{
  "best_metric": 7.713439464569092,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.6938421509106678,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009251228678808905,
      "grad_norm": 4.915218830108643,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 9.8817,
      "step": 1
    },
    {
      "epoch": 0.009251228678808905,
      "eval_loss": 9.016648292541504,
      "eval_runtime": 0.253,
      "eval_samples_per_second": 197.646,
      "eval_steps_per_second": 51.388,
      "step": 1
    },
    {
      "epoch": 0.01850245735761781,
      "grad_norm": 3.1345272064208984,
      "learning_rate": 6.666666666666667e-05,
      "loss": 9.243,
      "step": 2
    },
    {
      "epoch": 0.027753686036426712,
      "grad_norm": 2.805466651916504,
      "learning_rate": 0.0001,
      "loss": 9.0787,
      "step": 3
    },
    {
      "epoch": 0.03700491471523562,
      "grad_norm": 2.7379515171051025,
      "learning_rate": 9.99571699711836e-05,
      "loss": 8.8809,
      "step": 4
    },
    {
      "epoch": 0.04625614339404452,
      "grad_norm": 2.654404640197754,
      "learning_rate": 9.982876141412856e-05,
      "loss": 8.8783,
      "step": 5
    },
    {
      "epoch": 0.055507372072853424,
      "grad_norm": 2.6728150844573975,
      "learning_rate": 9.961501876182148e-05,
      "loss": 8.6961,
      "step": 6
    },
    {
      "epoch": 0.06475860075166233,
      "grad_norm": 2.6468095779418945,
      "learning_rate": 9.931634888554937e-05,
      "loss": 8.7102,
      "step": 7
    },
    {
      "epoch": 0.07400982943047124,
      "grad_norm": 2.580171823501587,
      "learning_rate": 9.893332032039701e-05,
      "loss": 8.6146,
      "step": 8
    },
    {
      "epoch": 0.08326105810928014,
      "grad_norm": 2.719038248062134,
      "learning_rate": 9.846666218300807e-05,
      "loss": 8.6246,
      "step": 9
    },
    {
      "epoch": 0.09251228678808904,
      "grad_norm": 2.8689608573913574,
      "learning_rate": 9.791726278367022e-05,
      "loss": 8.5889,
      "step": 10
    },
    {
      "epoch": 0.10176351546689795,
      "grad_norm": 3.076268196105957,
      "learning_rate": 9.728616793536588e-05,
      "loss": 8.7618,
      "step": 11
    },
    {
      "epoch": 0.11101474414570685,
      "grad_norm": 4.361219882965088,
      "learning_rate": 9.657457896300791e-05,
      "loss": 8.9535,
      "step": 12
    },
    {
      "epoch": 0.12026597282451576,
      "grad_norm": 5.026918411254883,
      "learning_rate": 9.578385041664925e-05,
      "loss": 9.3055,
      "step": 13
    },
    {
      "epoch": 0.12951720150332466,
      "grad_norm": 2.636685371398926,
      "learning_rate": 9.491548749301997e-05,
      "loss": 8.7216,
      "step": 14
    },
    {
      "epoch": 0.13876843018213356,
      "grad_norm": 1.9498603343963623,
      "learning_rate": 9.397114317029975e-05,
      "loss": 8.4862,
      "step": 15
    },
    {
      "epoch": 0.14801965886094248,
      "grad_norm": 1.7912940979003906,
      "learning_rate": 9.295261506157986e-05,
      "loss": 8.4745,
      "step": 16
    },
    {
      "epoch": 0.15727088753975138,
      "grad_norm": 1.6624524593353271,
      "learning_rate": 9.186184199300464e-05,
      "loss": 8.4023,
      "step": 17
    },
    {
      "epoch": 0.16652211621856028,
      "grad_norm": 1.699417233467102,
      "learning_rate": 9.070090031310558e-05,
      "loss": 8.3706,
      "step": 18
    },
    {
      "epoch": 0.17577334489736918,
