{
  "best_metric": 7.021544933319092,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0839278220730172,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003357112882920688,
      "grad_norm": 2.5430850982666016,
      "learning_rate": 5e-05,
      "loss": 7.832,
      "step": 1
    },
    {
      "epoch": 0.003357112882920688,
      "eval_loss": 7.705937385559082,
      "eval_runtime": 0.7486,
      "eval_samples_per_second": 66.791,
      "eval_steps_per_second": 17.366,
      "step": 1
    },
    {
      "epoch": 0.006714225765841376,
      "grad_norm": 2.514496088027954,
      "learning_rate": 0.0001,
      "loss": 7.5496,
      "step": 2
    },
    {
      "epoch": 0.010071338648762064,
      "grad_norm": 2.5135130882263184,
      "learning_rate": 9.990365154573717e-05,
      "loss": 7.4873,
      "step": 3
    },
    {
      "epoch": 0.013428451531682753,
      "grad_norm": 2.626904249191284,
      "learning_rate": 9.961501876182148e-05,
      "loss": 7.4043,
      "step": 4
    },
    {
      "epoch": 0.01678556441460344,
      "grad_norm": 2.5633034706115723,
      "learning_rate": 9.913533761814537e-05,
      "loss": 7.3291,
      "step": 5
    },
    {
      "epoch": 0.020142677297524128,
      "grad_norm": 2.401721239089966,
      "learning_rate": 9.846666218300807e-05,
      "loss": 7.2759,
      "step": 6
    },
    {
      "epoch": 0.02349979018044482,
      "grad_norm": 2.834110975265503,
      "learning_rate": 9.761185582727977e-05,
      "loss": 7.3426,
      "step": 7
    },
    {
      "epoch": 0.026856903063365505,
      "grad_norm": 2.8407764434814453,
      "learning_rate": 9.657457896300791e-05,
      "loss": 7.1319,
      "step": 8
    },
    {
      "epoch": 0.030214015946286196,
      "grad_norm": 3.355074405670166,
      "learning_rate": 9.535927336897098e-05,
      "loss": 7.2785,
      "step": 9
    },
    {
      "epoch": 0.03357112882920688,
      "grad_norm": 3.531038284301758,
      "learning_rate": 9.397114317029975e-05,
      "loss": 7.3777,
      "step": 10
    },
    {
      "epoch": 0.03692824171212757,
      "grad_norm": 4.6855058670043945,
      "learning_rate": 9.241613255361455e-05,
      "loss": 7.2524,
      "step": 11
    },
    {
      "epoch": 0.040285354595048256,
      "grad_norm": 4.948916435241699,
      "learning_rate": 9.070090031310558e-05,
      "loss": 7.6879,
      "step": 12
    },
    {
      "epoch": 0.043642467477968946,
      "grad_norm": 1.8742164373397827,
      "learning_rate": 8.883279133655399e-05,
      "loss": 7.8864,
      "step": 13
    },
    {
      "epoch": 0.04699958036088964,
      "grad_norm": 1.335532546043396,
      "learning_rate": 8.681980515339464e-05,
      "loss": 7.174,
      "step": 14
    },
    {
      "epoch": 0.05035669324381032,
      "grad_norm": 1.3148480653762817,
      "learning_rate": 8.467056167950311e-05,
      "loss": 7.0952,
      "step": 15
    },
    {
      "epoch": 0.05371380612673101,
      "grad_norm": 1.2804148197174072,
      "learning_rate": 8.239426430539243e-05,
      "loss": 7.0444,
      "step": 16
    },
    {
      "epoch": 0.0570709190096517,
      "grad_norm": 1.2791334390640259,
      "learning_rate": 8.000066048588211e-05,
      "loss": 7.0529,
      "step": 17
    },
    {
      "epoch": 0.06042803189257239,
      "grad_norm": 1.304823637008667,
      "learning_rate": 7.75e-05,
      "loss": 6.9528,
      "step": 18
    },
    {
      "epoch": 0.06378514477549307,
      "grad_norm": 1.479640245437622,
      "learning_rate": 7.490299105985507e-05,
      "loss": 7.1333,
      "step": 19
    },
    {
      "epoch": 0.06714225765841376,
      "grad_norm": 1.6118611097335815,
      "learning_rate": 7.222075445642904e-05,
      "loss": 7.0252,
      "step": 20
    },
    {
      "epoch": 0.07049937054133446,
      "grad_norm": 2.0745763778686523,
      "learning_rate": 6.946477593864228e-05,
      "loss": 6.8819,
      "step": 21
    },
    {
      "epoch": 0.07385648342425515,
      "grad_norm": 2.281806230545044,
      "learning_rate": 6.664685702961344e-05,
      "loss": 6.8558,
      "step": 22
    },
    {
      "epoch": 0.07721359630717582,
      "grad_norm": 2.6327695846557617,
      "learning_rate": 6.377906449072578e-05,
      "loss": 7.0346,
      "step": 23
    },
    {
      "epoch": 0.08057070919009651,
      "grad_norm": 3.486109495162964,
      "learning_rate": 6.087367864990233e-05,
      "loss": 7.0771,
      "step": 24
    },
    {
      "epoch": 0.0839278220730172,
      "grad_norm": 5.5846266746521,
      "learning_rate": 5.794314081535644e-05,
      "loss": 7.0188,
      "step": 25
    },
    {
      "epoch": 0.0839278220730172,
      "eval_loss": 7.021544933319092,
      "eval_runtime": 0.7649,
      "eval_samples_per_second": 65.364,
      "eval_steps_per_second": 16.995,
      "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": 116006898892800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}