{
  "best_metric": 4.000638484954834,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02107532032091965,
  "eval_steps": 25,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031932303516544927,
      "grad_norm": 5.508306503295898,
      "learning_rate": 5e-05,
      "loss": 3.4843,
      "step": 1
    },
    {
      "epoch": 0.00031932303516544927,
      "eval_loss": 6.9587225914001465,
      "eval_runtime": 14.4472,
      "eval_samples_per_second": 3.461,
      "eval_steps_per_second": 3.461,
      "step": 1
    },
    {
      "epoch": 0.0006386460703308985,
      "grad_norm": 6.429923057556152,
      "learning_rate": 0.0001,
      "loss": 4.189,
      "step": 2
    },
    {
      "epoch": 0.0009579691054963477,
      "grad_norm": 5.022256374359131,
      "learning_rate": 9.994579552923277e-05,
      "loss": 3.7926,
      "step": 3
    },
    {
      "epoch": 0.001277292140661797,
      "grad_norm": 3.6086912155151367,
      "learning_rate": 9.978331270024886e-05,
      "loss": 3.3853,
      "step": 4
    },
    {
      "epoch": 0.0015966151758272462,
      "grad_norm": 3.7427756786346436,
      "learning_rate": 9.951294294841516e-05,
      "loss": 3.2209,
      "step": 5
    },
    {
      "epoch": 0.0019159382109926954,
      "grad_norm": 3.153134822845459,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.0261,
      "step": 6
    },
    {
      "epoch": 0.0022352612461581448,
      "grad_norm": 3.2068698406219482,
      "learning_rate": 9.865140639375449e-05,
      "loss": 3.2692,
      "step": 7
    },
    {
      "epoch": 0.002554584281323594,
      "grad_norm": 3.194871664047241,
      "learning_rate": 9.80623151079494e-05,
      "loss": 3.5115,
      "step": 8
    },
    {
      "epoch": 0.002873907316489043,
      "grad_norm": 2.743932008743286,
      "learning_rate": 9.736948293323593e-05,
      "loss": 3.4101,
      "step": 9
    },
    {
      "epoch": 0.0031932303516544924,
      "grad_norm": 2.6319997310638428,
      "learning_rate": 9.657457896300791e-05,
      "loss": 3.1293,
      "step": 10
    },
    {
      "epoch": 0.003512553386819942,
      "grad_norm": 3.2812702655792236,
      "learning_rate": 9.567951819055496e-05,
      "loss": 3.353,
      "step": 11
    },
    {
      "epoch": 0.0038318764219853908,
      "grad_norm": 3.206648111343384,
      "learning_rate": 9.468645689567598e-05,
      "loss": 3.7939,
      "step": 12
    },
    {
      "epoch": 0.00415119945715084,
      "grad_norm": 3.4260575771331787,
      "learning_rate": 9.359778745001225e-05,
      "loss": 3.4403,
      "step": 13
    },
    {
      "epoch": 0.0044705224923162895,
      "grad_norm": 3.34879732131958,
      "learning_rate": 9.241613255361455e-05,
      "loss": 3.7215,
      "step": 14
    },
    {
      "epoch": 0.004789845527481739,
      "grad_norm": 3.991157054901123,
      "learning_rate": 9.114433891662902e-05,
      "loss": 3.7424,
      "step": 15
    },
    {
      "epoch": 0.005109168562647188,
      "grad_norm": 11.184669494628906,
      "learning_rate": 8.978547040132317e-05,
      "loss": 4.1454,
      "step": 16
    },
    {
      "epoch": 0.005428491597812638,
      "grad_norm": 7.331747531890869,
      "learning_rate": 8.834280064097317e-05,
      "loss": 3.4989,
      "step": 17
    },
    {
      "epoch": 0.005747814632978086,
      "grad_norm": 7.6846513748168945,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.1464,
      "step": 18
    },
    {
      "epoch": 0.0060671376681435355,
      "grad_norm": 5.366702079772949,
      "learning_rate": 8.522015296811584e-05,
      "loss": 3.1253,
      "step": 19
    },
    {
      "epoch": 0.006386460703308985,
      "grad_norm": 4.334587097167969,
      "learning_rate": 8.354769778736406e-05,
      "loss": 3.2567,
      "step": 20
    },
    {
      "epoch": 0.006705783738474434,
      "grad_norm": 4.938718318939209,
      "learning_rate": 8.180646870215952e-05,
      "loss": 4.0654,
      "step": 21
    },
    {
      "epoch": 0.007025106773639884,
      "grad_norm": 4.045793533325195,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.8355,
