{
  "best_metric": 11.930198669433594,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06284861340246681,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002513944536098672,
      "grad_norm": 0.01306601706892252,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 11.9327,
      "step": 1
    },
    {
      "epoch": 0.002513944536098672,
      "eval_loss": 11.931513786315918,
      "eval_runtime": 0.2553,
      "eval_samples_per_second": 195.821,
      "eval_steps_per_second": 50.913,
      "step": 1
    },
    {
      "epoch": 0.005027889072197344,
      "grad_norm": 0.013035156764090061,
      "learning_rate": 6.666666666666667e-05,
      "loss": 11.9322,
      "step": 2
    },
    {
      "epoch": 0.007541833608296017,
      "grad_norm": 0.013919487595558167,
      "learning_rate": 0.0001,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.010055778144394689,
      "grad_norm": 0.012912580743432045,
      "learning_rate": 9.99571699711836e-05,
      "loss": 11.9316,
      "step": 4
    },
    {
      "epoch": 0.012569722680493361,
      "grad_norm": 0.01366867870092392,
      "learning_rate": 9.982876141412856e-05,
      "loss": 11.932,
      "step": 5
    },
    {
      "epoch": 0.015083667216592034,
      "grad_norm": 0.018193839117884636,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9317,
      "step": 6
    },
    {
      "epoch": 0.017597611752690707,
      "grad_norm": 0.019369425252079964,
      "learning_rate": 9.931634888554937e-05,
      "loss": 11.931,
      "step": 7
    },
    {
      "epoch": 0.020111556288789377,
      "grad_norm": 0.019250450655817986,
      "learning_rate": 9.893332032039701e-05,
      "loss": 11.9308,
      "step": 8
    },
    {
      "epoch": 0.02262550082488805,
      "grad_norm": 0.027681566774845123,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9314,
      "step": 9
    },
    {
      "epoch": 0.025139445360986723,
      "grad_norm": 0.028774602338671684,
      "learning_rate": 9.791726278367022e-05,
      "loss": 11.9326,
      "step": 10
    },
    {
      "epoch": 0.027653389897085396,
      "grad_norm": 0.03369531035423279,
      "learning_rate": 9.728616793536588e-05,
      "loss": 11.9304,
      "step": 11
    },
    {
      "epoch": 0.03016733443318407,
      "grad_norm": 0.038345273584127426,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.928,
      "step": 12
    },
    {
      "epoch": 0.03268127896928274,
      "grad_norm": 0.01788642816245556,
      "learning_rate": 9.578385041664925e-05,
      "loss": 11.9323,
      "step": 13
    },
    {
      "epoch": 0.035195223505381415,
      "grad_norm": 0.01733534224331379,
      "learning_rate": 9.491548749301997e-05,
      "loss": 11.9322,
      "step": 14
    },
    {
      "epoch": 0.037709168041480084,
      "grad_norm": 0.017722493037581444,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9322,
      "step": 15
    },
    {
      "epoch": 0.040223112577578754,
      "grad_norm": 0.018521340563893318,
      "learning_rate": 9.295261506157986e-05,
      "loss": 11.9315,
      "step": 16
    },
    {
      "epoch": 0.04273705711367743,
      "grad_norm": 0.022729676216840744,
      "learning_rate": 9.186184199300464e-05,
      "loss": 11.9313,
      "step": 17
    },
    {
      "epoch": 0.0452510016497761,
      "grad_norm": 0.024669429287314415,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9309,
      "step": 18
    },
    {
      "epoch": 0.047764946185874776,
      "grad_norm": 0.025852613151073456,
      "learning_rate": 8.947199994035401e-05,
      "loss": 11.9314,
      "step": 19
    },
    {
      "epoch": 0.050278890721973446,
      "grad_norm": 0.03324759006500244,
      "learning_rate": 8.817748015645558e-05,
      "loss": 11.9309,
      "step": 20
    },
    {
      "epoch": 0.052792835258072116,
      "grad_norm": 0.032473403960466385,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9301,
      "step": 21
    },
    {
      "epoch": 0.05530677979417079,
      "grad_norm": 0.04105048254132271,
      "learning_rate": 8.540155934270471e-05,
      "loss": 11.9316,
      "step": 22
    },
    {
      "epoch": 0.05782072433026946,
      "grad_norm": 0.039779629558324814,
      "learning_rate": 8.392544243589427e-05,
      "loss": 11.9302,
      "step": 23
    },
    {
      "epoch": 0.06033466886636814,
      "grad_norm": 0.057441096752882004,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9324,
      "step": 24
    },
    {
      "epoch": 0.06284861340246681,
      "grad_norm": 0.07438816875219345,
      "learning_rate": 8.081093963579707e-05,
      "loss": 11.9318,
      "step": 25
    },
    {
      "epoch": 0.06284861340246681,
      "eval_loss": 11.930198669433594,
      "eval_runtime": 0.2524,
      "eval_samples_per_second": 198.062,
      "eval_steps_per_second": 51.496,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 521247129600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}