{
  "best_metric": 1.2670997381210327,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.7475083056478405,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016611295681063123,
      "eval_loss": 2.1715543270111084,
      "eval_runtime": 69.5427,
      "eval_samples_per_second": 14.581,
      "eval_steps_per_second": 3.652,
      "step": 1
    },
    {
      "epoch": 0.016611295681063124,
      "grad_norm": 0.28691908717155457,
      "learning_rate": 0.0002,
      "loss": 1.8097,
      "step": 10
    },
    {
      "epoch": 0.03322259136212625,
      "grad_norm": 0.39086708426475525,
      "learning_rate": 0.0001998582695676762,
      "loss": 1.4881,
      "step": 20
    },
    {
      "epoch": 0.04983388704318937,
      "grad_norm": 0.44144389033317566,
      "learning_rate": 0.00019943348002101371,
      "loss": 1.3426,
      "step": 30
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 0.45453155040740967,
      "learning_rate": 0.00019872683547213446,
      "loss": 1.3136,
      "step": 40
    },
    {
      "epoch": 0.08305647840531562,
      "grad_norm": 0.6533491015434265,
      "learning_rate": 0.00019774033898178667,
      "loss": 1.592,
      "step": 50
    },
    {
      "epoch": 0.08305647840531562,
      "eval_loss": 1.4280692338943481,
      "eval_runtime": 70.7159,
      "eval_samples_per_second": 14.339,
      "eval_steps_per_second": 3.592,
      "step": 50
    },
    {
      "epoch": 0.09966777408637874,
      "grad_norm": 0.2205391824245453,
      "learning_rate": 0.0001964767868814516,
      "loss": 1.4082,
      "step": 60
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.257103830575943,
      "learning_rate": 0.00019493976084683813,
      "loss": 1.2586,
      "step": 70
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 0.2941131293773651,
      "learning_rate": 0.00019313361774523385,
      "loss": 1.2236,
      "step": 80
    },
    {
      "epoch": 0.14950166112956811,
      "grad_norm": 0.4034242331981659,
      "learning_rate": 0.00019106347728549135,
      "loss": 1.2459,
      "step": 90
    },
    {
      "epoch": 0.16611295681063123,
      "grad_norm": 0.6419020891189575,
      "learning_rate": 0.00018873520750565718,
      "loss": 1.499,
      "step": 100
    },
    {
      "epoch": 0.16611295681063123,
      "eval_loss": 1.4120386838912964,
      "eval_runtime": 70.5417,
      "eval_samples_per_second": 14.374,
      "eval_steps_per_second": 3.601,
      "step": 100
    },
    {
      "epoch": 0.18272425249169436,
      "grad_norm": 0.28808289766311646,
      "learning_rate": 0.0001861554081393806,
      "loss": 1.336,
      "step": 110
    },
    {
      "epoch": 0.19933554817275748,
      "grad_norm": 0.29374128580093384,
      "learning_rate": 0.0001833313919082515,
      "loss": 1.2921,
      "step": 120
    },
    {
      "epoch": 0.2159468438538206,
      "grad_norm": 0.3089810907840729,
      "learning_rate": 0.00018027116379309638,
      "loss": 1.2395,
      "step": 130
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.43953055143356323,
      "learning_rate": 0.00017698339834299061,
      "loss": 1.1861,
      "step": 140
    },
    {
      "epoch": 0.24916943521594684,
      "grad_norm": 0.6231277585029602,
      "learning_rate": 0.00017347741508630672,
      "loss": 1.3598,
      "step": 150
    },
    {
      "epoch": 0.24916943521594684,
      "eval_loss": 1.4176186323165894,
      "eval_runtime": 70.5732,
      "eval_samples_per_second": 14.368,
      "eval_steps_per_second": 3.599,
      "step": 150
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 0.3004702031612396,
      "learning_rate": 0.0001697631521134985,
      "loss": 1.4307,
      "step": 160
    },
    {
      "epoch": 0.2823920265780731,
      "grad_norm": 0.2584735155105591,
      "learning_rate": 0.00016585113790650388,
      "loss": 1.2259,
      "step": 170
    },
    {
      "epoch": 0.29900332225913623,
      "grad_norm": 0.30790308117866516,
      "learning_rate": 0.0001617524614946192,
      "loss": 1.1969,
      "step": 180
    },
    {
      "epoch": 0.31561461794019935,
      "grad_norm": 0.45509302616119385,
      "learning_rate": 0.0001574787410214407,
      "loss": 1.2463,
      "step": 190
    },
    {
      "epoch": 0.33222591362126247,
      "grad_norm": 0.5611400604248047,
      "learning_rate": 0.00015304209081197425,
      "loss": 1.4207,
      "step": 200
    },
    {
      "epoch": 0.33222591362126247,
      "eval_loss": 1.404697299003601,
      "eval_runtime": 70.4401,
      "eval_samples_per_second": 14.395,
      "eval_steps_per_second": 3.606,
      "step": 200
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.27873846888542175,
      "learning_rate": 0.00014845508703326504,
      "loss": 1.3757,
      "step": 210
    },
    {
      "epoch": 0.3654485049833887,
      "grad_norm": 0.2696116268634796,
      "learning_rate": 0.00014373073204588556,
      "loss": 1.2607,
      "step": 220
    },
    {
      "epoch": 0.38205980066445183,
      "grad_norm": 0.31358882784843445,
