{
  "best_metric": 0.9335125088691711,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1890359168241966,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003780718336483932,
      "grad_norm": 25.16098976135254,
      "learning_rate": 1e-05,
      "loss": 4.6715,
      "step": 1
    },
    {
      "epoch": 0.003780718336483932,
      "eval_loss": 1.5147686004638672,
      "eval_runtime": 32.2459,
      "eval_samples_per_second": 13.831,
      "eval_steps_per_second": 3.473,
      "step": 1
    },
    {
      "epoch": 0.007561436672967864,
      "grad_norm": 27.060680389404297,
      "learning_rate": 2e-05,
      "loss": 4.6865,
      "step": 2
    },
    {
      "epoch": 0.011342155009451797,
      "grad_norm": 26.14573097229004,
      "learning_rate": 3e-05,
      "loss": 4.4814,
      "step": 3
    },
    {
      "epoch": 0.015122873345935728,
      "grad_norm": 22.122207641601562,
      "learning_rate": 4e-05,
      "loss": 4.1077,
      "step": 4
    },
    {
      "epoch": 0.01890359168241966,
      "grad_norm": 20.75678062438965,
      "learning_rate": 5e-05,
      "loss": 3.906,
      "step": 5
    },
    {
      "epoch": 0.022684310018903593,
      "grad_norm": 14.588601112365723,
      "learning_rate": 6e-05,
      "loss": 4.1167,
      "step": 6
    },
    {
      "epoch": 0.026465028355387523,
      "grad_norm": 14.807610511779785,
      "learning_rate": 7e-05,
      "loss": 3.8745,
      "step": 7
    },
    {
      "epoch": 0.030245746691871456,
      "grad_norm": 14.569311141967773,
      "learning_rate": 8e-05,
      "loss": 4.0067,
      "step": 8
    },
    {
      "epoch": 0.034026465028355386,
      "grad_norm": 11.986530303955078,
      "learning_rate": 9e-05,
      "loss": 3.772,
      "step": 9
    },
    {
      "epoch": 0.03780718336483932,
      "grad_norm": 14.717965126037598,
      "learning_rate": 0.0001,
      "loss": 3.762,
      "step": 10
    },
    {
      "epoch": 0.04158790170132325,
      "grad_norm": 13.476912498474121,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.0498,
      "step": 11
    },
    {
      "epoch": 0.045368620037807186,
      "grad_norm": 14.233503341674805,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.7616,
      "step": 12
    },
    {
      "epoch": 0.04914933837429111,
      "grad_norm": 12.872749328613281,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.7019,
      "step": 13
    },
    {
      "epoch": 0.052930056710775046,
      "grad_norm": 12.905577659606934,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.4222,
      "step": 14
    },
    {
      "epoch": 0.05671077504725898,
      "grad_norm": 13.652875900268555,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.4414,
      "step": 15
    },
    {
      "epoch": 0.06049149338374291,
      "grad_norm": 15.430229187011719,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.7592,
      "step": 16
    },
    {
      "epoch": 0.06427221172022685,
      "grad_norm": 11.641162872314453,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.6027,
      "step": 17
    },
    {
      "epoch": 0.06805293005671077,
      "grad_norm": 12.991557121276855,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.7312,
      "step": 18
    },
    {
      "epoch": 0.07183364839319471,
      "grad_norm": 12.716787338256836,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.8725,
      "step": 19
    },
    {
      "epoch": 0.07561436672967864,
      "grad_norm": 12.194295883178711,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.3815,
      "step": 20
    },
    {
      "epoch": 0.07939508506616257,
      "grad_norm": 10.72068977355957,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.0332,
      "step": 21
    },
    {
      "epoch": 0.0831758034026465,
      "grad_norm": 13.57220458984375,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.5567,
      "step": 22
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 11.49730396270752,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.6272,
      "step": 23
    },
    {
      "epoch": 0.09073724007561437,
      "grad_norm": 13.56385326385498,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.0481,
      "step": 24
    },
    {
      "epoch": 0.0945179584120983,
      "grad_norm": 11.78315544128418,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.3534,
      "step": 25
    },
    {
      "epoch": 0.09829867674858223,
