{
  "best_metric": 2.8705949783325195,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.4317789291882556,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008635578583765112,
      "eval_loss": 4.056758880615234,
      "eval_runtime": 6.4154,
      "eval_samples_per_second": 76.067,
      "eval_steps_per_second": 19.017,
      "step": 1
    },
    {
      "epoch": 0.008635578583765112,
      "grad_norm": 109.97903442382812,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 7.1856,
      "step": 10
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 128.83065795898438,
      "learning_rate": 8.080000000000001e-05,
      "loss": 7.2879,
      "step": 20
    },
    {
      "epoch": 0.025906735751295335,
      "grad_norm": 156.83480834960938,
      "learning_rate": 0.00012119999999999999,
      "loss": 6.7848,
      "step": 30
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 94.2466812133789,
      "learning_rate": 0.00016160000000000002,
      "loss": 6.6317,
      "step": 40
    },
    {
      "epoch": 0.04317789291882556,
      "grad_norm": 69.40169525146484,
      "learning_rate": 0.000202,
      "loss": 7.2513,
      "step": 50
    },
    {
      "epoch": 0.04317789291882556,
      "eval_loss": 3.4254961013793945,
      "eval_runtime": 6.4823,
      "eval_samples_per_second": 75.282,
      "eval_steps_per_second": 18.82,
      "step": 50
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 69.7632064819336,
      "learning_rate": 0.00020175396907624226,
      "loss": 6.6028,
      "step": 60
    },
    {
      "epoch": 0.06044905008635579,
      "grad_norm": 122.16877746582031,
      "learning_rate": 0.0002010170749428986,
      "loss": 5.9878,
      "step": 70
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 137.6359100341797,
      "learning_rate": 0.00019979290767411438,
      "loss": 5.9063,
      "step": 80
    },
    {
      "epoch": 0.07772020725388601,
      "grad_norm": 351.2722473144531,
      "learning_rate": 0.0001980874312897702,
      "loss": 6.7379,
      "step": 90
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 46.962703704833984,
      "learning_rate": 0.00019590895469937675,
      "loss": 7.5918,
      "step": 100
    },
    {
      "epoch": 0.08635578583765112,
      "eval_loss": 3.554054021835327,
      "eval_runtime": 6.3322,
      "eval_samples_per_second": 77.067,
      "eval_steps_per_second": 19.267,
      "step": 100
    },
    {
      "epoch": 0.09499136442141623,
      "grad_norm": 75.2490234375,
      "learning_rate": 0.0001932680912219027,
      "loss": 6.5258,
      "step": 110
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 60.61024856567383,
      "learning_rate": 0.00019017770687875164,
      "loss": 6.6532,
      "step": 120
    },
    {
      "epoch": 0.11226252158894647,
      "grad_norm": 64.55341339111328,
      "learning_rate": 0.000186652857711799,
      "loss": 6.1697,
      "step": 130
    },
    {
      "epoch": 0.12089810017271158,
      "grad_norm": 98.4996566772461,
      "learning_rate": 0.00018271071643186968,
      "loss": 6.6974,
      "step": 140
    },
    {
      "epoch": 0.12953367875647667,
      "grad_norm": 34.625057220458984,
      "learning_rate": 0.00017837048875501678,
      "loss": 6.6976,
      "step": 150
    },
    {
      "epoch": 0.12953367875647667,
      "eval_loss": 3.2074270248413086,
      "eval_runtime": 6.4564,
      "eval_samples_per_second": 75.583,
      "eval_steps_per_second": 18.896,
      "step": 150
    },
    {
      "epoch": 0.1381692573402418,
      "grad_norm": 51.142398834228516,
      "learning_rate": 0.00017365331983420376,
      "loss": 6.4538,
      "step": 160