      "grad_norm": 1.5451405048370361,
      "learning_rate": 8.947199994035401e-05,
      "loss": 8.2963,
      "step": 19
    },
    {
      "epoch": 0.18502457357617808,
      "grad_norm": 1.612066626548767,
      "learning_rate": 8.817748015645558e-05,
      "loss": 8.2006,
      "step": 20
    },
    {
      "epoch": 0.194275802254987,
      "grad_norm": 1.7445237636566162,
      "learning_rate": 8.681980515339464e-05,
      "loss": 8.1327,
      "step": 21
    },
    {
      "epoch": 0.2035270309337959,
      "grad_norm": 1.6736010313034058,
      "learning_rate": 8.540155934270471e-05,
      "loss": 8.1324,
      "step": 22
    },
    {
      "epoch": 0.2127782596126048,
      "grad_norm": 1.8691900968551636,
      "learning_rate": 8.392544243589427e-05,
      "loss": 8.1315,
      "step": 23
    },
    {
      "epoch": 0.2220294882914137,
      "grad_norm": 2.2615129947662354,
      "learning_rate": 8.239426430539243e-05,
      "loss": 8.2964,
      "step": 24
    },
    {
      "epoch": 0.2312807169702226,
      "grad_norm": 4.0689616203308105,
      "learning_rate": 8.081093963579707e-05,
      "loss": 8.7447,
      "step": 25
    },
    {
      "epoch": 0.2312807169702226,
      "eval_loss": 8.117505073547363,
      "eval_runtime": 0.2514,
      "eval_samples_per_second": 198.848,
      "eval_steps_per_second": 51.701,
      "step": 25
    },
    {
      "epoch": 0.24053194564903152,
      "grad_norm": 4.148464679718018,
      "learning_rate": 7.917848237560709e-05,
      "loss": 8.7488,
      "step": 26
    },
    {
      "epoch": 0.24978317432784042,
      "grad_norm": 1.7180299758911133,
      "learning_rate": 7.75e-05,
      "loss": 8.2221,
      "step": 27
    },
    {
      "epoch": 0.2590344030066493,
      "grad_norm": 1.566174864768982,
      "learning_rate": 7.577868759557654e-05,
      "loss": 8.1669,
      "step": 28
    },
    {
      "epoch": 0.2682856316854582,
      "grad_norm": 1.5013340711593628,
      "learning_rate": 7.401782177833148e-05,
      "loss": 8.1067,
      "step": 29
    },
    {
      "epoch": 0.2775368603642671,
      "grad_norm": 1.4089857339859009,
      "learning_rate": 7.222075445642904e-05,
      "loss": 8.0612,
      "step": 30
    },
    {
      "epoch": 0.286788089043076,
      "grad_norm": 1.3587747812271118,
      "learning_rate": 7.03909064496551e-05,
      "loss": 8.0095,
      "step": 31
    },
    {
      "epoch": 0.29603931772188496,
      "grad_norm": 1.3256354331970215,
      "learning_rate": 6.853176097769229e-05,
      "loss": 7.9363,
      "step": 32
    },
    {
      "epoch": 0.30529054640069386,
      "grad_norm": 1.3372445106506348,
      "learning_rate": 6.664685702961344e-05,
      "loss": 7.8896,
      "step": 33
    },
    {
      "epoch": 0.31454177507950276,
      "grad_norm": 1.2932922840118408,
      "learning_rate": 6.473978262721463e-05,
      "loss": 8.019,
      "step": 34
    },
    {
      "epoch": 0.32379300375831166,
      "grad_norm": 1.25713050365448,
      "learning_rate": 6.281416799501188e-05,
      "loss": 7.9925,
      "step": 35
    },
    {
      "epoch": 0.33304423243712056,
      "grad_norm": 1.523684024810791,
      "learning_rate": 6.087367864990233e-05,
      "loss": 8.0904,
      "step": 36
    },
    {
      "epoch": 0.34229546111592946,
      "grad_norm": 2.0476949214935303,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 8.2589,
      "step": 37
    },
    {
      "epoch": 0.35154668979473835,
