{
  "best_metric": 0.605172872543335,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.06793939805693322,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013587879611386643,
      "eval_loss": 1.3563776016235352,
      "eval_runtime": 107.0374,
      "eval_samples_per_second": 28.953,
      "eval_steps_per_second": 7.24,
      "step": 1
    },
    {
      "epoch": 0.0013587879611386643,
      "grad_norm": 1.4640918970108032,
      "learning_rate": 4.22e-05,
      "loss": 1.0927,
      "step": 10
    },
    {
      "epoch": 0.0027175759222773286,
      "grad_norm": 1.493091106414795,
      "learning_rate": 8.44e-05,
      "loss": 1.0984,
      "step": 20
    },
    {
      "epoch": 0.004076363883415993,
      "grad_norm": 2.1061794757843018,
      "learning_rate": 0.0001266,
      "loss": 0.8297,
      "step": 30
    },
    {
      "epoch": 0.005435151844554657,
      "grad_norm": 2.278705358505249,
      "learning_rate": 0.0001688,
      "loss": 0.9314,
      "step": 40
    },
    {
      "epoch": 0.006793939805693322,
      "grad_norm": 5.351311683654785,
      "learning_rate": 0.000211,
      "loss": 0.9659,
      "step": 50
    },
    {
      "epoch": 0.006793939805693322,
      "eval_loss": 0.8938509225845337,
      "eval_runtime": 106.6398,
      "eval_samples_per_second": 29.06,
      "eval_steps_per_second": 7.267,
      "step": 50
    },
    {
      "epoch": 0.008152727766831985,
      "grad_norm": 0.9359754920005798,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.9707,
      "step": 60
    },
    {
      "epoch": 0.00951151572797065,
      "grad_norm": 1.3968127965927124,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.8002,
      "step": 70
    },
    {
      "epoch": 0.010870303689109314,
      "grad_norm": 1.6609556674957275,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.8347,
      "step": 80
    },
    {
      "epoch": 0.012229091650247978,
      "grad_norm": 2.1346518993377686,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.8894,
      "step": 90
    },
    {
      "epoch": 0.013587879611386643,
      "grad_norm": 4.972044944763184,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.8672,
      "step": 100
    },
    {
      "epoch": 0.013587879611386643,
      "eval_loss": 0.8299378156661987,
      "eval_runtime": 107.1011,
      "eval_samples_per_second": 28.935,
      "eval_steps_per_second": 7.236,
      "step": 100
    },
    {
      "epoch": 0.014946667572525307,
      "grad_norm": 1.0790904760360718,
      "learning_rate": 0.0002018790457812944,
      "loss": 0.7337,
      "step": 110
    },
    {
      "epoch": 0.01630545553366397,
      "grad_norm": 1.803770661354065,
      "learning_rate": 0.0001986509710466168,
      "loss": 0.8218,
      "step": 120
    },
    {
      "epoch": 0.017664243494802636,
      "grad_norm": 1.342689037322998,
      "learning_rate": 0.00019496907414450293,
      "loss": 0.7395,
      "step": 130
    },
    {
      "epoch": 0.0190230314559413,
      "grad_norm": 1.7541184425354004,
      "learning_rate": 0.00019085129290655697,
      "loss": 0.806,
      "step": 140
    },
    {
      "epoch": 0.020381819417079963,
      "grad_norm": 4.03976583480835,
      "learning_rate": 0.00018631768874905217,
      "loss": 0.8152,
      "step": 150
    },
    {
      "epoch": 0.020381819417079963,
      "eval_loss": 0.7754325270652771,
      "eval_runtime": 108.3736,
      "eval_samples_per_second": 28.596,
      "eval_steps_per_second": 7.151,
      "step": 150
    },
    {
      "epoch": 0.02174060737821863,
      "grad_norm": 1.2430022954940796,
      "learning_rate": 0.0001813903489357277,
      "loss": 0.8218,
      "step": 160
    },
    {
      "epoch": 0.023099395339357294,
