{
  "best_metric": 11.926169395446777,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.020713046630246226,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004142609326049245,
      "grad_norm": 0.009111136198043823,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9291,
      "step": 1
    },
    {
      "epoch": 0.0004142609326049245,
      "eval_loss": 11.93281364440918,
      "eval_runtime": 0.2456,
      "eval_samples_per_second": 203.617,
      "eval_steps_per_second": 28.506,
      "step": 1
    },
    {
      "epoch": 0.000828521865209849,
      "grad_norm": 0.01578676700592041,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9311,
      "step": 2
    },
    {
      "epoch": 0.0012427827978147737,
      "grad_norm": 0.010788201354444027,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.9303,
      "step": 3
    },
    {
      "epoch": 0.001657043730419698,
      "grad_norm": 0.014519501477479935,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9288,
      "step": 4
    },
    {
      "epoch": 0.0020713046630246226,
      "grad_norm": 0.01510781329125166,
      "learning_rate": 0.00015,
      "loss": 11.9304,
      "step": 5
    },
    {
      "epoch": 0.0024855655956295473,
      "grad_norm": 0.013269297778606415,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9294,
      "step": 6
    },
    {
      "epoch": 0.0028998265282344717,
      "grad_norm": 0.013751151971518993,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9321,
      "step": 7
    },
    {
      "epoch": 0.003314087460839396,
      "grad_norm": 0.015573951415717602,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9287,
      "step": 8
    },
    {
      "epoch": 0.0037283483934443208,
      "grad_norm": 0.009504775516688824,
      "learning_rate": 0.00027,
      "loss": 11.9305,
      "step": 9
    },
    {
      "epoch": 0.004142609326049245,
      "grad_norm": 0.010801173746585846,
      "learning_rate": 0.0003,
      "loss": 11.9337,
      "step": 10
    },
    {
      "epoch": 0.0045568702586541695,
      "grad_norm": 0.011178042739629745,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.9278,
      "step": 11
    },
    {
      "epoch": 0.004971131191259095,
      "grad_norm": 0.014659388922154903,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9297,
      "step": 12
    },
    {
      "epoch": 0.005385392123864019,
      "grad_norm": 0.013904299587011337,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.9315,
      "step": 13
    },
    {
      "epoch": 0.005799653056468943,
      "grad_norm": 0.014901366084814072,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9306,
      "step": 14
    },
    {
      "epoch": 0.006213913989073868,
      "grad_norm": 0.014373673126101494,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9291,
      "step": 15
    },
    {
      "epoch": 0.006628174921678792,
      "grad_norm": 0.012232257053256035,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9292,
      "step": 16
    },
    {
      "epoch": 0.007042435854283717,
      "grad_norm": 0.011413573287427425,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9322,
      "step": 17
    },
    {
      "epoch": 0.0074566967868886416,
      "grad_norm": 0.016656706109642982,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.9324,
      "step": 18
    },
    {
      "epoch": 0.007870957719493567,
      "grad_norm": 0.014373266138136387,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.9318,
      "step": 19
    },
    {
      "epoch": 0.00828521865209849,
      "grad_norm": 0.015115369111299515,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9287,
      "step": 20
    },
    {
      "epoch": 0.008699479584703415,
      "grad_norm": 0.01734703592956066,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9309,
      "step": 21
    },
    {
      "epoch": 0.009113740517308339,
      "grad_norm": 0.014644989743828773,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9254,
      "step": 22
    },
    {
      "epoch": 0.009528001449913264,
      "grad_norm": 0.021497027948498726,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9302,
      "step": 23
    },
    {
      "epoch": 0.00994226238251819,
      "grad_norm": 0.01817285642027855,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9312,
      "step": 24
    },
    {
      "epoch": 0.010356523315123113,
      "grad_norm": 0.02207845263183117,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9284,
      "step": 25
    },
    {
      "epoch": 0.010356523315123113,
      "eval_loss": 11.93165397644043,
