{
  "best_metric": 0.47327739000320435,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.013232545445523264,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002646509089104653,
      "grad_norm": 0.3483770787715912,
      "learning_rate": 5e-05,
      "loss": 1.36,
      "step": 1
    },
    {
      "epoch": 0.0002646509089104653,
      "eval_loss": 1.4053138494491577,
      "eval_runtime": 327.5318,
      "eval_samples_per_second": 77.721,
      "eval_steps_per_second": 9.715,
      "step": 1
    },
    {
      "epoch": 0.0005293018178209306,
      "grad_norm": 0.4148556590080261,
      "learning_rate": 0.0001,
      "loss": 1.0781,
      "step": 2
    },
    {
      "epoch": 0.0007939527267313959,
      "grad_norm": 0.5990642309188843,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.2539,
      "step": 3
    },
    {
      "epoch": 0.0010586036356418612,
      "grad_norm": 0.951532781124115,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2818,
      "step": 4
    },
    {
      "epoch": 0.0013232545445523265,
      "grad_norm": 0.6008241772651672,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.1372,
      "step": 5
    },
    {
      "epoch": 0.0015879054534627918,
      "grad_norm": 0.6191050410270691,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.9204,
      "step": 6
    },
    {
      "epoch": 0.001852556362373257,
      "grad_norm": 0.7561085820198059,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.8789,
      "step": 7
    },
    {
      "epoch": 0.0021172072712837223,
      "grad_norm": 0.7463423609733582,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7839,
      "step": 8
    },
    {
      "epoch": 0.0023818581801941874,
      "grad_norm": 0.8081836700439453,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.7711,
      "step": 9
    },
    {
      "epoch": 0.002646509089104653,
      "grad_norm": 0.6905570030212402,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7002,
      "step": 10
    },
    {
      "epoch": 0.002911159998015118,
      "grad_norm": 0.7780414819717407,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5679,
      "step": 11
    },
    {
      "epoch": 0.0031758109069255835,
      "grad_norm": 0.8098108172416687,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5429,
      "step": 12
    },
    {
      "epoch": 0.0034404618158360486,
      "grad_norm": 0.8134570121765137,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.2309,
      "step": 13
    },
    {
      "epoch": 0.003705112724746514,
      "grad_norm": 0.8133260011672974,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9066,
      "step": 14
    },
    {
      "epoch": 0.00396976363365698,
      "grad_norm": 0.9493969678878784,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.8138,
      "step": 15
    },
    {
      "epoch": 0.004234414542567445,
      "grad_norm": 1.1345733404159546,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6304,
      "step": 16
    },
    {
      "epoch": 0.00449906545147791,
      "grad_norm": 0.6826173663139343,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6701,
      "step": 17
    },
    {
      "epoch": 0.004763716360388375,
      "grad_norm": 0.8246356248855591,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.657,
      "step": 18
    },
    {
      "epoch": 0.005028367269298841,
      "grad_norm": 0.915769636631012,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5794,
      "step": 19
    },
    {
      "epoch": 0.005293018178209306,
      "grad_norm": 0.6912714242935181,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5258,
      "step": 20
    },
    {
      "epoch": 0.005557669087119771,
      "grad_norm": 0.572390079498291,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.4488,
      "step": 21
    },
    {
      "epoch": 0.005822319996030236,
      "grad_norm": 0.5275750756263733,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4807,
      "step": 22
    },
    {
      "epoch": 0.006086970904940702,
      "grad_norm": 0.3919845521450043,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.4648,
      "step": 23
    },
    {
      "epoch": 0.006351621813851167,
      "grad_norm": 0.4671150743961334,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.3755,
      "step": 24
    },
    {
      "epoch": 0.006616272722761632,
      "grad_norm": 0.661691427230835,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.341,
      "step": 25
    },
    {
      "epoch": 0.006616272722761632,
      "eval_loss": 0.5180265307426453,