    },
    {
      "epoch": 0.14680483592400692,
      "grad_norm": 60.982696533203125,
      "learning_rate": 0.0001685821912422447,
      "loss": 6.1183,
      "step": 170
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 90.77964782714844,
      "learning_rate": 0.00016318180900789148,
      "loss": 6.2612,
      "step": 180
    },
    {
      "epoch": 0.16407599309153714,
      "grad_norm": 37.461490631103516,
      "learning_rate": 0.00015747848325054544,
      "loss": 6.2806,
      "step": 190
    },
    {
      "epoch": 0.17271157167530224,
      "grad_norm": 57.53730392456055,
      "learning_rate": 0.0001515,
      "loss": 6.4748,
      "step": 200
    },
    {
      "epoch": 0.17271157167530224,
      "eval_loss": 3.1944408416748047,
      "eval_runtime": 6.5289,
      "eval_samples_per_second": 74.744,
      "eval_steps_per_second": 18.686,
      "step": 200
    },
    {
      "epoch": 0.18134715025906736,
      "grad_norm": 26.914474487304688,
      "learning_rate": 0.00014527548582569683,
      "loss": 6.1732,
      "step": 210
    },
    {
      "epoch": 0.18998272884283246,
      "grad_norm": 42.907127380371094,
      "learning_rate": 0.00013883526593500714,
      "loss": 6.1321,
      "step": 220
    },
    {
      "epoch": 0.19861830742659758,
      "grad_norm": 61.954986572265625,
      "learning_rate": 0.0001322107164318697,
      "loss": 6.293,
      "step": 230
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 41.956809997558594,
      "learning_rate": 0.00012543411145556643,
      "loss": 6.3759,
      "step": 240
    },
    {
      "epoch": 0.2158894645941278,
      "grad_norm": 58.70474624633789,
      "learning_rate": 0.00011853846594435998,
      "loss": 6.4753,
      "step": 250
    },
    {
      "epoch": 0.2158894645941278,
      "eval_loss": 3.325136184692383,
      "eval_runtime": 6.5343,
      "eval_samples_per_second": 74.683,
      "eval_steps_per_second": 18.671,
      "step": 250
    },
    {
      "epoch": 0.22452504317789293,
      "grad_norm": 37.147239685058594,
      "learning_rate": 0.00011155737479003301,
      "loss": 6.4968,
      "step": 260
    },
    {
      "epoch": 0.23316062176165803,
      "grad_norm": 28.960235595703125,
      "learning_rate": 0.00010452484916695262,
      "loss": 6.153,
      "step": 270
    },
    {
      "epoch": 0.24179620034542315,
      "grad_norm": 50.646121978759766,
      "learning_rate": 9.747515083304742e-05,
      "loss": 6.4405,
      "step": 280
    },
    {
      "epoch": 0.2504317789291883,
      "grad_norm": 61.160247802734375,
      "learning_rate": 9.044262520996702e-05,
      "loss": 5.6587,
      "step": 290
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 126.3609848022461,
      "learning_rate": 8.346153405564004e-05,
      "loss": 6.0805,
      "step": 300
    },
    {
      "epoch": 0.25906735751295334,
      "eval_loss": 3.0865094661712646,
      "eval_runtime": 6.5059,
      "eval_samples_per_second": 75.008,
      "eval_steps_per_second": 18.752,
      "step": 300
    },
    {
      "epoch": 0.26770293609671847,
      "grad_norm": 107.83584594726562,
      "learning_rate": 7.656588854443357e-05,
      "loss": 6.5431,
      "step": 310
    },
    {
      "epoch": 0.2763385146804836,
      "grad_norm": 63.63986587524414,
      "learning_rate": 6.978928356813031e-05,
      "loss": 6.3199,
      "step": 320
    },
    {
      "epoch": 0.2849740932642487,
      "grad_norm": 61.55841064453125,
      "learning_rate": 6.316473406499288e-05,
      "loss": 6.3271,
      "step": 330
    },
    {
      "epoch": 0.29360967184801384,
      "grad_norm": 59.812896728515625,
      "learning_rate": 5.672451417430317e-05,
