{
  "best_metric": 2.6829404830932617,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0019504900606277327,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.501633535425775e-05,
      "eval_loss": 4.043483734130859,
      "eval_runtime": 359.3057,
      "eval_samples_per_second": 18.026,
      "eval_steps_per_second": 9.015,
      "step": 1
    },
    {
      "epoch": 0.00019504900606277329,
      "grad_norm": 4.626938343048096,
      "learning_rate": 6e-05,
      "loss": 3.9159,
      "step": 3
    },
    {
      "epoch": 0.00032508167677128876,
      "eval_loss": 3.4318971633911133,
      "eval_runtime": 361.5469,
      "eval_samples_per_second": 17.915,
      "eval_steps_per_second": 8.959,
      "step": 5
    },
    {
      "epoch": 0.00039009801212554657,
      "grad_norm": 3.844383478164673,
      "learning_rate": 0.00012,
      "loss": 3.6589,
      "step": 6
    },
    {
      "epoch": 0.0005851470181883198,
      "grad_norm": 3.1320598125457764,
      "learning_rate": 0.00018,
      "loss": 2.9485,
      "step": 9
    },
    {
      "epoch": 0.0006501633535425775,
      "eval_loss": 2.923651695251465,
      "eval_runtime": 360.2273,
      "eval_samples_per_second": 17.98,
      "eval_steps_per_second": 8.992,
      "step": 10
    },
    {
      "epoch": 0.0007801960242510931,
      "grad_norm": 3.082592725753784,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.1049,
      "step": 12
    },
    {
      "epoch": 0.0009752450303138663,
      "grad_norm": 1.2514885663986206,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.7436,
      "step": 15
    },
    {
      "epoch": 0.0009752450303138663,
      "eval_loss": 2.748525381088257,
      "eval_runtime": 360.1464,
      "eval_samples_per_second": 17.984,
      "eval_steps_per_second": 8.994,
      "step": 15
    },
    {
      "epoch": 0.0011702940363766397,
      "grad_norm": 1.15325129032135,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.6917,
      "step": 18
    },
    {
      "epoch": 0.001300326707085155,
      "eval_loss": 2.705315351486206,
      "eval_runtime": 359.9377,
      "eval_samples_per_second": 17.995,
      "eval_steps_per_second": 8.999,
      "step": 20
    },
    {
      "epoch": 0.0013653430424394129,
      "grad_norm": 1.1571309566497803,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.6742,
      "step": 21
    },
    {
      "epoch": 0.0015603920485021863,
      "grad_norm": 1.0296660661697388,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.6416,
      "step": 24
    },
    {
      "epoch": 0.0016254083838564439,
      "eval_loss": 2.6872406005859375,
      "eval_runtime": 359.9275,
      "eval_samples_per_second": 17.995,
      "eval_steps_per_second": 8.999,
      "step": 25
    },
    {
      "epoch": 0.0017554410545649595,
      "grad_norm": 0.9758339524269104,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.6216,
      "step": 27
    },
    {
      "epoch": 0.0019504900606277327,
      "grad_norm": 1.0820367336273193,
      "learning_rate": 0.0,
      "loss": 2.7111,
      "step": 30
    },
    {
      "epoch": 0.0019504900606277327,
      "eval_loss": 2.6829404830932617,
      "eval_runtime": 360.0892,
      "eval_samples_per_second": 17.987,
      "eval_steps_per_second": 8.995,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2951326036131840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}