{
  "best_metric": 1.5200674533843994,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.026319252533228057,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005263850506645612,
      "grad_norm": 93.07259368896484,
      "learning_rate": 1e-05,
      "loss": 12.3105,
      "step": 1
    },
    {
      "epoch": 0.0005263850506645612,
      "eval_loss": 2.796645402908325,
      "eval_runtime": 309.2946,
      "eval_samples_per_second": 10.346,
      "eval_steps_per_second": 2.587,
      "step": 1
    },
    {
      "epoch": 0.0010527701013291224,
      "grad_norm": 131.77566528320312,
      "learning_rate": 2e-05,
      "loss": 9.2268,
      "step": 2
    },
    {
      "epoch": 0.0015791551519936833,
      "grad_norm": 71.25743865966797,
      "learning_rate": 3e-05,
      "loss": 8.0512,
      "step": 3
    },
    {
      "epoch": 0.0021055402026582447,
      "grad_norm": 46.8036003112793,
      "learning_rate": 4e-05,
      "loss": 7.2551,
      "step": 4
    },
    {
      "epoch": 0.0026319252533228057,
      "grad_norm": 36.05014419555664,
      "learning_rate": 5e-05,
      "loss": 6.3495,
      "step": 5
    },
    {
      "epoch": 0.0031583103039873666,
      "grad_norm": 26.287073135375977,
      "learning_rate": 6e-05,
      "loss": 5.9319,
      "step": 6
    },
    {
      "epoch": 0.003684695354651928,
      "grad_norm": 38.00836944580078,
      "learning_rate": 7e-05,
      "loss": 5.5911,
      "step": 7
    },
    {
      "epoch": 0.004211080405316489,
      "grad_norm": 23.294231414794922,
      "learning_rate": 8e-05,
      "loss": 5.2376,
      "step": 8
    },
    {
      "epoch": 0.00473746545598105,
      "grad_norm": 22.907855987548828,
      "learning_rate": 9e-05,
      "loss": 4.5457,
      "step": 9
    },
    {
      "epoch": 0.005263850506645611,
      "grad_norm": 27.766204833984375,
      "learning_rate": 0.0001,
      "loss": 6.4629,
      "step": 10
    },
    {
      "epoch": 0.005790235557310172,
      "grad_norm": 24.227497100830078,
      "learning_rate": 9.999316524962345e-05,
      "loss": 5.8682,
      "step": 11
    },
    {
      "epoch": 0.006316620607974733,
      "grad_norm": 20.358135223388672,
      "learning_rate": 9.997266286704631e-05,
      "loss": 5.0779,
      "step": 12
    },
    {
      "epoch": 0.006843005658639294,
      "grad_norm": 22.879426956176758,
      "learning_rate": 9.993849845741524e-05,
      "loss": 5.0858,
      "step": 13
    },
    {
      "epoch": 0.007369390709303856,
      "grad_norm": 22.2658634185791,
      "learning_rate": 9.989068136093873e-05,
      "loss": 5.305,
      "step": 14
    },
    {
      "epoch": 0.007895775759968417,
      "grad_norm": 29.477561950683594,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.8577,
      "step": 15
    },
    {
      "epoch": 0.008422160810632979,
      "grad_norm": 21.121549606323242,
      "learning_rate": 9.975414512725057e-05,
      "loss": 6.6094,
      "step": 16
    },
    {
      "epoch": 0.008948545861297539,
      "grad_norm": 21.887968063354492,
      "learning_rate": 9.966546331768191e-05,
      "loss": 6.1797,
      "step": 17
    },
    {
      "epoch": 0.0094749309119621,
      "grad_norm": 19.13234519958496,
      "learning_rate": 9.956320346634876e-05,
      "loss": 5.6551,
      "step": 18
    },
    {
      "epoch": 0.010001315962626661,
      "grad_norm": 18.616533279418945,
      "learning_rate": 9.944739353007344e-05,
      "loss": 5.9483,
      "step": 19
    },
    {
      "epoch": 0.010527701013291223,
      "grad_norm": 18.95231056213379,
      "learning_rate": 9.931806517013612e-05,
      "loss": 5.4522,
      "step": 20
    },
    {
      "epoch": 0.011054086063955783,
      "grad_norm": 18.209264755249023,
      "learning_rate": 9.917525374361912e-05,
      "loss": 6.1536,
      "step": 21
    },
    {
      "epoch": 0.011580471114620345,
      "grad_norm": 16.42949867248535,
      "learning_rate": 9.901899829374047e-05,
      "loss": 6.0107,
      "step": 22
    },
    {
      "epoch": 0.012106856165284906,
      "grad_norm": 15.05119514465332,
      "learning_rate": 9.884934153917997e-05,
      "loss": 6.5074,
      "step": 23
    },
    {
      "epoch": 0.012633241215949467,
      "grad_norm": 16.25713348388672,
      "learning_rate": 9.86663298624003e-05,
      "loss": 7.0152,
      "step": 24
    },
    {
      "epoch": 0.013159626266614028,
      "grad_norm": 13.90926742553711,
      "learning_rate": 9.847001329696653e-05,
      "loss": 5.5108,
      "step": 25
    },
    {
      "epoch": 0.013686011317278588,
