{
  "best_metric": 0.3837742209434509,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.4810583283223091,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019242333132892364,
      "grad_norm": 1.0140029191970825,
      "learning_rate": 5e-05,
      "loss": 1.1964,
      "step": 1
    },
    {
      "epoch": 0.019242333132892364,
      "eval_loss": 2.864025831222534,
      "eval_runtime": 3.1777,
      "eval_samples_per_second": 15.735,
      "eval_steps_per_second": 4.091,
      "step": 1
    },
    {
      "epoch": 0.03848466626578473,
      "grad_norm": 1.1101826429367065,
      "learning_rate": 0.0001,
      "loss": 1.4017,
      "step": 2
    },
    {
      "epoch": 0.05772699939867709,
      "grad_norm": 1.2272922992706299,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.3868,
      "step": 3
    },
    {
      "epoch": 0.07696933253156946,
      "grad_norm": 1.3631421327590942,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.081,
      "step": 4
    },
    {
      "epoch": 0.09621166566446182,
      "grad_norm": 2.200516700744629,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.8681,
      "step": 5
    },
    {
      "epoch": 0.11545399879735418,
      "grad_norm": 1.3805807828903198,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.8853,
      "step": 6
    },
    {
      "epoch": 0.13469633193024655,
      "grad_norm": 1.2450817823410034,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.6568,
      "step": 7
    },
    {
      "epoch": 0.1539386650631389,
      "grad_norm": 1.5090079307556152,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.7122,
      "step": 8
    },
    {
      "epoch": 0.17318099819603128,
      "grad_norm": 1.4319216012954712,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.453,
      "step": 9
    },
    {
      "epoch": 0.19242333132892364,
      "grad_norm": 1.0754787921905518,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.4363,
      "step": 10
    },
    {
      "epoch": 0.211665664461816,
      "grad_norm": 0.9463075399398804,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.3905,
      "step": 11
    },
    {
      "epoch": 0.23090799759470837,
      "grad_norm": 1.0483767986297607,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.2824,
      "step": 12
    },
    {
      "epoch": 0.25015033072760073,
      "grad_norm": 1.6578969955444336,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.71,
      "step": 13
    },
    {
      "epoch": 0.2693926638604931,
      "grad_norm": 1.1501309871673584,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.7001,
      "step": 14
    },
    {
      "epoch": 0.28863499699338546,
      "grad_norm": 0.8691616654396057,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.598,
      "step": 15
    },
    {
      "epoch": 0.3078773301262778,
      "grad_norm": 0.576944887638092,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.5324,
      "step": 16
    },
    {
      "epoch": 0.3271196632591702,
      "grad_norm": 0.717441201210022,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.5939,
      "step": 17
    },
    {
      "epoch": 0.34636199639206255,
      "grad_norm": 0.7738677859306335,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.5341,
      "step": 18
    },
    {
      "epoch": 0.3656043295249549,
      "grad_norm": 0.8227935433387756,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.5257,
      "step": 19
    },
    {
      "epoch": 0.3848466626578473,
      "grad_norm": 1.0373902320861816,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.5542,
      "step": 20
    },
    {
      "epoch": 0.40408899579073965,
      "grad_norm": 1.0239254236221313,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.4895,
      "step": 21
    },
    {
      "epoch": 0.423331328923632,
      "grad_norm": 1.6681764125823975,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.5145,
      "step": 22
    },
    {
      "epoch": 0.4425736620565244,
      "grad_norm": 2.3572447299957275,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.4539,
      "step": 23
    },
    {
      "epoch": 0.46181599518941674,
      "grad_norm": 2.6213738918304443,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.4698,
      "step": 24
    },
    {
      "epoch": 0.4810583283223091,
      "grad_norm": 3.4735586643218994,
      "learning_rate": 1e-05,
      "loss": 0.486,
      "step": 25
    },
    {
      "epoch": 0.4810583283223091,
      "eval_loss": 0.3837742209434509,
      "eval_runtime": 3.225,
      "eval_samples_per_second": 15.504,
      "eval_steps_per_second": 4.031,
      "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": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}