{
  "best_metric": 2.425506353378296,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.03208213025344883,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.416426050689766e-05,
      "eval_loss": 3.0761466026306152,
      "eval_runtime": 248.0097,
      "eval_samples_per_second": 26.463,
      "eval_steps_per_second": 6.617,
      "step": 1
    },
    {
      "epoch": 0.0006416426050689766,
      "grad_norm": 2.1181607246398926,
      "learning_rate": 4.08e-05,
      "loss": 2.6512,
      "step": 10
    },
    {
      "epoch": 0.0012832852101379532,
      "grad_norm": 2.143641948699951,
      "learning_rate": 8.16e-05,
      "loss": 2.553,
      "step": 20
    },
    {
      "epoch": 0.0019249278152069298,
      "grad_norm": 2.2535758018493652,
      "learning_rate": 0.0001224,
      "loss": 2.4612,
      "step": 30
    },
    {
      "epoch": 0.0025665704202759063,
      "grad_norm": 2.534200668334961,
      "learning_rate": 0.0001632,
      "loss": 2.521,
      "step": 40
    },
    {
      "epoch": 0.003208213025344883,
      "grad_norm": 3.303925037384033,
      "learning_rate": 0.000204,
      "loss": 2.5419,
      "step": 50
    },
    {
      "epoch": 0.003208213025344883,
      "eval_loss": 2.524552345275879,
      "eval_runtime": 247.4632,
      "eval_samples_per_second": 26.521,
      "eval_steps_per_second": 6.631,
      "step": 50
    },
    {
      "epoch": 0.0038498556304138597,
      "grad_norm": 1.3380857706069946,
      "learning_rate": 0.00020375153312650207,
      "loss": 2.4129,
      "step": 60
    },
    {
      "epoch": 0.004491498235482836,
      "grad_norm": 1.7602264881134033,
      "learning_rate": 0.00020300734301164017,
      "loss": 2.4986,
      "step": 70
    },
    {
      "epoch": 0.005133140840551813,
      "grad_norm": 1.8537044525146484,
      "learning_rate": 0.00020177105527484818,
      "loss": 2.441,
      "step": 80
    },
    {
      "epoch": 0.005774783445620789,
      "grad_norm": 2.583019971847534,
      "learning_rate": 0.00020004869298570854,
      "loss": 2.5052,
      "step": 90
    },
    {
      "epoch": 0.006416426050689766,
      "grad_norm": 3.4130592346191406,
      "learning_rate": 0.00019784864732016265,
      "loss": 2.5278,
      "step": 100
    },
    {
      "epoch": 0.006416426050689766,
      "eval_loss": 2.5519673824310303,
      "eval_runtime": 247.2928,
      "eval_samples_per_second": 26.539,
      "eval_steps_per_second": 6.636,
      "step": 100
    },
    {
      "epoch": 0.007058068655758742,
      "grad_norm": 1.2456212043762207,
      "learning_rate": 0.00019518163667954527,
      "loss": 2.4501,
      "step": 110
    },
    {
      "epoch": 0.007699711260827719,
      "grad_norm": 1.8833853006362915,
      "learning_rate": 0.00019206065447161056,
      "loss": 2.4523,
      "step": 120
    },
    {
      "epoch": 0.008341353865896696,
      "grad_norm": 2.167327404022217,
      "learning_rate": 0.00018850090580795544,
      "loss": 2.5085,
      "step": 130
    },
    {
      "epoch": 0.008982996470965673,
      "grad_norm": 2.533130645751953,
      "learning_rate": 0.00018451973342624464,
      "loss": 2.4788,
      "step": 140
    },
    {
      "epoch": 0.009624639076034648,
      "grad_norm": 3.3289971351623535,
      "learning_rate": 0.00018013653319813575,
      "loss": 2.3569,
      "step": 150
    },
    {
      "epoch": 0.009624639076034648,
      "eval_loss": 2.561899423599243,
      "eval_runtime": 248.4044,
      "eval_samples_per_second": 26.421,
      "eval_steps_per_second": 6.606,
      "step": 150
    },
    {
      "epoch": 0.010266281681103625,
      "grad_norm": 1.4331955909729004,
      "learning_rate": 0.0001753726596345424,
      "loss": 2.5594,
      "step": 160
    },
    {
