{
  "best_metric": 1.770018458366394,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.007801833430856251,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000156036668617125,
      "grad_norm": 0.6086230874061584,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.8397,
      "step": 1
    },
    {
      "epoch": 0.000156036668617125,
      "eval_loss": 2.050737142562866,
      "eval_runtime": 4.681,
      "eval_samples_per_second": 10.682,
      "eval_steps_per_second": 1.495,
      "step": 1
    },
    {
      "epoch": 0.00031207333723425,
      "grad_norm": 0.8839565515518188,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.9253,
      "step": 2
    },
    {
      "epoch": 0.0004681100058513751,
      "grad_norm": 0.5914949178695679,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.7086,
      "step": 3
    },
    {
      "epoch": 0.0006241466744685,
      "grad_norm": 0.6697356104850769,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.676,
      "step": 4
    },
    {
      "epoch": 0.0007801833430856252,
      "grad_norm": 0.7815700173377991,
      "learning_rate": 0.00015,
      "loss": 1.7765,
      "step": 5
    },
    {
      "epoch": 0.0009362200117027502,
      "grad_norm": 0.8394500613212585,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.7859,
      "step": 6
    },
    {
      "epoch": 0.001092256680319875,
      "grad_norm": 0.6029866337776184,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.6454,
      "step": 7
    },
    {
      "epoch": 0.001248293348937,
      "grad_norm": 0.5297218561172485,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.7182,
      "step": 8
    },
    {
      "epoch": 0.0014043300175541251,
      "grad_norm": 0.8180967569351196,
      "learning_rate": 0.00027,
      "loss": 1.8304,
      "step": 9
    },
    {
      "epoch": 0.0015603666861712503,
      "grad_norm": 0.9878036379814148,
      "learning_rate": 0.0003,
      "loss": 1.7367,
      "step": 10
    },
    {
      "epoch": 0.0017164033547883754,
      "grad_norm": 0.5219380855560303,
      "learning_rate": 0.0002999794957488703,
      "loss": 1.878,
      "step": 11
    },
    {
      "epoch": 0.0018724400234055004,
      "grad_norm": 0.5020744800567627,
      "learning_rate": 0.0002999179886011389,
      "loss": 1.8158,
      "step": 12
    },
    {
      "epoch": 0.0020284766920226254,
      "grad_norm": 0.5324579477310181,
      "learning_rate": 0.0002998154953722457,
      "loss": 1.562,
      "step": 13
    },
    {
      "epoch": 0.00218451336063975,
      "grad_norm": 0.849560558795929,
      "learning_rate": 0.00029967204408281613,
      "loss": 1.6667,
      "step": 14
    },
    {
      "epoch": 0.0023405500292568754,
      "grad_norm": 0.5848795771598816,
      "learning_rate": 0.00029948767395100045,
      "loss": 1.6083,
      "step": 15
    },
    {
      "epoch": 0.002496586697874,
      "grad_norm": 0.6541223526000977,
      "learning_rate": 0.0002992624353817517,
      "loss": 1.6179,
      "step": 16
    },
    {
      "epoch": 0.0026526233664911254,
      "grad_norm": 0.6580960154533386,
      "learning_rate": 0.0002989963899530457,
      "loss": 1.4159,
      "step": 17
    },
    {
      "epoch": 0.0028086600351082502,
      "grad_norm": 0.5440740585327148,
      "learning_rate": 0.00029868961039904624,
      "loss": 1.5937,
      "step": 18
    },
    {
      "epoch": 0.0029646967037253755,
      "grad_norm": 0.6181334257125854,
      "learning_rate": 0.00029834218059022024,
      "loss": 1.5747,
      "step": 19
    },
    {
      "epoch": 0.0031207333723425007,
      "grad_norm": 0.7562193870544434,
      "learning_rate": 0.00029795419551040833,
      "loss": 1.4357,
      "step": 20
    },
    {
      "epoch": 0.0032767700409596255,
      "grad_norm": 0.9943856000900269,
      "learning_rate": 0.00029752576123085736,
      "loss": 1.5356,
      "step": 21
    },
    {
      "epoch": 0.0034328067095767507,
      "grad_norm": 0.7195516228675842,
      "learning_rate": 0.0002970569948812214,
      "loss": 1.3726,
      "step": 22
    },
    {
      "epoch": 0.0035888433781938755,
      "grad_norm": 0.9126946330070496,
      "learning_rate": 0.0002965480246175399,
      "loss": 1.3734,
      "step": 23
    },
    {
      "epoch": 0.0037448800468110007,
      "grad_norm": 0.6467637419700623,
      "learning_rate": 0.0002959989895872009,
      "loss": 1.3602,
      "step": 24
    },
    {
      "epoch": 0.0039009167154281255,
      "grad_norm": 0.5799360275268555,
      "learning_rate": 0.0002954100398908995,
      "loss": 1.2958,
      "step": 25
    },
    {
      "epoch": 0.0039009167154281255,
      "eval_loss": 1.5699554681777954,
      "eval_runtime": 4.237,