      "eval_runtime": 0.2441,
      "eval_samples_per_second": 204.847,
      "eval_steps_per_second": 28.679,
      "step": 25
    },
    {
      "epoch": 0.010770784247728038,
      "grad_norm": 0.017103340476751328,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9297,
      "step": 26
    },
    {
      "epoch": 0.011185045180332961,
      "grad_norm": 0.0265261959284544,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9303,
      "step": 27
    },
    {
      "epoch": 0.011599306112937887,
      "grad_norm": 0.031121160835027695,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9264,
      "step": 28
    },
    {
      "epoch": 0.012013567045542812,
      "grad_norm": 0.020733291283249855,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9311,
      "step": 29
    },
    {
      "epoch": 0.012427827978147735,
      "grad_norm": 0.019345130771398544,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9295,
      "step": 30
    },
    {
      "epoch": 0.01284208891075266,
      "grad_norm": 0.025070849806070328,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9307,
      "step": 31
    },
    {
      "epoch": 0.013256349843357584,
      "grad_norm": 0.02109096758067608,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.927,
      "step": 32
    },
    {
      "epoch": 0.01367061077596251,
      "grad_norm": 0.027676530182361603,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9296,
      "step": 33
    },
    {
      "epoch": 0.014084871708567434,
      "grad_norm": 0.02774973399937153,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9294,
      "step": 34
    },
    {
      "epoch": 0.014499132641172358,
      "grad_norm": 0.026240255683660507,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9283,
      "step": 35
    },
    {
      "epoch": 0.014913393573777283,
      "grad_norm": 0.03300342708826065,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9277,
      "step": 36
    },
    {
      "epoch": 0.015327654506382208,
      "grad_norm": 0.03084516152739525,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.9284,
      "step": 37
    },
    {
      "epoch": 0.015741915438987134,
      "grad_norm": 0.03772755712270737,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9301,
      "step": 38
    },
    {
      "epoch": 0.016156176371592057,
      "grad_norm": 0.044647328555583954,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.929,
      "step": 39
    },
    {
      "epoch": 0.01657043730419698,
      "grad_norm": 0.0458788201212883,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9261,
      "step": 40
    },
    {
      "epoch": 0.016984698236801904,
      "grad_norm": 0.062342319637537,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9292,
      "step": 41
    },
    {
      "epoch": 0.01739895916940683,
      "grad_norm": 0.04045253247022629,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9276,
      "step": 42
    },
    {
      "epoch": 0.017813220102011754,
      "grad_norm": 0.05095702409744263,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9244,
      "step": 43
    },
    {
      "epoch": 0.018227481034616678,
      "grad_norm": 0.04911315068602562,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9264,
      "step": 44
    },
    {
      "epoch": 0.018641741967221605,
      "grad_norm": 0.04607488214969635,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9244,
      "step": 45
    },
    {
      "epoch": 0.019056002899826528,
      "grad_norm": 0.05658293142914772,
      "learning_rate": 0.000274201324672203,
      "loss": 11.9224,
      "step": 46
    },
    {
      "epoch": 0.01947026383243145,
      "grad_norm": 0.050977252423763275,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9255,
      "step": 47
    },
    {
      "epoch": 0.01988452476503638,
      "grad_norm": 0.06175487861037254,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9218,
      "step": 48
    },
    {
      "epoch": 0.020298785697641302,
      "grad_norm": 0.049341753125190735,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.927,
      "step": 49
    },
    {
      "epoch": 0.020713046630246226,
      "grad_norm": 0.0748741626739502,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.9258,
      "step": 50
    },
    {
      "epoch": 0.020713046630246226,
      "eval_loss": 11.926169395446777,
      "eval_runtime": 0.2445,
      "eval_samples_per_second": 204.526,
      "eval_steps_per_second": 28.634,
      "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": 1,
  "trial_name": null,
  "trial_params": null
}