{
  "best_metric": 0.1467157006263733,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.4434589800443459,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008869179600886918,
      "eval_loss": 2.8770248889923096,
      "eval_runtime": 38.2755,
      "eval_samples_per_second": 12.41,
      "eval_steps_per_second": 3.109,
      "step": 1
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 2.3135693073272705,
      "learning_rate": 4.08e-05,
      "loss": 1.7025,
      "step": 10
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 5.826132774353027,
      "learning_rate": 8.16e-05,
      "loss": 1.2575,
      "step": 20
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 2.034158706665039,
      "learning_rate": 0.0001224,
      "loss": 0.6409,
      "step": 30
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 1.2038573026657104,
      "learning_rate": 0.0001632,
      "loss": 0.3877,
      "step": 40
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 2.602550506591797,
      "learning_rate": 0.000204,
      "loss": 0.4058,
      "step": 50
    },
    {
      "epoch": 0.04434589800443459,
      "eval_loss": 0.48393380641937256,
      "eval_runtime": 38.458,
      "eval_samples_per_second": 12.351,
      "eval_steps_per_second": 3.094,
      "step": 50
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 1.0940451622009277,
      "learning_rate": 0.00020375153312650207,
      "loss": 0.4035,
      "step": 60
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 1.9350886344909668,
      "learning_rate": 0.00020300734301164017,
      "loss": 0.4885,
      "step": 70
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 1.2535470724105835,
      "learning_rate": 0.00020177105527484818,
      "loss": 0.4405,
      "step": 80
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 1.0557414293289185,
      "learning_rate": 0.00020004869298570854,
      "loss": 0.3142,
      "step": 90
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.4732565879821777,
      "learning_rate": 0.00019784864732016265,
      "loss": 0.2543,
      "step": 100
    },
    {
      "epoch": 0.08869179600886919,
      "eval_loss": 0.3842791020870209,
      "eval_runtime": 38.3252,
      "eval_samples_per_second": 12.394,
      "eval_steps_per_second": 3.105,
      "step": 100
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 1.707848310470581,
      "learning_rate": 0.00019518163667954527,
      "loss": 0.3664,
      "step": 110
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 2.2555489540100098,
      "learning_rate": 0.00019206065447161056,
      "loss": 0.4011,
      "step": 120
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 1.6298093795776367,
      "learning_rate": 0.00018850090580795544,
      "loss": 0.3865,
      "step": 130
    },
    {
      "epoch": 0.12416851441241686,
      "grad_norm": 0.8985351324081421,
      "learning_rate": 0.00018451973342624464,
      "loss": 0.2434,
      "step": 140
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 1.4685873985290527,
      "learning_rate": 0.00018013653319813575,
      "loss": 0.2117,
      "step": 150
    },
    {
      "epoch": 0.13303769401330376,
      "eval_loss": 0.3515245020389557,
      "eval_runtime": 38.3502,
      "eval_samples_per_second": 12.386,
      "eval_steps_per_second": 3.103,
      "step": 150
    },
    {
      "epoch": 0.1419068736141907,
      "grad_norm": 0.8023963570594788,
      "learning_rate": 0.0001753726596345424,
      "loss": 0.3351,
      "step": 160
    },
    {
      "epoch": 0.15077605321507762,
      "grad_norm": 2.3489186763763428,
      "learning_rate": 0.00017025132184860355,
      "loss": 0.3505,
      "step": 170
    },
    {
      "epoch": 0.15964523281596452,
      "grad_norm": 1.0971386432647705,
      "learning_rate": 0.00016479747048321714,
      "loss": 0.3321,
      "step": 180
    },
    {
      "epoch": 0.16851441241685144,
      "grad_norm": 1.2261146306991577,
      "learning_rate": 0.00015903767615401616,
      "loss": 0.2225,
      "step": 190
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 2.1225969791412354,
      "learning_rate": 0.000153,
      "loss": 0.2255,
      "step": 200
    },
    {
      "epoch": 0.17738359201773837,
      "eval_loss": 0.33060675859451294,
      "eval_runtime": 38.2506,
      "eval_samples_per_second": 12.418,
      "eval_steps_per_second": 3.111,
      "step": 200
    },
    {
      "epoch": 0.18625277161862527,
      "grad_norm": 0.7228109836578369,
      "learning_rate": 0.0001467138569724859,
      "loss": 0.3361,
      "step": 210
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 1.9913522005081177,
      "learning_rate": 0.00014020987252842305,
      "loss": 0.3271,
      "step": 220
    },
    {
      "epoch": 0.2039911308203991,
      "grad_norm": 0.4413537085056305,
      "learning_rate": 0.00013351973342624464,
      "loss": 0.2218,
      "step": 230
    },
    {
      "epoch": 0.21286031042128603,
      "grad_norm": 1.145608901977539,
      "learning_rate": 0.00012667603335116609,
      "loss": 0.2622,
      "step": 240
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 0.9548584818840027,
      "learning_rate": 0.00011971211412202691,
      "loss": 0.1617,
      "step": 250
    },
    {
      "epoch": 0.22172949002217296,
      "eval_loss": 0.28546851873397827,
      "eval_runtime": 38.6472,
      "eval_samples_per_second": 12.291,
      "eval_steps_per_second": 3.079,
