{
  "best_metric": 0.2870234549045563,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.015524816419045845,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.104963283809169e-05,
      "eval_loss": 3.7327520847320557,
      "eval_runtime": 1160.7988,
      "eval_samples_per_second": 11.682,
      "eval_steps_per_second": 2.921,
      "step": 1
    },
    {
      "epoch": 0.0003104963283809169,
      "grad_norm": 3.784548759460449,
      "learning_rate": 4.08e-05,
      "loss": 3.065,
      "step": 10
    },
    {
      "epoch": 0.0006209926567618338,
      "grad_norm": 3.344172954559326,
      "learning_rate": 8.16e-05,
      "loss": 2.3919,
      "step": 20
    },
    {
      "epoch": 0.0009314889851427506,
      "grad_norm": 1.5794700384140015,
      "learning_rate": 0.0001224,
      "loss": 0.8608,
      "step": 30
    },
    {
      "epoch": 0.0012419853135236677,
      "grad_norm": 3.304838180541992,
      "learning_rate": 0.0001632,
      "loss": 0.4056,
      "step": 40
    },
    {
      "epoch": 0.0015524816419045845,
      "grad_norm": 0.6182494163513184,
      "learning_rate": 0.000204,
      "loss": 0.3099,
      "step": 50
    },
    {
      "epoch": 0.0015524816419045845,
      "eval_loss": 0.34165456891059875,
      "eval_runtime": 1161.9557,
      "eval_samples_per_second": 11.671,
      "eval_steps_per_second": 2.918,
      "step": 50
    },
    {
      "epoch": 0.0018629779702855013,
      "grad_norm": 0.9414771199226379,
      "learning_rate": 0.00020375153312650207,
      "loss": 0.3528,
      "step": 60
    },
    {
      "epoch": 0.0021734742986664183,
      "grad_norm": 3.154303789138794,
      "learning_rate": 0.00020300734301164017,
      "loss": 0.3092,
      "step": 70
    },
    {
      "epoch": 0.0024839706270473353,
      "grad_norm": 4.68408727645874,
      "learning_rate": 0.00020177105527484818,
      "loss": 0.5714,
      "step": 80
    },
    {
      "epoch": 0.002794466955428252,
      "grad_norm": 6.463703155517578,
      "learning_rate": 0.00020004869298570854,
      "loss": 0.3781,
      "step": 90
    },
    {
      "epoch": 0.003104963283809169,
      "grad_norm": 0.6307673454284668,
      "learning_rate": 0.00019784864732016265,
      "loss": 0.2635,
      "step": 100
    },
    {
      "epoch": 0.003104963283809169,
      "eval_loss": 0.36230921745300293,
      "eval_runtime": 1160.8503,
      "eval_samples_per_second": 11.682,
      "eval_steps_per_second": 2.921,
      "step": 100
    },
    {
      "epoch": 0.003415459612190086,
      "grad_norm": 3.080695390701294,
      "learning_rate": 0.00019518163667954527,
      "loss": 0.3737,
      "step": 110
    },
    {
      "epoch": 0.0037259559405710026,
      "grad_norm": 0.564507782459259,
      "learning_rate": 0.00019206065447161056,
      "loss": 0.3038,
      "step": 120
    },
    {
      "epoch": 0.00403645226895192,
      "grad_norm": 0.3009290099143982,
      "learning_rate": 0.00018850090580795544,
      "loss": 0.3419,
      "step": 130
    },
    {
      "epoch": 0.004346948597332837,
      "grad_norm": 7.988672733306885,
      "learning_rate": 0.00018451973342624464,
      "loss": 2.1628,
      "step": 140
    },
    {
      "epoch": 0.004657444925713753,
      "grad_norm": 3.4192960262298584,
      "learning_rate": 0.00018013653319813575,
      "loss": 0.8874,
      "step": 150
    },
    {
      "epoch": 0.004657444925713753,
      "eval_loss": 0.3869711458683014,
      "eval_runtime": 1161.6515,
      "eval_samples_per_second": 11.674,
      "eval_steps_per_second": 2.919,
      "step": 150
    },
    {
      "epoch": 0.004967941254094671,
      "grad_norm": 0.5543773770332336,
      "learning_rate": 0.0001753726596345424,
      "loss": 0.3118,
      "step": 160
    },
    {
