{
  "best_metric": 6.504799842834473,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.7155635062611807,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 63.07804870605469,
      "learning_rate": 5.000000000000001e-07,
      "loss": 55.8303,
      "step": 1
    },
    {
      "epoch": 0.007155635062611807,
      "eval_loss": 8.064038276672363,
      "eval_runtime": 21.6914,
      "eval_samples_per_second": 10.88,
      "eval_steps_per_second": 2.72,
      "step": 1
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 47.44363784790039,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 57.0338,
      "step": 2
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 54.36549758911133,
      "learning_rate": 1.5e-06,
      "loss": 57.0304,
      "step": 3
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 51.64623260498047,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 52.5478,
      "step": 4
    },
    {
      "epoch": 0.03577817531305903,
      "grad_norm": 59.063106536865234,
      "learning_rate": 2.5e-06,
      "loss": 57.2634,
      "step": 5
    },
    {
      "epoch": 0.04293381037567084,
      "grad_norm": 50.631046295166016,
      "learning_rate": 3e-06,
      "loss": 55.0657,
      "step": 6
    },
    {
      "epoch": 0.05008944543828265,
      "grad_norm": 65.40850830078125,
      "learning_rate": 3.5e-06,
      "loss": 58.9552,
      "step": 7
    },
    {
      "epoch": 0.057245080500894455,
      "grad_norm": 52.03582000732422,
      "learning_rate": 4.000000000000001e-06,
      "loss": 60.8162,
      "step": 8
    },
    {
      "epoch": 0.06440071556350627,
      "grad_norm": 71.69737243652344,
      "learning_rate": 4.5e-06,
      "loss": 63.0307,
      "step": 9
    },
    {
      "epoch": 0.07155635062611806,
      "grad_norm": 66.26720428466797,
      "learning_rate": 5e-06,
      "loss": 62.048,
      "step": 10
    },
    {
      "epoch": 0.07871198568872988,
      "grad_norm": 47.20499038696289,
      "learning_rate": 4.99847706754774e-06,
      "loss": 59.9577,
      "step": 11
    },
    {
      "epoch": 0.08586762075134168,
      "grad_norm": 50.71089553833008,
      "learning_rate": 4.993910125649561e-06,
      "loss": 64.3391,
      "step": 12
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 56.87615203857422,
      "learning_rate": 4.986304738420684e-06,
      "loss": 62.9932,
      "step": 13
    },
    {
      "epoch": 0.1001788908765653,
      "grad_norm": 57.271766662597656,
      "learning_rate": 4.975670171853926e-06,
      "loss": 64.1028,
      "step": 14
    },
    {
      "epoch": 0.1073345259391771,
      "grad_norm": 56.15481948852539,
      "learning_rate": 4.962019382530521e-06,
      "loss": 67.4748,
      "step": 15
    },
    {
      "epoch": 0.11449016100178891,
      "grad_norm": 44.163082122802734,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 53.8473,
      "step": 16
    },
    {
      "epoch": 0.12164579606440072,
      "grad_norm": 54.03547668457031,
      "learning_rate": 4.925739315689991e-06,
      "loss": 57.9262,
      "step": 17
    },
    {
      "epoch": 0.12880143112701253,
      "grad_norm": 68.97274780273438,
      "learning_rate": 4.903154239845798e-06,
      "loss": 61.3954,
      "step": 18
    },
    {
      "epoch": 0.13595706618962433,
      "grad_norm": 53.48569869995117,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 64.557,
      "step": 19
    },
    {
      "epoch": 0.14311270125223613,
      "grad_norm": 64.57427978515625,
      "learning_rate": 4.849231551964771e-06,
      "loss": 67.3172,
      "step": 20
    },
    {
      "epoch": 0.15026833631484796,
      "grad_norm": 58.888912200927734,
      "learning_rate": 4.817959636416969e-06,
      "loss": 59.5499,
      "step": 21
    },
    {
      "epoch": 0.15742397137745975,
      "grad_norm": 53.7679443359375,
      "learning_rate": 4.783863644106502e-06,
      "loss": 61.4948,
      "step": 22
    },
    {
      "epoch": 0.16457960644007155,
      "grad_norm": 60.130409240722656,
      "learning_rate": 4.746985115747918e-06,
      "loss": 64.6237,
      "step": 23
    },
    {
      "epoch": 0.17173524150268335,
      "grad_norm": 48.91883850097656,
      "learning_rate": 4.707368982147318e-06,
      "loss": 69.1527,
      "step": 24
    },
    {
      "epoch": 0.17889087656529518,
      "grad_norm": 46.37879943847656,
