{
  "best_metric": 0.09762722998857498,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.1328462304882099,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005313849219528396,
      "grad_norm": 23.735429763793945,
      "learning_rate": 5e-05,
      "loss": 10.8963,
      "step": 1
    },
    {
      "epoch": 0.005313849219528396,
      "eval_loss": 11.031381607055664,
      "eval_runtime": 3.8477,
      "eval_samples_per_second": 12.995,
      "eval_steps_per_second": 3.379,
      "step": 1
    },
    {
      "epoch": 0.010627698439056792,
      "grad_norm": 23.870187759399414,
      "learning_rate": 0.0001,
      "loss": 11.0229,
      "step": 2
    },
    {
      "epoch": 0.015941547658585187,
      "grad_norm": 27.29892349243164,
      "learning_rate": 9.990365154573717e-05,
      "loss": 9.6982,
      "step": 3
    },
    {
      "epoch": 0.021255396878113585,
      "grad_norm": 23.930377960205078,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.9348,
      "step": 4
    },
    {
      "epoch": 0.02656924609764198,
      "grad_norm": 6.183684349060059,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.9608,
      "step": 5
    },
    {
      "epoch": 0.031883095317170373,
      "grad_norm": 11.842926025390625,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.0285,
      "step": 6
    },
    {
      "epoch": 0.03719694453669877,
      "grad_norm": 1.7357816696166992,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.7126,
      "step": 7
    },
    {
      "epoch": 0.04251079375622717,
      "grad_norm": 1.9517472982406616,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.7058,
      "step": 8
    },
    {
      "epoch": 0.04782464297575556,
      "grad_norm": 2.457921266555786,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.7232,
      "step": 9
    },
    {
      "epoch": 0.05313849219528396,
      "grad_norm": 1.7132893800735474,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.6842,
      "step": 10
    },
    {
      "epoch": 0.058452341414812356,
      "grad_norm": 1.8711906671524048,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.6185,
      "step": 11
    },
    {
      "epoch": 0.06376619063434075,
      "grad_norm": 3.989243507385254,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.5226,
      "step": 12
    },
    {
      "epoch": 0.06908003985386915,
      "grad_norm": 5.848659515380859,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.4455,
      "step": 13
    },
    {
      "epoch": 0.07439388907339754,
      "grad_norm": 3.6532959938049316,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.3719,
      "step": 14
    },
    {
      "epoch": 0.07970773829292593,
      "grad_norm": 5.245995044708252,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.3358,
      "step": 15
    },
    {
      "epoch": 0.08502158751245434,
      "grad_norm": 2.672791004180908,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.3515,
      "step": 16
    },
    {
      "epoch": 0.09033543673198273,
      "grad_norm": 3.914903163909912,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.3683,
      "step": 17
    },
    {
      "epoch": 0.09564928595151112,
      "grad_norm": 2.5333163738250732,
      "learning_rate": 7.75e-05,
      "loss": 0.3497,
      "step": 18
    },
    {
      "epoch": 0.10096313517103953,
      "grad_norm": 2.873622417449951,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.2874,
      "step": 19
    },
    {
      "epoch": 0.10627698439056792,
      "grad_norm": 2.7790403366088867,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.2946,
      "step": 20
    },
    {
      "epoch": 0.11159083361009631,
      "grad_norm": 2.632528066635132,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.2481,
      "step": 21
    },
    {
      "epoch": 0.11690468282962471,
      "grad_norm": 1.862103819847107,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.2376,
      "step": 22
    },
    {
      "epoch": 0.1222185320491531,
      "grad_norm": 2.213386058807373,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.2337,
      "step": 23
    },
    {
      "epoch": 0.1275323812686815,
      "grad_norm": 2.59668231010437,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.2321,
      "step": 24
    },
    {
      "epoch": 0.1328462304882099,
      "grad_norm": 2.26269268989563,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.168,
      "step": 25
    },
    {
      "epoch": 0.1328462304882099,
      "eval_loss": 0.09762722998857498,
      "eval_runtime": 3.4978,
      "eval_samples_per_second": 14.295,
      "eval_steps_per_second": 3.717,
      "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}