{
  "best_metric": 1.1073193550109863,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.012519953676171399,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005007981470468559,
      "grad_norm": 7.2735490798950195,
      "learning_rate": 5e-05,
      "loss": 27.6765,
      "step": 1
    },
    {
      "epoch": 0.0005007981470468559,
      "eval_loss": 1.6915992498397827,
      "eval_runtime": 3.9192,
      "eval_samples_per_second": 12.758,
      "eval_steps_per_second": 3.317,
      "step": 1
    },
    {
      "epoch": 0.0010015962940937118,
      "grad_norm": 9.645286560058594,
      "learning_rate": 0.0001,
      "loss": 28.8861,
      "step": 2
    },
    {
      "epoch": 0.0015023944411405679,
      "grad_norm": 6.561025619506836,
      "learning_rate": 9.990365154573717e-05,
      "loss": 23.5428,
      "step": 3
    },
    {
      "epoch": 0.0020031925881874237,
      "grad_norm": 6.4700422286987305,
      "learning_rate": 9.961501876182148e-05,
      "loss": 23.4867,
      "step": 4
    },
    {
      "epoch": 0.0025039907352342795,
      "grad_norm": 6.575279712677002,
      "learning_rate": 9.913533761814537e-05,
      "loss": 22.8772,
      "step": 5
    },
    {
      "epoch": 0.0030047888822811357,
      "grad_norm": 5.742631912231445,
      "learning_rate": 9.846666218300807e-05,
      "loss": 22.2415,
      "step": 6
    },
    {
      "epoch": 0.0035055870293279915,
      "grad_norm": 5.252403259277344,
      "learning_rate": 9.761185582727977e-05,
      "loss": 21.6715,
      "step": 7
    },
    {
      "epoch": 0.004006385176374847,
      "grad_norm": 4.608903884887695,
      "learning_rate": 9.657457896300791e-05,
      "loss": 20.1559,
      "step": 8
    },
    {
      "epoch": 0.004507183323421703,
      "grad_norm": 4.294509410858154,
      "learning_rate": 9.535927336897098e-05,
      "loss": 22.0346,
      "step": 9
    },
    {
      "epoch": 0.005007981470468559,
      "grad_norm": 5.621428966522217,
      "learning_rate": 9.397114317029975e-05,
      "loss": 21.4893,
      "step": 10
    },
    {
      "epoch": 0.005508779617515415,
      "grad_norm": 5.655107498168945,
      "learning_rate": 9.241613255361455e-05,
      "loss": 18.073,
      "step": 11
    },
    {
      "epoch": 0.0060095777645622715,
      "grad_norm": 4.809823036193848,
      "learning_rate": 9.070090031310558e-05,
      "loss": 16.1442,
      "step": 12
    },
    {
      "epoch": 0.006510375911609127,
      "grad_norm": 8.046764373779297,
      "learning_rate": 8.883279133655399e-05,
      "loss": 21.9141,
      "step": 13
    },
    {
      "epoch": 0.007011174058655983,
      "grad_norm": 7.144588470458984,
      "learning_rate": 8.681980515339464e-05,
      "loss": 22.6744,
      "step": 14
    },
    {
      "epoch": 0.007511972205702839,
      "grad_norm": 5.577089786529541,
      "learning_rate": 8.467056167950311e-05,
      "loss": 19.4013,
      "step": 15
    },
    {
      "epoch": 0.008012770352749695,
      "grad_norm": 4.5405731201171875,
      "learning_rate": 8.239426430539243e-05,
      "loss": 17.4941,
      "step": 16
    },
    {
      "epoch": 0.00851356849979655,
      "grad_norm": 5.8107147216796875,
      "learning_rate": 8.000066048588211e-05,
      "loss": 18.2896,
      "step": 17
    },
    {
      "epoch": 0.009014366646843406,
      "grad_norm": 4.332961082458496,
      "learning_rate": 7.75e-05,
      "loss": 18.1127,
      "step": 18
    },
    {
      "epoch": 0.009515164793890262,
      "grad_norm": 4.734344959259033,
      "learning_rate": 7.490299105985507e-05,
      "loss": 18.5457,
      "step": 19
    },
    {
      "epoch": 0.010015962940937118,
      "grad_norm": 4.264060020446777,
      "learning_rate": 7.222075445642904e-05,
      "loss": 18.2222,
      "step": 20
    },
    {
      "epoch": 0.010516761087983974,
      "grad_norm": 3.800395965576172,
      "learning_rate": 6.946477593864228e-05,
      "loss": 18.5526,
      "step": 21
    },
    {
      "epoch": 0.01101755923503083,
      "grad_norm": 3.4941272735595703,
      "learning_rate": 6.664685702961344e-05,
      "loss": 17.8441,
      "step": 22
    },
    {
      "epoch": 0.011518357382077687,
      "grad_norm": 3.7239904403686523,
      "learning_rate": 6.377906449072578e-05,
      "loss": 18.2648,
      "step": 23
    },
    {
      "epoch": 0.012019155529124543,
      "grad_norm": 3.749605655670166,
      "learning_rate": 6.087367864990233e-05,
      "loss": 17.3797,
      "step": 24
    },
    {
      "epoch": 0.012519953676171399,
      "grad_norm": 6.037412643432617,
      "learning_rate": 5.794314081535644e-05,
      "loss": 18.479,
      "step": 25
    },
    {
      "epoch": 0.012519953676171399,
      "eval_loss": 1.1073193550109863,
      "eval_runtime": 3.9929,
      "eval_samples_per_second": 12.522,
      "eval_steps_per_second": 3.256,
      "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": 2.9582754301188506e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}