{
  "best_metric": 0.5803007483482361,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9950248756218906,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 0.13538791239261627,
      "learning_rate": 5e-05,
      "loss": 0.7752,
      "step": 1
    },
    {
      "epoch": 0.03980099502487562,
      "eval_loss": 0.7566336393356323,
      "eval_runtime": 5.1026,
      "eval_samples_per_second": 33.316,
      "eval_steps_per_second": 4.312,
      "step": 1
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 0.13740819692611694,
      "learning_rate": 0.0001,
      "loss": 0.756,
      "step": 2
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 0.14167937636375427,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.7529,
      "step": 3
    },
    {
      "epoch": 0.15920398009950248,
      "grad_norm": 0.1538102775812149,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7392,
      "step": 4
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.1964820772409439,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.7395,
      "step": 5
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 0.12592492997646332,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.6386,
      "step": 6
    },
    {
      "epoch": 0.27860696517412936,
      "grad_norm": 0.12350691109895706,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.6686,
      "step": 7
    },
    {
      "epoch": 0.31840796019900497,
      "grad_norm": 0.14032255113124847,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.682,
      "step": 8
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 0.14228299260139465,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6878,
      "step": 9
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.10774895548820496,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.634,
      "step": 10
    },
    {
      "epoch": 0.43781094527363185,
      "grad_norm": 0.10263238102197647,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.604,
      "step": 11
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.10312753170728683,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6044,
      "step": 12
    },
    {
      "epoch": 0.5174129353233831,
      "grad_norm": 0.07034023106098175,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6199,
      "step": 13
    },
    {
      "epoch": 0.5572139303482587,
      "grad_norm": 0.07299194484949112,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6362,
      "step": 14
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.07921850681304932,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.6404,
      "step": 15
    },
    {
      "epoch": 0.6368159203980099,
      "grad_norm": 0.07726301997900009,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6213,
      "step": 16
    },
    {
      "epoch": 0.6766169154228856,
      "grad_norm": 0.07813425362110138,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.5873,
      "step": 17
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.10323521494865417,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5738,
      "step": 18
    },
    {
      "epoch": 0.7562189054726368,
      "grad_norm": 0.07982894033193588,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5988,
      "step": 19
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.06970314681529999,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6514,
      "step": 20
    },
    {
      "epoch": 0.835820895522388,
      "grad_norm": 0.07304966449737549,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6176,
      "step": 21
    },
    {
      "epoch": 0.8756218905472637,
      "grad_norm": 0.10210943222045898,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5853,
      "step": 22
    },
    {
      "epoch": 0.9154228855721394,
      "grad_norm": 0.08298351615667343,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5827,
      "step": 23
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.07600322365760803,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.573,
      "step": 24
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.08038770407438278,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.5355,
      "step": 25
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.5803007483482361,
      "eval_runtime": 5.094,
      "eval_samples_per_second": 33.373,
      "eval_steps_per_second": 4.319,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.629578157719552e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}