      "step": 22
    },
    {
      "epoch": 0.007344429808805333,
      "grad_norm": 10.687291145324707,
      "learning_rate": 7.813462348869497e-05,
      "loss": 2.3498,
      "step": 23
    },
    {
      "epoch": 0.0076637528439707815,
      "grad_norm": 5.829076766967773,
      "learning_rate": 7.62128531571699e-05,
      "loss": 1.7846,
      "step": 24
    },
    {
      "epoch": 0.007983075879136232,
      "grad_norm": 4.1889424324035645,
      "learning_rate": 7.42399792043627e-05,
      "loss": 1.9843,
      "step": 25
    },
    {
      "epoch": 0.007983075879136232,
      "eval_loss": 3.5693531036376953,
      "eval_runtime": 14.6152,
      "eval_samples_per_second": 3.421,
      "eval_steps_per_second": 3.421,
      "step": 25
    },
    {
      "epoch": 0.00830239891430168,
      "grad_norm": 5.976337909698486,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.8225,
      "step": 26
    },
    {
      "epoch": 0.00862172194946713,
      "grad_norm": 7.094808101654053,
      "learning_rate": 7.01600434026499e-05,
      "loss": 2.3825,
      "step": 27
    },
    {
      "epoch": 0.008941044984632579,
      "grad_norm": 13.234283447265625,
      "learning_rate": 6.80628104764508e-05,
      "loss": 3.6424,
      "step": 28
    },
    {
      "epoch": 0.009260368019798028,
      "grad_norm": 13.326498985290527,
      "learning_rate": 6.593410809564689e-05,
      "loss": 4.4563,
      "step": 29
    },
    {
      "epoch": 0.009579691054963478,
      "grad_norm": 9.808164596557617,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.4519,
      "step": 30
    },
    {
      "epoch": 0.009899014090128926,
      "grad_norm": 5.980898857116699,
      "learning_rate": 6.160287135049127e-05,
      "loss": 4.3998,
      "step": 31
    },
    {
      "epoch": 0.010218337125294377,
      "grad_norm": 4.547826766967773,
      "learning_rate": 5.941077131483025e-05,
      "loss": 4.0411,
      "step": 32
    },
    {
      "epoch": 0.010537660160459825,
      "grad_norm": 4.85554313659668,
      "learning_rate": 5.720804534473382e-05,
      "loss": 4.4836,
      "step": 33
    },
    {
      "epoch": 0.010856983195625275,
      "grad_norm": 4.402012348175049,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.2954,
      "step": 34
    },
    {
      "epoch": 0.011176306230790724,
      "grad_norm": 5.091377258300781,
      "learning_rate": 5.27919546552662e-05,
      "loss": 4.311,
      "step": 35
    },
    {
      "epoch": 0.011495629265956172,
      "grad_norm": 5.752288341522217,
      "learning_rate": 5.058922868516978e-05,
      "loss": 4.2278,
      "step": 36
    },
    {
      "epoch": 0.011814952301121623,
      "grad_norm": 6.53019905090332,
      "learning_rate": 4.839712864950873e-05,
      "loss": 3.4952,
      "step": 37
    },
    {
      "epoch": 0.012134275336287071,
      "grad_norm": 5.096629619598389,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 3.7458,
      "step": 38
    },
    {
      "epoch": 0.012453598371452521,
      "grad_norm": 5.266465187072754,
      "learning_rate": 4.406589190435313e-05,
      "loss": 3.6961,
      "step": 39
    },
    {
      "epoch": 0.01277292140661797,
      "grad_norm": 5.592081069946289,
      "learning_rate": 4.19371895235492e-05,
      "loss": 3.4962,
      "step": 40
    },
    {
      "epoch": 0.013092244441783418,
      "grad_norm": 4.7566609382629395,
      "learning_rate": 3.98399565973501e-05,
      "loss": 3.6898,
      "step": 41
    },
    {
      "epoch": 0.013411567476948869,
      "grad_norm": 3.937934637069702,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.7817,
      "step": 42
    },
    {
      "epoch": 0.013730890512114317,
      "grad_norm": 4.427155494689941,
      "learning_rate": 3.576002079563732e-05,
      "loss": 3.7729,
      "step": 43
    },
    {
      "epoch": 0.014050213547279767,
      "grad_norm": 5.204694747924805,
      "learning_rate": 3.378714684283011e-05,
      "loss": 4.3146,
      "step": 44
    },
    {
      "epoch": 0.014369536582445216,
