{
  "best_metric": 1.9572868347167969,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.18014772113132768,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003602954422626554,
      "eval_loss": 2.904447555541992,
      "eval_runtime": 63.3703,
      "eval_samples_per_second": 18.447,
      "eval_steps_per_second": 4.624,
      "step": 1
    },
    {
      "epoch": 0.0036029544226265538,
      "grad_norm": 1.3350719213485718,
      "learning_rate": 4.02e-05,
      "loss": 2.9148,
      "step": 10
    },
    {
      "epoch": 0.0072059088452531075,
      "grad_norm": 0.9005210399627686,
      "learning_rate": 8.04e-05,
      "loss": 2.5671,
      "step": 20
    },
    {
      "epoch": 0.010808863267879661,
      "grad_norm": 0.7564655542373657,
      "learning_rate": 0.0001206,
      "loss": 2.4647,
      "step": 30
    },
    {
      "epoch": 0.014411817690506215,
      "grad_norm": 0.7415841817855835,
      "learning_rate": 0.0001608,
      "loss": 2.0857,
      "step": 40
    },
    {
      "epoch": 0.01801477211313277,
      "grad_norm": 1.4382355213165283,
      "learning_rate": 0.000201,
      "loss": 2.1977,
      "step": 50
    },
    {
      "epoch": 0.01801477211313277,
      "eval_loss": 2.32846999168396,
      "eval_runtime": 63.5256,
      "eval_samples_per_second": 18.402,
      "eval_steps_per_second": 4.612,
      "step": 50
    },
    {
      "epoch": 0.021617726535759323,
      "grad_norm": 0.6720779538154602,
      "learning_rate": 0.00020075518705111234,
      "loss": 2.4082,
      "step": 60
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 0.6647239327430725,
      "learning_rate": 0.00020002194090852784,
      "loss": 2.2645,
      "step": 70
    },
    {
      "epoch": 0.02882363538101243,
      "grad_norm": 0.6222731471061707,
      "learning_rate": 0.00019880383387374748,
      "loss": 2.2457,
      "step": 80
    },
    {
      "epoch": 0.03242658980363899,
      "grad_norm": 0.6799861192703247,
      "learning_rate": 0.00019710680044180106,
      "loss": 2.0081,
      "step": 90
    },
    {
      "epoch": 0.03602954422626554,
      "grad_norm": 1.6060737371444702,
      "learning_rate": 0.0001949391083889838,
      "loss": 2.1461,
      "step": 100
    },
    {
      "epoch": 0.03602954422626554,
      "eval_loss": 2.2165262699127197,
      "eval_runtime": 63.3419,
      "eval_samples_per_second": 18.455,
      "eval_steps_per_second": 4.626,
      "step": 100
    },
    {
      "epoch": 0.039632498648892095,
      "grad_norm": 0.6089875102043152,
      "learning_rate": 0.00019231131849308138,
      "loss": 2.2921,
      "step": 110
    },
    {
      "epoch": 0.043235453071518645,
      "grad_norm": 0.6623978614807129,
      "learning_rate": 0.00018923623308232218,
      "loss": 2.1825,
      "step": 120
    },
    {
      "epoch": 0.0468384074941452,
      "grad_norm": 0.6278699040412903,
      "learning_rate": 0.00018572883366372081,
      "loss": 2.1697,
      "step": 130
    },
    {
      "epoch": 0.05044136191677175,
      "grad_norm": 0.6262252330780029,
      "learning_rate": 0.00018180620793468224,
      "loss": 1.9721,
      "step": 140
    },
    {
      "epoch": 0.05404431633939831,
      "grad_norm": 1.050173282623291,
      "learning_rate": 0.00017748746653345728,
      "loss": 2.068,
      "step": 150
    },
    {
      "epoch": 0.05404431633939831,
      "eval_loss": 2.16098952293396,
      "eval_runtime": 63.2967,
      "eval_samples_per_second": 18.469,
      "eval_steps_per_second": 4.629,
      "step": 150
    },
    {
      "epoch": 0.05764727076202486,
      "grad_norm": 0.6275399327278137,
      "learning_rate": 0.00017279364993403443,
      "loss": 2.2454,
      "step": 160
    },
    {
      "epoch": 0.06125022518465142,
