{
  "best_metric": 0.600761353969574,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.008699812954021488,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017399625908042976,
      "grad_norm": 0.39873817563056946,
      "learning_rate": 2e-05,
      "loss": 0.5969,
      "step": 1
    },
    {
      "epoch": 0.00017399625908042976,
      "eval_loss": 0.8338358402252197,
      "eval_runtime": 187.6808,
      "eval_samples_per_second": 51.577,
      "eval_steps_per_second": 6.447,
      "step": 1
    },
    {
      "epoch": 0.00034799251816085953,
      "grad_norm": 0.4863181412220001,
      "learning_rate": 4e-05,
      "loss": 0.6603,
      "step": 2
    },
    {
      "epoch": 0.0005219887772412893,
      "grad_norm": 0.5386459231376648,
      "learning_rate": 6e-05,
      "loss": 0.7033,
      "step": 3
    },
    {
      "epoch": 0.0006959850363217191,
      "grad_norm": 0.39798977971076965,
      "learning_rate": 8e-05,
      "loss": 0.7345,
      "step": 4
    },
    {
      "epoch": 0.0008699812954021488,
      "grad_norm": 0.3186977803707123,
      "learning_rate": 0.0001,
      "loss": 0.6615,
      "step": 5
    },
    {
      "epoch": 0.0010439775544825785,
      "grad_norm": 0.34269002079963684,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6994,
      "step": 6
    },
    {
      "epoch": 0.0012179738135630084,
      "grad_norm": 0.3942001461982727,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.6634,
      "step": 7
    },
    {
      "epoch": 0.0013919700726434381,
      "grad_norm": 0.3934086859226227,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6807,
      "step": 8
    },
    {
      "epoch": 0.001565966331723868,
      "grad_norm": 0.37781572341918945,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6854,
      "step": 9
    },
    {
      "epoch": 0.0017399625908042977,
      "grad_norm": 0.2989943027496338,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5964,
      "step": 10
    },
    {
      "epoch": 0.0019139588498847274,
      "grad_norm": 0.29578524827957153,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6164,
      "step": 11
    },
    {
      "epoch": 0.002087955108965157,
      "grad_norm": 0.29217201471328735,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6332,
      "step": 12
    },
    {
      "epoch": 0.002261951368045587,
      "grad_norm": 0.29421859979629517,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.6277,
      "step": 13
    },
    {
      "epoch": 0.002435947627126017,
      "grad_norm": 0.2795340120792389,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6298,
      "step": 14
    },
    {
      "epoch": 0.0026099438862064468,
      "grad_norm": 0.2845260500907898,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.6672,
      "step": 15
    },
    {
      "epoch": 0.0027839401452868762,
      "grad_norm": 0.281961053609848,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6222,
      "step": 16
    },
    {
      "epoch": 0.002957936404367306,
      "grad_norm": 0.2901883125305176,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.6315,
      "step": 17
    },
    {
      "epoch": 0.003131932663447736,
      "grad_norm": 0.30355149507522583,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6605,
      "step": 18
    },
    {
      "epoch": 0.0033059289225281655,
      "grad_norm": 0.2829739451408386,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.5833,
      "step": 19
    },
    {
      "epoch": 0.0034799251816085954,
      "grad_norm": 0.29905346035957336,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6496,
      "step": 20
    },
    {
      "epoch": 0.0036539214406890253,
      "grad_norm": 0.2922212481498718,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.6493,
      "step": 21
    },
    {
      "epoch": 0.0038279176997694547,
      "grad_norm": 0.2920663356781006,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5786,
      "step": 22
    },
    {
      "epoch": 0.004001913958849885,
      "grad_norm": 0.3486131429672241,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6126,
      "step": 23
    },
    {
      "epoch": 0.004175910217930314,
      "grad_norm": 0.3035872280597687,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.6319,
      "step": 24
    },
    {
      "epoch": 0.004349906477010744,
      "grad_norm": 0.306221604347229,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6473,
      "step": 25
    },
    {
      "epoch": 0.004349906477010744,
      "eval_loss": 0.6226545572280884,
      "eval_runtime": 189.0594,
      "eval_samples_per_second": 51.201,
