{
  "best_metric": 1.6822460889816284,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.026232948583420776,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005246589716684155,
      "grad_norm": 1.1576203107833862,
      "learning_rate": 1e-05,
      "loss": 3.0341,
      "step": 1
    },
    {
      "epoch": 0.0005246589716684155,
      "eval_loss": 5.070003986358643,
      "eval_runtime": 225.3527,
      "eval_samples_per_second": 14.244,
      "eval_steps_per_second": 3.563,
      "step": 1
    },
    {
      "epoch": 0.001049317943336831,
      "grad_norm": 1.779099702835083,
      "learning_rate": 2e-05,
      "loss": 3.6263,
      "step": 2
    },
    {
      "epoch": 0.0015739769150052466,
      "grad_norm": 1.921130657196045,
      "learning_rate": 3e-05,
      "loss": 3.8827,
      "step": 3
    },
    {
      "epoch": 0.002098635886673662,
      "grad_norm": 2.182387351989746,
      "learning_rate": 4e-05,
      "loss": 3.6948,
      "step": 4
    },
    {
      "epoch": 0.0026232948583420775,
      "grad_norm": 2.538600444793701,
      "learning_rate": 5e-05,
      "loss": 3.8578,
      "step": 5
    },
    {
      "epoch": 0.0031479538300104933,
      "grad_norm": 2.443502902984619,
      "learning_rate": 6e-05,
      "loss": 3.3757,
      "step": 6
    },
    {
      "epoch": 0.0036726128016789086,
      "grad_norm": 1.8905384540557861,
      "learning_rate": 7e-05,
      "loss": 3.4544,
      "step": 7
    },
    {
      "epoch": 0.004197271773347324,
      "grad_norm": 2.2534008026123047,
      "learning_rate": 8e-05,
      "loss": 3.1179,
      "step": 8
    },
    {
      "epoch": 0.00472193074501574,
      "grad_norm": 2.419541835784912,
      "learning_rate": 9e-05,
      "loss": 2.72,
      "step": 9
    },
    {
      "epoch": 0.005246589716684155,
      "grad_norm": 2.5247607231140137,
      "learning_rate": 0.0001,
      "loss": 2.6931,
      "step": 10
    },
    {
      "epoch": 0.005771248688352571,
      "grad_norm": 4.06483268737793,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.2914,
      "step": 11
    },
    {
      "epoch": 0.0062959076600209865,
      "grad_norm": 2.091320753097534,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8288,
      "step": 12
    },
    {
      "epoch": 0.006820566631689402,
      "grad_norm": 2.039874315261841,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7895,
      "step": 13
    },
    {
      "epoch": 0.007345225603357817,
      "grad_norm": 1.7094388008117676,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7866,
      "step": 14
    },
    {
      "epoch": 0.007869884575026232,
      "grad_norm": 1.3983663320541382,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.6987,
      "step": 15
    },
    {
      "epoch": 0.008394543546694649,
      "grad_norm": 2.4380130767822266,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5988,
      "step": 16
    },
    {
      "epoch": 0.008919202518363064,
      "grad_norm": 1.3538730144500732,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.7902,
      "step": 17
    },
    {
      "epoch": 0.00944386149003148,
      "grad_norm": 1.3163968324661255,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6041,
      "step": 18
    },
    {
      "epoch": 0.009968520461699895,
      "grad_norm": 1.4796921014785767,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6951,
      "step": 19
    },
    {
      "epoch": 0.01049317943336831,
      "grad_norm": 1.0245383977890015,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5077,
      "step": 20
    },
    {
      "epoch": 0.011017838405036727,
      "grad_norm": 1.2236641645431519,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8279,
      "step": 21
    },
    {
      "epoch": 0.011542497376705142,
      "grad_norm": 1.142067313194275,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.642,
      "step": 22
    },
    {
      "epoch": 0.012067156348373556,
      "grad_norm": 0.9749924540519714,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.7097,
      "step": 23
    },
    {
      "epoch": 0.012591815320041973,
      "grad_norm": 1.0015535354614258,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.431,
      "step": 24
    },
    {
      "epoch": 0.013116474291710388,
      "grad_norm": 0.9406030774116516,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5726,
      "step": 25
    },
    {
