{
  "best_metric": 0.789313018321991,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7326007326007326,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 42.63615417480469,
      "learning_rate": 5e-05,
      "loss": 10.8108,
      "step": 1
    },
    {
      "epoch": 0.029304029304029304,
      "eval_loss": 11.66943359375,
      "eval_runtime": 12.0274,
      "eval_samples_per_second": 19.123,
      "eval_steps_per_second": 2.411,
      "step": 1
    },
    {
      "epoch": 0.05860805860805861,
      "grad_norm": 43.70536804199219,
      "learning_rate": 0.0001,
      "loss": 11.4368,
      "step": 2
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 30.874406814575195,
      "learning_rate": 9.989294616193017e-05,
      "loss": 8.1072,
      "step": 3
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 17.766359329223633,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.914,
      "step": 4
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 10.942605972290039,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.2661,
      "step": 5
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 4.077508926391602,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1809,
      "step": 6
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 4.200634479522705,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.0111,
      "step": 7
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 2.5703258514404297,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9798,
      "step": 8
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 1.4646650552749634,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.8646,
      "step": 9
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 1.0245696306228638,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7594,
      "step": 10
    },
    {
      "epoch": 0.32234432234432236,
      "grad_norm": 0.7607440948486328,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.7369,
      "step": 11
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 1.600371241569519,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.8084,
      "step": 12
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.577329397201538,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.7607,
      "step": 13
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 1.0018422603607178,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8165,
      "step": 14
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.8424701690673828,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8129,
      "step": 15
    },
    {
      "epoch": 0.46886446886446886,
      "grad_norm": 0.5086039900779724,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8195,
      "step": 16
    },
    {
      "epoch": 0.4981684981684982,
      "grad_norm": 0.6842309236526489,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8075,
      "step": 17
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.6705095767974854,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7247,
      "step": 18
    },
    {
      "epoch": 0.5567765567765568,
      "grad_norm": 0.24981459975242615,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.741,
      "step": 19
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.3129333257675171,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7393,
      "step": 20
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.7338513135910034,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.7904,
      "step": 21
    },
    {
      "epoch": 0.6446886446886447,
      "grad_norm": 1.3784418106079102,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8909,
      "step": 22
    },
    {
      "epoch": 0.673992673992674,
      "grad_norm": 0.8394548296928406,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.8305,
      "step": 23
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.29354768991470337,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.8116,
      "step": 24
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 0.3640207350254059,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.8095,
      "step": 25
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 0.789313018321991,
      "eval_runtime": 12.0233,
      "eval_samples_per_second": 19.13,
      "eval_steps_per_second": 2.412,
      "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": 3.315690861756416e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}