{
  "best_metric": 1.805835247039795,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.025839793281653745,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010335917312661498,
      "grad_norm": 0.9239017367362976,
      "learning_rate": 5e-05,
      "loss": 2.0724,
      "step": 1
    },
    {
      "epoch": 0.0010335917312661498,
      "eval_loss": 2.6242575645446777,
      "eval_runtime": 0.778,
      "eval_samples_per_second": 64.271,
      "eval_steps_per_second": 16.71,
      "step": 1
    },
    {
      "epoch": 0.0020671834625322996,
      "grad_norm": 1.0708829164505005,
      "learning_rate": 0.0001,
      "loss": 2.1152,
      "step": 2
    },
    {
      "epoch": 0.0031007751937984496,
      "grad_norm": 1.0626616477966309,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.1412,
      "step": 3
    },
    {
      "epoch": 0.004134366925064599,
      "grad_norm": 1.091120719909668,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.016,
      "step": 4
    },
    {
      "epoch": 0.00516795865633075,
      "grad_norm": 0.9137864112854004,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.9655,
      "step": 5
    },
    {
      "epoch": 0.006201550387596899,
      "grad_norm": 0.8222112059593201,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.9691,
      "step": 6
    },
    {
      "epoch": 0.007235142118863049,
      "grad_norm": 0.8061633706092834,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.9128,
      "step": 7
    },
    {
      "epoch": 0.008268733850129198,
      "grad_norm": 0.8582802414894104,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.8709,
      "step": 8
    },
    {
      "epoch": 0.009302325581395349,
      "grad_norm": 0.9123162031173706,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.9577,
      "step": 9
    },
    {
      "epoch": 0.0103359173126615,
      "grad_norm": 0.7822127938270569,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.8656,
      "step": 10
    },
    {
      "epoch": 0.011369509043927648,
      "grad_norm": 0.9331071972846985,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.9662,
      "step": 11
    },
    {
      "epoch": 0.012403100775193798,
      "grad_norm": 1.3675150871276855,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.9806,
      "step": 12
    },
    {
      "epoch": 0.013436692506459949,
      "grad_norm": 1.1646320819854736,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.8357,
      "step": 13
    },
    {
      "epoch": 0.014470284237726097,
      "grad_norm": 1.270059585571289,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.7306,
      "step": 14
    },
    {
      "epoch": 0.015503875968992248,
      "grad_norm": 1.0986566543579102,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.6902,
      "step": 15
    },
    {
      "epoch": 0.016537467700258397,
      "grad_norm": 0.9277008175849915,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.5689,
      "step": 16
    },
    {
      "epoch": 0.01757105943152455,
      "grad_norm": 0.7451536655426025,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.7069,
      "step": 17
    },
    {
      "epoch": 0.018604651162790697,
      "grad_norm": 0.6214572787284851,
      "learning_rate": 7.75e-05,
      "loss": 1.6968,
      "step": 18
    },
    {
      "epoch": 0.019638242894056846,
      "grad_norm": 0.683086097240448,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.6891,
      "step": 19
    },
    {
      "epoch": 0.020671834625323,
      "grad_norm": 0.7283631563186646,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.6948,
      "step": 20
    },
    {
      "epoch": 0.021705426356589147,
      "grad_norm": 0.7793617248535156,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.8125,
      "step": 21
    },
    {
      "epoch": 0.022739018087855296,
      "grad_norm": 0.8741857409477234,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.8514,
      "step": 22
    },
    {
      "epoch": 0.023772609819121448,
      "grad_norm": 0.9736992120742798,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.8525,
      "step": 23
    },
    {
      "epoch": 0.024806201550387597,
      "grad_norm": 1.1014063358306885,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.8171,
      "step": 24
    },
    {
      "epoch": 0.025839793281653745,
      "grad_norm": 1.6239304542541504,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.8691,
      "step": 25
    },
    {
      "epoch": 0.025839793281653745,
      "eval_loss": 1.805835247039795,
      "eval_runtime": 0.7785,
      "eval_samples_per_second": 64.225,
      "eval_steps_per_second": 16.698,
      "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": 5.29768176943104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}