{
  "best_metric": 0.543145477771759,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.13311148086522462,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005324459234608985,
      "grad_norm": 4.088531970977783,
      "learning_rate": 5e-05,
      "loss": 5.1662,
      "step": 1
    },
    {
      "epoch": 0.005324459234608985,
      "eval_loss": 5.456347465515137,
      "eval_runtime": 37.1933,
      "eval_samples_per_second": 34.011,
      "eval_steps_per_second": 4.275,
      "step": 1
    },
    {
      "epoch": 0.01064891846921797,
      "grad_norm": 4.171426773071289,
      "learning_rate": 0.0001,
      "loss": 4.9325,
      "step": 2
    },
    {
      "epoch": 0.015973377703826955,
      "grad_norm": 4.523000717163086,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.6926,
      "step": 3
    },
    {
      "epoch": 0.02129783693843594,
      "grad_norm": 4.592573642730713,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.1592,
      "step": 4
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 4.462768077850342,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.4883,
      "step": 5
    },
    {
      "epoch": 0.03194675540765391,
      "grad_norm": 3.6760053634643555,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.7529,
      "step": 6
    },
    {
      "epoch": 0.03727121464226289,
      "grad_norm": 3.266521692276001,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.3894,
      "step": 7
    },
    {
      "epoch": 0.04259567387687188,
      "grad_norm": 2.4213409423828125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0191,
      "step": 8
    },
    {
      "epoch": 0.04792013311148086,
      "grad_norm": 2.726236581802368,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9415,
      "step": 9
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 3.0345311164855957,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8787,
      "step": 10
    },
    {
      "epoch": 0.05856905158069883,
      "grad_norm": 3.6178336143493652,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.0712,
      "step": 11
    },
    {
      "epoch": 0.06389351081530782,
      "grad_norm": 3.8217687606811523,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.015,
      "step": 12
    },
    {
      "epoch": 0.06921797004991681,
      "grad_norm": 3.0923008918762207,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.7464,
      "step": 13
    },
    {
      "epoch": 0.07454242928452579,
      "grad_norm": 3.973829984664917,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3454,
      "step": 14
    },
    {
      "epoch": 0.07986688851913477,
      "grad_norm": 3.0622823238372803,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2509,
      "step": 15
    },
    {
      "epoch": 0.08519134775374376,
      "grad_norm": 2.638644218444824,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.1201,
      "step": 16
    },
    {
      "epoch": 0.09051580698835275,
      "grad_norm": 2.270491123199463,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.0201,
      "step": 17
    },
    {
      "epoch": 0.09584026622296173,
      "grad_norm": 2.1647579669952393,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9262,
      "step": 18
    },
    {
      "epoch": 0.10116472545757071,
      "grad_norm": 1.9108171463012695,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7262,
      "step": 19
    },
    {
      "epoch": 0.1064891846921797,
      "grad_norm": 1.6335346698760986,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7414,
      "step": 20
    },
    {
      "epoch": 0.11181364392678869,
      "grad_norm": 1.5329469442367554,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6769,
      "step": 21
    },
    {
      "epoch": 0.11713810316139767,
      "grad_norm": 1.835329532623291,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.5839,
      "step": 22
    },
    {
      "epoch": 0.12246256239600666,
      "grad_norm": 1.8949499130249023,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.5463,
      "step": 23
    },
    {
      "epoch": 0.12778702163061564,
      "grad_norm": 2.221313238143921,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6961,
      "step": 24
    },
    {
      "epoch": 0.13311148086522462,
      "grad_norm": 3.7558910846710205,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.018,
      "step": 25
    },
    {
      "epoch": 0.13311148086522462,
      "eval_loss": 0.543145477771759,
      "eval_runtime": 37.5153,
      "eval_samples_per_second": 33.72,
      "eval_steps_per_second": 4.238,
      "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": 2.66009604784128e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}