{
  "best_metric": 2.8629980087280273,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.00816293212521938,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016325864250438759,
      "grad_norm": 0.8632163405418396,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.6076,
      "step": 1
    },
    {
      "epoch": 0.00016325864250438759,
      "eval_loss": 3.252528667449951,
      "eval_runtime": 363.3093,
      "eval_samples_per_second": 28.395,
      "eval_steps_per_second": 14.197,
      "step": 1
    },
    {
      "epoch": 0.00032651728500877517,
      "grad_norm": 0.8164938688278198,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.7626,
      "step": 2
    },
    {
      "epoch": 0.0004897759275131628,
      "grad_norm": 1.0135329961776733,
      "learning_rate": 1e-05,
      "loss": 3.2325,
      "step": 3
    },
    {
      "epoch": 0.0006530345700175503,
      "grad_norm": 1.0819627046585083,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.3302,
      "step": 4
    },
    {
      "epoch": 0.0008162932125219379,
      "grad_norm": 1.0888584852218628,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.2608,
      "step": 5
    },
    {
      "epoch": 0.0009795518550263255,
      "grad_norm": 1.1022908687591553,
      "learning_rate": 2e-05,
      "loss": 3.3397,
      "step": 6
    },
    {
      "epoch": 0.001142810497530713,
      "grad_norm": 1.0631771087646484,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 3.2714,
      "step": 7
    },
    {
      "epoch": 0.0013060691400351007,
      "grad_norm": 1.1249130964279175,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 3.3009,
      "step": 8
    },
    {
      "epoch": 0.0014693277825394882,
      "grad_norm": 1.2283929586410522,
      "learning_rate": 3e-05,
      "loss": 3.3171,
      "step": 9
    },
    {
      "epoch": 0.0016325864250438759,
      "grad_norm": 1.0188909769058228,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.7293,
      "step": 10
    },
    {
      "epoch": 0.0017958450675482633,
      "grad_norm": 1.2337793111801147,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 3.0187,
      "step": 11
    },
    {
      "epoch": 0.001959103710052651,
      "grad_norm": 1.0160133838653564,
      "learning_rate": 4e-05,
      "loss": 2.897,
      "step": 12
    },
    {
      "epoch": 0.0021223623525570383,
      "grad_norm": 0.9511106610298157,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 3.2403,
      "step": 13
    },
    {
      "epoch": 0.002285620995061426,
      "grad_norm": 0.9372708797454834,
      "learning_rate": 4.666666666666667e-05,
      "loss": 3.0862,
      "step": 14
    },
    {
      "epoch": 0.0024488796375658137,
      "grad_norm": 0.7635182738304138,
      "learning_rate": 5e-05,
      "loss": 2.9518,
      "step": 15
    },
    {
      "epoch": 0.0026121382800702014,
      "grad_norm": 0.9754545092582703,
      "learning_rate": 5.333333333333333e-05,
      "loss": 2.789,
      "step": 16
    },
    {
      "epoch": 0.0027753969225745886,
      "grad_norm": 0.8830393552780151,
      "learning_rate": 5.666666666666667e-05,
      "loss": 2.8314,
      "step": 17
    },
    {
      "epoch": 0.0029386555650789763,
      "grad_norm": 0.7772381901741028,
      "learning_rate": 6e-05,
      "loss": 2.6371,
      "step": 18
    },
    {
      "epoch": 0.003101914207583364,
      "grad_norm": 1.0107795000076294,
      "learning_rate": 6.333333333333333e-05,
      "loss": 2.858,
      "step": 19
    },
    {
      "epoch": 0.0032651728500877517,
      "grad_norm": 1.1810671091079712,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.2062,
      "step": 20
    },
    {
      "epoch": 0.003428431492592139,
      "grad_norm": 0.9577175378799438,
      "learning_rate": 7e-05,
      "loss": 3.1488,
      "step": 21
    },
    {
      "epoch": 0.0035916901350965267,
      "grad_norm": 0.898638904094696,
      "learning_rate": 7.333333333333333e-05,
      "loss": 3.3016,
      "step": 22
    },
    {
      "epoch": 0.0037549487776009144,
      "grad_norm": 1.1327389478683472,
      "learning_rate": 7.666666666666667e-05,
      "loss": 2.8533,
      "step": 23
    },
    {
      "epoch": 0.003918207420105302,
      "grad_norm": 0.9358575940132141,
      "learning_rate": 8e-05,
      "loss": 3.1331,
      "step": 24
    },
    {
      "epoch": 0.00408146606260969,
      "grad_norm": 0.9725240468978882,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.9826,
      "step": 25
    },
    {
      "epoch": 0.004244724705114077,
