{
  "best_metric": 0.8746353387832642,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.23889154323936931,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047778308647873863,
      "eval_loss": 4.255342483520508,
      "eval_runtime": 12.2428,
      "eval_samples_per_second": 72.043,
      "eval_steps_per_second": 18.051,
      "step": 1
    },
    {
      "epoch": 0.004777830864787387,
      "grad_norm": 93.89539337158203,
      "learning_rate": 4.2600000000000005e-05,
      "loss": 6.865,
      "step": 10
    },
    {
      "epoch": 0.009555661729574774,
      "grad_norm": 192.6894073486328,
      "learning_rate": 8.520000000000001e-05,
      "loss": 4.7086,
      "step": 20
    },
    {
      "epoch": 0.01433349259436216,
      "grad_norm": 185.80467224121094,
      "learning_rate": 0.0001278,
      "loss": 3.7399,
      "step": 30
    },
    {
      "epoch": 0.019111323459149548,
      "grad_norm": 120.97589874267578,
      "learning_rate": 0.00017040000000000002,
      "loss": 3.3705,
      "step": 40
    },
    {
      "epoch": 0.023889154323936932,
      "grad_norm": 87.03988647460938,
      "learning_rate": 0.000213,
      "loss": 3.1617,
      "step": 50
    },
    {
      "epoch": 0.023889154323936932,
      "eval_loss": 1.551166296005249,
      "eval_runtime": 12.1727,
      "eval_samples_per_second": 72.457,
      "eval_steps_per_second": 18.155,
      "step": 50
    },
    {
      "epoch": 0.02866698518872432,
      "grad_norm": 99.68428039550781,
      "learning_rate": 0.00021274057135267128,
      "loss": 2.759,
      "step": 60
    },
    {
      "epoch": 0.033444816053511704,
      "grad_norm": 31.421096801757812,
      "learning_rate": 0.00021196354932097723,
      "loss": 3.1152,
      "step": 70
    },
    {
      "epoch": 0.038222646918299095,
      "grad_norm": 17.666555404663086,
      "learning_rate": 0.0002106727194781503,
      "loss": 2.3276,
      "step": 80
    },
    {
      "epoch": 0.04300047778308648,
      "grad_norm": 21.751888275146484,
      "learning_rate": 0.00020887437061743096,
      "loss": 2.3262,
      "step": 90
    },
    {
      "epoch": 0.047778308647873864,
      "grad_norm": 14.296065330505371,
      "learning_rate": 0.00020657726411369925,
      "loss": 2.4236,
      "step": 100
    },
    {
      "epoch": 0.047778308647873864,
      "eval_loss": 1.1035537719726562,
      "eval_runtime": 12.2578,
      "eval_samples_per_second": 71.954,
      "eval_steps_per_second": 18.029,
      "step": 100
    },
    {
      "epoch": 0.05255613951266125,
      "grad_norm": 31.222625732421875,
      "learning_rate": 0.000203792591238937,
      "loss": 1.611,
      "step": 110
    },
    {
      "epoch": 0.05733397037744864,
      "grad_norm": 108.65278625488281,
      "learning_rate": 0.0002005339186394757,
      "loss": 2.0965,
      "step": 120
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 33.067230224609375,
      "learning_rate": 0.00019681712224065936,
      "loss": 2.2948,
      "step": 130
    },
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 33.02948760986328,
      "learning_rate": 0.0001926603099009319,
      "loss": 2.8421,
      "step": 140
    },
    {
      "epoch": 0.0716674629718108,
      "grad_norm": 15.799519538879395,
      "learning_rate": 0.00018808373319217114,
      "loss": 2.8939,
      "step": 150
    },
    {
      "epoch": 0.0716674629718108,
      "eval_loss": 1.215044379234314,
      "eval_runtime": 12.0789,
      "eval_samples_per_second": 73.02,
      "eval_steps_per_second": 18.296,
      "step": 150
    },
    {
      "epoch": 0.07644529383659819,
      "grad_norm": 27.139089584350586,
      "learning_rate": 0.00018310968873606635,
      "loss": 1.9604,