      "grad_norm": 4.7950215339660645,
      "learning_rate": 5.696287243144013e-05,
      "loss": 8.5362,
      "step": 38
    },
    {
      "epoch": 0.36079791847354725,
      "grad_norm": 1.919904351234436,
      "learning_rate": 5.500000000000001e-05,
      "loss": 8.1789,
      "step": 39
    },
    {
      "epoch": 0.37004914715235615,
      "grad_norm": 1.2518750429153442,
      "learning_rate": 5.303712756855988e-05,
      "loss": 7.9093,
      "step": 40
    },
    {
      "epoch": 0.3793003758311651,
      "grad_norm": 1.1971595287322998,
      "learning_rate": 5.107799157635538e-05,
      "loss": 8.0114,
      "step": 41
    },
    {
      "epoch": 0.388551604509974,
      "grad_norm": 1.086124062538147,
      "learning_rate": 4.912632135009769e-05,
      "loss": 7.8303,
      "step": 42
    },
    {
      "epoch": 0.3978028331887829,
      "grad_norm": 1.0968059301376343,
      "learning_rate": 4.718583200498814e-05,
      "loss": 7.9518,
      "step": 43
    },
    {
      "epoch": 0.4070540618675918,
      "grad_norm": 1.0983154773712158,
      "learning_rate": 4.526021737278538e-05,
      "loss": 7.8751,
      "step": 44
    },
    {
      "epoch": 0.4163052905464007,
      "grad_norm": 1.188271164894104,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 7.9831,
      "step": 45
    },
    {
      "epoch": 0.4255565192252096,
      "grad_norm": 1.155224323272705,
      "learning_rate": 4.146823902230772e-05,
      "loss": 7.8468,
      "step": 46
    },
    {
      "epoch": 0.4348077479040185,
      "grad_norm": 1.1883093118667603,
      "learning_rate": 3.960909355034491e-05,
      "loss": 7.8794,
      "step": 47
    },
    {
      "epoch": 0.4440589765828274,
      "grad_norm": 1.2450655698776245,
      "learning_rate": 3.777924554357096e-05,
      "loss": 7.8607,
      "step": 48
    },
    {
      "epoch": 0.4533102052616363,
      "grad_norm": 1.6155924797058105,
      "learning_rate": 3.598217822166854e-05,
      "loss": 7.962,
      "step": 49
    },
    {
      "epoch": 0.4625614339404452,
      "grad_norm": 3.3712172508239746,
      "learning_rate": 3.422131240442349e-05,
      "loss": 8.1619,
      "step": 50
    },
    {
      "epoch": 0.4625614339404452,
      "eval_loss": 7.796533584594727,
      "eval_runtime": 0.2509,
      "eval_samples_per_second": 199.255,
      "eval_steps_per_second": 51.806,
      "step": 50
    },
    {
      "epoch": 0.47181266261925414,
      "grad_norm": 3.21820330619812,
      "learning_rate": 3.250000000000001e-05,
      "loss": 8.093,
      "step": 51
    },
    {
      "epoch": 0.48106389129806304,
      "grad_norm": 1.3702133893966675,
      "learning_rate": 3.082151762439293e-05,
      "loss": 7.9204,
      "step": 52
    },
    {
      "epoch": 0.49031511997687194,
      "grad_norm": 1.031348705291748,
      "learning_rate": 2.9189060364202943e-05,
      "loss": 7.8885,
      "step": 53
    },
    {
      "epoch": 0.49956634865568084,
      "grad_norm": 1.0596493482589722,
      "learning_rate": 2.760573569460757e-05,
      "loss": 7.843,
      "step": 54
    },
    {
      "epoch": 0.5088175773344897,
      "grad_norm": 0.9369666576385498,
      "learning_rate": 2.6074557564105727e-05,
      "loss": 7.7847,
      "step": 55
    },
    {
      "epoch": 0.5180688060132986,
      "grad_norm": 0.9409084320068359,
      "learning_rate": 2.459844065729529e-05,
      "loss": 7.8721,
      "step": 56
    },
    {
      "epoch": 0.5273200346921075,
