{
  "best_metric": 1.6654880046844482,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.45300113250283125,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01812004530011325,
      "grad_norm": 3.353853464126587,
      "learning_rate": 5e-05,
      "loss": 2.8413,
      "step": 1
    },
    {
      "epoch": 0.01812004530011325,
      "eval_loss": 3.0799570083618164,
      "eval_runtime": 5.4479,
      "eval_samples_per_second": 68.283,
      "eval_steps_per_second": 8.627,
      "step": 1
    },
    {
      "epoch": 0.0362400906002265,
      "grad_norm": 3.207507848739624,
      "learning_rate": 0.0001,
      "loss": 2.8953,
      "step": 2
    },
    {
      "epoch": 0.05436013590033975,
      "grad_norm": 3.2653355598449707,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.8512,
      "step": 3
    },
    {
      "epoch": 0.072480181200453,
      "grad_norm": 2.8341968059539795,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.5232,
      "step": 4
    },
    {
      "epoch": 0.09060022650056625,
      "grad_norm": 2.4388608932495117,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.4585,
      "step": 5
    },
    {
      "epoch": 0.1087202718006795,
      "grad_norm": 2.7728500366210938,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.2371,
      "step": 6
    },
    {
      "epoch": 0.12684031710079274,
      "grad_norm": 2.378784418106079,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.2098,
      "step": 7
    },
    {
      "epoch": 0.144960362400906,
      "grad_norm": 2.1482527256011963,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0943,
      "step": 8
    },
    {
      "epoch": 0.16308040770101925,
      "grad_norm": 1.8638383150100708,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9817,
      "step": 9
    },
    {
      "epoch": 0.1812004530011325,
      "grad_norm": 2.0654704570770264,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8742,
      "step": 10
    },
    {
      "epoch": 0.19932049830124576,
      "grad_norm": 2.1612489223480225,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.866,
      "step": 11
    },
    {
      "epoch": 0.217440543601359,
      "grad_norm": 2.3690574169158936,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.8765,
      "step": 12
    },
    {
      "epoch": 0.23556058890147225,
      "grad_norm": 2.7848353385925293,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.9321,
      "step": 13
    },
    {
      "epoch": 0.2536806342015855,
      "grad_norm": 2.7931432723999023,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9226,
      "step": 14
    },
    {
      "epoch": 0.2718006795016987,
      "grad_norm": 1.4447989463806152,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.8,
      "step": 15
    },
    {
      "epoch": 0.289920724801812,
      "grad_norm": 1.5375866889953613,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7758,
      "step": 16
    },
    {
      "epoch": 0.30804077010192527,
      "grad_norm": 1.5753406286239624,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.7916,
      "step": 17
    },
    {
      "epoch": 0.3261608154020385,
      "grad_norm": 1.5804219245910645,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8195,
      "step": 18
    },
    {
      "epoch": 0.34428086070215175,
      "grad_norm": 1.3650116920471191,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.7344,
      "step": 19
    },
    {
      "epoch": 0.362400906002265,
      "grad_norm": 1.371211051940918,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6936,
      "step": 20
    },
    {
      "epoch": 0.38052095130237823,
      "grad_norm": 1.268407940864563,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.7248,
      "step": 21
    },
    {
      "epoch": 0.3986409966024915,
      "grad_norm": 1.227617621421814,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6816,
      "step": 22
    },
    {
      "epoch": 0.41676104190260477,
      "grad_norm": 1.3453476428985596,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5177,
      "step": 23
    },
    {
      "epoch": 0.434881087202718,
      "grad_norm": 1.6464775800704956,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.6804,
      "step": 24
    },
    {
      "epoch": 0.45300113250283125,
      "grad_norm": 2.041501522064209,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.6316,
      "step": 25
    },
    {
      "epoch": 0.45300113250283125,
      "eval_loss": 1.6654880046844482,
      "eval_runtime": 5.4794,
      "eval_samples_per_second": 67.891,
      "eval_steps_per_second": 8.578,
      "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": 1.47650456322048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}