044,
      "step": 12
    },
    {
      "epoch": 0.035893011216566004,
      "grad_norm": 27.033920288085938,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.1015,
      "step": 13
    },
    {
      "epoch": 0.038654012079378776,
      "grad_norm": 25.252769470214844,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2373,
      "step": 14
    },
    {
      "epoch": 0.04141501294219154,
      "grad_norm": 15.015902519226074,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.966,
      "step": 15
    },
    {
      "epoch": 0.04417601380500431,
      "grad_norm": 11.274029731750488,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.8608,
      "step": 16
    },
    {
      "epoch": 0.046937014667817085,
      "grad_norm": 6.833890914916992,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8622,
      "step": 17
    },
    {
      "epoch": 0.04969801553062985,
      "grad_norm": 4.205880641937256,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7259,
      "step": 18
    },
    {
      "epoch": 0.05245901639344262,
      "grad_norm": 8.309425354003906,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.8331,
      "step": 19
    },
    {
      "epoch": 0.055220017256255395,
      "grad_norm": 1.8611191511154175,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.7104,
      "step": 20
    },
    {
      "epoch": 0.05798101811906816,
      "grad_norm": 3.5068414211273193,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6505,
      "step": 21
    },
    {
      "epoch": 0.06074201898188093,
      "grad_norm": 6.320912837982178,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6542,
      "step": 22
    },
    {
      "epoch": 0.0635030198446937,
      "grad_norm": 3.254844903945923,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.6272,
      "step": 23
    },
    {
      "epoch": 0.06626402070750648,
      "grad_norm": 20.136241912841797,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.3386,
      "step": 24
    },
    {
      "epoch": 0.06902502157031924,
      "grad_norm": 39.7511100769043,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.4797,
      "step": 25
    },
    {
      "epoch": 0.06902502157031924,
      "eval_loss": 1.9534236192703247,
      "eval_runtime": 22.1838,
      "eval_samples_per_second": 109.99,
      "eval_steps_per_second": 13.749,
      "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": 4.16708196040704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}