{
  "best_metric": 11.920056343078613,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.015238095238095238,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015238095238095237,
      "grad_norm": 0.01340496726334095,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.9277,
      "step": 1
    },
    {
      "epoch": 0.00015238095238095237,
      "eval_loss": 11.932770729064941,
      "eval_runtime": 0.3373,
      "eval_samples_per_second": 148.236,
      "eval_steps_per_second": 20.753,
      "step": 1
    },
    {
      "epoch": 0.00030476190476190474,
      "grad_norm": 0.01209985837340355,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.9322,
      "step": 2
    },
    {
      "epoch": 0.00045714285714285713,
      "grad_norm": 0.012650331482291222,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.9317,
      "step": 3
    },
    {
      "epoch": 0.0006095238095238095,
      "grad_norm": 0.010324247181415558,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.9319,
      "step": 4
    },
    {
      "epoch": 0.0007619047619047619,
      "grad_norm": 0.010827633552253246,
      "learning_rate": 0.00015,
      "loss": 11.9311,
      "step": 5
    },
    {
      "epoch": 0.0009142857142857143,
      "grad_norm": 0.01144388411194086,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.9307,
      "step": 6
    },
    {
      "epoch": 0.0010666666666666667,
      "grad_norm": 0.01133989542722702,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.9306,
      "step": 7
    },
    {
      "epoch": 0.001219047619047619,
      "grad_norm": 0.009713858366012573,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.9315,
      "step": 8
    },
    {
      "epoch": 0.0013714285714285714,
      "grad_norm": 0.011050593107938766,
      "learning_rate": 0.00027,
      "loss": 11.9319,
      "step": 9
    },
    {
      "epoch": 0.0015238095238095239,
      "grad_norm": 0.010406149551272392,
      "learning_rate": 0.0003,
      "loss": 11.9312,
      "step": 10
    },
    {
      "epoch": 0.001676190476190476,
      "grad_norm": 0.011947591789066792,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.933,
      "step": 11
    },
    {
      "epoch": 0.0018285714285714285,
      "grad_norm": 0.01505028735846281,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.9299,
      "step": 12
    },
    {
      "epoch": 0.001980952380952381,
      "grad_norm": 0.01627309061586857,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.9306,
      "step": 13
    },
    {
      "epoch": 0.0021333333333333334,
      "grad_norm": 0.013440248556435108,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.9314,
      "step": 14
    },
    {
      "epoch": 0.002285714285714286,
      "grad_norm": 0.013199551962316036,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.9304,
      "step": 15
    },
    {
      "epoch": 0.002438095238095238,
      "grad_norm": 0.016703762114048004,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.9309,
      "step": 16
    },
    {
      "epoch": 0.0025904761904761904,
      "grad_norm": 0.022426387295126915,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.9301,
      "step": 17
    },
    {
      "epoch": 0.002742857142857143,
      "grad_norm": 0.016040390357375145,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.9312,
      "step": 18
    },
    {
      "epoch": 0.0028952380952380953,
      "grad_norm": 0.03560283035039902,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.93,
      "step": 19
    },
    {
      "epoch": 0.0030476190476190477,
      "grad_norm": 0.024731332436203957,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.9307,
      "step": 20
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.029315967112779617,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.9301,
      "step": 21
    },
    {
      "epoch": 0.003352380952380952,
      "grad_norm": 0.03906835615634918,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.9296,
      "step": 22
    },
    {
      "epoch": 0.0035047619047619046,
      "grad_norm": 0.026998696848750114,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.9312,
      "step": 23
    },
    {
      "epoch": 0.003657142857142857,
      "grad_norm": 0.03217875957489014,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.9292,
      "step": 24
    },
    {
      "epoch": 0.0038095238095238095,
      "grad_norm": 0.03475233539938927,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.9288,
      "step": 25
    },
    {
      "epoch": 0.0038095238095238095,
      "eval_loss": 11.930586814880371,
      "eval_runtime": 0.3295,
      "eval_samples_per_second": 151.738,
      "eval_steps_per_second": 21.243,
      "step": 25
    },
    {
      "epoch": 0.003961904761904762,
      "grad_norm": 0.049299657344818115,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.9276,
      "step": 26
    },
    {
      "epoch": 0.004114285714285714,
      "grad_norm": 0.040789611637592316,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.928,
      "step": 27
    },
    {
      "epoch": 0.004266666666666667,
      "grad_norm": 0.04697525128722191,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.9287,
      "step": 28
    },
    {
      "epoch": 0.004419047619047619,
      "grad_norm": 0.057105280458927155,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.9274,
      "step": 29
    },
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 0.05554262176156044,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.9263,
      "step": 30
    },
    {
      "epoch": 0.004723809523809524,
      "grad_norm": 0.059702690690755844,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.9256,
      "step": 31
    },
    {
      "epoch": 0.004876190476190476,
      "grad_norm": 0.05958414077758789,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.9274,
      "step": 32
    },
    {
      "epoch": 0.005028571428571428,