      "learning_rate": 0.00013888241754733208,
      "loss": 1.2161,
      "step": 230
    },
    {
      "epoch": 0.39867109634551495,
      "grad_norm": 0.4030625820159912,
      "learning_rate": 0.00013392388661180303,
      "loss": 1.2135,
      "step": 240
    },
    {
      "epoch": 0.4152823920265781,
      "grad_norm": 0.4767776131629944,
      "learning_rate": 0.0001288691947339621,
      "loss": 1.3493,
      "step": 250
    },
    {
      "epoch": 0.4152823920265781,
      "eval_loss": 1.3333581686019897,
      "eval_runtime": 70.4196,
      "eval_samples_per_second": 14.399,
      "eval_steps_per_second": 3.607,
      "step": 250
    },
    {
      "epoch": 0.4318936877076412,
      "grad_norm": 0.2525186538696289,
      "learning_rate": 0.0001237326699871115,
      "loss": 1.312,
      "step": 260
    },
    {
      "epoch": 0.4485049833887043,
      "grad_norm": 0.2510424554347992,
      "learning_rate": 0.00011852887240871145,
      "loss": 1.2663,
      "step": 270
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.27276328206062317,
      "learning_rate": 0.00011327255272837221,
      "loss": 1.149,
      "step": 280
    },
    {
      "epoch": 0.48172757475083056,
      "grad_norm": 0.43301859498023987,
      "learning_rate": 0.00010797861055530831,
      "loss": 1.1877,
      "step": 290
    },
    {
      "epoch": 0.4983388704318937,
      "grad_norm": 0.5607919096946716,
      "learning_rate": 0.00010266205214377748,
      "loss": 1.3628,
      "step": 300
    },
    {
      "epoch": 0.4983388704318937,
      "eval_loss": 1.299776554107666,
      "eval_runtime": 70.6911,
      "eval_samples_per_second": 14.344,
      "eval_steps_per_second": 3.593,
      "step": 300
    },
    {
      "epoch": 0.5149501661129569,
      "grad_norm": 0.2536980211734772,
      "learning_rate": 9.733794785622253e-05,
      "loss": 1.365,
      "step": 310
    },
    {
      "epoch": 0.53156146179402,
      "grad_norm": 0.28358352184295654,
      "learning_rate": 9.202138944469168e-05,
      "loss": 1.2521,
      "step": 320
    },
    {
      "epoch": 0.5481727574750831,
      "grad_norm": 0.2929559350013733,
      "learning_rate": 8.672744727162781e-05,
      "loss": 1.2241,
      "step": 330
    },
    {
      "epoch": 0.5647840531561462,
      "grad_norm": 0.4324483573436737,
      "learning_rate": 8.147112759128859e-05,
      "loss": 1.2225,
      "step": 340
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.47393572330474854,
      "learning_rate": 7.626733001288851e-05,
      "loss": 1.3531,
      "step": 350
    },
    {
      "epoch": 0.5813953488372093,
      "eval_loss": 1.2868059873580933,
      "eval_runtime": 70.612,
      "eval_samples_per_second": 14.36,
      "eval_steps_per_second": 3.597,
      "step": 350
    },
    {
      "epoch": 0.5980066445182725,
      "grad_norm": 0.26292383670806885,
      "learning_rate": 7.113080526603792e-05,
      "loss": 1.3364,
      "step": 360
    },
    {
      "epoch": 0.6146179401993356,
      "grad_norm": 0.28483420610427856,
      "learning_rate": 6.607611338819697e-05,
      "loss": 1.2009,
      "step": 370
    },
    {
      "epoch": 0.6312292358803987,
      "grad_norm": 0.3586254119873047,
      "learning_rate": 6.111758245266794e-05,
      "loss": 1.2086,
      "step": 380
    },
    {
      "epoch": 0.6478405315614618,
      "grad_norm": 0.374376505613327,
      "learning_rate": 5.626926795411447e-05,
      "loss": 1.2017,
      "step": 390
    },
    {
      "epoch": 0.6644518272425249,
      "grad_norm": 0.546507716178894,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 1.2866,
      "step": 400
    },
    {
      "epoch": 0.6644518272425249,
      "eval_loss": 1.272492527961731,
      "eval_runtime": 70.4532,
      "eval_samples_per_second": 14.393,
      "eval_steps_per_second": 3.605,
      "step": 400
    },
    {
      "epoch": 0.6810631229235881,
      "grad_norm": 0.2525825500488281,
      "learning_rate": 4.695790918802576e-05,
      "loss": 1.3349,
      "step": 410
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.2703811824321747,
      "learning_rate": 4.252125897855932e-05,
      "loss": 1.2055,
      "step": 420
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.2996411919593811,
      "learning_rate": 3.824753850538082e-05,
      "loss": 1.2155,
      "step": 430
    },
    {
      "epoch": 0.7308970099667774,
      "grad_norm": 0.3596253991127014,
      "learning_rate": 3.414886209349615e-05,
      "loss": 1.1916,
      "step": 440
    },
    {
      "epoch": 0.7475083056478405,
      "grad_norm": 0.48794233798980713,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 1.3421,
      "step": 450
    },
    {
      "epoch": 0.7475083056478405,
      "eval_loss": 1.2670997381210327,
      "eval_runtime": 70.6313,
      "eval_samples_per_second": 14.356,
      "eval_steps_per_second": 3.596,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 150,
  "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": 5.7504888703156224e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}