{
  "best_metric": 2.256721258163452,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.8658008658008658,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 2.8118698596954346,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.3893,
      "eval_samples_per_second": 22.327,
      "eval_steps_per_second": 5.696,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 4.973637104034424,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.760875225067139,
      "learning_rate": 3e-05,
      "loss": 2.7876,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.113471508026123,
      "learning_rate": 4e-05,
      "loss": 2.7467,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.091151475906372,
      "learning_rate": 5e-05,
      "loss": 2.8543,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.6705322265625,
      "learning_rate": 6e-05,
      "loss": 2.9262,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8101789951324463,
      "learning_rate": 7e-05,
      "loss": 2.6595,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.463834285736084,
      "learning_rate": 8e-05,
      "loss": 2.833,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.838789701461792,
      "learning_rate": 9e-05,
      "loss": 2.8904,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.6583943367004395,
      "learning_rate": 0.0001,
      "loss": 2.8253,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.103412628173828,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5754,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.752767562866211,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7909,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.6153974533081055,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8612,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.671820163726807,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.2352,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.8995760679244995,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8384,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.86356782913208,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4272,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.6119074821472168,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3626,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.67992103099823,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2748,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6707350015640259,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.1881,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8515558242797852,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.0334,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.1287074089050293,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.3509,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.0685789585113525,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.2955,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.199742317199707,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3759,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.4112186431884766,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5115,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.319316864013672,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5079,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.4952006340026855,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.546,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.641359329223633,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4089,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.115784168243408,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1355,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3380645513534546,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.6216,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.2748000621795654,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2642,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6783227920532227,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.0759,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5664422512054443,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0632,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5744460821151733,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.0214,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7587584257125854,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0404,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.9254662990570068,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.2543,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.965366005897522,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1501,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.1672956943511963,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3718,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.3108174800872803,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.6269,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.326822280883789,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3544,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.420606851577759,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.33,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.5650737285614014,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.3837,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.262178897857666,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3165,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.9868830442428589,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7471,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.710825800895691,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.0541,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.7059110403060913,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0234,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.6046017408370972,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8639,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.6054553985595703,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1819,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.4989557266235352,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0109,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6607235670089722,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.8743,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.8187165260314941,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.148,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.256721258163452,
      "eval_runtime": 4.4013,
      "eval_samples_per_second": 22.266,
      "eval_steps_per_second": 5.68,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "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": 2.07184013033472e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}