      "epoch": 0.010907924286172602,
      "grad_norm": 1.6859421730041504,
      "learning_rate": 0.00017025132184860355,
      "loss": 2.4436,
      "step": 170
    },
    {
      "epoch": 0.011549566891241578,
      "grad_norm": 2.1262240409851074,
      "learning_rate": 0.00016479747048321714,
      "loss": 2.5153,
      "step": 180
    },
    {
      "epoch": 0.012191209496310555,
      "grad_norm": 2.288388252258301,
      "learning_rate": 0.00015903767615401616,
      "loss": 2.4702,
      "step": 190
    },
    {
      "epoch": 0.012832852101379532,
      "grad_norm": 3.3808329105377197,
      "learning_rate": 0.000153,
      "loss": 2.4684,
      "step": 200
    },
    {
      "epoch": 0.012832852101379532,
      "eval_loss": 2.4939587116241455,
      "eval_runtime": 247.9007,
      "eval_samples_per_second": 26.474,
      "eval_steps_per_second": 6.62,
      "step": 200
    },
    {
      "epoch": 0.013474494706448507,
      "grad_norm": 1.3569692373275757,
      "learning_rate": 0.0001467138569724859,
      "loss": 2.463,
      "step": 210
    },
    {
      "epoch": 0.014116137311517485,
      "grad_norm": 1.664777159690857,
      "learning_rate": 0.00014020987252842305,
      "loss": 2.5294,
      "step": 220
    },
    {
      "epoch": 0.014757779916586462,
      "grad_norm": 1.891471266746521,
      "learning_rate": 0.00013351973342624464,
      "loss": 2.4667,
      "step": 230
    },
    {
      "epoch": 0.015399422521655439,
      "grad_norm": 2.472409248352051,
      "learning_rate": 0.00012667603335116609,
      "loss": 2.4393,
      "step": 240
    },
    {
      "epoch": 0.016041065126724416,
      "grad_norm": 3.5608251094818115,
      "learning_rate": 0.00011971211412202691,
      "loss": 2.3954,
      "step": 250
    },
    {
      "epoch": 0.016041065126724416,
      "eval_loss": 2.4938225746154785,
      "eval_runtime": 247.9352,
      "eval_samples_per_second": 26.471,
      "eval_steps_per_second": 6.619,
      "step": 250
    },
    {
      "epoch": 0.01668270773179339,
      "grad_norm": 1.4132589101791382,
      "learning_rate": 0.00011266190325330066,
      "loss": 2.4294,
      "step": 260
    },
    {
      "epoch": 0.017324350336862367,
      "grad_norm": 1.6854068040847778,
      "learning_rate": 0.00010555974866365511,
      "loss": 2.4818,
      "step": 270
    },
    {
      "epoch": 0.017965992941931345,
      "grad_norm": 1.9312472343444824,
      "learning_rate": 9.844025133634492e-05,
      "loss": 2.575,
      "step": 280
    },
    {
      "epoch": 0.01860763554700032,
      "grad_norm": 2.2843751907348633,
      "learning_rate": 9.133809674669937e-05,
      "loss": 2.4306,
      "step": 290
    },
    {
      "epoch": 0.019249278152069296,
      "grad_norm": 3.1359288692474365,
      "learning_rate": 8.428788587797311e-05,
      "loss": 2.4642,
      "step": 300
    },
    {
      "epoch": 0.019249278152069296,
      "eval_loss": 2.4635369777679443,
      "eval_runtime": 248.3558,
      "eval_samples_per_second": 26.426,
      "eval_steps_per_second": 6.607,
      "step": 300
    },
    {
      "epoch": 0.019890920757138275,
      "grad_norm": 1.1439577341079712,
      "learning_rate": 7.73239666488339e-05,
      "loss": 2.4846,
      "step": 310
    },
    {
      "epoch": 0.02053256336220725,
      "grad_norm": 1.5837206840515137,
      "learning_rate": 7.048026657375537e-05,
      "loss": 2.4171,
      "step": 320
    },
    {
      "epoch": 0.021174205967276226,
      "grad_norm": 1.7678472995758057,
      "learning_rate": 6.379012747157697e-05,
      "loss": 2.3862,
      "step": 330
    },
    {
      "epoch": 0.021815848572345205,
      "grad_norm": 2.200498342514038,
      "learning_rate": 5.7286143027514095e-05,
      "loss": 2.4574,
      "step": 340