      "epoch": 0.013641133263378805,
      "grad_norm": 1.0338419675827026,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5226,
      "step": 26
    },
    {
      "epoch": 0.01416579223504722,
      "grad_norm": 1.0772449970245361,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.7288,
      "step": 27
    },
    {
      "epoch": 0.014690451206715634,
      "grad_norm": 1.0847026109695435,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4969,
      "step": 28
    },
    {
      "epoch": 0.015215110178384051,
      "grad_norm": 0.8713697195053101,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3882,
      "step": 29
    },
    {
      "epoch": 0.015739769150052464,
      "grad_norm": 1.143677830696106,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.53,
      "step": 30
    },
    {
      "epoch": 0.01626442812172088,
      "grad_norm": 1.400123119354248,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.6644,
      "step": 31
    },
    {
      "epoch": 0.016789087093389297,
      "grad_norm": 0.9827703833580017,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.6692,
      "step": 32
    },
    {
      "epoch": 0.017313746065057714,
      "grad_norm": 1.1392353773117065,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.6507,
      "step": 33
    },
    {
      "epoch": 0.017838405036726127,
      "grad_norm": 1.22384512424469,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.7154,
      "step": 34
    },
    {
      "epoch": 0.018363064008394544,
      "grad_norm": 0.9324412941932678,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.4078,
      "step": 35
    },
    {
      "epoch": 0.01888772298006296,
      "grad_norm": 1.0731570720672607,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.6842,
      "step": 36
    },
    {
      "epoch": 0.019412381951731374,
      "grad_norm": 0.8245493769645691,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1563,
      "step": 37
    },
    {
      "epoch": 0.01993704092339979,
      "grad_norm": 0.8980649709701538,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.5008,
      "step": 38
    },
    {
      "epoch": 0.020461699895068207,
      "grad_norm": 0.864634096622467,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2187,
      "step": 39
    },
    {
      "epoch": 0.02098635886673662,
      "grad_norm": 0.9761171340942383,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.381,
      "step": 40
    },
    {
      "epoch": 0.021511017838405037,
      "grad_norm": 1.0606969594955444,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.4,
      "step": 41
    },
    {
      "epoch": 0.022035676810073453,
      "grad_norm": 1.2640045881271362,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.6077,
      "step": 42
    },
    {
      "epoch": 0.022560335781741866,
      "grad_norm": 1.207768440246582,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5555,
      "step": 43
    },
    {
      "epoch": 0.023084994753410283,
      "grad_norm": 1.0950582027435303,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2568,
      "step": 44
    },
    {
      "epoch": 0.0236096537250787,
      "grad_norm": 1.3536014556884766,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.2712,
      "step": 45
    },
    {
      "epoch": 0.024134312696747113,
      "grad_norm": 1.1610876321792603,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4622,
      "step": 46
    },
    {
      "epoch": 0.02465897166841553,
      "grad_norm": 0.9861035346984863,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.1073,
      "step": 47
    },
    {
      "epoch": 0.025183630640083946,
      "grad_norm": 1.32306969165802,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2821,
      "step": 48
    },
    {
      "epoch": 0.02570828961175236,
      "grad_norm": 1.0001379251480103,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1953,
      "step": 49
    },
    {
      "epoch": 0.026232948583420776,
      "grad_norm": 1.2933019399642944,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.1879,
      "step": 50
    },
    {
      "epoch": 0.026232948583420776,
      "eval_loss": 1.6822460889816284,
      "eval_runtime": 226.9494,
      "eval_samples_per_second": 14.144,
      "eval_steps_per_second": 3.538,
      "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": 6.71020323176448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}