{
  "best_metric": 0.000480437942314893,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.11092623405435385,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022185246810870773,
      "grad_norm": 0.4043624699115753,
      "learning_rate": 1e-05,
      "loss": 0.0218,
      "step": 1
    },
    {
      "epoch": 0.0022185246810870773,
      "eval_loss": 0.06729624420404434,
      "eval_runtime": 61.4063,
      "eval_samples_per_second": 12.36,
      "eval_steps_per_second": 3.094,
      "step": 1
    },
    {
      "epoch": 0.004437049362174155,
      "grad_norm": 0.5323770642280579,
      "learning_rate": 2e-05,
      "loss": 0.0272,
      "step": 2
    },
    {
      "epoch": 0.0066555740432612314,
      "grad_norm": 0.39081913232803345,
      "learning_rate": 3e-05,
      "loss": 0.0224,
      "step": 3
    },
    {
      "epoch": 0.00887409872434831,
      "grad_norm": 0.2355053573846817,
      "learning_rate": 4e-05,
      "loss": 0.014,
      "step": 4
    },
    {
      "epoch": 0.011092623405435386,
      "grad_norm": 0.20560254156589508,
      "learning_rate": 5e-05,
      "loss": 0.007,
      "step": 5
    },
    {
      "epoch": 0.013311148086522463,
      "grad_norm": 0.3132166564464569,
      "learning_rate": 6e-05,
      "loss": 0.003,
      "step": 6
    },
    {
      "epoch": 0.01552967276760954,
      "grad_norm": 0.15627335011959076,
      "learning_rate": 7e-05,
      "loss": 0.0015,
      "step": 7
    },
    {
      "epoch": 0.01774819744869662,
      "grad_norm": 0.5707840919494629,
      "learning_rate": 8e-05,
      "loss": 0.0024,
      "step": 8
    },
    {
      "epoch": 0.019966722129783693,
      "grad_norm": 2.011200189590454,
      "learning_rate": 9e-05,
      "loss": 0.0111,
      "step": 9
    },
    {
      "epoch": 0.022185246810870772,
      "grad_norm": 0.16989780962467194,
      "learning_rate": 0.0001,
      "loss": 0.0006,
      "step": 10
    },
    {
      "epoch": 0.024403771491957847,
      "grad_norm": 0.2541530728340149,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0019,
      "step": 11
    },
    {
      "epoch": 0.026622296173044926,
      "grad_norm": 0.03248166665434837,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0004,
      "step": 12
    },
    {
      "epoch": 0.028840820854132,
      "grad_norm": 0.07936106622219086,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0003,
      "step": 13
    },
    {
      "epoch": 0.03105934553521908,
      "grad_norm": 0.5282761454582214,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0007,
      "step": 14
    },
    {
      "epoch": 0.033277870216306155,
      "grad_norm": 0.09327798336744308,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0004,
      "step": 15
    },
    {
      "epoch": 0.03549639489739324,
      "grad_norm": 0.11142992228269577,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0002,
      "step": 16
    },
    {
      "epoch": 0.03771491957848031,
      "grad_norm": 0.09578566998243332,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0002,
      "step": 17
    },
    {
      "epoch": 0.03993344425956739,
      "grad_norm": 0.12011338770389557,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0011,
      "step": 18
    },
    {
      "epoch": 0.04215196894065446,
      "grad_norm": 0.1782669723033905,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0004,
      "step": 19
    },
    {
      "epoch": 0.044370493621741544,
      "grad_norm": 0.014049503020942211,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0001,
      "step": 20
    },
    {
      "epoch": 0.04658901830282862,
      "grad_norm": 0.0027807666920125484,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.048807542983915694,
      "grad_norm": 0.7871737480163574,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0008,
      "step": 22
    },
    {
      "epoch": 0.051026067665002776,
      "grad_norm": 0.0016747310291975737,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.05324459234608985,
      "grad_norm": 0.008830898441374302,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05546311702717693,
      "grad_norm": 0.2443714439868927,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.001,
      "step": 25
    },
    {
      "epoch": 0.057681641708264,
      "grad_norm": 0.03958623483777046,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0001,
      "step": 26
    },
    {
      "epoch": 0.059900166389351084,
      "grad_norm": 1.1243643760681152,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0021,
      "step": 27
    },
    {
      "epoch": 0.06211869107043816,
      "grad_norm": 0.3090110719203949,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0014,
      "step": 28
    },
    {
      "epoch": 0.06433721575152523,
      "grad_norm": 0.07031821459531784,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0001,
      "step": 29
    },
    {
      "epoch": 0.06655574043261231,
      "grad_norm": 0.12087582051753998,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.06877426511369938,
      "grad_norm": 0.19821757078170776,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0006,
      "step": 31
    },
    {
      "epoch": 0.07099278979478647,
      "grad_norm": 0.3484724760055542,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0008,
      "step": 32
    },
    {
      "epoch": 0.07321131447587355,
      "grad_norm": 0.2582204341888428,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0005,
      "step": 33
    },
    {
      "epoch": 0.07542983915696062,
      "grad_norm": 0.2562151551246643,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0006,
      "step": 34
    },
    {
      "epoch": 0.0776483638380477,
      "grad_norm": 0.3555851876735687,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0003,
      "step": 35
    },
    {
      "epoch": 0.07986688851913477,
      "grad_norm": 0.0783495083451271,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0015,
      "step": 36
    },
    {
      "epoch": 0.08208541320022185,
      "grad_norm": 0.005454628728330135,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.08430393788130892,
      "grad_norm": 1.9236397743225098,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0027,
      "step": 38
    },
    {
      "epoch": 0.08652246256239601,
      "grad_norm": 0.003536924021318555,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.08874098724348309,
      "grad_norm": 10.864886283874512,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0289,
      "step": 40
    },
    {
      "epoch": 0.09095951192457016,
      "grad_norm": 0.004927365109324455,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0001,
      "step": 41
    },
    {
      "epoch": 0.09317803660565724,
      "grad_norm": 0.4415525794029236,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0021,
      "step": 42
    },
    {
      "epoch": 0.09539656128674431,
      "grad_norm": 0.024674855172634125,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0001,
      "step": 43
    },
    {
      "epoch": 0.09761508596783139,
      "grad_norm": 0.36924272775650024,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0011,
      "step": 44
    },
    {
      "epoch": 0.09983361064891846,
      "grad_norm": 0.09015581756830215,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0005,
      "step": 45
    },
    {
      "epoch": 0.10205213533000555,
      "grad_norm": 0.01934026926755905,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0002,
      "step": 46
    },
    {
      "epoch": 0.10427066001109263,
      "grad_norm": 0.004875717218965292,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.1064891846921797,
      "grad_norm": 0.008644173853099346,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.10870770937326678,
      "grad_norm": 0.3154628276824951,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0005,
      "step": 49
    },
    {
      "epoch": 0.11092623405435385,
      "grad_norm": 0.23197360336780548,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0007,
      "step": 50
    },
    {
      "epoch": 0.11092623405435385,
      "eval_loss": 0.000480437942314893,
      "eval_runtime": 62.4124,
      "eval_samples_per_second": 12.161,
      "eval_steps_per_second": 3.044,
      "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": 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": 7.655843656472986e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}