      "grad_norm": 18.407567977905273,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.2758,
      "step": 26
    },
    {
      "epoch": 0.10207939508506617,
      "grad_norm": 13.258454322814941,
      "learning_rate": 9.803768380684242e-05,
      "loss": 3.6035,
      "step": 27
    },
    {
      "epoch": 0.10586011342155009,
      "grad_norm": 10.505517959594727,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.2197,
      "step": 28
    },
    {
      "epoch": 0.10964083175803403,
      "grad_norm": 11.3196439743042,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.6479,
      "step": 29
    },
    {
      "epoch": 0.11342155009451796,
      "grad_norm": 12.575491905212402,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.5406,
      "step": 30
    },
    {
      "epoch": 0.11720226843100189,
      "grad_norm": 12.494804382324219,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.6458,
      "step": 31
    },
    {
      "epoch": 0.12098298676748583,
      "grad_norm": 14.734025001525879,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.5121,
      "step": 32
    },
    {
      "epoch": 0.12476370510396975,
      "grad_norm": 10.00881290435791,
      "learning_rate": 9.642770192448536e-05,
      "loss": 3.2603,
      "step": 33
    },
    {
      "epoch": 0.1285444234404537,
      "grad_norm": 11.375361442565918,
      "learning_rate": 9.611448774886924e-05,
      "loss": 3.5365,
      "step": 34
    },
    {
      "epoch": 0.1323251417769376,
      "grad_norm": 10.176946640014648,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.3114,
      "step": 35
    },
    {
      "epoch": 0.13610586011342155,
      "grad_norm": 10.291150093078613,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.2982,
      "step": 36
    },
    {
      "epoch": 0.13988657844990549,
      "grad_norm": 13.161905288696289,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.9598,
      "step": 37
    },
    {
      "epoch": 0.14366729678638943,
      "grad_norm": 11.773653030395508,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.2511,
      "step": 38
    },
    {
      "epoch": 0.14744801512287334,
      "grad_norm": 12.06856632232666,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.7918,
      "step": 39
    },
    {
      "epoch": 0.15122873345935728,
      "grad_norm": 12.7516450881958,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.2789,
      "step": 40
    },
    {
      "epoch": 0.15500945179584122,
      "grad_norm": 11.407308578491211,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.479,
      "step": 41
    },
    {
      "epoch": 0.15879017013232513,
      "grad_norm": 11.646713256835938,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.302,
      "step": 42
    },
    {
      "epoch": 0.16257088846880907,
      "grad_norm": 10.183646202087402,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.882,
      "step": 43
    },
    {
      "epoch": 0.166351606805293,
      "grad_norm": 11.927104949951172,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.5429,
      "step": 44
    },
    {
      "epoch": 0.17013232514177692,
      "grad_norm": 10.855883598327637,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.4548,
      "step": 45
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 11.88790512084961,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.0145,
      "step": 46
    },
    {
      "epoch": 0.1776937618147448,
      "grad_norm": 13.963061332702637,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.2849,
      "step": 47
    },
    {
      "epoch": 0.18147448015122875,
      "grad_norm": 13.203959465026855,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.8767,
      "step": 48
    },
    {
      "epoch": 0.18525519848771266,
      "grad_norm": 16.107746124267578,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.171,
      "step": 49
    },
    {
      "epoch": 0.1890359168241966,
      "grad_norm": 15.196197509765625,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.0762,
      "step": 50
    },
    {
      "epoch": 0.1890359168241966,
      "eval_loss": 0.9335125088691711,
      "eval_runtime": 32.8629,
      "eval_samples_per_second": 13.572,
      "eval_steps_per_second": 3.408,
      "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": 7.15499809800192e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}