{
  "best_metric": 1.1979334354400635,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.004227436060029592,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "grad_norm": 0.17550809681415558,
      "learning_rate": 2e-05,
      "loss": 1.4716,
      "step": 1
    },
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 1.4504181146621704,
      "eval_runtime": 242.0264,
      "eval_samples_per_second": 10.288,
      "eval_steps_per_second": 5.144,
      "step": 1
    },
    {
      "epoch": 0.0003381948848023674,
      "grad_norm": 0.17377100884914398,
      "learning_rate": 4e-05,
      "loss": 1.3987,
      "step": 2
    },
    {
      "epoch": 0.000507292327203551,
      "grad_norm": 0.1798679381608963,
      "learning_rate": 6e-05,
      "loss": 1.4557,
      "step": 3
    },
    {
      "epoch": 0.0006763897696047348,
      "grad_norm": 0.1888498216867447,
      "learning_rate": 8e-05,
      "loss": 1.2931,
      "step": 4
    },
    {
      "epoch": 0.0008454872120059184,
      "grad_norm": 0.19294755160808563,
      "learning_rate": 0.0001,
      "loss": 1.4079,
      "step": 5
    },
    {
      "epoch": 0.0008454872120059184,
      "eval_loss": 1.4390275478363037,
      "eval_runtime": 241.2782,
      "eval_samples_per_second": 10.32,
      "eval_steps_per_second": 5.16,
      "step": 5
    },
    {
      "epoch": 0.001014584654407102,
      "grad_norm": 0.18222397565841675,
      "learning_rate": 0.00012,
      "loss": 1.29,
      "step": 6
    },
    {
      "epoch": 0.0011836820968082857,
      "grad_norm": 0.24962863326072693,
      "learning_rate": 0.00014,
      "loss": 1.3893,
      "step": 7
    },
    {
      "epoch": 0.0013527795392094695,
      "grad_norm": 0.20723213255405426,
      "learning_rate": 0.00016,
      "loss": 1.4284,
      "step": 8
    },
    {
      "epoch": 0.0015218769816106531,
      "grad_norm": 0.24590528011322021,
      "learning_rate": 0.00018,
      "loss": 1.3146,
      "step": 9
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": 0.2495718002319336,
      "learning_rate": 0.0002,
      "loss": 1.3742,
      "step": 10
    },
    {
      "epoch": 0.0016909744240118367,
      "eval_loss": 1.3625589609146118,
      "eval_runtime": 236.1752,
      "eval_samples_per_second": 10.543,
      "eval_steps_per_second": 5.272,
      "step": 10
    },
    {
      "epoch": 0.0018600718664130206,
      "grad_norm": 0.2833280563354492,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.3302,
      "step": 11
    },
    {
      "epoch": 0.002029169308814204,
      "grad_norm": 0.2836049497127533,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.2318,
      "step": 12
    },
    {
      "epoch": 0.002198266751215388,
      "grad_norm": 0.36313438415527344,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4881,
      "step": 13
    },
    {
      "epoch": 0.0023673641936165714,
      "grad_norm": 0.300369530916214,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.2701,
      "step": 14
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": 0.43918246030807495,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3829,
      "step": 15
    },
    {
      "epoch": 0.0025364616360177552,
      "eval_loss": 1.2555962800979614,
      "eval_runtime": 247.5095,
      "eval_samples_per_second": 10.06,
      "eval_steps_per_second": 5.03,
      "step": 15
    },
    {
      "epoch": 0.002705559078418939,
      "grad_norm": 0.4566807150840759,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2792,
      "step": 16
    },
    {
      "epoch": 0.0028746565208201224,
      "grad_norm": 0.3033914268016815,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.1142,
      "step": 17
    },
    {
      "epoch": 0.0030437539632213063,
      "grad_norm": 0.42483752965927124,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.1218,
      "step": 18
    },
    {
      "epoch": 0.00321285140562249,
      "grad_norm": 0.38355574011802673,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.1258,
      "step": 19
    },
    {
      "epoch": 0.0033819488480236735,
      "grad_norm": 0.40342947840690613,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.1126,
      "step": 20
    },
    {
      "epoch": 0.0033819488480236735,
      "eval_loss": 1.2051751613616943,
      "eval_runtime": 243.4746,
      "eval_samples_per_second": 10.227,
      "eval_steps_per_second": 5.113,
      "step": 20
    },
    {
      "epoch": 0.0035510462904248573,
      "grad_norm": 0.4114494323730469,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.2128,
      "step": 21
    },
    {
      "epoch": 0.003720143732826041,
      "grad_norm": 0.36479702591896057,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.0317,
      "step": 22
    },
    {
      "epoch": 0.0038892411752272245,
      "grad_norm": 0.3829120993614197,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.1817,
      "step": 23
    },
    {
      "epoch": 0.004058338617628408,
      "grad_norm": 0.400522381067276,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.2204,
      "step": 24
    },
    {
      "epoch": 0.004227436060029592,
      "grad_norm": 0.39131632447242737,
      "learning_rate": 0.0,
      "loss": 1.2579,
      "step": 25
    },
    {
      "epoch": 0.004227436060029592,
      "eval_loss": 1.1979334354400635,
      "eval_runtime": 251.7367,
      "eval_samples_per_second": 9.891,
      "eval_steps_per_second": 4.946,
      "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": 819422772068352.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}