      "grad_norm": 0.6378840208053589,
      "learning_rate": 0.00016774762593906525,
      "loss": 2.1606,
      "step": 170
    },
    {
      "epoch": 0.06485317960727797,
      "grad_norm": 0.6081838011741638,
      "learning_rate": 0.00016237397827022866,
      "loss": 2.0971,
      "step": 180
    },
    {
      "epoch": 0.06845613402990453,
      "grad_norm": 0.5905754566192627,
      "learning_rate": 0.00015669888679881007,
      "loss": 1.9485,
      "step": 190
    },
    {
      "epoch": 0.07205908845253108,
      "grad_norm": 1.0750936269760132,
      "learning_rate": 0.00015075,
      "loss": 2.0445,
      "step": 200
    },
    {
      "epoch": 0.07205908845253108,
      "eval_loss": 2.1002931594848633,
      "eval_runtime": 63.4836,
      "eval_samples_per_second": 18.414,
      "eval_steps_per_second": 4.615,
      "step": 200
    },
    {
      "epoch": 0.07566204287515763,
      "grad_norm": 0.6942563652992249,
      "learning_rate": 0.00014455630025230227,
      "loss": 2.1977,
      "step": 210
    },
    {
      "epoch": 0.07926499729778419,
      "grad_norm": 0.6279932856559753,
      "learning_rate": 0.00013814796263829918,
      "loss": 2.1514,
      "step": 220
    },
    {
      "epoch": 0.08286795172041074,
      "grad_norm": 0.5558415055274963,
      "learning_rate": 0.00013155620793468223,
      "loss": 2.0617,
      "step": 230
    },
    {
      "epoch": 0.08647090614303729,
      "grad_norm": 0.532662034034729,
      "learning_rate": 0.0001248131505077666,
      "loss": 1.904,
      "step": 240
    },
    {
      "epoch": 0.09007386056566384,
      "grad_norm": 1.1002955436706543,
      "learning_rate": 0.00011795164185552652,
      "loss": 1.9553,
      "step": 250
    },
    {
      "epoch": 0.09007386056566384,
      "eval_loss": 2.065007448196411,
      "eval_runtime": 63.3385,
      "eval_samples_per_second": 18.456,
      "eval_steps_per_second": 4.626,
      "step": 250
    },
    {
      "epoch": 0.0936768149882904,
      "grad_norm": 0.5946807861328125,
      "learning_rate": 0.00011100511055839919,
      "loss": 2.193,
      "step": 260
    },
    {
      "epoch": 0.09727976941091696,
      "grad_norm": 0.5511180758476257,
      "learning_rate": 0.00010400739941860137,
      "loss": 2.0602,
      "step": 270
    },
    {
      "epoch": 0.1008827238335435,
      "grad_norm": 0.5188409090042114,
      "learning_rate": 9.699260058139868e-05,
      "loss": 2.0481,
      "step": 280
    },
    {
      "epoch": 0.10448567825617006,
      "grad_norm": 0.5795491337776184,
      "learning_rate": 8.999488944160085e-05,
      "loss": 1.8138,
      "step": 290
    },
    {
      "epoch": 0.10808863267879662,
      "grad_norm": 0.9792818427085876,
      "learning_rate": 8.30483581444735e-05,
      "loss": 1.8413,
      "step": 300
    },
    {
      "epoch": 0.10808863267879662,
      "eval_loss": 2.025852680206299,
      "eval_runtime": 63.3985,
      "eval_samples_per_second": 18.439,
      "eval_steps_per_second": 4.622,
      "step": 300
    },
    {
      "epoch": 0.11169158710142317,
      "grad_norm": 0.5762483477592468,
      "learning_rate": 7.618684949223341e-05,
      "loss": 2.1275,
      "step": 310
    },
    {
      "epoch": 0.11529454152404972,
      "grad_norm": 0.5712476968765259,
      "learning_rate": 6.94437920653178e-05,
      "loss": 2.0378,
      "step": 320
    },
    {
      "epoch": 0.11889749594667627,
      "grad_norm": 0.5272972583770752,
      "learning_rate": 6.285203736170084e-05,
      "loss": 1.9894,
      "step": 330
    },
    {
      "epoch": 0.12250045036930284,
      "grad_norm": 0.6240211129188538,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 1.8432,
      "step": 340
    },
