{
  "best_metric": 0.2953316271305084,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.012046741356463078,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024093482712926153,
      "grad_norm": 2.7897026538848877,
      "learning_rate": 1e-05,
      "loss": 5.8362,
      "step": 1
    },
    {
      "epoch": 0.00024093482712926153,
      "eval_loss": 5.242364883422852,
      "eval_runtime": 509.5798,
      "eval_samples_per_second": 13.717,
      "eval_steps_per_second": 3.43,
      "step": 1
    },
    {
      "epoch": 0.00048186965425852307,
      "grad_norm": 2.6845810413360596,
      "learning_rate": 2e-05,
      "loss": 4.8628,
      "step": 2
    },
    {
      "epoch": 0.0007228044813877846,
      "grad_norm": 2.5649805068969727,
      "learning_rate": 3e-05,
      "loss": 4.7359,
      "step": 3
    },
    {
      "epoch": 0.0009637393085170461,
      "grad_norm": 3.1907050609588623,
      "learning_rate": 4e-05,
      "loss": 5.09,
      "step": 4
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 2.8700222969055176,
      "learning_rate": 5e-05,
      "loss": 4.6159,
      "step": 5
    },
    {
      "epoch": 0.0014456089627755693,
      "grad_norm": 3.2576119899749756,
      "learning_rate": 6e-05,
      "loss": 4.6056,
      "step": 6
    },
    {
      "epoch": 0.0016865437899048308,
      "grad_norm": 3.8452327251434326,
      "learning_rate": 7e-05,
      "loss": 4.3039,
      "step": 7
    },
    {
      "epoch": 0.0019274786170340923,
      "grad_norm": 3.6989893913269043,
      "learning_rate": 8e-05,
      "loss": 3.6032,
      "step": 8
    },
    {
      "epoch": 0.0021684134441633538,
      "grad_norm": 3.7668285369873047,
      "learning_rate": 9e-05,
      "loss": 2.9093,
      "step": 9
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 3.5740230083465576,
      "learning_rate": 0.0001,
      "loss": 2.2147,
      "step": 10
    },
    {
      "epoch": 0.002650283098421877,
      "grad_norm": 3.976719856262207,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7271,
      "step": 11
    },
    {
      "epoch": 0.0028912179255511385,
      "grad_norm": 2.956078290939331,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9299,
      "step": 12
    },
    {
      "epoch": 0.0031321527526804,
      "grad_norm": 3.046994209289551,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7804,
      "step": 13
    },
    {
      "epoch": 0.0033730875798096615,
      "grad_norm": 2.9345862865448,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5992,
      "step": 14
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 2.556488037109375,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4438,
      "step": 15
    },
    {
      "epoch": 0.0038549572340681845,
      "grad_norm": 3.2892167568206787,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4652,
      "step": 16
    },
    {
      "epoch": 0.004095892061197446,
      "grad_norm": 2.5346927642822266,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3075,
      "step": 17
    },
    {
      "epoch": 0.0043368268883267076,
      "grad_norm": 1.4730305671691895,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2703,
      "step": 18
    },
    {
      "epoch": 0.004577761715455969,
      "grad_norm": 2.9341955184936523,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.3485,
      "step": 19
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.3553968667984009,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3135,
      "step": 20
    },
    {
      "epoch": 0.005059631369714492,
      "grad_norm": 1.0334441661834717,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2394,
      "step": 21
    },
    {
      "epoch": 0.005300566196843754,
      "grad_norm": 1.1508598327636719,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2423,
      "step": 22
    },
    {
      "epoch": 0.005541501023973015,
      "grad_norm": 2.3248560428619385,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3399,
      "step": 23
    },
    {
      "epoch": 0.005782435851102277,
      "grad_norm": 1.3670281171798706,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2859,
      "step": 24
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.5140188932418823,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.2533,
      "step": 25
    },
    {
      "epoch": 0.0062643055053608,
      "grad_norm": 1.4202511310577393,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2423,
      "step": 26
    },
    {
      "epoch": 0.006505240332490061,
      "grad_norm": 1.0033921003341675,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2302,
      "step": 27
    },
    {
      "epoch": 0.006746175159619323,
      "grad_norm": 1.338563323020935,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2563,
      "step": 28
    },
    {
      "epoch": 0.006987109986748585,
      "grad_norm": 1.742248296737671,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.356,
      "step": 29
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.6856114864349365,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3796,
      "step": 30
    },
    {
      "epoch": 0.007468979641007107,
      "grad_norm": 1.2257651090621948,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.3383,
      "step": 31
    },
    {
      "epoch": 0.007709914468136369,
      "grad_norm": 1.0800436735153198,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2814,
      "step": 32
    },
    {
      "epoch": 0.00795084929526563,
      "grad_norm": 1.1578192710876465,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2607,
      "step": 33
    },
    {
      "epoch": 0.008191784122394892,
      "grad_norm": 0.7927069067955017,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2871,
      "step": 34
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 0.7488431930541992,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2815,
      "step": 35
    },
    {
      "epoch": 0.008673653776653415,
      "grad_norm": 0.8880829811096191,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2472,
      "step": 36
    },
    {
      "epoch": 0.008914588603782676,
      "grad_norm": 0.785861611366272,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.254,
      "step": 37
    },
    {
      "epoch": 0.009155523430911939,
      "grad_norm": 0.9267710447311401,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.31,
      "step": 38
    },
    {
      "epoch": 0.0093964582580412,
      "grad_norm": 0.9613037109375,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2692,
      "step": 39
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 0.7821824550628662,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2649,
      "step": 40
    },
    {
      "epoch": 0.009878327912299723,
      "grad_norm": 0.34622684121131897,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.2259,
      "step": 41
    },
    {
      "epoch": 0.010119262739428984,
      "grad_norm": 0.9428150057792664,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3055,
      "step": 42
    },
    {
      "epoch": 0.010360197566558246,
      "grad_norm": 0.6529460549354553,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2491,
      "step": 43
    },
    {
      "epoch": 0.010601132393687507,
      "grad_norm": 0.959650456905365,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2854,
      "step": 44
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 0.9203677773475647,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2827,
      "step": 45
    },
    {
      "epoch": 0.01108300204794603,
      "grad_norm": 0.6406137943267822,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2689,
      "step": 46
    },
    {
      "epoch": 0.011323936875075291,
      "grad_norm": 0.6154417395591736,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.28,
      "step": 47
    },
    {
      "epoch": 0.011564871702204554,
      "grad_norm": 0.6750221848487854,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.255,
      "step": 48
    },
    {
      "epoch": 0.011805806529333815,
      "grad_norm": 0.8649730682373047,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3184,
      "step": 49
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 0.9113279581069946,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3207,
      "step": 50
    },
    {
      "epoch": 0.012046741356463078,
      "eval_loss": 0.2953316271305084,
      "eval_runtime": 511.8644,
      "eval_samples_per_second": 13.656,
      "eval_steps_per_second": 3.415,
      "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": 6.731079410201395e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}