{
  "best_metric": 11.92931842803955,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.04549590536851683,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009099181073703367,
      "grad_norm": 0.04135997220873833,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9246,
      "step": 1
    },
    {
      "epoch": 0.0009099181073703367,
      "eval_loss": 11.937775611877441,
      "eval_runtime": 0.3953,
      "eval_samples_per_second": 126.499,
      "eval_steps_per_second": 126.499,
      "step": 1
    },
    {
      "epoch": 0.0018198362147406734,
      "grad_norm": 0.04857102036476135,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9222,
      "step": 2
    },
    {
      "epoch": 0.00272975432211101,
      "grad_norm": 0.04188262298703194,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.9244,
      "step": 3
    },
    {
      "epoch": 0.003639672429481347,
      "grad_norm": 0.0355207696557045,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9192,
      "step": 4
    },
    {
      "epoch": 0.004549590536851683,
      "grad_norm": 0.03408201411366463,
      "learning_rate": 0.00015,
      "loss": 11.9284,
      "step": 5
    },
    {
      "epoch": 0.00545950864422202,
      "grad_norm": 0.04698517918586731,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9289,
      "step": 6
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 0.028339426964521408,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9301,
      "step": 7
    },
    {
      "epoch": 0.007279344858962694,
      "grad_norm": 0.033868804574012756,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9284,
      "step": 8
    },
    {
      "epoch": 0.00818926296633303,
      "grad_norm": 0.025452876463532448,
      "learning_rate": 0.00027,
      "loss": 11.9306,
      "step": 9
    },
    {
      "epoch": 0.009099181073703366,
      "grad_norm": 0.030591776594519615,
      "learning_rate": 0.0003,
      "loss": 11.9325,
      "step": 10
    },
    {
      "epoch": 0.010009099181073703,
      "grad_norm": 0.028602290898561478,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.9304,
      "step": 11
    },
    {
      "epoch": 0.01091901728844404,
      "grad_norm": 0.0217262115329504,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9296,
      "step": 12
    },
    {
      "epoch": 0.011828935395814377,
      "grad_norm": 0.0400615856051445,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.93,
      "step": 13
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.025656167417764664,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9278,
      "step": 14
    },
    {
      "epoch": 0.01364877161055505,
      "grad_norm": 0.03284378722310066,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9305,
      "step": 15
    },
    {
      "epoch": 0.014558689717925387,
      "grad_norm": 0.03374679386615753,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9269,
      "step": 16
    },
    {
      "epoch": 0.015468607825295723,
      "grad_norm": 0.03800738975405693,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9266,
      "step": 17
    },
    {
      "epoch": 0.01637852593266606,
      "grad_norm": 0.03509436547756195,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.931,
      "step": 18
    },
    {
      "epoch": 0.017288444040036398,
      "grad_norm": 0.038303714245557785,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.9259,
      "step": 19
    },
    {
      "epoch": 0.018198362147406732,
      "grad_norm": 0.031731538474559784,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9318,
      "step": 20
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.03439212962985039,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9271,
      "step": 21
    },
    {
      "epoch": 0.020018198362147407,
      "grad_norm": 0.04004055634140968,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9296,
      "step": 22
    },
    {
      "epoch": 0.020928116469517744,
      "grad_norm": 0.03706061467528343,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.932,
      "step": 23
    },
    {
      "epoch": 0.02183803457688808,
      "grad_norm": 0.02771821990609169,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9353,
      "step": 24
    },
    {
      "epoch": 0.022747952684258416,
      "grad_norm": 0.029228534549474716,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9244,
      "step": 25
    },
    {
      "epoch": 0.022747952684258416,
      "eval_loss": 11.93565559387207,
      "eval_runtime": 0.4023,
      "eval_samples_per_second": 124.295,
      "eval_steps_per_second": 124.295,
      "step": 25
    },
    {
      "epoch": 0.023657870791628753,
      "grad_norm": 0.034826189279556274,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9279,
      "step": 26
    },
    {
      "epoch": 0.02456778889899909,
      "grad_norm": 0.03567393496632576,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9287,
      "step": 27
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.038747385144233704,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9257,
      "step": 28
    },
    {
      "epoch": 0.026387625113739762,
      "grad_norm": 0.046440187841653824,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9298,
      "step": 29
    },
    {
      "epoch": 0.0272975432211101,
      "grad_norm": 0.035133399069309235,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9304,
      "step": 30
    },
    {
      "epoch": 0.028207461328480437,
      "grad_norm": 0.032283294945955276,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9251,
      "step": 31
    },
    {
      "epoch": 0.029117379435850774,
      "grad_norm": 0.03427290543913841,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.9269,
      "step": 32
    },
    {
      "epoch": 0.03002729754322111,
      "grad_norm": 0.04527918994426727,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9327,
      "step": 33
    },
    {
      "epoch": 0.030937215650591446,
      "grad_norm": 0.05488235875964165,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.929,
      "step": 34
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 0.05063425749540329,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9281,
      "step": 35
    },
    {
      "epoch": 0.03275705186533212,
      "grad_norm": 0.04788482189178467,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9271,
      "step": 36
    },
    {
      "epoch": 0.03366696997270246,
      "grad_norm": 0.04777894541621208,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.929,
      "step": 37
    },
    {
      "epoch": 0.034576888080072796,
      "grad_norm": 0.05248137190937996,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9288,
      "step": 38
    },
    {
      "epoch": 0.03548680618744313,
      "grad_norm": 0.053672585636377335,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.9281,
      "step": 39
    },
    {
      "epoch": 0.036396724294813464,
      "grad_norm": 0.03825056925415993,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9321,
      "step": 40
    },
    {
      "epoch": 0.0373066424021838,
      "grad_norm": 0.05029003694653511,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9258,
      "step": 41
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": 0.035441625863313675,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9275,
      "step": 42
    },
    {
      "epoch": 0.039126478616924476,
      "grad_norm": 0.05929926037788391,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9292,
      "step": 43
    },
    {
      "epoch": 0.040036396724294813,
      "grad_norm": 0.06052996218204498,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9249,
      "step": 44
    },
    {
      "epoch": 0.04094631483166515,
      "grad_norm": 0.0721125602722168,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9298,
      "step": 45
    },
    {
      "epoch": 0.04185623293903549,
      "grad_norm": 0.057127729058265686,
      "learning_rate": 0.000274201324672203,
      "loss": 11.934,
      "step": 46
    },
    {
      "epoch": 0.042766151046405826,
      "grad_norm": 0.06003405153751373,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9309,
      "step": 47
    },
    {
      "epoch": 0.04367606915377616,
      "grad_norm": 0.05513525381684303,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9282,
      "step": 48
    },
    {
      "epoch": 0.044585987261146494,
      "grad_norm": 0.05979841947555542,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.9289,
      "step": 49
    },
    {
      "epoch": 0.04549590536851683,
      "grad_norm": 0.07970727235078812,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.929,
      "step": 50
    },
    {
      "epoch": 0.04549590536851683,
      "eval_loss": 11.92931842803955,
      "eval_runtime": 0.3938,
      "eval_samples_per_second": 126.97,
      "eval_steps_per_second": 126.97,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 79631155200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}