{
  "best_metric": 11.921051025390625,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.4672897196261682,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004672897196261682,
      "grad_norm": 0.012287290766835213,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9336,
      "step": 1
    },
    {
      "epoch": 0.004672897196261682,
      "eval_loss": 11.933741569519043,
      "eval_runtime": 0.3116,
      "eval_samples_per_second": 160.464,
      "eval_steps_per_second": 22.465,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.007687127683311701,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9349,
      "step": 2
    },
    {
      "epoch": 0.014018691588785047,
      "grad_norm": 0.011557426303625107,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.9336,
      "step": 3
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.0096749821677804,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9343,
      "step": 4
    },
    {
      "epoch": 0.02336448598130841,
      "grad_norm": 0.011569755151867867,
      "learning_rate": 0.00015,
      "loss": 11.9332,
      "step": 5
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 0.009253166615962982,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9324,
      "step": 6
    },
    {
      "epoch": 0.03271028037383177,
      "grad_norm": 0.014671793207526207,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9335,
      "step": 7
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 0.009677017107605934,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9347,
      "step": 8
    },
    {
      "epoch": 0.04205607476635514,
      "grad_norm": 0.010931613855063915,
      "learning_rate": 0.00027,
      "loss": 11.9333,
      "step": 9
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 0.007789121475070715,
      "learning_rate": 0.0003,
      "loss": 11.9356,
      "step": 10
    },
    {
      "epoch": 0.0514018691588785,
      "grad_norm": 0.01007977407425642,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.933,
      "step": 11
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.011012083850800991,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9328,
      "step": 12
    },
    {
      "epoch": 0.06074766355140187,
      "grad_norm": 0.011678499169647694,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.934,
      "step": 13
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 0.00791614968329668,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9359,
      "step": 14
    },
    {
      "epoch": 0.07009345794392523,
      "grad_norm": 0.011806285940110683,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9335,
      "step": 15
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 0.013282974250614643,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9321,
      "step": 16
    },
    {
      "epoch": 0.0794392523364486,
      "grad_norm": 0.010643936693668365,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9329,
      "step": 17
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.009988749399781227,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.9339,
      "step": 18
    },
    {
      "epoch": 0.08878504672897196,
      "grad_norm": 0.012497678399085999,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.933,
      "step": 19
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.01283989381045103,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9325,
      "step": 20
    },
    {
      "epoch": 0.09813084112149532,
      "grad_norm": 0.011552334763109684,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9321,
      "step": 21
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 0.012469599023461342,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9342,
      "step": 22
    },
    {
      "epoch": 0.10747663551401869,
      "grad_norm": 0.013510530814528465,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9341,
      "step": 23
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.015959424898028374,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9338,
      "step": 24
    },
    {
      "epoch": 0.11682242990654206,
      "grad_norm": 0.017688067629933357,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9333,
      "step": 25
    },
    {
      "epoch": 0.11682242990654206,
      "eval_loss": 11.932760238647461,
      "eval_runtime": 0.3111,
      "eval_samples_per_second": 160.696,
      "eval_steps_per_second": 22.497,
      "step": 25
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.018132586032152176,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9355,
      "step": 26
    },
    {
      "epoch": 0.1261682242990654,
      "grad_norm": 0.01555582694709301,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.9327,
      "step": 27
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 0.010587092489004135,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9306,
      "step": 28
    },
    {
      "epoch": 0.13551401869158877,
      "grad_norm": 0.016130341216921806,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.934,
      "step": 29
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.016748711466789246,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9327,
      "step": 30
    },
    {
      "epoch": 0.14485981308411214,
      "grad_norm": 0.02337314747273922,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9312,
      "step": 31
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 0.031070569530129433,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.931,
      "step": 32
    },
    {
      "epoch": 0.1542056074766355,
      "grad_norm": 0.030112041160464287,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.931,
      "step": 33
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 0.025763792917132378,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9341,
      "step": 34
    },
    {
      "epoch": 0.16355140186915887,
      "grad_norm": 0.020702293142676353,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9302,
      "step": 35
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.032018788158893585,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9305,
      "step": 36
    },
    {
      "epoch": 0.17289719626168223,
      "grad_norm": 0.03408855199813843,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.9297,
      "step": 37
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.03538135811686516,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9297,
      "step": 38
    },
    {
      "epoch": 0.1822429906542056,
      "grad_norm": 0.042890459299087524,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.931,
      "step": 39
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.04696235433220863,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9326,
      "step": 40
    },
    {
      "epoch": 0.19158878504672897,
      "grad_norm": 0.04607512429356575,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9304,
      "step": 41
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 0.059835415333509445,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9319,
      "step": 42
    },
    {
      "epoch": 0.20093457943925233,
      "grad_norm": 0.041718047112226486,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9292,
      "step": 43
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.06262337416410446,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9337,
      "step": 44
    },
    {
      "epoch": 0.2102803738317757,
      "grad_norm": 0.054845791310071945,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9268,
      "step": 45
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 0.0817423015832901,
      "learning_rate": 0.000274201324672203,
      "loss": 11.9276,
      "step": 46
    },
    {
      "epoch": 0.21962616822429906,
      "grad_norm": 0.0744045227766037,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9311,
      "step": 47
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 0.092995785176754,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.9277,
      "step": 48
    },
    {
      "epoch": 0.22897196261682243,
      "grad_norm": 0.07758913189172745,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.929,
      "step": 49
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 0.0959334447979927,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.932,
      "step": 50
    },
    {
      "epoch": 0.2336448598130841,
      "eval_loss": 11.926326751708984,
      "eval_runtime": 0.309,