      "step": 160
    },
    {
      "epoch": 0.08122312470138557,
      "grad_norm": 37.57059097290039,
      "learning_rate": 0.0001777624095772184,
      "loss": 1.692,
      "step": 170
    },
    {
      "epoch": 0.08600095556617296,
      "grad_norm": 101.7945556640625,
      "learning_rate": 0.0001720679471221826,
      "loss": 3.0551,
      "step": 180
    },
    {
      "epoch": 0.09077878643096035,
      "grad_norm": 65.89530181884766,
      "learning_rate": 0.00016605404421963453,
      "loss": 2.2188,
      "step": 190
    },
    {
      "epoch": 0.09555661729574773,
      "grad_norm": 30.504783630371094,
      "learning_rate": 0.00015975,
      "loss": 2.4033,
      "step": 200
    },
    {
      "epoch": 0.09555661729574773,
      "eval_loss": 1.0835368633270264,
      "eval_runtime": 12.393,
      "eval_samples_per_second": 71.169,
      "eval_steps_per_second": 17.833,
      "step": 200
    },
    {
      "epoch": 0.10033444816053512,
      "grad_norm": 52.85816192626953,
      "learning_rate": 0.00015318652713303674,
      "loss": 1.599,
      "step": 210
    },
    {
      "epoch": 0.1051122790253225,
      "grad_norm": 19.591501235961914,
      "learning_rate": 0.00014639560219879464,
      "loss": 1.7043,
      "step": 220
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 81.96508026123047,
      "learning_rate": 0.0001394103099009319,
      "loss": 2.1468,
      "step": 230
    },
    {
      "epoch": 0.11466794075489728,
      "grad_norm": 30.87833595275879,
      "learning_rate": 0.0001322646818813646,
      "loss": 2.161,
      "step": 240
    },
    {
      "epoch": 0.11944577161968466,
      "grad_norm": 42.904701232910156,
      "learning_rate": 0.0001249935309215281,
      "loss": 2.5615,
      "step": 250
    },
    {
      "epoch": 0.11944577161968466,
      "eval_loss": 1.1374989748001099,
      "eval_runtime": 12.4118,
      "eval_samples_per_second": 71.061,
      "eval_steps_per_second": 17.806,
      "step": 250
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 26.0584716796875,
      "learning_rate": 0.0001176322813380051,
      "loss": 1.8027,
      "step": 260
    },
    {
      "epoch": 0.12900143334925943,
      "grad_norm": 19.178482055664062,
      "learning_rate": 0.00011021679639881638,
      "loss": 1.6998,
      "step": 270
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 24.075414657592773,
      "learning_rate": 0.00010278320360118368,
      "loss": 2.3066,
      "step": 280
    },
    {
      "epoch": 0.1385570950788342,
      "grad_norm": 19.714353561401367,
      "learning_rate": 9.536771866199493e-05,
      "loss": 2.4782,
      "step": 290
    },
    {
      "epoch": 0.1433349259436216,
      "grad_norm": 13.794386863708496,
      "learning_rate": 8.800646907847192e-05,
      "loss": 2.4282,
      "step": 300
    },
    {
      "epoch": 0.1433349259436216,
      "eval_loss": 1.0520588159561157,
      "eval_runtime": 12.5021,
      "eval_samples_per_second": 70.548,
      "eval_steps_per_second": 17.677,
      "step": 300
    },
    {
      "epoch": 0.148112756808409,
      "grad_norm": 67.06897735595703,
      "learning_rate": 8.07353181186354e-05,
      "loss": 1.7239,
      "step": 310
    },
    {
      "epoch": 0.15289058767319638,
      "grad_norm": 51.10677719116211,
      "learning_rate": 7.35896900990681e-05,
      "loss": 1.6737,
      "step": 320
    },
    {
      "epoch": 0.15766841853798375,
      "grad_norm": 54.609580993652344,
      "learning_rate": 6.660439780120536e-05,
      "loss": 2.0017,
      "step": 330
    },
    {
      "epoch": 0.16244624940277114,
      "grad_norm": 39.43727111816406,
      "learning_rate": 5.981347286696324e-05,
      "loss": 2.1488,