      "grad_norm": 1.0362480878829956,
      "learning_rate": 0.00017609327897085954,
      "loss": 0.8232,
      "step": 170
    },
    {
      "epoch": 0.024458183300495956,
      "grad_norm": 1.4525357484817505,
      "learning_rate": 0.00017045228564685694,
      "loss": 0.6424,
      "step": 180
    },
    {
      "epoch": 0.02581697126163462,
      "grad_norm": 1.2485445737838745,
      "learning_rate": 0.0001644948513161638,
      "loss": 0.7053,
      "step": 190
    },
    {
      "epoch": 0.027175759222773287,
      "grad_norm": 2.9002437591552734,
      "learning_rate": 0.00015825,
      "loss": 0.8009,
      "step": 200
    },
    {
      "epoch": 0.027175759222773287,
      "eval_loss": 0.7341800928115845,
      "eval_runtime": 107.2893,
      "eval_samples_per_second": 28.885,
      "eval_steps_per_second": 7.223,
      "step": 200
    },
    {
      "epoch": 0.028534547183911952,
      "grad_norm": 0.9287257790565491,
      "learning_rate": 0.00015174815598624768,
      "loss": 0.6629,
      "step": 210
    },
    {
      "epoch": 0.029893335145050614,
      "grad_norm": 1.1831426620483398,
      "learning_rate": 0.00014502099560537873,
      "loss": 0.6634,
      "step": 220
    },
    {
      "epoch": 0.03125212310618928,
      "grad_norm": 1.1457595825195312,
      "learning_rate": 0.00013810129290655696,
      "loss": 0.7747,
      "step": 230
    },
    {
      "epoch": 0.03261091106732794,
      "grad_norm": 1.4589345455169678,
      "learning_rate": 0.00013102275998576495,
      "loss": 0.7169,
      "step": 240
    },
    {
      "epoch": 0.03396969902846661,
      "grad_norm": 2.5174882411956787,
      "learning_rate": 0.00012381988274386116,
      "loss": 0.8532,
      "step": 250
    },
    {
      "epoch": 0.03396969902846661,
      "eval_loss": 0.700812816619873,
      "eval_runtime": 106.8127,
      "eval_samples_per_second": 29.013,
      "eval_steps_per_second": 7.256,
      "step": 250
    },
    {
      "epoch": 0.03532848698960527,
      "grad_norm": 1.1443958282470703,
      "learning_rate": 0.00011652775287473745,
      "loss": 0.7206,
      "step": 260
    },
    {
      "epoch": 0.036687274950743934,
      "grad_norm": 1.2649402618408203,
      "learning_rate": 0.00010918189690211387,
      "loss": 0.6299,
      "step": 270
    },
    {
      "epoch": 0.0380460629118826,
      "grad_norm": 1.2043739557266235,
      "learning_rate": 0.00010181810309788618,
      "loss": 0.7015,
      "step": 280
    },
    {
      "epoch": 0.039404850873021265,
      "grad_norm": 1.6436249017715454,
      "learning_rate": 9.447224712526258e-05,
      "loss": 0.7122,
      "step": 290
    },
    {
      "epoch": 0.040763638834159927,
      "grad_norm": 4.384402751922607,
      "learning_rate": 8.718011725613886e-05,
      "loss": 0.8016,
      "step": 300
    },
    {
      "epoch": 0.040763638834159927,
      "eval_loss": 0.6677300333976746,
      "eval_runtime": 107.5581,
      "eval_samples_per_second": 28.812,
      "eval_steps_per_second": 7.205,
      "step": 300
    },
    {
      "epoch": 0.042122426795298595,
      "grad_norm": 0.9002043008804321,
      "learning_rate": 7.997724001423507e-05,
      "loss": 0.6582,
      "step": 310
    },
    {
      "epoch": 0.04348121475643726,
      "grad_norm": 0.8867592215538025,
      "learning_rate": 7.289870709344306e-05,
      "loss": 0.5994,
      "step": 320
    },
    {
      "epoch": 0.04484000271757592,
      "grad_norm": 0.9701396822929382,
      "learning_rate": 6.597900439462128e-05,
      "loss": 0.5906,
      "step": 330
    },
    {
      "epoch": 0.04619879067871459,
      "grad_norm": 1.048840045928955,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 0.5943,