      "eval_samples_per_second": 11.801,
      "eval_steps_per_second": 1.652,
      "step": 25
    },
    {
      "epoch": 0.004056953384045251,
      "grad_norm": 0.6595892310142517,
      "learning_rate": 0.0002947813365416023,
      "loss": 1.3138,
      "step": 26
    },
    {
      "epoch": 0.004212990052662376,
      "grad_norm": 0.6430525779724121,
      "learning_rate": 0.0002941130514205272,
      "loss": 1.3484,
      "step": 27
    },
    {
      "epoch": 0.0043690267212795,
      "grad_norm": 0.6260256171226501,
      "learning_rate": 0.0002934053672301536,
      "loss": 1.4841,
      "step": 28
    },
    {
      "epoch": 0.004525063389896626,
      "grad_norm": 0.644149899482727,
      "learning_rate": 0.00029265847744427303,
      "loss": 1.3044,
      "step": 29
    },
    {
      "epoch": 0.004681100058513751,
      "grad_norm": 0.5812307596206665,
      "learning_rate": 0.00029187258625509513,
      "loss": 1.2462,
      "step": 30
    },
    {
      "epoch": 0.004837136727130876,
      "grad_norm": 0.5822577476501465,
      "learning_rate": 0.00029104790851742417,
      "loss": 1.333,
      "step": 31
    },
    {
      "epoch": 0.004993173395748,
      "grad_norm": 0.7623059749603271,
      "learning_rate": 0.0002901846696899191,
      "loss": 1.269,
      "step": 32
    },
    {
      "epoch": 0.005149210064365126,
      "grad_norm": 0.6771302223205566,
      "learning_rate": 0.00028928310577345606,
      "loss": 1.4905,
      "step": 33
    },
    {
      "epoch": 0.005305246732982251,
      "grad_norm": 0.7112970948219299,
      "learning_rate": 0.0002883434632466077,
      "loss": 1.3871,
      "step": 34
    },
    {
      "epoch": 0.005461283401599376,
      "grad_norm": 0.7185697555541992,
      "learning_rate": 0.00028736599899825856,
      "loss": 1.2095,
      "step": 35
    },
    {
      "epoch": 0.0056173200702165004,
      "grad_norm": 0.8005110025405884,
      "learning_rate": 0.00028635098025737434,
      "loss": 1.3555,
      "step": 36
    },
    {
      "epoch": 0.005773356738833626,
      "grad_norm": 0.8502066135406494,
      "learning_rate": 0.00028529868451994384,
      "loss": 1.3121,
      "step": 37
    },
    {
      "epoch": 0.005929393407450751,
      "grad_norm": 0.8016048073768616,
      "learning_rate": 0.0002842093994731145,
      "loss": 1.058,
      "step": 38
    },
    {
      "epoch": 0.006085430076067876,
      "grad_norm": 0.8298421502113342,
      "learning_rate": 0.00028308342291654174,
      "loss": 1.1519,
      "step": 39
    },
    {
      "epoch": 0.006241466744685001,
      "grad_norm": 0.9262282848358154,
      "learning_rate": 0.00028192106268097334,
      "loss": 1.2059,
      "step": 40
    },
    {
      "epoch": 0.006397503413302126,
      "grad_norm": 0.9439979195594788,
      "learning_rate": 0.00028072263654409154,
      "loss": 1.0447,
      "step": 41
    },
    {
      "epoch": 0.006553540081919251,
      "grad_norm": 1.0094624757766724,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.9239,
      "step": 42
    },
    {
      "epoch": 0.006709576750536376,
      "grad_norm": 0.9697788953781128,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.8678,
      "step": 43
    },
    {
      "epoch": 0.006865613419153501,
      "grad_norm": 1.063493251800537,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.7462,
      "step": 44
    },
    {
      "epoch": 0.007021650087770626,
      "grad_norm": 0.9183794856071472,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.9486,
      "step": 45
    },
    {
      "epoch": 0.007177686756387751,
      "grad_norm": 1.2309966087341309,
      "learning_rate": 0.000274201324672203,
      "loss": 0.9477,
      "step": 46
    },
    {
      "epoch": 0.007333723425004876,
      "grad_norm": 1.1949628591537476,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.9138,
      "step": 47
    },
    {
      "epoch": 0.0074897600936220015,
      "grad_norm": 1.3658891916275024,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.8504,
      "step": 48
    },
    {
      "epoch": 0.007645796762239126,
      "grad_norm": 1.4715008735656738,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.7391,
      "step": 49
    },
    {
      "epoch": 0.007801833430856251,
      "grad_norm": 2.4105653762817383,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.5911,
      "step": 50
    },
    {
      "epoch": 0.007801833430856251,
      "eval_loss": 1.770018458366394,
      "eval_runtime": 4.2306,
      "eval_samples_per_second": 11.819,
      "eval_steps_per_second": 1.655,
      "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": 7.88255238782976e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}