      "step": 250
    },
    {
      "epoch": 0.23059866962305986,
      "grad_norm": 0.7428591251373291,
      "learning_rate": 0.00011266190325330066,
      "loss": 0.2523,
      "step": 260
    },
    {
      "epoch": 0.2394678492239468,
      "grad_norm": 2.0171639919281006,
      "learning_rate": 0.00010555974866365511,
      "loss": 0.2735,
      "step": 270
    },
    {
      "epoch": 0.24833702882483372,
      "grad_norm": 0.6927977204322815,
      "learning_rate": 9.844025133634492e-05,
      "loss": 0.2121,
      "step": 280
    },
    {
      "epoch": 0.2572062084257206,
      "grad_norm": 0.654840350151062,
      "learning_rate": 9.133809674669937e-05,
      "loss": 0.1686,
      "step": 290
    },
    {
      "epoch": 0.2660753880266075,
      "grad_norm": 1.0191060304641724,
      "learning_rate": 8.428788587797311e-05,
      "loss": 0.1575,
      "step": 300
    },
    {
      "epoch": 0.2660753880266075,
      "eval_loss": 0.23826612532138824,
      "eval_runtime": 38.3953,
      "eval_samples_per_second": 12.371,
      "eval_steps_per_second": 3.099,
      "step": 300
    },
    {
      "epoch": 0.2749445676274945,
      "grad_norm": 0.6559511423110962,
      "learning_rate": 7.73239666488339e-05,
      "loss": 0.248,
      "step": 310
    },
    {
      "epoch": 0.2838137472283814,
      "grad_norm": 0.7280802130699158,
      "learning_rate": 7.048026657375537e-05,
      "loss": 0.2783,
      "step": 320
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.5098235011100769,
      "learning_rate": 6.379012747157697e-05,
      "loss": 0.1791,
      "step": 330
    },
    {
      "epoch": 0.30155210643015523,
      "grad_norm": 0.6742261052131653,
      "learning_rate": 5.7286143027514095e-05,
      "loss": 0.1799,
      "step": 340
    },
    {
      "epoch": 0.31042128603104213,
      "grad_norm": 1.0782533884048462,
      "learning_rate": 5.100000000000002e-05,
      "loss": 0.179,
      "step": 350
    },
    {
      "epoch": 0.31042128603104213,
      "eval_loss": 0.18237313628196716,
      "eval_runtime": 38.749,
      "eval_samples_per_second": 12.258,
      "eval_steps_per_second": 3.071,
      "step": 350
    },
    {
      "epoch": 0.31929046563192903,
      "grad_norm": 0.7198016047477722,
      "learning_rate": 4.496232384598384e-05,
      "loss": 0.202,
      "step": 360
    },
    {
      "epoch": 0.328159645232816,
      "grad_norm": 0.6748245358467102,
      "learning_rate": 3.9202529516782854e-05,
      "loss": 0.219,
      "step": 370
    },
    {
      "epoch": 0.3370288248337029,
      "grad_norm": 1.0296882390975952,
      "learning_rate": 3.374867815139649e-05,
      "loss": 0.1495,
      "step": 380
    },
    {
      "epoch": 0.3458980044345898,
      "grad_norm": 0.3503113090991974,
      "learning_rate": 2.8627340365457602e-05,
      "loss": 0.108,
      "step": 390
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 1.1339133977890015,
      "learning_rate": 2.3863466801864254e-05,
      "loss": 0.1444,
      "step": 400
    },
    {
      "epoch": 0.35476718403547675,
      "eval_loss": 0.16124120354652405,
      "eval_runtime": 38.5634,
      "eval_samples_per_second": 12.317,
      "eval_steps_per_second": 3.086,
      "step": 400
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.4983493685722351,
      "learning_rate": 1.9480266573755372e-05,
      "loss": 0.1827,
      "step": 410
    },
    {
      "epoch": 0.37250554323725055,
      "grad_norm": 0.9665442109107971,
      "learning_rate": 1.5499094192044554e-05,
      "loss": 0.2299,
      "step": 420
    },
    {
      "epoch": 0.38137472283813745,
      "grad_norm": 0.6066753268241882,
      "learning_rate": 1.1939345528389446e-05,
      "loss": 0.1402,
      "step": 430
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.4985198974609375,
      "learning_rate": 8.818363320454701e-06,
      "loss": 0.1197,
      "step": 440
    },
    {
      "epoch": 0.3991130820399113,
      "grad_norm": 0.3755505383014679,
      "learning_rate": 6.1513526798373514e-06,
      "loss": 0.1243,
      "step": 450
    },
    {
      "epoch": 0.3991130820399113,
      "eval_loss": 0.1467157006263733,
      "eval_runtime": 38.6346,
      "eval_samples_per_second": 12.295,
      "eval_steps_per_second": 3.08,
      "step": 450
    },
    {
      "epoch": 0.4079822616407982,
      "grad_norm": 0.6651077270507812,
      "learning_rate": 3.9513070142914725e-06,
      "loss": 0.1562,
      "step": 460
    },
    {
      "epoch": 0.41685144124168516,
      "grad_norm": 1.4017401933670044,
      "learning_rate": 2.2289447251518195e-06,
      "loss": 0.1808,
      "step": 470
    },
    {
      "epoch": 0.42572062084257206,
      "grad_norm": 0.4009847640991211,
      "learning_rate": 9.92656988359823e-07,
      "loss": 0.1463,
      "step": 480
    },
    {
      "epoch": 0.43458980044345896,
      "grad_norm": 0.2714759409427643,
      "learning_rate": 2.4846687349793185e-07,
      "loss": 0.11,
      "step": 490
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 1.1573147773742676,
      "learning_rate": 0.0,
      "loss": 0.0943,
      "step": 500
    },
    {
      "epoch": 0.4434589800443459,
      "eval_loss": 0.14757481217384338,
      "eval_runtime": 38.3424,
      "eval_samples_per_second": 12.388,
      "eval_steps_per_second": 3.104,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2480978011081933e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}