    },
    {
      "epoch": 0.02245749117741418,
      "grad_norm": 2.8402225971221924,
      "learning_rate": 5.100000000000002e-05,
      "loss": 2.458,
      "step": 350
    },
    {
      "epoch": 0.02245749117741418,
      "eval_loss": 2.4442172050476074,
      "eval_runtime": 248.9891,
      "eval_samples_per_second": 26.359,
      "eval_steps_per_second": 6.591,
      "step": 350
    },
    {
      "epoch": 0.023099133782483156,
      "grad_norm": 1.2951734066009521,
      "learning_rate": 4.496232384598384e-05,
      "loss": 2.3697,
      "step": 360
    },
    {
      "epoch": 0.023740776387552134,
      "grad_norm": 1.5272811651229858,
      "learning_rate": 3.9202529516782854e-05,
      "loss": 2.4261,
      "step": 370
    },
    {
      "epoch": 0.02438241899262111,
      "grad_norm": 1.9741696119308472,
      "learning_rate": 3.374867815139649e-05,
      "loss": 2.4812,
      "step": 380
    },
    {
      "epoch": 0.025024061597690085,
      "grad_norm": 1.9671711921691895,
      "learning_rate": 2.8627340365457602e-05,
      "loss": 2.414,
      "step": 390
    },
    {
      "epoch": 0.025665704202759064,
      "grad_norm": 3.4139561653137207,
      "learning_rate": 2.3863466801864254e-05,
      "loss": 2.3964,
      "step": 400
    },
    {
      "epoch": 0.025665704202759064,
      "eval_loss": 2.4310266971588135,
      "eval_runtime": 248.5605,
      "eval_samples_per_second": 26.404,
      "eval_steps_per_second": 6.602,
      "step": 400
    },
    {
      "epoch": 0.02630734680782804,
      "grad_norm": 1.3299930095672607,
      "learning_rate": 1.9480266573755372e-05,
      "loss": 2.4124,
      "step": 410
    },
    {
      "epoch": 0.026948989412897015,
      "grad_norm": 1.694121241569519,
      "learning_rate": 1.5499094192044554e-05,
      "loss": 2.4622,
      "step": 420
    },
    {
      "epoch": 0.027590632017965994,
      "grad_norm": 1.9327712059020996,
      "learning_rate": 1.1939345528389446e-05,
      "loss": 2.4714,
      "step": 430
    },
    {
      "epoch": 0.02823227462303497,
      "grad_norm": 2.3316149711608887,
      "learning_rate": 8.818363320454701e-06,
      "loss": 2.4211,
      "step": 440
    },
    {
      "epoch": 0.028873917228103944,
      "grad_norm": 3.5221705436706543,
      "learning_rate": 6.1513526798373514e-06,
      "loss": 2.4161,
      "step": 450
    },
    {
      "epoch": 0.028873917228103944,
      "eval_loss": 2.426518440246582,
      "eval_runtime": 248.4092,
      "eval_samples_per_second": 26.42,
      "eval_steps_per_second": 6.606,
      "step": 450
    },
    {
      "epoch": 0.029515559833172923,
      "grad_norm": 1.2081670761108398,
      "learning_rate": 3.9513070142914725e-06,
      "loss": 2.4222,
      "step": 460
    },
    {
      "epoch": 0.0301572024382419,
      "grad_norm": 1.6027675867080688,
      "learning_rate": 2.2289447251518195e-06,
      "loss": 2.4569,
      "step": 470
    },
    {
      "epoch": 0.030798845043310877,
      "grad_norm": 2.0222573280334473,
      "learning_rate": 9.92656988359823e-07,
      "loss": 2.4387,
      "step": 480
    },
    {
      "epoch": 0.03144048764837985,
      "grad_norm": 2.331239700317383,
      "learning_rate": 2.4846687349793185e-07,
      "loss": 2.4296,
      "step": 490
    },
    {
      "epoch": 0.03208213025344883,
      "grad_norm": 3.7559499740600586,
      "learning_rate": 0.0,
      "loss": 2.5162,
      "step": 500
    },
    {
      "epoch": 0.03208213025344883,
      "eval_loss": 2.425506353378296,
      "eval_runtime": 248.6079,
      "eval_samples_per_second": 26.399,
      "eval_steps_per_second": 6.601,
      "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": 2.8513699793731584e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}