      "step": 340
    },
    {
      "epoch": 0.04755757863985325,
      "grad_norm": 3.3718419075012207,
      "learning_rate": 5.275000000000002e-05,
      "loss": 0.699,
      "step": 350
    },
    {
      "epoch": 0.04755757863985325,
      "eval_loss": 0.6332987546920776,
      "eval_runtime": 107.0675,
      "eval_samples_per_second": 28.944,
      "eval_steps_per_second": 7.238,
      "step": 350
    },
    {
      "epoch": 0.04891636660099191,
      "grad_norm": 1.145810842514038,
      "learning_rate": 4.650514868383623e-05,
      "loss": 0.6295,
      "step": 360
    },
    {
      "epoch": 0.05027515456213058,
      "grad_norm": 1.1212451457977295,
      "learning_rate": 4.054771435314305e-05,
      "loss": 0.6049,
      "step": 370
    },
    {
      "epoch": 0.05163394252326924,
      "grad_norm": 0.9168316125869751,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 0.6003,
      "step": 380
    },
    {
      "epoch": 0.05299273048440791,
      "grad_norm": 1.6479551792144775,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 0.5984,
      "step": 390
    },
    {
      "epoch": 0.05435151844554657,
      "grad_norm": 3.574457883834839,
      "learning_rate": 2.468231125094783e-05,
      "loss": 0.7865,
      "step": 400
    },
    {
      "epoch": 0.05435151844554657,
      "eval_loss": 0.6135333776473999,
      "eval_runtime": 109.2481,
      "eval_samples_per_second": 28.367,
      "eval_steps_per_second": 7.094,
      "step": 400
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 0.8942111730575562,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 0.5637,
      "step": 410
    },
    {
      "epoch": 0.057069094367823904,
      "grad_norm": 0.902525007724762,
      "learning_rate": 1.603092585549706e-05,
      "loss": 0.5596,
      "step": 420
    },
    {
      "epoch": 0.058427882328962566,
      "grad_norm": 1.6095370054244995,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 0.6365,
      "step": 430
    },
    {
      "epoch": 0.05978667029010123,
      "grad_norm": 1.0048199892044067,
      "learning_rate": 9.120954218705596e-06,
      "loss": 0.6629,
      "step": 440
    },
    {
      "epoch": 0.0611454582512399,
      "grad_norm": 0.9756484627723694,
      "learning_rate": 6.362428507086673e-06,
      "loss": 0.5837,
      "step": 450
    },
    {
      "epoch": 0.0611454582512399,
      "eval_loss": 0.605172872543335,
      "eval_runtime": 107.5051,
      "eval_samples_per_second": 28.827,
      "eval_steps_per_second": 7.209,
      "step": 450
    },
    {
      "epoch": 0.06250424621237856,
      "grad_norm": 0.8563281297683716,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 0.6515,
      "step": 460
    },
    {
      "epoch": 0.06386303417351723,
      "grad_norm": 0.7993525862693787,
      "learning_rate": 2.3054281225835e-06,
      "loss": 0.5302,
      "step": 470
    },
    {
      "epoch": 0.06522182213465588,
      "grad_norm": 1.025873064994812,
      "learning_rate": 1.026718747764327e-06,
      "loss": 0.5259,
      "step": 480
    },
    {
      "epoch": 0.06658061009579455,
      "grad_norm": 1.3596103191375732,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 0.7144,
      "step": 490
    },
    {
      "epoch": 0.06793939805693322,
      "grad_norm": 2.885481357574463,
      "learning_rate": 0.0,
      "loss": 0.5879,
      "step": 500
    },
    {
      "epoch": 0.06793939805693322,
      "eval_loss": 0.6053472757339478,
      "eval_runtime": 107.1698,
      "eval_samples_per_second": 28.917,
      "eval_steps_per_second": 7.232,
      "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": 4.243271882637312e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}