{
  "best_metric": 2.1353137493133545,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.74487895716946,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0297951582867784,
      "grad_norm": 5.255026817321777,
      "learning_rate": 5e-05,
      "loss": 3.7359,
      "step": 1
    },
    {
      "epoch": 0.0297951582867784,
      "eval_loss": 4.239082336425781,
      "eval_runtime": 2.9162,
      "eval_samples_per_second": 77.842,
      "eval_steps_per_second": 9.945,
      "step": 1
    },
    {
      "epoch": 0.0595903165735568,
      "grad_norm": 6.154642581939697,
      "learning_rate": 0.0001,
      "loss": 4.0273,
      "step": 2
    },
    {
      "epoch": 0.0893854748603352,
      "grad_norm": 6.228611469268799,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.1499,
      "step": 3
    },
    {
      "epoch": 0.1191806331471136,
      "grad_norm": 5.3180623054504395,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.1502,
      "step": 4
    },
    {
      "epoch": 0.148975791433892,
      "grad_norm": 5.917397499084473,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.9261,
      "step": 5
    },
    {
      "epoch": 0.1787709497206704,
      "grad_norm": 5.27532434463501,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.4381,
      "step": 6
    },
    {
      "epoch": 0.2085661080074488,
      "grad_norm": 3.5522358417510986,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.8911,
      "step": 7
    },
    {
      "epoch": 0.2383612662942272,
      "grad_norm": 3.5772132873535156,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.2964,
      "step": 8
    },
    {
      "epoch": 0.2681564245810056,
      "grad_norm": 5.116891384124756,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.6329,
      "step": 9
    },
    {
      "epoch": 0.297951582867784,
      "grad_norm": 4.258176326751709,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.8402,
      "step": 10
    },
    {
      "epoch": 0.32774674115456237,
      "grad_norm": 3.147491931915283,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.6133,
      "step": 11
    },
    {
      "epoch": 0.3575418994413408,
      "grad_norm": 2.7201478481292725,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.5179,
      "step": 12
    },
    {
      "epoch": 0.38733705772811916,
      "grad_norm": 3.547346591949463,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.41,
      "step": 13
    },
    {
      "epoch": 0.4171322160148976,
      "grad_norm": 2.9750421047210693,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3717,
      "step": 14
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 2.5824129581451416,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.5694,
      "step": 15
    },
    {
      "epoch": 0.4767225325884544,
      "grad_norm": 2.871670722961426,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.909,
      "step": 16
    },
    {
      "epoch": 0.5065176908752328,
      "grad_norm": 2.181304931640625,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.238,
      "step": 17
    },
    {
      "epoch": 0.5363128491620112,
      "grad_norm": 2.4061832427978516,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3752,
      "step": 18
    },
    {
      "epoch": 0.5661080074487895,
      "grad_norm": 1.8905714750289917,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.2268,
      "step": 19
    },
    {
      "epoch": 0.595903165735568,
      "grad_norm": 1.8679147958755493,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1416,
      "step": 20
    },
    {
      "epoch": 0.6256983240223464,
      "grad_norm": 3.0014896392822266,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.0755,
      "step": 21
    },
    {
      "epoch": 0.6554934823091247,
      "grad_norm": 4.232528209686279,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.2963,
      "step": 22
    },
    {
      "epoch": 0.6852886405959032,
      "grad_norm": 2.2052879333496094,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8984,
      "step": 23
    },
    {
      "epoch": 0.7150837988826816,
      "grad_norm": 2.3755292892456055,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.8503,
      "step": 24
    },
    {
      "epoch": 0.74487895716946,
      "grad_norm": 2.062422513961792,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.0566,
      "step": 25
    },
    {
      "epoch": 0.74487895716946,
      "eval_loss": 2.1353137493133545,
      "eval_runtime": 2.9818,
      "eval_samples_per_second": 76.128,
      "eval_steps_per_second": 9.726,
      "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": 2.4694538849222656e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}