{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.004736109877749164,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018944439510996654,
      "grad_norm": 3.264355182647705,
      "learning_rate": 5e-05,
      "loss": 3.1199,
      "step": 1
    },
    {
      "epoch": 0.00018944439510996654,
      "eval_loss": NaN,
      "eval_runtime": 5.4634,
      "eval_samples_per_second": 9.152,
      "eval_steps_per_second": 9.152,
      "step": 1
    },
    {
      "epoch": 0.0003788887902199331,
      "grad_norm": 4.2460713386535645,
      "learning_rate": 0.0001,
      "loss": 3.2707,
      "step": 2
    },
    {
      "epoch": 0.0005683331853298996,
      "grad_norm": 3.954056978225708,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.0906,
      "step": 3
    },
    {
      "epoch": 0.0007577775804398662,
      "grad_norm": 3.6541836261749268,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.0425,
      "step": 4
    },
    {
      "epoch": 0.0009472219755498328,
      "grad_norm": 3.752495050430298,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.6957,
      "step": 5
    },
    {
      "epoch": 0.0011366663706597992,
      "grad_norm": 6.510428428649902,
      "learning_rate": 9.846666218300807e-05,
      "loss": 3.4514,
      "step": 6
    },
    {
      "epoch": 0.0013261107657697659,
      "grad_norm": 4.765082836151123,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.4753,
      "step": 7
    },
    {
      "epoch": 0.0015155551608797323,
      "grad_norm": 5.17319917678833,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.3487,
      "step": 8
    },
    {
      "epoch": 0.001704999555989699,
      "grad_norm": 6.483305931091309,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.8691,
      "step": 9
    },
    {
      "epoch": 0.0018944439510996656,
      "grad_norm": 5.846699237823486,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.6593,
      "step": 10
    },
    {
      "epoch": 0.002083888346209632,
      "grad_norm": 5.230606555938721,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.7168,
      "step": 11
    },
    {
      "epoch": 0.0022733327413195985,
      "grad_norm": 6.455722332000732,
      "learning_rate": 9.070090031310558e-05,
      "loss": 3.1,
      "step": 12
    },
    {
      "epoch": 0.0024627771364295653,
      "grad_norm": 3.4264791011810303,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.5991,
      "step": 13
    },
    {
      "epoch": 0.0026522215315395318,
      "grad_norm": 5.551114082336426,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.3684,
      "step": 14
    },
    {
      "epoch": 0.002841665926649498,
      "grad_norm": 8.614983558654785,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.4897,
      "step": 15
    },
    {
      "epoch": 0.0030311103217594646,
      "grad_norm": 5.568994045257568,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.6835,
      "step": 16
    },
    {
      "epoch": 0.0032205547168694315,
      "grad_norm": 6.834268093109131,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.7415,
      "step": 17
    },
    {
      "epoch": 0.003409999111979398,
      "grad_norm": 6.758293628692627,
      "learning_rate": 7.75e-05,
      "loss": 2.3813,
      "step": 18
    },
    {
      "epoch": 0.0035994435070893643,
      "grad_norm": 7.973887920379639,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.2036,
      "step": 19
    },
    {
      "epoch": 0.003788887902199331,
      "grad_norm": 5.2876996994018555,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.0686,
      "step": 20
    },
    {
      "epoch": 0.003978332297309297,
      "grad_norm": 0.0,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.004167776692419264,
      "grad_norm": 8.569087982177734,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.0977,
      "step": 22
    },
    {
      "epoch": 0.004357221087529231,
      "grad_norm": 5.491764068603516,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.2723,
      "step": 23
    },
    {
      "epoch": 0.004546665482639197,
      "grad_norm": 12.329565048217773,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.3138,
      "step": 24
    },
    {
      "epoch": 0.004736109877749164,
      "grad_norm": 13.543659210205078,
      "learning_rate": 5.794314081535644e-05,
      "loss": 2.946,
      "step": 25
    },
    {
      "epoch": 0.004736109877749164,
      "eval_loss": NaN,
      "eval_runtime": 5.4757,
      "eval_samples_per_second": 9.131,
      "eval_steps_per_second": 9.131,
      "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": 3691261408051200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}