      "grad_norm": 18.535930633544922,
      "learning_rate": 9.826044551386744e-05,
      "loss": 5.9702,
      "step": 26
    },
    {
      "epoch": 0.01421239636794315,
      "grad_norm": 15.170503616333008,
      "learning_rate": 9.803768380684242e-05,
      "loss": 5.659,
      "step": 27
    },
    {
      "epoch": 0.014738781418607712,
      "grad_norm": 17.371408462524414,
      "learning_rate": 9.780178907671789e-05,
      "loss": 5.9414,
      "step": 28
    },
    {
      "epoch": 0.015265166469272272,
      "grad_norm": 15.820178031921387,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.1419,
      "step": 29
    },
    {
      "epoch": 0.015791551519936834,
      "grad_norm": 14.776792526245117,
      "learning_rate": 9.729086208503174e-05,
      "loss": 5.402,
      "step": 30
    },
    {
      "epoch": 0.016317936570601394,
      "grad_norm": 16.17049217224121,
      "learning_rate": 9.701596950580806e-05,
      "loss": 6.1015,
      "step": 31
    },
    {
      "epoch": 0.016844321621265958,
      "grad_norm": 15.148641586303711,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.9903,
      "step": 32
    },
    {
      "epoch": 0.017370706671930518,
      "grad_norm": 15.8573637008667,
      "learning_rate": 9.642770192448536e-05,
      "loss": 6.3152,
      "step": 33
    },
    {
      "epoch": 0.017897091722595078,
      "grad_norm": 14.71132755279541,
      "learning_rate": 9.611448774886924e-05,
      "loss": 5.4481,
      "step": 34
    },
    {
      "epoch": 0.018423476773259638,
      "grad_norm": 14.21374797821045,
      "learning_rate": 9.578866633275288e-05,
      "loss": 6.3535,
      "step": 35
    },
    {
      "epoch": 0.0189498618239242,
      "grad_norm": 15.075162887573242,
      "learning_rate": 9.545032675245813e-05,
      "loss": 7.1606,
      "step": 36
    },
    {
      "epoch": 0.01947624687458876,
      "grad_norm": 14.579214096069336,
      "learning_rate": 9.509956150664796e-05,
      "loss": 7.253,
      "step": 37
    },
    {
      "epoch": 0.020002631925253322,
      "grad_norm": 13.596733093261719,
      "learning_rate": 9.473646649103818e-05,
      "loss": 6.1713,
      "step": 38
    },
    {
      "epoch": 0.020529016975917885,
      "grad_norm": 12.464555740356445,
      "learning_rate": 9.43611409721806e-05,
      "loss": 5.6624,
      "step": 39
    },
    {
      "epoch": 0.021055402026582445,
      "grad_norm": 15.085432052612305,
      "learning_rate": 9.397368756032445e-05,
      "loss": 6.6267,
      "step": 40
    },
    {
      "epoch": 0.021581787077247006,
      "grad_norm": 15.069063186645508,
      "learning_rate": 9.357421218136386e-05,
      "loss": 7.4622,
      "step": 41
    },
    {
      "epoch": 0.022108172127911566,
      "grad_norm": 13.953812599182129,
      "learning_rate": 9.316282404787871e-05,
      "loss": 6.3665,
      "step": 42
    },
    {
      "epoch": 0.02263455717857613,
      "grad_norm": 13.846559524536133,
      "learning_rate": 9.273963562927695e-05,
      "loss": 7.0589,
      "step": 43
    },
    {
      "epoch": 0.02316094222924069,
      "grad_norm": 14.49377155303955,
      "learning_rate": 9.230476262104677e-05,
      "loss": 7.26,
      "step": 44
    },
    {
      "epoch": 0.02368732727990525,
      "grad_norm": 12.730331420898438,
      "learning_rate": 9.185832391312644e-05,
      "loss": 7.1364,
      "step": 45
    },
    {
      "epoch": 0.024213712330569813,
      "grad_norm": 12.382709503173828,
      "learning_rate": 9.140044155740101e-05,
      "loss": 6.424,
      "step": 46
    },
    {
      "epoch": 0.024740097381234373,
      "grad_norm": 13.245918273925781,
      "learning_rate": 9.093124073433463e-05,
      "loss": 6.5557,
      "step": 47
    },
    {
      "epoch": 0.025266482431898933,
      "grad_norm": 16.19131851196289,
      "learning_rate": 9.045084971874738e-05,
      "loss": 6.636,
      "step": 48
    },
    {
      "epoch": 0.025792867482563497,
      "grad_norm": 13.08187484741211,
      "learning_rate": 8.995939984474624e-05,
      "loss": 7.1473,
      "step": 49
    },
    {
      "epoch": 0.026319252533228057,
      "grad_norm": 13.130578994750977,
      "learning_rate": 8.945702546981969e-05,
      "loss": 7.0864,
      "step": 50
    },
    {
      "epoch": 0.026319252533228057,
      "eval_loss": 1.5200674533843994,
      "eval_runtime": 312.2573,
      "eval_samples_per_second": 10.248,
      "eval_steps_per_second": 2.562,
      "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": 7.226539945387622e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}