{
  "best_metric": 1.0340933799743652,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.004733307694583321,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018933230778333285,
      "grad_norm": 26.538738250732422,
      "learning_rate": 5e-05,
      "loss": 32.5509,
      "step": 1
    },
    {
      "epoch": 0.00018933230778333285,
      "eval_loss": 1.500787615776062,
      "eval_runtime": 13.2544,
      "eval_samples_per_second": 3.772,
      "eval_steps_per_second": 3.772,
      "step": 1
    },
    {
      "epoch": 0.0003786646155666657,
      "grad_norm": 29.488525390625,
      "learning_rate": 0.0001,
      "loss": 36.5778,
      "step": 2
    },
    {
      "epoch": 0.0005679969233499985,
      "grad_norm": 36.321956634521484,
      "learning_rate": 9.958086757163489e-05,
      "loss": 41.7217,
      "step": 3
    },
    {
      "epoch": 0.0007573292311333314,
      "grad_norm": 34.57386016845703,
      "learning_rate": 9.833127793065098e-05,
      "loss": 40.5149,
      "step": 4
    },
    {
      "epoch": 0.0009466615389166642,
      "grad_norm": 25.122905731201172,
      "learning_rate": 9.627450856774539e-05,
      "loss": 34.4766,
      "step": 5
    },
    {
      "epoch": 0.001135993846699997,
      "grad_norm": 26.807296752929688,
      "learning_rate": 9.3448873204592e-05,
      "loss": 36.1043,
      "step": 6
    },
    {
      "epoch": 0.00132532615448333,
      "grad_norm": 23.09415626525879,
      "learning_rate": 8.990700808169889e-05,
      "loss": 34.7522,
      "step": 7
    },
    {
      "epoch": 0.0015146584622666628,
      "grad_norm": 22.82590103149414,
      "learning_rate": 8.571489144483944e-05,
      "loss": 35.5535,
      "step": 8
    },
    {
      "epoch": 0.0017039907700499956,
      "grad_norm": 23.842958450317383,
      "learning_rate": 8.095061449516903e-05,
      "loss": 34.4606,
      "step": 9
    },
    {
      "epoch": 0.0018933230778333285,
      "grad_norm": 25.988386154174805,
      "learning_rate": 7.570292669790186e-05,
      "loss": 33.901,
      "step": 10
    },
    {
      "epoch": 0.002082655385616661,
      "grad_norm": 20.00263786315918,
      "learning_rate": 7.006958254769438e-05,
      "loss": 30.6267,
      "step": 11
    },
    {
      "epoch": 0.002271987693399994,
      "grad_norm": 22.96904754638672,
      "learning_rate": 6.415552058736854e-05,
      "loss": 30.5838,
      "step": 12
    },
    {
      "epoch": 0.002461320001183327,
      "grad_norm": 19.958139419555664,
      "learning_rate": 5.80709086014102e-05,
      "loss": 37.5163,
      "step": 13
    },
    {
      "epoch": 0.00265065230896666,
      "grad_norm": 20.89811134338379,
      "learning_rate": 5.192909139858981e-05,
      "loss": 35.0669,
      "step": 14
    },
    {
      "epoch": 0.0028399846167499925,
      "grad_norm": 18.02518081665039,
      "learning_rate": 4.584447941263149e-05,
      "loss": 31.9782,
      "step": 15
    },
    {
      "epoch": 0.0030293169245333255,
      "grad_norm": 18.874174118041992,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 33.0318,
      "step": 16
    },
    {
      "epoch": 0.003218649232316658,
      "grad_norm": 17.94559097290039,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 31.2892,
      "step": 17
    },
    {
      "epoch": 0.0034079815400999912,
      "grad_norm": 21.376195907592773,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 34.6142,
      "step": 18
    },
    {
      "epoch": 0.003597313847883324,
      "grad_norm": 20.425045013427734,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 36.647,
      "step": 19
    },
    {
      "epoch": 0.003786646155666657,
      "grad_norm": 22.36380958557129,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 32.5341,
      "step": 20
    },
    {
      "epoch": 0.00397597846344999,
      "grad_norm": 19.978683471679688,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 35.2849,
      "step": 21
    },
    {
      "epoch": 0.004165310771233322,
      "grad_norm": 18.254627227783203,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 31.8784,
      "step": 22
    },
    {
      "epoch": 0.004354643079016655,
      "grad_norm": 23.935752868652344,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 34.3253,
      "step": 23
    },
    {
      "epoch": 0.004543975386799988,
      "grad_norm": 20.54456329345703,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 31.752,
      "step": 24
    },
    {
      "epoch": 0.004733307694583321,
      "grad_norm": 20.954647064208984,
      "learning_rate": 1e-05,
      "loss": 34.6768,
      "step": 25
    },
    {
      "epoch": 0.004733307694583321,
      "eval_loss": 1.0340933799743652,
      "eval_runtime": 13.3951,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 3.733,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.71355818089513e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}