      "loss": 6.2607,
      "step": 340
    },
    {
      "epoch": 0.3022452504317789,
      "grad_norm": 81.45887756347656,
      "learning_rate": 5.050000000000002e-05,
      "loss": 6.3402,
      "step": 350
    },
    {
      "epoch": 0.3022452504317789,
      "eval_loss": 3.0198187828063965,
      "eval_runtime": 6.5239,
      "eval_samples_per_second": 74.802,
      "eval_steps_per_second": 18.7,
      "step": 350
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 37.4752082824707,
      "learning_rate": 4.452151674945458e-05,
      "loss": 6.201,
      "step": 360
    },
    {
      "epoch": 0.31951640759930916,
      "grad_norm": 46.92196273803711,
      "learning_rate": 3.8818190992108515e-05,
      "loss": 5.6539,
      "step": 370
    },
    {
      "epoch": 0.3281519861830743,
      "grad_norm": 111.72332763671875,
      "learning_rate": 3.3417808757755355e-05,
      "loss": 6.1284,
      "step": 380
    },
    {
      "epoch": 0.33678756476683935,
      "grad_norm": 140.5625,
      "learning_rate": 2.8346680165796253e-05,
      "loss": 6.0232,
      "step": 390
    },
    {
      "epoch": 0.3454231433506045,
      "grad_norm": 49.17171096801758,
      "learning_rate": 2.362951124498323e-05,
      "loss": 6.0123,
      "step": 400
    },
    {
      "epoch": 0.3454231433506045,
      "eval_loss": 2.9118363857269287,
      "eval_runtime": 6.5191,
      "eval_samples_per_second": 74.857,
      "eval_steps_per_second": 18.714,
      "step": 400
    },
    {
      "epoch": 0.3540587219343696,
      "grad_norm": 94.65570068359375,
      "learning_rate": 1.928928356813032e-05,
      "loss": 5.9852,
      "step": 410
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 134.4743194580078,
      "learning_rate": 1.5347142288200977e-05,
      "loss": 5.8302,
      "step": 420
    },
    {
      "epoch": 0.37132987910189985,
      "grad_norm": 459.3276672363281,
      "learning_rate": 1.1822293121248375e-05,
      "loss": 5.3816,
      "step": 430
    },
    {
      "epoch": 0.3799654576856649,
      "grad_norm": 118.11572265625,
      "learning_rate": 8.731908778097302e-06,
      "loss": 5.7221,
      "step": 440
    },
    {
      "epoch": 0.38860103626943004,
      "grad_norm": 46.101783752441406,
      "learning_rate": 6.09104530062326e-06,
      "loss": 5.6217,
      "step": 450
    },
    {
      "epoch": 0.38860103626943004,
      "eval_loss": 2.882382869720459,
      "eval_runtime": 6.5287,
      "eval_samples_per_second": 74.746,
      "eval_steps_per_second": 18.687,
      "step": 450
    },
    {
      "epoch": 0.39723661485319517,
      "grad_norm": 48.339908599853516,
      "learning_rate": 3.912568710229791e-06,
      "loss": 6.0256,
      "step": 460
    },
    {
      "epoch": 0.4058721934369603,
      "grad_norm": 83.55408477783203,
      "learning_rate": 2.2070923258856255e-06,
      "loss": 5.9578,
      "step": 470
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 55.561649322509766,
      "learning_rate": 9.829250571013935e-07,
      "loss": 5.9324,
      "step": 480
    },
    {
      "epoch": 0.4231433506044905,
      "grad_norm": 66.6230239868164,
      "learning_rate": 2.4603092375775605e-07,
      "loss": 5.6569,
      "step": 490
    },
    {
      "epoch": 0.4317789291882556,
      "grad_norm": 116.90052032470703,
      "learning_rate": 0.0,
      "loss": 6.1575,
      "step": 500
    },
    {
      "epoch": 0.4317789291882556,
      "eval_loss": 2.8705949783325195,
      "eval_runtime": 6.5205,
      "eval_samples_per_second": 74.841,
      "eval_steps_per_second": 18.71,
      "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
}