{
  "best_metric": 2.0449941158294678,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.028851702250432775,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001154068090017311,
      "grad_norm": 10.938200950622559,
      "learning_rate": 2e-05,
      "loss": 6.2035,
      "step": 1
    },
    {
      "epoch": 0.001154068090017311,
      "eval_loss": 2.122575283050537,
      "eval_runtime": 54.6024,
      "eval_samples_per_second": 26.739,
      "eval_steps_per_second": 3.352,
      "step": 1
    },
    {
      "epoch": 0.002308136180034622,
      "grad_norm": 11.67940902709961,
      "learning_rate": 4e-05,
      "loss": 7.7797,
      "step": 2
    },
    {
      "epoch": 0.003462204270051933,
      "grad_norm": 11.162690162658691,
      "learning_rate": 6e-05,
      "loss": 7.6768,
      "step": 3
    },
    {
      "epoch": 0.004616272360069244,
      "grad_norm": 9.086465835571289,
      "learning_rate": 8e-05,
      "loss": 7.7911,
      "step": 4
    },
    {
      "epoch": 0.005770340450086555,
      "grad_norm": 8.803955078125,
      "learning_rate": 0.0001,
      "loss": 7.7189,
      "step": 5
    },
    {
      "epoch": 0.006924408540103866,
      "grad_norm": 8.171338081359863,
      "learning_rate": 9.987820251299122e-05,
      "loss": 7.5216,
      "step": 6
    },
    {
      "epoch": 0.008078476630121177,
      "grad_norm": 8.607847213745117,
      "learning_rate": 9.951340343707852e-05,
      "loss": 7.8374,
      "step": 7
    },
    {
      "epoch": 0.009232544720138488,
      "grad_norm": 7.716111183166504,
      "learning_rate": 9.890738003669029e-05,
      "loss": 7.2367,
      "step": 8
    },
    {
      "epoch": 0.0103866128101558,
      "grad_norm": 7.701160907745361,
      "learning_rate": 9.806308479691595e-05,
      "loss": 7.6365,
      "step": 9
    },
    {
      "epoch": 0.01154068090017311,
      "grad_norm": 8.31236743927002,
      "learning_rate": 9.698463103929542e-05,
      "loss": 7.4108,
      "step": 10
    },
    {
      "epoch": 0.012694748990190421,
      "grad_norm": 8.164664268493652,
      "learning_rate": 9.567727288213005e-05,
      "loss": 7.3503,
      "step": 11
    },
    {
      "epoch": 0.013848817080207732,
      "grad_norm": 7.869163990020752,
      "learning_rate": 9.414737964294636e-05,
      "loss": 7.8775,
      "step": 12
    },
    {
      "epoch": 0.015002885170225043,
      "grad_norm": 8.522551536560059,
      "learning_rate": 9.24024048078213e-05,
      "loss": 7.5652,
      "step": 13
    },
    {
      "epoch": 0.016156953260242354,
      "grad_norm": 8.944220542907715,
      "learning_rate": 9.045084971874738e-05,
      "loss": 7.72,
      "step": 14
    },
    {
      "epoch": 0.017311021350259664,
      "grad_norm": 7.63972282409668,
      "learning_rate": 8.83022221559489e-05,
      "loss": 7.6611,
      "step": 15
    },
    {
      "epoch": 0.018465089440276975,
      "grad_norm": 8.285905838012695,
      "learning_rate": 8.596699001693255e-05,
      "loss": 7.9625,
      "step": 16
    },
    {
      "epoch": 0.019619157530294286,
      "grad_norm": 9.12864875793457,
      "learning_rate": 8.345653031794292e-05,
      "loss": 8.054,
      "step": 17
    },
    {
      "epoch": 0.0207732256203116,
      "grad_norm": 8.1249418258667,
      "learning_rate": 8.07830737662829e-05,
      "loss": 7.9919,
      "step": 18
    },
    {
      "epoch": 0.02192729371032891,
      "grad_norm": 8.116121292114258,
      "learning_rate": 7.795964517353735e-05,
      "loss": 7.9385,
      "step": 19
    },
    {
      "epoch": 0.02308136180034622,
      "grad_norm": 8.311835289001465,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.4027,
      "step": 20
    },
    {
      "epoch": 0.024235429890363532,
      "grad_norm": 8.091967582702637,
      "learning_rate": 7.191855733945387e-05,
      "loss": 7.9201,
      "step": 21
    },
    {
      "epoch": 0.025389497980380843,
      "grad_norm": 7.40118932723999,
      "learning_rate": 6.873032967079561e-05,
      "loss": 7.9214,
      "step": 22
    },
    {
      "epoch": 0.026543566070398154,
      "grad_norm": 7.898697376251221,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.9338,
      "step": 23
    },
    {
      "epoch": 0.027697634160415464,
      "grad_norm": 7.743147373199463,
      "learning_rate": 6.209609477998338e-05,
      "loss": 7.6968,
      "step": 24
    },
    {
      "epoch": 0.028851702250432775,
      "grad_norm": 8.870253562927246,
      "learning_rate": 5.868240888334653e-05,
      "loss": 7.362,
      "step": 25
    },
    {
      "epoch": 0.028851702250432775,
      "eval_loss": 2.0449941158294678,
      "eval_runtime": 55.5094,
      "eval_samples_per_second": 26.302,
      "eval_steps_per_second": 3.297,
      "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": 5,
        "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": 1.806637019745485e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}