      "grad_norm": 0.9563072919845581,
      "learning_rate": 8.666666666666667e-05,
      "loss": 2.9238,
      "step": 26
    },
    {
      "epoch": 0.004407983347618464,
      "grad_norm": 0.8429107069969177,
      "learning_rate": 9e-05,
      "loss": 2.8076,
      "step": 27
    },
    {
      "epoch": 0.004571241990122852,
      "grad_norm": 0.938100278377533,
      "learning_rate": 9.333333333333334e-05,
      "loss": 2.9171,
      "step": 28
    },
    {
      "epoch": 0.00473450063262724,
      "grad_norm": 1.0879822969436646,
      "learning_rate": 9.666666666666667e-05,
      "loss": 3.0946,
      "step": 29
    },
    {
      "epoch": 0.004897759275131627,
      "grad_norm": 1.012676477432251,
      "learning_rate": 0.0001,
      "loss": 2.8535,
      "step": 30
    },
    {
      "epoch": 0.005061017917636015,
      "grad_norm": 0.864611029624939,
      "learning_rate": 9.994965332706573e-05,
      "loss": 2.8619,
      "step": 31
    },
    {
      "epoch": 0.005224276560140403,
      "grad_norm": 0.9068366885185242,
      "learning_rate": 9.979871469976196e-05,
      "loss": 2.7014,
      "step": 32
    },
    {
      "epoch": 0.00538753520264479,
      "grad_norm": 1.1143074035644531,
      "learning_rate": 9.954748808839674e-05,
      "loss": 2.7219,
      "step": 33
    },
    {
      "epoch": 0.005550793845149177,
      "grad_norm": 1.0027602910995483,
      "learning_rate": 9.919647942993148e-05,
      "loss": 3.1337,
      "step": 34
    },
    {
      "epoch": 0.005714052487653565,
      "grad_norm": 0.9993074536323547,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.906,
      "step": 35
    },
    {
      "epoch": 0.005877311130157953,
      "grad_norm": 0.9074757695198059,
      "learning_rate": 9.819814303479267e-05,
      "loss": 2.7418,
      "step": 36
    },
    {
      "epoch": 0.00604056977266234,
      "grad_norm": 1.012048602104187,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.594,
      "step": 37
    },
    {
      "epoch": 0.006203828415166728,
      "grad_norm": 0.8783692717552185,
      "learning_rate": 9.681174353198687e-05,
      "loss": 3.0345,
      "step": 38
    },
    {
      "epoch": 0.006367087057671116,
      "grad_norm": 1.058866262435913,
      "learning_rate": 9.597638862757255e-05,
      "loss": 2.9908,
      "step": 39
    },
    {
      "epoch": 0.006530345700175503,
      "grad_norm": 0.9666945338249207,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.8316,
      "step": 40
    },
    {
      "epoch": 0.00669360434267989,
      "grad_norm": 0.8591721653938293,
      "learning_rate": 9.40297765928369e-05,
      "loss": 2.723,
      "step": 41
    },
    {
      "epoch": 0.006856862985184278,
      "grad_norm": 0.9416791796684265,
      "learning_rate": 9.292243968009331e-05,
      "loss": 2.781,
      "step": 42
    },
    {
      "epoch": 0.007020121627688666,
      "grad_norm": 1.2646563053131104,
      "learning_rate": 9.172866268606513e-05,
      "loss": 2.9002,
      "step": 43
    },
    {
      "epoch": 0.007183380270193053,
      "grad_norm": 1.0307127237319946,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.8108,
      "step": 44
    },
    {
      "epoch": 0.007346638912697441,
      "grad_norm": 1.0498608350753784,
      "learning_rate": 8.90915741234015e-05,
      "loss": 2.4317,
      "step": 45
    },
    {
      "epoch": 0.007509897555201829,
      "grad_norm": 1.1443825960159302,
      "learning_rate": 8.765357330018056e-05,
      "loss": 2.7738,
      "step": 46
    },
    {
      "epoch": 0.007673156197706216,
      "grad_norm": 1.4476778507232666,
      "learning_rate": 8.613974319136958e-05,
      "loss": 2.6264,
      "step": 47
    },
    {
      "epoch": 0.007836414840210604,
      "grad_norm": 1.4269299507141113,
      "learning_rate": 8.455313244934324e-05,
      "loss": 2.4248,
      "step": 48
    },
    {
      "epoch": 0.007999673482714992,
      "grad_norm": 1.6290944814682007,
      "learning_rate": 8.289693629698564e-05,
      "loss": 2.6149,
      "step": 49
    },
    {
      "epoch": 0.00816293212521938,
      "grad_norm": 2.4885928630828857,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.1892,
      "step": 50
    },
    {
      "epoch": 0.00816293212521938,
      "eval_loss": 2.8629980087280273,
      "eval_runtime": 363.5686,
      "eval_samples_per_second": 28.374,
      "eval_steps_per_second": 14.187,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.367527271694336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}