      "grad_norm": 1.0068604946136475,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 7.6884,
      "step": 57
    },
    {
      "epoch": 0.5365712633709164,
      "grad_norm": 1.0114176273345947,
      "learning_rate": 2.1822519843544424e-05,
      "loss": 7.76,
      "step": 58
    },
    {
      "epoch": 0.5458224920497253,
      "grad_norm": 1.04805588722229,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 7.784,
      "step": 59
    },
    {
      "epoch": 0.5550737207285342,
      "grad_norm": 1.1247358322143555,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 7.728,
      "step": 60
    },
    {
      "epoch": 0.5643249494073431,
      "grad_norm": 1.232703447341919,
      "learning_rate": 1.8138158006995364e-05,
      "loss": 7.99,
      "step": 61
    },
    {
      "epoch": 0.573576178086152,
      "grad_norm": 2.0546152591705322,
      "learning_rate": 1.7047384938420154e-05,
      "loss": 8.099,
      "step": 62
    },
    {
      "epoch": 0.5828274067649609,
      "grad_norm": 3.923598527908325,
      "learning_rate": 1.602885682970026e-05,
      "loss": 8.0151,
      "step": 63
    },
    {
      "epoch": 0.5920786354437699,
      "grad_norm": 1.3706938028335571,
      "learning_rate": 1.5084512506980026e-05,
      "loss": 7.9288,
      "step": 64
    },
    {
      "epoch": 0.6013298641225788,
      "grad_norm": 0.9312557578086853,
      "learning_rate": 1.4216149583350754e-05,
      "loss": 7.7455,
      "step": 65
    },
    {
      "epoch": 0.6105810928013877,
      "grad_norm": 0.908347487449646,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 7.7296,
      "step": 66
    },
    {
      "epoch": 0.6198323214801966,
      "grad_norm": 0.9519467949867249,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 7.7021,
      "step": 67
    },
    {
      "epoch": 0.6290835501590055,
      "grad_norm": 0.8736981153488159,
      "learning_rate": 1.2082737216329794e-05,
      "loss": 7.7688,
      "step": 68
    },
    {
      "epoch": 0.6383347788378144,
      "grad_norm": 0.9096718430519104,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 7.6644,
      "step": 69
    },
    {
      "epoch": 0.6475860075166233,
      "grad_norm": 0.9509488940238953,
      "learning_rate": 1.1066679679603e-05,
      "loss": 7.7987,
      "step": 70
    },
    {
      "epoch": 0.6568372361954322,
      "grad_norm": 0.9723087549209595,
      "learning_rate": 1.0683651114450641e-05,
      "loss": 7.6467,
      "step": 71
    },
    {
      "epoch": 0.6660884648742411,
      "grad_norm": 1.0477325916290283,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 7.6163,
      "step": 72
    },
    {
      "epoch": 0.67533969355305,
      "grad_norm": 1.1920454502105713,
      "learning_rate": 1.017123858587145e-05,
      "loss": 7.7597,
      "step": 73
    },
    {
      "epoch": 0.6845909222318589,
      "grad_norm": 1.7579151391983032,
      "learning_rate": 1.00428300288164e-05,
      "loss": 7.9359,
      "step": 74
    },
    {
      "epoch": 0.6938421509106678,
      "grad_norm": 3.6170880794525146,
      "learning_rate": 1e-05,
      "loss": 8.2457,
      "step": 75
    },
    {
      "epoch": 0.6938421509106678,
      "eval_loss": 7.713439464569092,
      "eval_runtime": 0.2521,
      "eval_samples_per_second": 198.357,
      "eval_steps_per_second": 51.573,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 348419471704064.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}