{
  "best_metric": 6.917348861694336,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.20629190304280556,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008251676121712223,
      "grad_norm": 0.19168157875537872,
      "learning_rate": 5e-05,
      "loss": 6.8773,
      "step": 1
    },
    {
      "epoch": 0.008251676121712223,
      "eval_loss": 6.937580585479736,
      "eval_runtime": 0.7847,
      "eval_samples_per_second": 1041.193,
      "eval_steps_per_second": 131.264,
      "step": 1
    },
    {
      "epoch": 0.016503352243424446,
      "grad_norm": 0.18501441180706024,
      "learning_rate": 0.0001,
      "loss": 6.858,
      "step": 2
    },
    {
      "epoch": 0.02475502836513667,
      "grad_norm": 0.2035323530435562,
      "learning_rate": 9.989294616193017e-05,
      "loss": 6.8447,
      "step": 3
    },
    {
      "epoch": 0.03300670448684889,
      "grad_norm": 0.18418113887310028,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.8303,
      "step": 4
    },
    {
      "epoch": 0.041258380608561115,
      "grad_norm": 0.1808152049779892,
      "learning_rate": 9.903926402016153e-05,
      "loss": 6.8184,
      "step": 5
    },
    {
      "epoch": 0.04951005673027334,
      "grad_norm": 0.18681049346923828,
      "learning_rate": 9.829629131445342e-05,
      "loss": 6.8055,
      "step": 6
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": 0.1917319893836975,
      "learning_rate": 9.73465064747553e-05,
      "loss": 6.7878,
      "step": 7
    },
    {
      "epoch": 0.06601340897369778,
      "grad_norm": 0.21119892597198486,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.7692,
      "step": 8
    },
    {
      "epoch": 0.07426508509541001,
      "grad_norm": 0.21528777480125427,
      "learning_rate": 9.484363707663442e-05,
      "loss": 6.7501,
      "step": 9
    },
    {
      "epoch": 0.08251676121712223,
      "grad_norm": 0.25786951184272766,
      "learning_rate": 9.330127018922194e-05,
      "loss": 6.7128,
      "step": 10
    },
    {
      "epoch": 0.09076843733883445,
      "grad_norm": 0.2376754879951477,
      "learning_rate": 9.157348061512727e-05,
      "loss": 6.6128,
      "step": 11
    },
    {
      "epoch": 0.09902011346054668,
      "grad_norm": 0.30647096037864685,
      "learning_rate": 8.966766701456177e-05,
      "loss": 6.3771,
      "step": 12
    },
    {
      "epoch": 0.1072717895822589,
      "grad_norm": 0.1863364428281784,
      "learning_rate": 8.759199037394887e-05,
      "loss": 6.8238,
      "step": 13
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 0.19649076461791992,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.8565,
      "step": 14
    },
    {
      "epoch": 0.12377514182568335,
      "grad_norm": 0.2133394181728363,
      "learning_rate": 8.296729075500344e-05,
      "loss": 6.8416,
      "step": 15
    },
    {
      "epoch": 0.13202681794739557,
      "grad_norm": 0.20794269442558289,
      "learning_rate": 8.043807145043604e-05,
      "loss": 6.8263,
      "step": 16
    },
    {
      "epoch": 0.14027849406910778,
      "grad_norm": 0.19656820595264435,
      "learning_rate": 7.777851165098012e-05,
      "loss": 6.8141,
      "step": 17
    },
    {
      "epoch": 0.14853017019082002,
      "grad_norm": 0.19225075840950012,
      "learning_rate": 7.500000000000001e-05,
      "loss": 6.7973,
      "step": 18
    },
    {
      "epoch": 0.15678184631253222,
      "grad_norm": 0.21045391261577606,
      "learning_rate": 7.211443451095007e-05,
      "loss": 6.7831,
      "step": 19
    },
    {
      "epoch": 0.16503352243424446,
      "grad_norm": 0.21318703889846802,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.7698,
      "step": 20
    },
    {
      "epoch": 0.17328519855595667,
      "grad_norm": 0.2291601151227951,
      "learning_rate": 6.607197326515808e-05,
      "loss": 6.7493,
      "step": 21
    },
    {
      "epoch": 0.1815368746776689,
      "grad_norm": 0.24010586738586426,
      "learning_rate": 6.294095225512603e-05,
      "loss": 6.7229,
      "step": 22
    },
    {
      "epoch": 0.18978855079938112,
      "grad_norm": 0.24575382471084595,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 6.6626,
      "step": 23
    },
    {
      "epoch": 0.19804022692109335,
      "grad_norm": 0.2697991132736206,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 6.4914,
      "step": 24
    },
    {
      "epoch": 0.20629190304280556,
      "grad_norm": 0.30134379863739014,
      "learning_rate": 5.327015646150716e-05,
      "loss": 6.1847,
      "step": 25
    },
    {
      "epoch": 0.20629190304280556,
      "eval_loss": 6.917348861694336,
      "eval_runtime": 0.7988,
      "eval_samples_per_second": 1022.73,
      "eval_steps_per_second": 128.937,
      "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": 2852978688000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}