{
  "best_metric": 6.877920150756836,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.001594111352663262,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.376445410653048e-05,
      "grad_norm": 0.12487476319074631,
      "learning_rate": 5e-05,
      "loss": 6.9383,
      "step": 1
    },
    {
      "epoch": 6.376445410653048e-05,
      "eval_loss": 6.918209075927734,
      "eval_runtime": 0.6566,
      "eval_samples_per_second": 76.154,
      "eval_steps_per_second": 76.154,
      "step": 1
    },
    {
      "epoch": 0.00012752890821306095,
      "grad_norm": 0.581697940826416,
      "learning_rate": 0.0001,
      "loss": 6.9323,
      "step": 2
    },
    {
      "epoch": 0.00019129336231959142,
      "grad_norm": 0.6627447009086609,
      "learning_rate": 9.958086757163489e-05,
      "loss": 6.9406,
      "step": 3
    },
    {
      "epoch": 0.0002550578164261219,
      "grad_norm": 0.5978795289993286,
      "learning_rate": 9.833127793065098e-05,
      "loss": 6.9376,
      "step": 4
    },
    {
      "epoch": 0.0003188222705326524,
      "grad_norm": 0.5981859564781189,
      "learning_rate": 9.627450856774539e-05,
      "loss": 6.9196,
      "step": 5
    },
    {
      "epoch": 0.00038258672463918283,
      "grad_norm": 0.5714685320854187,
      "learning_rate": 9.3448873204592e-05,
      "loss": 6.9483,
      "step": 6
    },
    {
      "epoch": 0.0004463511787457133,
      "grad_norm": 0.6686998605728149,
      "learning_rate": 8.990700808169889e-05,
      "loss": 6.9253,
      "step": 7
    },
    {
      "epoch": 0.0005101156328522438,
      "grad_norm": 0.600262463092804,
      "learning_rate": 8.571489144483944e-05,
      "loss": 6.9238,
      "step": 8
    },
    {
      "epoch": 0.0005738800869587743,
      "grad_norm": 0.6122546792030334,
      "learning_rate": 8.095061449516903e-05,
      "loss": 6.914,
      "step": 9
    },
    {
      "epoch": 0.0006376445410653048,
      "grad_norm": 0.5982901453971863,
      "learning_rate": 7.570292669790186e-05,
      "loss": 6.9117,
      "step": 10
    },
    {
      "epoch": 0.0007014089951718353,
      "grad_norm": 0.5691618919372559,
      "learning_rate": 7.006958254769438e-05,
      "loss": 6.9223,
      "step": 11
    },
    {
      "epoch": 0.0007651734492783657,
      "grad_norm": 0.5796125531196594,
      "learning_rate": 6.415552058736854e-05,
      "loss": 6.915,
      "step": 12
    },
    {
      "epoch": 0.0008289379033848962,
      "grad_norm": 0.6872209310531616,
      "learning_rate": 5.80709086014102e-05,
      "loss": 6.9145,
      "step": 13
    },
    {
      "epoch": 0.0008927023574914266,
      "grad_norm": 0.7043810486793518,
      "learning_rate": 5.192909139858981e-05,
      "loss": 6.9125,
      "step": 14
    },
    {
      "epoch": 0.0009564668115979571,
      "grad_norm": 0.5867166519165039,
      "learning_rate": 4.584447941263149e-05,
      "loss": 6.9113,
      "step": 15
    },
    {
      "epoch": 0.0010202312657044876,
      "grad_norm": 0.6672064065933228,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 6.8929,
      "step": 16
    },
    {
      "epoch": 0.001083995719811018,
      "grad_norm": 0.7145550847053528,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 6.8994,
      "step": 17
    },
    {
      "epoch": 0.0011477601739175486,
      "grad_norm": 0.7720252275466919,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 6.8884,
      "step": 18
    },
    {
      "epoch": 0.001211524628024079,
      "grad_norm": 0.7148048281669617,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 6.8987,
      "step": 19
    },
    {
      "epoch": 0.0012752890821306096,
      "grad_norm": 0.5864389538764954,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 6.8975,
      "step": 20
    },
    {
      "epoch": 0.00133905353623714,
      "grad_norm": 0.7181539535522461,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 6.8793,
      "step": 21
    },
    {
      "epoch": 0.0014028179903436706,
      "grad_norm": 0.8100740313529968,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 6.8868,
      "step": 22
    },
    {
      "epoch": 0.001466582444450201,
      "grad_norm": 0.6360393762588501,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 6.9064,
      "step": 23
    },
    {
      "epoch": 0.0015303468985567313,
      "grad_norm": 0.7050322890281677,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 6.8892,
      "step": 24
    },
    {
      "epoch": 0.001594111352663262,
      "grad_norm": 0.6015287041664124,
      "learning_rate": 1e-05,
      "loss": 6.9053,
      "step": 25
    },
    {
      "epoch": 0.001594111352663262,
      "eval_loss": 6.877920150756836,
      "eval_runtime": 0.3052,
      "eval_samples_per_second": 163.825,
      "eval_steps_per_second": 163.825,
      "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": 781894471680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}