      "learning_rate": 4.665063509461098e-06,
      "loss": 62.3713,
      "step": 25
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 50.134422302246094,
      "learning_rate": 4.620120240391065e-06,
      "loss": 64.926,
      "step": 26
    },
    {
      "epoch": 0.19320214669051877,
      "grad_norm": 46.87827682495117,
      "learning_rate": 4.572593931387604e-06,
      "loss": 63.1828,
      "step": 27
    },
    {
      "epoch": 0.2003577817531306,
      "grad_norm": 54.75893783569336,
      "learning_rate": 4.522542485937369e-06,
      "loss": 60.6643,
      "step": 28
    },
    {
      "epoch": 0.2075134168157424,
      "grad_norm": 52.367431640625,
      "learning_rate": 4.470026884016805e-06,
      "loss": 68.0454,
      "step": 29
    },
    {
      "epoch": 0.2146690518783542,
      "grad_norm": 50.618350982666016,
      "learning_rate": 4.415111107797445e-06,
      "loss": 71.5049,
      "step": 30
    },
    {
      "epoch": 0.22182468694096602,
      "grad_norm": 47.27493667602539,
      "learning_rate": 4.357862063693486e-06,
      "loss": 61.6825,
      "step": 31
    },
    {
      "epoch": 0.22898032200357782,
      "grad_norm": 51.643550872802734,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 66.9774,
      "step": 32
    },
    {
      "epoch": 0.23613595706618962,
      "grad_norm": 65.83971405029297,
      "learning_rate": 4.236645926147493e-06,
      "loss": 62.7222,
      "step": 33
    },
    {
      "epoch": 0.24329159212880144,
      "grad_norm": 49.59482955932617,
      "learning_rate": 4.172826515897146e-06,
      "loss": 61.6222,
      "step": 34
    },
    {
      "epoch": 0.2504472271914132,
      "grad_norm": 53.057708740234375,
      "learning_rate": 4.106969024216348e-06,
      "loss": 55.4643,
      "step": 35
    },
    {
      "epoch": 0.25760286225402507,
      "grad_norm": 90.77571105957031,
      "learning_rate": 4.039153688314146e-06,
      "loss": 55.8806,
      "step": 36
    },
    {
      "epoch": 0.26475849731663686,
      "grad_norm": 71.54025268554688,
      "learning_rate": 3.969463130731183e-06,
      "loss": 53.0835,
      "step": 37
    },
    {
      "epoch": 0.27191413237924866,
      "grad_norm": 72.8661117553711,
      "learning_rate": 3.897982258676867e-06,
      "loss": 49.935,
      "step": 38
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 61.325645446777344,
      "learning_rate": 3.824798160583012e-06,
      "loss": 52.0931,
      "step": 39
    },
    {
      "epoch": 0.28622540250447226,
      "grad_norm": 95.67042541503906,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 55.6016,
      "step": 40
    },
    {
      "epoch": 0.29338103756708406,
      "grad_norm": 61.53566360473633,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 54.4276,
      "step": 41
    },
    {
      "epoch": 0.3005366726296959,
      "grad_norm": 95.13054656982422,
      "learning_rate": 3.595927866972694e-06,
      "loss": 51.2729,
      "step": 42
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 73.37828826904297,
      "learning_rate": 3.516841607689501e-06,
      "loss": 55.4188,
      "step": 43
    },
    {
      "epoch": 0.3148479427549195,
      "grad_norm": 73.3287124633789,
      "learning_rate": 3.436516483539781e-06,
      "loss": 53.3134,
      "step": 44
    },
    {
      "epoch": 0.3220035778175313,
      "grad_norm": 69.86181640625,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 51.2279,
      "step": 45
    },
    {
      "epoch": 0.3291592128801431,
      "grad_norm": 88.11177062988281,
      "learning_rate": 3.272542485937369e-06,
      "loss": 52.3788,
      "step": 46
    },
    {
      "epoch": 0.3363148479427549,
      "grad_norm": 77.78619384765625,
      "learning_rate": 3.189093389542498e-06,
      "loss": 55.5405,
      "step": 47
    },
    {
      "epoch": 0.3434704830053667,
      "grad_norm": 54.31289291381836,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 53.7706,
      "step": 48
    },
    {
      "epoch": 0.35062611806797855,
      "grad_norm": 92.552734375,
      "learning_rate": 3.019779227044398e-06,
      "loss": 48.2176,
      "step": 49
    },
    {
      "epoch": 0.35778175313059035,
      "grad_norm": 55.199222564697266,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 55.8397,
      "step": 50
    },
    {
      "epoch": 0.35778175313059035,
      "eval_loss": 7.059117317199707,