      "eval_runtime": 326.2917,
      "eval_samples_per_second": 78.016,
      "eval_steps_per_second": 9.752,
      "step": 25
    },
    {
      "epoch": 0.006880923631672097,
      "grad_norm": 0.420188307762146,
      "learning_rate": 5e-05,
      "loss": 0.937,
      "step": 26
    },
    {
      "epoch": 0.007145574540582563,
      "grad_norm": 0.5700767636299133,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.695,
      "step": 27
    },
    {
      "epoch": 0.007410225449493028,
      "grad_norm": 0.5167895555496216,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.6035,
      "step": 28
    },
    {
      "epoch": 0.007674876358403493,
      "grad_norm": 0.6467077732086182,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.4506,
      "step": 29
    },
    {
      "epoch": 0.00793952726731396,
      "grad_norm": 0.45690345764160156,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.5379,
      "step": 30
    },
    {
      "epoch": 0.008204178176224423,
      "grad_norm": 0.4311066269874573,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.4912,
      "step": 31
    },
    {
      "epoch": 0.00846882908513489,
      "grad_norm": 0.39850619435310364,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.46,
      "step": 32
    },
    {
      "epoch": 0.008733479994045355,
      "grad_norm": 0.3314412534236908,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.4209,
      "step": 33
    },
    {
      "epoch": 0.00899813090295582,
      "grad_norm": 0.4438161849975586,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3976,
      "step": 34
    },
    {
      "epoch": 0.009262781811866285,
      "grad_norm": 0.36361584067344666,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.3816,
      "step": 35
    },
    {
      "epoch": 0.00952743272077675,
      "grad_norm": 0.3931230902671814,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.3412,
      "step": 36
    },
    {
      "epoch": 0.009792083629687216,
      "grad_norm": 0.4425284266471863,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3258,
      "step": 37
    },
    {
      "epoch": 0.010056734538597682,
      "grad_norm": 0.32975614070892334,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9773,
      "step": 38
    },
    {
      "epoch": 0.010321385447508146,
      "grad_norm": 0.3308790326118469,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6732,
      "step": 39
    },
    {
      "epoch": 0.010586036356418612,
      "grad_norm": 0.4055446982383728,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6384,
      "step": 40
    },
    {
      "epoch": 0.010850687265329078,
      "grad_norm": 0.4504941999912262,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.4432,
      "step": 41
    },
    {
      "epoch": 0.011115338174239542,
      "grad_norm": 0.3198263347148895,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.543,
      "step": 42
    },
    {
      "epoch": 0.011379989083150008,
      "grad_norm": 0.34442195296287537,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.5181,
      "step": 43
    },
    {
      "epoch": 0.011644639992060472,
      "grad_norm": 0.3284602463245392,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4109,
      "step": 44
    },
    {
      "epoch": 0.011909290900970938,
      "grad_norm": 0.33481574058532715,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.3932,
      "step": 45
    },
    {
      "epoch": 0.012173941809881404,
      "grad_norm": 0.3298023045063019,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.3983,
      "step": 46
    },
    {
      "epoch": 0.012438592718791868,
      "grad_norm": 0.28835529088974,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.3985,
      "step": 47
    },
    {
      "epoch": 0.012703243627702334,
      "grad_norm": 0.343580037355423,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.3632,
      "step": 48
    },
    {
      "epoch": 0.0129678945366128,
      "grad_norm": 0.3463713228702545,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.2849,
      "step": 49
    },
    {
      "epoch": 0.013232545445523264,
      "grad_norm": 0.4292154908180237,
      "learning_rate": 0.0,
      "loss": 0.3038,
      "step": 50
    },
    {
      "epoch": 0.013232545445523264,
      "eval_loss": 0.47327739000320435,
      "eval_runtime": 328.3977,
      "eval_samples_per_second": 77.516,
      "eval_steps_per_second": 9.689,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0683649061237555e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}