      "eval_samples_per_second": 161.815,
      "eval_steps_per_second": 22.654,
      "step": 50
    },
    {
      "epoch": 0.2383177570093458,
      "grad_norm": 0.0555480420589447,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.9239,
      "step": 51
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 0.03427752107381821,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.9273,
      "step": 52
    },
    {
      "epoch": 0.24766355140186916,
      "grad_norm": 0.051935601979494095,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.9254,
      "step": 53
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.05068502947688103,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.9243,
      "step": 54
    },
    {
      "epoch": 0.2570093457943925,
      "grad_norm": 0.042215969413518906,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.9256,
      "step": 55
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.03927940875291824,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.9255,
      "step": 56
    },
    {
      "epoch": 0.26635514018691586,
      "grad_norm": 0.041530344635248184,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.9267,
      "step": 57
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.05640103295445442,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.9244,
      "step": 58
    },
    {
      "epoch": 0.2757009345794392,
      "grad_norm": 0.039908554404973984,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.9261,
      "step": 59
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.03271481394767761,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.9258,
      "step": 60
    },
    {
      "epoch": 0.2850467289719626,
      "grad_norm": 0.0314725823700428,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.9223,
      "step": 61
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.03497527167201042,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.9226,
      "step": 62
    },
    {
      "epoch": 0.29439252336448596,
      "grad_norm": 0.03343958035111427,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.9246,
      "step": 63
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.03223850205540657,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.9208,
      "step": 64
    },
    {
      "epoch": 0.3037383177570093,
      "grad_norm": 0.03138720244169235,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.9224,
      "step": 65
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.02842772752046585,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.9213,
      "step": 66
    },
    {
      "epoch": 0.3130841121495327,
      "grad_norm": 0.033133890479803085,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.9225,
      "step": 67
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.032245416194200516,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.9209,
      "step": 68
    },
    {
      "epoch": 0.32242990654205606,
      "grad_norm": 0.026734715327620506,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.925,
      "step": 69
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 0.025514936074614525,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.9217,
      "step": 70
    },
    {
      "epoch": 0.3317757009345794,
      "grad_norm": 0.018397009000182152,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.9264,
      "step": 71
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 0.017135081812739372,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.9244,
      "step": 72
    },
    {
      "epoch": 0.3411214953271028,
      "grad_norm": 0.02699720673263073,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.9216,
      "step": 73
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 0.024376867339015007,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.9232,
      "step": 74
    },
    {
      "epoch": 0.35046728971962615,
      "grad_norm": 0.023777619004249573,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.9243,
      "step": 75
    },
    {
      "epoch": 0.35046728971962615,
      "eval_loss": 11.921453475952148,
      "eval_runtime": 0.3108,
      "eval_samples_per_second": 160.851,
      "eval_steps_per_second": 22.519,
      "step": 75
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.02467428147792816,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.9218,
      "step": 76
    },
    {
      "epoch": 0.3598130841121495,
      "grad_norm": 0.014774040319025517,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.9219,
      "step": 77
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 0.01568908616900444,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.9206,
      "step": 78
    },
    {
      "epoch": 0.3691588785046729,
      "grad_norm": 0.021154990419745445,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.9222,
      "step": 79
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.01931612752377987,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.9229,
      "step": 80
    },
    {
      "epoch": 0.37850467289719625,
      "grad_norm": 0.02147780731320381,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.923,
      "step": 81
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 0.01698346436023712,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.9215,
      "step": 82
    },
    {
      "epoch": 0.3878504672897196,
      "grad_norm": 0.021959029138088226,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.9202,
      "step": 83
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.018221363425254822,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.9213,
      "step": 84
    },
    {
      "epoch": 0.397196261682243,
      "grad_norm": 0.014806934632360935,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.921,
      "step": 85
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 0.019513826817274094,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.9189,
      "step": 86
    },
    {
      "epoch": 0.40654205607476634,
      "grad_norm": 0.01412623468786478,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.9225,
      "step": 87
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 0.01801372691988945,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.9201,
      "step": 88
    },
    {
      "epoch": 0.4158878504672897,
      "grad_norm": 0.019024653360247612,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.9205,
      "step": 89
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.021895864978432655,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.9216,
      "step": 90
    },
    {
      "epoch": 0.4252336448598131,
      "grad_norm": 0.025304431095719337,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.9214,
      "step": 91
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.0259839054197073,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.9253,
      "step": 92
    },
    {
      "epoch": 0.43457943925233644,
      "grad_norm": 0.04013689234852791,
      "learning_rate": 0.000179567554117722,
      "loss": 11.9211,
      "step": 93
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.032571107149124146,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.9246,
      "step": 94
    },
    {
      "epoch": 0.4439252336448598,
      "grad_norm": 0.04223785176873207,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.9277,
      "step": 95
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.01614546775817871,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.9202,
      "step": 96
    },
    {
      "epoch": 0.4532710280373832,
      "grad_norm": 0.05689317733049393,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.9215,
      "step": 97
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.04419248178601265,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.9244,
      "step": 98
    },
    {
      "epoch": 0.46261682242990654,
      "grad_norm": 0.05944395065307617,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.9218,
      "step": 99
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.05680546537041664,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.9257,
      "step": 100
    },
    {
      "epoch": 0.4672897196261682,
      "eval_loss": 11.921051025390625,
      "eval_runtime": 0.3127,
      "eval_samples_per_second": 159.909,
      "eval_steps_per_second": 22.387,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 159262310400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}