      "eval_runtime": 22.0275,
      "eval_samples_per_second": 10.714,
      "eval_steps_per_second": 2.678,
      "step": 50
    },
    {
      "epoch": 0.36493738819320215,
      "grad_norm": 70.5916519165039,
      "learning_rate": 2.847932752400164e-06,
      "loss": 58.9163,
      "step": 51
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 66.9151840209961,
      "learning_rate": 2.761321158169134e-06,
      "loss": 50.1909,
      "step": 52
    },
    {
      "epoch": 0.37924865831842575,
      "grad_norm": 51.34752655029297,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 53.5236,
      "step": 53
    },
    {
      "epoch": 0.38640429338103754,
      "grad_norm": 63.0931510925293,
      "learning_rate": 2.587248741756253e-06,
      "loss": 59.101,
      "step": 54
    },
    {
      "epoch": 0.3935599284436494,
      "grad_norm": 71.14337921142578,
      "learning_rate": 2.5e-06,
      "loss": 55.9521,
      "step": 55
    },
    {
      "epoch": 0.4007155635062612,
      "grad_norm": 64.30337524414062,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 50.8157,
      "step": 56
    },
    {
      "epoch": 0.407871198568873,
      "grad_norm": 63.9760627746582,
      "learning_rate": 2.325608815639687e-06,
      "loss": 52.2343,
      "step": 57
    },
    {
      "epoch": 0.4150268336314848,
      "grad_norm": 69.6192855834961,
      "learning_rate": 2.238678841830867e-06,
      "loss": 55.5242,
      "step": 58
    },
    {
      "epoch": 0.4221824686940966,
      "grad_norm": 76.87415313720703,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 53.0602,
      "step": 59
    },
    {
      "epoch": 0.4293381037567084,
      "grad_norm": 58.04973220825195,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 56.443,
      "step": 60
    },
    {
      "epoch": 0.4364937388193202,
      "grad_norm": 66.81076049804688,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 54.4524,
      "step": 61
    },
    {
      "epoch": 0.44364937388193204,
      "grad_norm": 64.75467681884766,
      "learning_rate": 1.895195261000831e-06,
      "loss": 57.5205,
      "step": 62
    },
    {
      "epoch": 0.45080500894454384,
      "grad_norm": 54.86395263671875,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 55.5413,
      "step": 63
    },
    {
      "epoch": 0.45796064400715564,
      "grad_norm": 49.26187515258789,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 51.8988,
      "step": 64
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 70.07756805419922,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 58.8367,
      "step": 65
    },
    {
      "epoch": 0.47227191413237923,
      "grad_norm": 61.31855392456055,
      "learning_rate": 1.56348351646022e-06,
      "loss": 54.1545,
      "step": 66
    },
    {
      "epoch": 0.47942754919499103,
      "grad_norm": 63.78771209716797,
      "learning_rate": 1.4831583923105e-06,
      "loss": 56.2443,
      "step": 67
    },
    {
      "epoch": 0.4865831842576029,
      "grad_norm": 51.51386260986328,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 53.1392,
      "step": 68
    },
    {
      "epoch": 0.4937388193202147,
      "grad_norm": 64.99959564208984,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 45.8676,
      "step": 69
    },
    {
      "epoch": 0.5008944543828264,
      "grad_norm": 122.9439926147461,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 47.0922,
      "step": 70
    },
    {
      "epoch": 0.5080500894454383,
      "grad_norm": 83.07128143310547,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 42.5292,
      "step": 71
    },
    {
      "epoch": 0.5152057245080501,
      "grad_norm": 84.25505828857422,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 43.7117,
      "step": 72
    },
    {
      "epoch": 0.5223613595706619,
      "grad_norm": 74.06256103515625,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 48.1763,
      "step": 73
    },
    {
      "epoch": 0.5295169946332737,
      "grad_norm": 96.82910919189453,
      "learning_rate": 9.608463116858544e-07,
      "loss": 48.4631,
      "step": 74
    },
    {
      "epoch": 0.5366726296958855,
      "grad_norm": 73.7818832397461,
      "learning_rate": 8.930309757836517e-07,
      "loss": 46.4936,
      "step": 75
    },
    {
      "epoch": 0.5438282647584973,
      "grad_norm": 98.01385498046875,
      "learning_rate": 8.271734841028553e-07,