      "epoch": 0.005278437582475587,
      "grad_norm": 3.5551018714904785,
      "learning_rate": 0.00017025132184860355,
      "loss": 0.4065,
      "step": 170
    },
    {
      "epoch": 0.005588933910856504,
      "grad_norm": 0.8357908725738525,
      "learning_rate": 0.00016479747048321714,
      "loss": 0.4147,
      "step": 180
    },
    {
      "epoch": 0.005899430239237421,
      "grad_norm": 0.5181112289428711,
      "learning_rate": 0.00015903767615401616,
      "loss": 0.2827,
      "step": 190
    },
    {
      "epoch": 0.006209926567618338,
      "grad_norm": 1.829988956451416,
      "learning_rate": 0.000153,
      "loss": 0.2747,
      "step": 200
    },
    {
      "epoch": 0.006209926567618338,
      "eval_loss": 0.31800615787506104,
      "eval_runtime": 1161.2828,
      "eval_samples_per_second": 11.678,
      "eval_steps_per_second": 2.92,
      "step": 200
    },
    {
      "epoch": 0.0065204228959992545,
      "grad_norm": 1.3195180892944336,
      "learning_rate": 0.0001467138569724859,
      "loss": 0.3177,
      "step": 210
    },
    {
      "epoch": 0.006830919224380172,
      "grad_norm": 2.611358642578125,
      "learning_rate": 0.00014020987252842305,
      "loss": 0.3129,
      "step": 220
    },
    {
      "epoch": 0.0071414155527610886,
      "grad_norm": 23.8262996673584,
      "learning_rate": 0.00013351973342624464,
      "loss": 0.5152,
      "step": 230
    },
    {
      "epoch": 0.007451911881142005,
      "grad_norm": 0.7884902954101562,
      "learning_rate": 0.00012667603335116609,
      "loss": 0.867,
      "step": 240
    },
    {
      "epoch": 0.007762408209522923,
      "grad_norm": 0.3505696654319763,
      "learning_rate": 0.00011971211412202691,
      "loss": 0.2918,
      "step": 250
    },
    {
      "epoch": 0.007762408209522923,
      "eval_loss": 0.3034397065639496,
      "eval_runtime": 1160.652,
      "eval_samples_per_second": 11.684,
      "eval_steps_per_second": 2.922,
      "step": 250
    },
    {
      "epoch": 0.00807290453790384,
      "grad_norm": 0.6287646889686584,
      "learning_rate": 0.00011266190325330066,
      "loss": 0.3212,
      "step": 260
    },
    {
      "epoch": 0.008383400866284757,
      "grad_norm": 1.5718376636505127,
      "learning_rate": 0.00010555974866365511,
      "loss": 0.2674,
      "step": 270
    },
    {
      "epoch": 0.008693897194665673,
      "grad_norm": 0.6371111869812012,
      "learning_rate": 9.844025133634492e-05,
      "loss": 0.4243,
      "step": 280
    },
    {
      "epoch": 0.00900439352304659,
      "grad_norm": 0.7290711402893066,
      "learning_rate": 9.133809674669937e-05,
      "loss": 0.2891,
      "step": 290
    },
    {
      "epoch": 0.009314889851427506,
      "grad_norm": 0.5713692307472229,
      "learning_rate": 8.428788587797311e-05,
      "loss": 0.2543,
      "step": 300
    },
    {
      "epoch": 0.009314889851427506,
      "eval_loss": 0.3538323938846588,
      "eval_runtime": 1160.2598,
      "eval_samples_per_second": 11.688,
      "eval_steps_per_second": 2.923,
      "step": 300
    },
    {
      "epoch": 0.009625386179808423,
      "grad_norm": 6.953015327453613,
      "learning_rate": 7.73239666488339e-05,
      "loss": 0.3133,
      "step": 310
    },
    {
      "epoch": 0.009935882508189341,
      "grad_norm": 2.1346802711486816,
      "learning_rate": 7.048026657375537e-05,
      "loss": 0.334,
      "step": 320
    },
    {
      "epoch": 0.010246378836570258,
      "grad_norm": 2.4181416034698486,
      "learning_rate": 6.379012747157697e-05,
      "loss": 0.3077,
      "step": 330
    },
    {
      "epoch": 0.010556875164951175,
      "grad_norm": 0.9341647624969482,
      "learning_rate": 5.7286143027514095e-05,
      "loss": 0.3673,
      "step": 340
    },
