{
  "best_metric": 4.178318977355957,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0733810310034856,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002935241240139424,
      "grad_norm": 1.0239430665969849,
      "learning_rate": 5e-05,
      "loss": 3.8981,
      "step": 1
    },
    {
      "epoch": 0.002935241240139424,
      "eval_loss": 5.815672874450684,
      "eval_runtime": 14.0337,
      "eval_samples_per_second": 163.606,
      "eval_steps_per_second": 20.451,
      "step": 1
    },
    {
      "epoch": 0.005870482480278848,
      "grad_norm": 1.9530309438705444,
      "learning_rate": 0.0001,
      "loss": 4.5273,
      "step": 2
    },
    {
      "epoch": 0.008805723720418272,
      "grad_norm": 1.8931856155395508,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.7057,
      "step": 3
    },
    {
      "epoch": 0.011740964960557695,
      "grad_norm": 2.567333221435547,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.7502,
      "step": 4
    },
    {
      "epoch": 0.01467620620069712,
      "grad_norm": 1.4395949840545654,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.8912,
      "step": 5
    },
    {
      "epoch": 0.017611447440836543,
      "grad_norm": 1.5201845169067383,
      "learning_rate": 9.829629131445342e-05,
      "loss": 5.056,
      "step": 6
    },
    {
      "epoch": 0.020546688680975967,
      "grad_norm": 1.8026448488235474,
      "learning_rate": 9.73465064747553e-05,
      "loss": 5.1448,
      "step": 7
    },
    {
      "epoch": 0.02348192992111539,
      "grad_norm": 1.9539623260498047,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.1671,
      "step": 8
    },
    {
      "epoch": 0.026417171161254815,
      "grad_norm": 2.1242480278015137,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.4479,
      "step": 9
    },
    {
      "epoch": 0.02935241240139424,
      "grad_norm": 2.840369701385498,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.4989,
      "step": 10
    },
    {
      "epoch": 0.032287653641533666,
      "grad_norm": 3.428213357925415,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.7564,
      "step": 11
    },
    {
      "epoch": 0.035222894881673086,
      "grad_norm": 2.512089967727661,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.7054,
      "step": 12
    },
    {
      "epoch": 0.038158136121812514,
      "grad_norm": 0.8332175016403198,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.8813,
      "step": 13
    },
    {
      "epoch": 0.041093377361951934,
      "grad_norm": 1.1140429973602295,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.9291,
      "step": 14
    },
    {
      "epoch": 0.04402861860209136,
      "grad_norm": 1.1462697982788086,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.9426,
      "step": 15
    },
    {
      "epoch": 0.04696385984223078,
      "grad_norm": 1.049325704574585,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.8919,
      "step": 16
    },
    {
      "epoch": 0.04989910108237021,
      "grad_norm": 1.6786147356033325,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.1401,
      "step": 17
    },
    {
      "epoch": 0.05283434232250963,
      "grad_norm": 1.5152158737182617,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.3537,
      "step": 18
    },
    {
      "epoch": 0.05576958356264906,
      "grad_norm": 1.5700799226760864,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.1969,
      "step": 19
    },
    {
      "epoch": 0.05870482480278848,
      "grad_norm": 1.7648606300354004,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.2697,
      "step": 20
    },
    {
      "epoch": 0.061640066042927905,
      "grad_norm": 2.7130236625671387,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.3922,
      "step": 21
    },
    {
      "epoch": 0.06457530728306733,
      "grad_norm": 2.8758461475372314,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.5291,
      "step": 22
    },
    {
      "epoch": 0.06751054852320675,
      "grad_norm": 2.656874418258667,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.454,
      "step": 23
    },
    {
      "epoch": 0.07044578976334617,
      "grad_norm": 2.822298288345337,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.6382,
      "step": 24
    },
    {
      "epoch": 0.0733810310034856,
      "grad_norm": 2.601090669631958,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.7237,
      "step": 25
    },
    {
      "epoch": 0.0733810310034856,
      "eval_loss": 4.178318977355957,
      "eval_runtime": 13.9396,
      "eval_samples_per_second": 164.711,
      "eval_steps_per_second": 20.589,
      "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": 5686862177894400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}