      "grad_norm": 0.06670510023832321,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.9244,
      "step": 33
    },
    {
      "epoch": 0.005180952380952381,
      "grad_norm": 0.0594896636903286,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.9259,
      "step": 34
    },
    {
      "epoch": 0.005333333333333333,
      "grad_norm": 0.08420071005821228,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.9243,
      "step": 35
    },
    {
      "epoch": 0.005485714285714286,
      "grad_norm": 0.06888625770807266,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.9224,
      "step": 36
    },
    {
      "epoch": 0.005638095238095238,
      "grad_norm": 0.07287950813770294,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.9234,
      "step": 37
    },
    {
      "epoch": 0.0057904761904761905,
      "grad_norm": 0.04395854473114014,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.9249,
      "step": 38
    },
    {
      "epoch": 0.005942857142857143,
      "grad_norm": 0.05748274549841881,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.9233,
      "step": 39
    },
    {
      "epoch": 0.006095238095238095,
      "grad_norm": 0.08280626684427261,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.9219,
      "step": 40
    },
    {
      "epoch": 0.006247619047619048,
      "grad_norm": 0.049897756427526474,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.9233,
      "step": 41
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.049588147550821304,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.9248,
      "step": 42
    },
    {
      "epoch": 0.006552380952380953,
      "grad_norm": 0.0516531839966774,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.9216,
      "step": 43
    },
    {
      "epoch": 0.006704761904761904,
      "grad_norm": 0.03678146004676819,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.9212,
      "step": 44
    },
    {
      "epoch": 0.006857142857142857,
      "grad_norm": 0.046402495354413986,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.9203,
      "step": 45
    },
    {
      "epoch": 0.007009523809523809,
      "grad_norm": 0.05032557621598244,
      "learning_rate": 0.000274201324672203,
      "loss": 11.9188,
      "step": 46
    },
    {
      "epoch": 0.007161904761904762,
      "grad_norm": 0.038833487778902054,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.9214,
      "step": 47
    },
    {
      "epoch": 0.007314285714285714,
      "grad_norm": 0.04270482808351517,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.918,
      "step": 48
    },
    {
      "epoch": 0.007466666666666667,
      "grad_norm": 0.05103209614753723,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.9203,
      "step": 49
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 0.050319772213697433,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.9171,
      "step": 50
    },
    {
      "epoch": 0.007619047619047619,
      "eval_loss": 11.921985626220703,
      "eval_runtime": 0.3251,
      "eval_samples_per_second": 153.816,
      "eval_steps_per_second": 21.534,
      "step": 50
    },
    {
      "epoch": 0.0077714285714285715,
      "grad_norm": 0.04554375633597374,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.9228,
      "step": 51
    },
    {
      "epoch": 0.007923809523809524,
      "grad_norm": 0.04022262990474701,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.9199,
      "step": 52
    },
    {
      "epoch": 0.008076190476190476,
      "grad_norm": 0.033325254917144775,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.9218,
      "step": 53
    },
    {
      "epoch": 0.008228571428571429,
      "grad_norm": 0.04107801243662834,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.9205,
      "step": 54
    },
    {
      "epoch": 0.008380952380952381,
      "grad_norm": 0.027698513120412827,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.9217,
      "step": 55
    },
    {
      "epoch": 0.008533333333333334,
      "grad_norm": 0.03343752399086952,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.9195,
      "step": 56
    },
    {
      "epoch": 0.008685714285714286,
      "grad_norm": 0.03319195285439491,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.9203,
      "step": 57
    },
    {
      "epoch": 0.008838095238095239,
      "grad_norm": 0.03573085740208626,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.9196,
      "step": 58
    },
    {
      "epoch": 0.008990476190476191,
      "grad_norm": 0.01422872580587864,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.919,
      "step": 59
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 0.026226388290524483,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.9193,
      "step": 60
    },
    {
      "epoch": 0.009295238095238096,
      "grad_norm": 0.021446671336889267,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.9194,
      "step": 61
    },
    {
      "epoch": 0.009447619047619048,
      "grad_norm": 0.014439309947192669,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.919,
      "step": 62
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.037217725068330765,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.9196,
      "step": 63
    },
    {
      "epoch": 0.009752380952380952,
      "grad_norm": 0.023248059675097466,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.9185,
      "step": 64
    },
    {
      "epoch": 0.009904761904761904,
      "grad_norm": 0.014870691113173962,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.9191,
      "step": 65
    },
    {
      "epoch": 0.010057142857142857,
      "grad_norm": 0.02193147875368595,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.9207,
      "step": 66
    },
    {
      "epoch": 0.010209523809523809,
      "grad_norm": 0.017094288021326065,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.9193,
      "step": 67
    },
    {