    {
      "epoch": 0.010867371493332091,
      "grad_norm": 0.5034169554710388,
      "learning_rate": 5.100000000000002e-05,
      "loss": 0.2662,
      "step": 350
    },
    {
      "epoch": 0.010867371493332091,
      "eval_loss": 0.2990635335445404,
      "eval_runtime": 1159.9666,
      "eval_samples_per_second": 11.691,
      "eval_steps_per_second": 2.923,
      "step": 350
    },
    {
      "epoch": 0.011177867821713008,
      "grad_norm": 0.6715922951698303,
      "learning_rate": 4.496232384598384e-05,
      "loss": 0.3294,
      "step": 360
    },
    {
      "epoch": 0.011488364150093924,
      "grad_norm": 0.6445696353912354,
      "learning_rate": 3.9202529516782854e-05,
      "loss": 0.2706,
      "step": 370
    },
    {
      "epoch": 0.011798860478474843,
      "grad_norm": 0.26978200674057007,
      "learning_rate": 3.374867815139649e-05,
      "loss": 0.3663,
      "step": 380
    },
    {
      "epoch": 0.01210935680685576,
      "grad_norm": 0.5984402298927307,
      "learning_rate": 2.8627340365457602e-05,
      "loss": 0.2697,
      "step": 390
    },
    {
      "epoch": 0.012419853135236676,
      "grad_norm": 0.7722185254096985,
      "learning_rate": 2.3863466801864254e-05,
      "loss": 0.2701,
      "step": 400
    },
    {
      "epoch": 0.012419853135236676,
      "eval_loss": 0.2882494032382965,
      "eval_runtime": 1161.5989,
      "eval_samples_per_second": 11.674,
      "eval_steps_per_second": 2.919,
      "step": 400
    },
    {
      "epoch": 0.012730349463617592,
      "grad_norm": 0.4869549572467804,
      "learning_rate": 1.9480266573755372e-05,
      "loss": 0.3046,
      "step": 410
    },
    {
      "epoch": 0.013040845791998509,
      "grad_norm": 1.2998945713043213,
      "learning_rate": 1.5499094192044554e-05,
      "loss": 0.2766,
      "step": 420
    },
    {
      "epoch": 0.013351342120379427,
      "grad_norm": 1.5833019018173218,
      "learning_rate": 1.1939345528389446e-05,
      "loss": 0.3613,
      "step": 430
    },
    {
      "epoch": 0.013661838448760344,
      "grad_norm": 0.3303629159927368,
      "learning_rate": 8.818363320454701e-06,
      "loss": 0.2713,
      "step": 440
    },
    {
      "epoch": 0.01397233477714126,
      "grad_norm": 0.5843662619590759,
      "learning_rate": 6.1513526798373514e-06,
      "loss": 0.2793,
      "step": 450
    },
    {
      "epoch": 0.01397233477714126,
      "eval_loss": 0.2871423065662384,
      "eval_runtime": 1162.0849,
      "eval_samples_per_second": 11.67,
      "eval_steps_per_second": 2.918,
      "step": 450
    },
    {
      "epoch": 0.014282831105522177,
      "grad_norm": 0.6200801134109497,
      "learning_rate": 3.9513070142914725e-06,
      "loss": 0.2882,
      "step": 460
    },
    {
      "epoch": 0.014593327433903094,
      "grad_norm": 1.349033236503601,
      "learning_rate": 2.2289447251518195e-06,
      "loss": 0.2813,
      "step": 470
    },
    {
      "epoch": 0.01490382376228401,
      "grad_norm": 0.3599369525909424,
      "learning_rate": 9.92656988359823e-07,
      "loss": 0.3312,
      "step": 480
    },
    {
      "epoch": 0.015214320090664929,
      "grad_norm": 0.32290154695510864,
      "learning_rate": 2.4846687349793185e-07,
      "loss": 0.2915,
      "step": 490
    },
    {
      "epoch": 0.015524816419045845,
      "grad_norm": 0.5347475409507751,
      "learning_rate": 0.0,
      "loss": 0.2675,
      "step": 500
    },
    {
      "epoch": 0.015524816419045845,
      "eval_loss": 0.2870234549045563,
      "eval_runtime": 1160.4192,
      "eval_samples_per_second": 11.686,
      "eval_steps_per_second": 2.922,
      "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": 1.3954559915537203e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}