      "eval_steps_per_second": 6.4,
      "step": 25
    },
    {
      "epoch": 0.004523902736091174,
      "grad_norm": 0.3160538673400879,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6095,
      "step": 26
    },
    {
      "epoch": 0.004697898995171604,
      "grad_norm": 0.3224450349807739,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.6285,
      "step": 27
    },
    {
      "epoch": 0.004871895254252034,
      "grad_norm": 0.3256780505180359,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.594,
      "step": 28
    },
    {
      "epoch": 0.005045891513332464,
      "grad_norm": 0.3396569788455963,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.5926,
      "step": 29
    },
    {
      "epoch": 0.0052198877724128935,
      "grad_norm": 0.31964659690856934,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6237,
      "step": 30
    },
    {
      "epoch": 0.0053938840314933225,
      "grad_norm": 0.34242039918899536,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.6296,
      "step": 31
    },
    {
      "epoch": 0.0055678802905737524,
      "grad_norm": 0.33837223052978516,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6333,
      "step": 32
    },
    {
      "epoch": 0.005741876549654182,
      "grad_norm": 0.3152254819869995,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.538,
      "step": 33
    },
    {
      "epoch": 0.005915872808734612,
      "grad_norm": 0.35449615120887756,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6579,
      "step": 34
    },
    {
      "epoch": 0.006089869067815042,
      "grad_norm": 0.36308395862579346,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6059,
      "step": 35
    },
    {
      "epoch": 0.006263865326895472,
      "grad_norm": 0.35584306716918945,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6145,
      "step": 36
    },
    {
      "epoch": 0.006437861585975902,
      "grad_norm": 0.4302743077278137,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7358,
      "step": 37
    },
    {
      "epoch": 0.006611857845056331,
      "grad_norm": 0.39490967988967896,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.6569,
      "step": 38
    },
    {
      "epoch": 0.006785854104136761,
      "grad_norm": 0.3838157057762146,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.571,
      "step": 39
    },
    {
      "epoch": 0.006959850363217191,
      "grad_norm": 0.43212297558784485,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.6841,
      "step": 40
    },
    {
      "epoch": 0.007133846622297621,
      "grad_norm": 0.4221954643726349,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6014,
      "step": 41
    },
    {
      "epoch": 0.0073078428813780506,
      "grad_norm": 0.460354745388031,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.6769,
      "step": 42
    },
    {
      "epoch": 0.0074818391404584805,
      "grad_norm": 0.456825852394104,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6126,
      "step": 43
    },
    {
      "epoch": 0.0076558353995389095,
      "grad_norm": 0.49616795778274536,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5843,
      "step": 44
    },
    {
      "epoch": 0.00782983165861934,
      "grad_norm": 0.531218409538269,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.611,
      "step": 45
    },
    {
      "epoch": 0.00800382791769977,
      "grad_norm": 0.5422489047050476,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.5836,
      "step": 46
    },
    {
      "epoch": 0.0081778241767802,
      "grad_norm": 0.5895936489105225,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6907,
      "step": 47
    },
    {
      "epoch": 0.008351820435860628,
      "grad_norm": 0.6002499461174011,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.635,
      "step": 48
    },
    {
      "epoch": 0.008525816694941058,
      "grad_norm": 0.6959513425827026,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.6863,
      "step": 49
    },
    {
      "epoch": 0.008699812954021488,
      "grad_norm": 1.0589532852172852,
      "learning_rate": 0.0,
      "loss": 0.759,
      "step": 50
    },
    {
      "epoch": 0.008699812954021488,
      "eval_loss": 0.600761353969574,
      "eval_runtime": 188.8374,
      "eval_samples_per_second": 51.261,
      "eval_steps_per_second": 6.408,
      "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": 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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9218902751969280.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}