      "epoch": 0.010361904761904761,
      "grad_norm": 0.009804649278521538,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.9193,
      "step": 68
    },
    {
      "epoch": 0.010514285714285714,
      "grad_norm": 0.0146781075745821,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.917,
      "step": 69
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 0.019102444872260094,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.9194,
      "step": 70
    },
    {
      "epoch": 0.010819047619047619,
      "grad_norm": 0.02413802035152912,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.9202,
      "step": 71
    },
    {
      "epoch": 0.010971428571428571,
      "grad_norm": 0.013724091462790966,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.918,
      "step": 72
    },
    {
      "epoch": 0.011123809523809524,
      "grad_norm": 0.015044189058244228,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.9201,
      "step": 73
    },
    {
      "epoch": 0.011276190476190476,
      "grad_norm": 0.01973019354045391,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.9213,
      "step": 74
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 0.01863853819668293,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.919,
      "step": 75
    },
    {
      "epoch": 0.011428571428571429,
      "eval_loss": 11.919951438903809,
      "eval_runtime": 0.3345,
      "eval_samples_per_second": 149.462,
      "eval_steps_per_second": 20.925,
      "step": 75
    },
    {
      "epoch": 0.011580952380952381,
      "grad_norm": 0.016588257625699043,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.9198,
      "step": 76
    },
    {
      "epoch": 0.011733333333333333,
      "grad_norm": 0.012788133695721626,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.9192,
      "step": 77
    },
    {
      "epoch": 0.011885714285714286,
      "grad_norm": 0.019622452557086945,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.9176,
      "step": 78
    },
    {
      "epoch": 0.012038095238095238,
      "grad_norm": 0.0162656269967556,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.9194,
      "step": 79
    },
    {
      "epoch": 0.01219047619047619,
      "grad_norm": 0.012881246395409107,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.9186,
      "step": 80
    },
    {
      "epoch": 0.012342857142857143,
      "grad_norm": 0.025122717022895813,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.9199,
      "step": 81
    },
    {
      "epoch": 0.012495238095238096,
      "grad_norm": 0.020889850333333015,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.9174,
      "step": 82
    },
    {
      "epoch": 0.012647619047619048,
      "grad_norm": 0.013086607679724693,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.9196,
      "step": 83
    },
    {
      "epoch": 0.0128,
      "grad_norm": 0.021250098943710327,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.918,
      "step": 84
    },
    {
      "epoch": 0.012952380952380953,
      "grad_norm": 0.015169636346399784,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.9175,
      "step": 85
    },
    {
      "epoch": 0.013104761904761906,
      "grad_norm": 0.025091208517551422,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.9211,
      "step": 86
    },
    {
      "epoch": 0.013257142857142858,
      "grad_norm": 0.020077206194400787,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.9199,
      "step": 87
    },
    {
      "epoch": 0.013409523809523809,
      "grad_norm": 0.03454453870654106,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.9181,
      "step": 88
    },
    {
      "epoch": 0.013561904761904761,
      "grad_norm": 0.02208181656897068,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.9196,
      "step": 89
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.021397177129983902,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.923,
      "step": 90
    },
    {
      "epoch": 0.013866666666666666,
      "grad_norm": 0.025557834655046463,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.9196,
      "step": 91
    },
    {
      "epoch": 0.014019047619047618,
      "grad_norm": 0.02345367893576622,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.9207,
      "step": 92
    },
    {
      "epoch": 0.014171428571428571,
      "grad_norm": 0.02872537262737751,
      "learning_rate": 0.000179567554117722,
      "loss": 11.9172,
      "step": 93
    },
    {
      "epoch": 0.014323809523809523,
      "grad_norm": 0.02754749357700348,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.9197,
      "step": 94
    },
    {
      "epoch": 0.014476190476190476,
      "grad_norm": 0.025062963366508484,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.9182,
      "step": 95
    },
    {
      "epoch": 0.014628571428571428,
      "grad_norm": 0.022489259019494057,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.9189,
      "step": 96
    },
    {
      "epoch": 0.01478095238095238,
      "grad_norm": 0.01625611074268818,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.9195,
      "step": 97
    },
    {
      "epoch": 0.014933333333333333,
      "grad_norm": 0.024079998955130577,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.9175,
      "step": 98
    },
    {
      "epoch": 0.015085714285714286,
      "grad_norm": 0.028555238619446754,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.9192,
      "step": 99
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 0.050129834562540054,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.9216,
      "step": 100
    },
    {
      "epoch": 0.015238095238095238,
      "eval_loss": 11.920056343078613,
      "eval_runtime": 0.3197,
      "eval_samples_per_second": 156.391,
      "eval_steps_per_second": 21.895,
      "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": 162049400832.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}