      "loss": 44.3822,
      "step": 76
    },
    {
      "epoch": 0.5509838998211091,
      "grad_norm": 100.22280883789062,
      "learning_rate": 7.633540738525066e-07,
      "loss": 47.598,
      "step": 77
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 79.705322265625,
      "learning_rate": 7.016504991533727e-07,
      "loss": 52.3615,
      "step": 78
    },
    {
      "epoch": 0.5652951699463328,
      "grad_norm": 76.27445220947266,
      "learning_rate": 6.421379363065142e-07,
      "loss": 46.7347,
      "step": 79
    },
    {
      "epoch": 0.5724508050089445,
      "grad_norm": 91.04290771484375,
      "learning_rate": 5.848888922025553e-07,
      "loss": 45.2536,
      "step": 80
    },
    {
      "epoch": 0.5796064400715564,
      "grad_norm": 102.24838256835938,
      "learning_rate": 5.299731159831953e-07,
      "loss": 46.5595,
      "step": 81
    },
    {
      "epoch": 0.5867620751341681,
      "grad_norm": 75.27155303955078,
      "learning_rate": 4.774575140626317e-07,
      "loss": 50.9991,
      "step": 82
    },
    {
      "epoch": 0.59391771019678,
      "grad_norm": 81.08625793457031,
      "learning_rate": 4.27406068612396e-07,
      "loss": 44.8026,
      "step": 83
    },
    {
      "epoch": 0.6010733452593918,
      "grad_norm": 102.80239868164062,
      "learning_rate": 3.798797596089351e-07,
      "loss": 51.6388,
      "step": 84
    },
    {
      "epoch": 0.6082289803220036,
      "grad_norm": 63.9753532409668,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 48.8587,
      "step": 85
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 68.33111572265625,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 51.9723,
      "step": 86
    },
    {
      "epoch": 0.6225402504472272,
      "grad_norm": 73.3394775390625,
      "learning_rate": 2.53014884252083e-07,
      "loss": 46.4974,
      "step": 87
    },
    {
      "epoch": 0.629695885509839,
      "grad_norm": 54.423213958740234,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 52.1191,
      "step": 88
    },
    {
      "epoch": 0.6368515205724508,
      "grad_norm": 75.42688751220703,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 51.9796,
      "step": 89
    },
    {
      "epoch": 0.6440071556350626,
      "grad_norm": 77.87445068359375,
      "learning_rate": 1.507684480352292e-07,
      "loss": 51.9779,
      "step": 90
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 73.0838394165039,
      "learning_rate": 1.223587092621162e-07,
      "loss": 50.208,
      "step": 91
    },
    {
      "epoch": 0.6583184257602862,
      "grad_norm": 63.85371780395508,
      "learning_rate": 9.684576015420277e-08,
      "loss": 54.3247,
      "step": 92
    },
    {
      "epoch": 0.6654740608228981,
      "grad_norm": 64.33513641357422,
      "learning_rate": 7.426068431000883e-08,
      "loss": 53.0616,
      "step": 93
    },
    {
      "epoch": 0.6726296958855098,
      "grad_norm": 65.0680160522461,
      "learning_rate": 5.463099816548578e-08,
      "loss": 55.7809,
      "step": 94
    },
    {
      "epoch": 0.6797853309481217,
      "grad_norm": 77.23161315917969,
      "learning_rate": 3.798061746947995e-08,
      "loss": 54.7041,
      "step": 95
    },
    {
      "epoch": 0.6869409660107334,
      "grad_norm": 55.58324432373047,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 52.5574,
      "step": 96
    },
    {
      "epoch": 0.6940966010733453,
      "grad_norm": 75.79041290283203,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 55.3405,
      "step": 97
    },
    {
      "epoch": 0.7012522361359571,
      "grad_norm": 78.58323669433594,
      "learning_rate": 6.089874350439507e-09,
      "loss": 54.7342,
      "step": 98
    },
    {
      "epoch": 0.7084078711985689,
      "grad_norm": 76.88545989990234,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 55.309,
      "step": 99
    },
    {
      "epoch": 0.7155635062611807,
      "grad_norm": 73.43214416503906,
      "learning_rate": 0.0,
      "loss": 61.4194,
      "step": 100
    },
    {
      "epoch": 0.7155635062611807,
      "eval_loss": 6.504799842834473,
      "eval_runtime": 22.0165,
      "eval_samples_per_second": 10.719,
      "eval_steps_per_second": 2.68,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.306929288708096e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}