{
  "best_metric": 2.743968963623047,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.006383250351078769,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025533001404315077,
      "grad_norm": 3.7897307872772217,
      "learning_rate": 1e-05,
      "loss": 12.3906,
      "step": 1
    },
    {
      "epoch": 0.00025533001404315077,
      "eval_loss": 3.1754887104034424,
      "eval_runtime": 240.088,
      "eval_samples_per_second": 6.868,
      "eval_steps_per_second": 3.436,
      "step": 1
    },
    {
      "epoch": 0.0005106600280863015,
      "grad_norm": 2.942302703857422,
      "learning_rate": 2e-05,
      "loss": 12.2644,
      "step": 2
    },
    {
      "epoch": 0.0007659900421294523,
      "grad_norm": 2.851736307144165,
      "learning_rate": 3e-05,
      "loss": 11.6151,
      "step": 3
    },
    {
      "epoch": 0.001021320056172603,
      "grad_norm": 4.135279178619385,
      "learning_rate": 4e-05,
      "loss": 14.0861,
      "step": 4
    },
    {
      "epoch": 0.0012766500702157538,
      "grad_norm": 2.8848330974578857,
      "learning_rate": 5e-05,
      "loss": 12.3282,
      "step": 5
    },
    {
      "epoch": 0.0012766500702157538,
      "eval_loss": 3.1596250534057617,
      "eval_runtime": 239.404,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 3.446,
      "step": 5
    },
    {
      "epoch": 0.0015319800842589046,
      "grad_norm": 3.5226523876190186,
      "learning_rate": 6e-05,
      "loss": 12.5954,
      "step": 6
    },
    {
      "epoch": 0.0017873100983020554,
      "grad_norm": 3.465043544769287,
      "learning_rate": 7e-05,
      "loss": 12.1819,
      "step": 7
    },
    {
      "epoch": 0.002042640112345206,
      "grad_norm": 3.612983226776123,
      "learning_rate": 8e-05,
      "loss": 12.8036,
      "step": 8
    },
    {
      "epoch": 0.002297970126388357,
      "grad_norm": 3.537229537963867,
      "learning_rate": 9e-05,
      "loss": 12.7598,
      "step": 9
    },
    {
      "epoch": 0.0025533001404315077,
      "grad_norm": 3.7051985263824463,
      "learning_rate": 0.0001,
      "loss": 11.8222,
      "step": 10
    },
    {
      "epoch": 0.0025533001404315077,
      "eval_loss": 2.994251012802124,
      "eval_runtime": 239.2798,
      "eval_samples_per_second": 6.892,
      "eval_steps_per_second": 3.448,
      "step": 10
    },
    {
      "epoch": 0.0028086301544746587,
      "grad_norm": 3.594055652618408,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.2811,
      "step": 11
    },
    {
      "epoch": 0.003063960168517809,
      "grad_norm": 3.8312735557556152,
      "learning_rate": 9.567727288213005e-05,
      "loss": 12.0274,
      "step": 12
    },
    {
      "epoch": 0.00331929018256096,
      "grad_norm": 3.5473875999450684,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.4537,
      "step": 13
    },
    {
      "epoch": 0.0035746201966041107,
      "grad_norm": 3.679525136947632,
      "learning_rate": 8.345653031794292e-05,
      "loss": 11.3362,
      "step": 14
    },
    {
      "epoch": 0.0038299502106472617,
      "grad_norm": 3.626020669937134,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.4638,
      "step": 15
    },
    {
      "epoch": 0.0038299502106472617,
      "eval_loss": 2.8082637786865234,
      "eval_runtime": 239.4581,
      "eval_samples_per_second": 6.886,
      "eval_steps_per_second": 3.445,
      "step": 15
    },
    {
      "epoch": 0.004085280224690412,
      "grad_norm": 4.261275291442871,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.2856,
      "step": 16
    },
    {
      "epoch": 0.004340610238733563,
      "grad_norm": 3.995574474334717,
      "learning_rate": 5.522642316338268e-05,
      "loss": 9.9208,
      "step": 17
    },
    {
      "epoch": 0.004595940252776714,
      "grad_norm": 4.395712375640869,
      "learning_rate": 4.477357683661734e-05,
      "loss": 11.021,
      "step": 18
    },
    {
      "epoch": 0.004851270266819864,
      "grad_norm": 4.019805431365967,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.1573,
      "step": 19
    },
    {
      "epoch": 0.005106600280863015,
      "grad_norm": 3.8426027297973633,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.1888,
      "step": 20
    },
    {
      "epoch": 0.005106600280863015,
      "eval_loss": 2.756742477416992,
      "eval_runtime": 239.7146,
      "eval_samples_per_second": 6.879,
      "eval_steps_per_second": 3.442,
      "step": 20
    },
    {
      "epoch": 0.005361930294906166,
      "grad_norm": 4.26030158996582,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 11.4889,
      "step": 21
    },
    {
      "epoch": 0.005617260308949317,
      "grad_norm": 6.210017681121826,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.0761,
      "step": 22
    },
    {
      "epoch": 0.005872590322992467,
      "grad_norm": 3.9016616344451904,
      "learning_rate": 4.322727117869951e-06,
      "loss": 9.6805,
      "step": 23
    },
    {
      "epoch": 0.006127920337035618,
      "grad_norm": 4.461097717285156,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.136,
      "step": 24
    },
    {
      "epoch": 0.006383250351078769,
      "grad_norm": 3.818615674972534,
      "learning_rate": 0.0,
      "loss": 11.7023,
      "step": 25
    },
    {
      "epoch": 0.006383250351078769,
      "eval_loss": 2.743968963623047,
      "eval_runtime": 239.0686,
      "eval_samples_per_second": 6.898,
      "eval_steps_per_second": 3.451,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 7132013395968000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}