      "step": 340
    },
    {
      "epoch": 0.16722408026755853,
      "grad_norm": 30.269664764404297,
      "learning_rate": 5.325000000000002e-05,
      "loss": 2.3871,
      "step": 350
    },
    {
      "epoch": 0.16722408026755853,
      "eval_loss": 0.9656849503517151,
      "eval_runtime": 12.1772,
      "eval_samples_per_second": 72.43,
      "eval_steps_per_second": 18.149,
      "step": 350
    },
    {
      "epoch": 0.17200191113234592,
      "grad_norm": 30.008037567138672,
      "learning_rate": 4.6945955780365475e-05,
      "loss": 1.4687,
      "step": 360
    },
    {
      "epoch": 0.1767797419971333,
      "grad_norm": 30.746850967407227,
      "learning_rate": 4.0932052877817393e-05,
      "loss": 1.5686,
      "step": 370
    },
    {
      "epoch": 0.1815575728619207,
      "grad_norm": 29.426549911499023,
      "learning_rate": 3.523759042278163e-05,
      "loss": 1.6911,
      "step": 380
    },
    {
      "epoch": 0.18633540372670807,
      "grad_norm": 33.3541145324707,
      "learning_rate": 2.989031126393367e-05,
      "loss": 2.0111,
      "step": 390
    },
    {
      "epoch": 0.19111323459149546,
      "grad_norm": 15.817224502563477,
      "learning_rate": 2.4916266807828855e-05,
      "loss": 2.2564,
      "step": 400
    },
    {
      "epoch": 0.19111323459149546,
      "eval_loss": 0.9130141735076904,
      "eval_runtime": 12.0386,
      "eval_samples_per_second": 73.264,
      "eval_steps_per_second": 18.358,
      "step": 400
    },
    {
      "epoch": 0.19589106545628285,
      "grad_norm": 40.40257263183594,
      "learning_rate": 2.033969009906811e-05,
      "loss": 1.4211,
      "step": 410
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 28.919811248779297,
      "learning_rate": 1.6182877759340637e-05,
      "loss": 1.5233,
      "step": 420
    },
    {
      "epoch": 0.20544672718585763,
      "grad_norm": 18.431303024291992,
      "learning_rate": 1.2466081360524275e-05,
      "loss": 1.7242,
      "step": 430
    },
    {
      "epoch": 0.210224558050645,
      "grad_norm": 15.968626022338867,
      "learning_rate": 9.207408761062996e-06,
      "loss": 1.9384,
      "step": 440
    },
    {
      "epoch": 0.21500238891543239,
      "grad_norm": 35.02082061767578,
      "learning_rate": 6.422735886300764e-06,
      "loss": 2.1484,
      "step": 450
    },
    {
      "epoch": 0.21500238891543239,
      "eval_loss": 0.8792083859443665,
      "eval_runtime": 12.2699,
      "eval_samples_per_second": 71.883,
      "eval_steps_per_second": 18.011,
      "step": 450
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 28.86961555480957,
      "learning_rate": 4.125629382569038e-06,
      "loss": 1.3139,
      "step": 460
    },
    {
      "epoch": 0.22455805064500717,
      "grad_norm": 38.519046783447266,
      "learning_rate": 2.327280521849694e-06,
      "loss": 1.4227,
      "step": 470
    },
    {
      "epoch": 0.22933588150979456,
      "grad_norm": 20.339561462402344,
      "learning_rate": 1.0364506790227565e-06,
      "loss": 1.6595,
      "step": 480
    },
    {
      "epoch": 0.23411371237458195,
      "grad_norm": 55.318058013916016,
      "learning_rate": 2.5942864732872295e-07,
      "loss": 1.9445,
      "step": 490
    },
    {
      "epoch": 0.23889154323936931,
      "grad_norm": 15.225406646728516,
      "learning_rate": 0.0,
      "loss": 2.0612,
      "step": 500
    },
    {
      "epoch": 0.23889154323936931,
      "eval_loss": 0.8746353387832642,
      "eval_runtime": 12.2579,
      "eval_samples_per_second": 71.953,
      "eval_steps_per_second": 18.029,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 4657011228672000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}