{
  "best_metric": 3.4557735919952393,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.9501187648456056,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03800475059382423,
      "grad_norm": 0.33629336953163147,
      "learning_rate": 5e-05,
      "loss": 3.669,
      "step": 1
    },
    {
      "epoch": 0.03800475059382423,
      "eval_loss": 3.8881068229675293,
      "eval_runtime": 2.4606,
      "eval_samples_per_second": 72.339,
      "eval_steps_per_second": 9.347,
      "step": 1
    },
    {
      "epoch": 0.07600950118764846,
      "grad_norm": 0.42253753542900085,
      "learning_rate": 0.0001,
      "loss": 3.6932,
      "step": 2
    },
    {
      "epoch": 0.11401425178147269,
      "grad_norm": 0.4703884422779083,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.6224,
      "step": 3
    },
    {
      "epoch": 0.15201900237529692,
      "grad_norm": 0.5285553932189941,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.72,
      "step": 4
    },
    {
      "epoch": 0.19002375296912113,
      "grad_norm": 0.5211747884750366,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.7434,
      "step": 5
    },
    {
      "epoch": 0.22802850356294538,
      "grad_norm": 0.5990889072418213,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.9806,
      "step": 6
    },
    {
      "epoch": 0.2660332541567696,
      "grad_norm": 0.28917452692985535,
      "learning_rate": 9.73465064747553e-05,
      "loss": 3.6418,
      "step": 7
    },
    {
      "epoch": 0.30403800475059384,
      "grad_norm": 0.3966493308544159,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.571,
      "step": 8
    },
    {
      "epoch": 0.342042755344418,
      "grad_norm": 0.4186142385005951,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.5154,
      "step": 9
    },
    {
      "epoch": 0.38004750593824227,
      "grad_norm": 0.4471973776817322,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.4972,
      "step": 10
    },
    {
      "epoch": 0.4180522565320665,
      "grad_norm": 0.5375720262527466,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.5775,
      "step": 11
    },
    {
      "epoch": 0.45605700712589076,
      "grad_norm": 0.5469061136245728,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.6396,
      "step": 12
    },
    {
      "epoch": 0.49406175771971494,
      "grad_norm": 0.7819376587867737,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.9765,
      "step": 13
    },
    {
      "epoch": 0.5320665083135392,
      "grad_norm": 0.3394373655319214,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.5144,
      "step": 14
    },
    {
      "epoch": 0.5700712589073634,
      "grad_norm": 0.3765534460544586,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.4602,
      "step": 15
    },
    {
      "epoch": 0.6080760095011877,
      "grad_norm": 0.36004090309143066,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.3679,
      "step": 16
    },
    {
      "epoch": 0.6460807600950119,
      "grad_norm": 0.40536168217658997,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.402,
      "step": 17
    },
    {
      "epoch": 0.684085510688836,
      "grad_norm": 0.43434950709342957,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2927,
      "step": 18
    },
    {
      "epoch": 0.7220902612826603,
      "grad_norm": 0.4626035988330841,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.6605,
      "step": 19
    },
    {
      "epoch": 0.7600950118764845,
      "grad_norm": 0.38905563950538635,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.4843,
      "step": 20
    },
    {
      "epoch": 0.7980997624703088,
      "grad_norm": 0.4623677432537079,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.4253,
      "step": 21
    },
    {
      "epoch": 0.836104513064133,
      "grad_norm": 0.5135887861251831,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.3537,
      "step": 22
    },
    {
      "epoch": 0.8741092636579573,
      "grad_norm": 0.48013439774513245,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.4339,
      "step": 23
    },
    {
      "epoch": 0.9121140142517815,
      "grad_norm": 0.40351372957229614,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.1647,
      "step": 24
    },
    {
      "epoch": 0.9501187648456056,
      "grad_norm": 0.44421958923339844,
      "learning_rate": 5.327015646150716e-05,
      "loss": 3.4674,
      "step": 25
    },
    {
      "epoch": 0.9501187648456056,
      "eval_loss": 3.4557735919952393,
      "eval_runtime": 2.4794,
      "eval_samples_per_second": 71.79,
      "eval_steps_per_second": 9.276,
      "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": 5.337414377668608e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}