      "grad_norm": 6.423009872436523,
      "learning_rate": 3.186537651130503e-05,
      "loss": 3.687,
      "step": 45
    },
    {
      "epoch": 0.014688859617610666,
      "grad_norm": 6.450584888458252,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.7906,
      "step": 46
    },
    {
      "epoch": 0.015008182652776115,
      "grad_norm": 5.856997013092041,
      "learning_rate": 2.8193531297840503e-05,
      "loss": 3.8841,
      "step": 47
    },
    {
      "epoch": 0.015327505687941563,
      "grad_norm": 6.467741012573242,
      "learning_rate": 2.645230221263596e-05,
      "loss": 3.3666,
      "step": 48
    },
    {
      "epoch": 0.015646828723107013,
      "grad_norm": 8.139485359191895,
      "learning_rate": 2.4779847031884175e-05,
      "loss": 3.674,
      "step": 49
    },
    {
      "epoch": 0.015966151758272464,
      "grad_norm": 13.278364181518555,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.9755,
      "step": 50
    },
    {
      "epoch": 0.015966151758272464,
      "eval_loss": 4.000638484954834,
      "eval_runtime": 14.6038,
      "eval_samples_per_second": 3.424,
      "eval_steps_per_second": 3.424,
      "step": 50
    },
    {
      "epoch": 0.01628547479343791,
      "grad_norm": 18.63812255859375,
      "learning_rate": 2.165719935902685e-05,
      "loss": 3.9371,
      "step": 51
    },
    {
      "epoch": 0.01660479782860336,
      "grad_norm": 15.783567428588867,
      "learning_rate": 2.0214529598676836e-05,
      "loss": 3.4496,
      "step": 52
    },
    {
      "epoch": 0.01692412086376881,
      "grad_norm": 16.15505599975586,
      "learning_rate": 1.8855661083370986e-05,
      "loss": 3.1263,
      "step": 53
    },
    {
      "epoch": 0.01724344389893426,
      "grad_norm": 12.968737602233887,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.0368,
      "step": 54
    },
    {
      "epoch": 0.017562766934099708,
      "grad_norm": 9.380385398864746,
      "learning_rate": 1.6402212549987762e-05,
      "loss": 2.9326,
      "step": 55
    },
    {
      "epoch": 0.017882089969265158,
      "grad_norm": 7.317039489746094,
      "learning_rate": 1.531354310432403e-05,
      "loss": 2.5816,
      "step": 56
    },
    {
      "epoch": 0.01820141300443061,
      "grad_norm": 4.853557109832764,
      "learning_rate": 1.4320481809445051e-05,
      "loss": 2.6577,
      "step": 57
    },
    {
      "epoch": 0.018520736039596055,
      "grad_norm": 4.9439239501953125,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.1326,
      "step": 58
    },
    {
      "epoch": 0.018840059074761505,
      "grad_norm": 4.261263847351074,
      "learning_rate": 1.2630517066764069e-05,
      "loss": 2.8784,
      "step": 59
    },
    {
      "epoch": 0.019159382109926956,
      "grad_norm": 3.9718527793884277,
      "learning_rate": 1.1937684892050604e-05,
      "loss": 3.032,
      "step": 60
    },
    {
      "epoch": 0.019478705145092406,
      "grad_norm": 3.4298315048217773,
      "learning_rate": 1.1348593606245522e-05,
      "loss": 2.6723,
      "step": 61
    },
    {
      "epoch": 0.019798028180257853,
      "grad_norm": 3.560950994491577,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 2.7488,
      "step": 62
    },
    {
      "epoch": 0.020117351215423303,
      "grad_norm": 3.4607114791870117,
      "learning_rate": 1.0487057051584856e-05,
      "loss": 2.5312,
      "step": 63
    },
    {
      "epoch": 0.020436674250588753,
      "grad_norm": 3.4417977333068848,
      "learning_rate": 1.0216687299751144e-05,
      "loss": 3.2348,
      "step": 64
    },
    {
      "epoch": 0.0207559972857542,
      "grad_norm": 3.5609071254730225,
      "learning_rate": 1.0054204470767243e-05,
      "loss": 3.0496,
      "step": 65
    },
    {
      "epoch": 0.02107532032091965,
      "grad_norm": 5.164323806762695,
      "learning_rate": 1e-05,
      "loss": 2.4215,
      "step": 66
    }
  ],
  "logging_steps": 1,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 1.969468656718971e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}