    {
      "epoch": 0.12610340479192939,
      "grad_norm": 0.9896277785301208,
      "learning_rate": 5.025000000000002e-05,
      "loss": 1.8631,
      "step": 350
    },
    {
      "epoch": 0.12610340479192939,
      "eval_loss": 1.9985251426696777,
      "eval_runtime": 63.5342,
      "eval_samples_per_second": 18.4,
      "eval_steps_per_second": 4.612,
      "step": 350
    },
    {
      "epoch": 0.12970635921455595,
      "grad_norm": 0.5958810448646545,
      "learning_rate": 4.430111320118996e-05,
      "loss": 2.1226,
      "step": 360
    },
    {
      "epoch": 0.13330931363718249,
      "grad_norm": 0.5658702254295349,
      "learning_rate": 3.862602172977134e-05,
      "loss": 2.008,
      "step": 370
    },
    {
      "epoch": 0.13691226805980905,
      "grad_norm": 0.5407539010047913,
      "learning_rate": 3.325237406093478e-05,
      "loss": 1.9236,
      "step": 380
    },
    {
      "epoch": 0.1405152224824356,
      "grad_norm": 0.521379292011261,
      "learning_rate": 2.820635006596558e-05,
      "loss": 1.7738,
      "step": 390
    },
    {
      "epoch": 0.14411817690506215,
      "grad_norm": 1.012351393699646,
      "learning_rate": 2.351253346654272e-05,
      "loss": 1.8504,
      "step": 400
    },
    {
      "epoch": 0.14411817690506215,
      "eval_loss": 1.971751093864441,
      "eval_runtime": 63.2383,
      "eval_samples_per_second": 18.486,
      "eval_steps_per_second": 4.633,
      "step": 400
    },
    {
      "epoch": 0.14772113132768872,
      "grad_norm": 0.5679916143417358,
      "learning_rate": 1.9193792065317794e-05,
      "loss": 2.0539,
      "step": 410
    },
    {
      "epoch": 0.15132408575031525,
      "grad_norm": 0.5590336918830872,
      "learning_rate": 1.5271166336279193e-05,
      "loss": 2.0377,
      "step": 420
    },
    {
      "epoch": 0.15492704017294182,
      "grad_norm": 0.5411215424537659,
      "learning_rate": 1.1763766917677837e-05,
      "loss": 1.9581,
      "step": 430
    },
    {
      "epoch": 0.15852999459556838,
      "grad_norm": 0.5810568928718567,
      "learning_rate": 8.688681506918602e-06,
      "loss": 1.8081,
      "step": 440
    },
    {
      "epoch": 0.16213294901819492,
      "grad_norm": 1.0498058795928955,
      "learning_rate": 6.060891611016215e-06,
      "loss": 1.8513,
      "step": 450
    },
    {
      "epoch": 0.16213294901819492,
      "eval_loss": 1.9625978469848633,
      "eval_runtime": 63.3636,
      "eval_samples_per_second": 18.449,
      "eval_steps_per_second": 4.624,
      "step": 450
    },
    {
      "epoch": 0.16573590344082148,
      "grad_norm": 0.5630381107330322,
      "learning_rate": 3.893199558198952e-06,
      "loss": 2.0962,
      "step": 460
    },
    {
      "epoch": 0.16933885786344802,
      "grad_norm": 0.5653451681137085,
      "learning_rate": 2.1961661262525285e-06,
      "loss": 1.948,
      "step": 470
    },
    {
      "epoch": 0.17294181228607458,
      "grad_norm": 0.528786838054657,
      "learning_rate": 9.780590914721787e-07,
      "loss": 1.9981,
      "step": 480
    },
    {
      "epoch": 0.17654476670870115,
      "grad_norm": 0.5580498576164246,
      "learning_rate": 2.4481294888766817e-07,
      "loss": 1.8072,
      "step": 490
    },
    {
      "epoch": 0.18014772113132768,
      "grad_norm": 1.0382150411605835,
      "learning_rate": 0.0,
      "loss": 1.8913,
      "step": 500
    },
    {
      "epoch": 0.18014772113132768,
      "eval_loss": 1.9572868347167969,
      "eval_runtime": 63.3164,
      "eval_samples_per_second": 18.463,
      "eval_steps_per_second": 4.628,
      "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": 7.000556687327232e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}