{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7167381974248928,
  "eval_steps": 4,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034334763948497854,
      "grad_norm": 19.15982437133789,
      "learning_rate": 2e-05,
      "loss": 13.5674,
      "step": 1
    },
    {
      "epoch": 0.034334763948497854,
      "eval_loss": 1.6727509498596191,
      "eval_runtime": 8.0648,
      "eval_samples_per_second": 6.076,
      "eval_steps_per_second": 1.612,
      "step": 1
    },
    {
      "epoch": 0.06866952789699571,
      "grad_norm": 16.63048553466797,
      "learning_rate": 4e-05,
      "loss": 14.7517,
      "step": 2
    },
    {
      "epoch": 0.10300429184549356,
      "grad_norm": 15.25049877166748,
      "learning_rate": 6e-05,
      "loss": 13.1345,
      "step": 3
    },
    {
      "epoch": 0.13733905579399142,
      "grad_norm": 17.173583984375,
      "learning_rate": 8e-05,
      "loss": 11.7391,
      "step": 4
    },
    {
      "epoch": 0.13733905579399142,
      "eval_loss": 1.4845433235168457,
      "eval_runtime": 8.0677,
      "eval_samples_per_second": 6.074,
      "eval_steps_per_second": 1.611,
      "step": 4
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 15.846421241760254,
      "learning_rate": 0.0001,
      "loss": 13.1035,
      "step": 5
    },
    {
      "epoch": 0.20600858369098712,
      "grad_norm": 13.740381240844727,
      "learning_rate": 0.00012,
      "loss": 10.3992,
      "step": 6
    },
    {
      "epoch": 0.24034334763948498,
      "grad_norm": 10.496570587158203,
      "learning_rate": 0.00014,
      "loss": 9.9128,
      "step": 7
    },
    {
      "epoch": 0.27467811158798283,
      "grad_norm": 8.85119342803955,
      "learning_rate": 0.00016,
      "loss": 7.9807,
      "step": 8
    },
    {
      "epoch": 0.27467811158798283,
      "eval_loss": 0.9227344989776611,
      "eval_runtime": 8.0856,
      "eval_samples_per_second": 6.06,
      "eval_steps_per_second": 1.608,
      "step": 8
    },
    {
      "epoch": 0.3090128755364807,
      "grad_norm": 8.351367950439453,
      "learning_rate": 0.00018,
      "loss": 6.646,
      "step": 9
    },
    {
      "epoch": 0.34334763948497854,
      "grad_norm": 11.750950813293457,
      "learning_rate": 0.0002,
      "loss": 7.369,
      "step": 10
    },
    {
      "epoch": 0.3776824034334764,
      "grad_norm": 12.794264793395996,
      "learning_rate": 0.0001996917333733128,
      "loss": 5.8694,
      "step": 11
    },
    {
      "epoch": 0.41201716738197425,
      "grad_norm": 21.229198455810547,
      "learning_rate": 0.00019876883405951377,
      "loss": 6.5926,
      "step": 12
    },
    {
      "epoch": 0.41201716738197425,
      "eval_loss": 0.6635634899139404,
      "eval_runtime": 8.081,
      "eval_samples_per_second": 6.064,
      "eval_steps_per_second": 1.609,
      "step": 12
    },
    {
      "epoch": 0.44635193133047213,
      "grad_norm": 15.183062553405762,
      "learning_rate": 0.00019723699203976766,
      "loss": 5.3242,
      "step": 13
    },
    {
      "epoch": 0.48068669527896996,
      "grad_norm": 11.120061874389648,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.0979,
      "step": 14
    },
    {
      "epoch": 0.5150214592274678,
      "grad_norm": 9.379684448242188,
      "learning_rate": 0.0001923879532511287,
      "loss": 4.2185,
      "step": 15
    },
    {
      "epoch": 0.5493562231759657,
      "grad_norm": 9.187313079833984,
      "learning_rate": 0.0001891006524188368,
      "loss": 3.9636,
      "step": 16
    },
    {
      "epoch": 0.5493562231759657,
      "eval_loss": 0.5391715168952942,
      "eval_runtime": 8.0725,
      "eval_samples_per_second": 6.07,
      "eval_steps_per_second": 1.61,
      "step": 16
    },
    {
      "epoch": 0.5836909871244635,
      "grad_norm": 7.920268535614014,
      "learning_rate": 0.00018526401643540922,
      "loss": 3.4412,
      "step": 17
    },
    {
      "epoch": 0.6180257510729614,
      "grad_norm": 8.719185829162598,
      "learning_rate": 0.00018090169943749476,
      "loss": 4.7588,
      "step": 18
    },
    {
      "epoch": 0.6523605150214592,
      "grad_norm": 7.354686260223389,
      "learning_rate": 0.0001760405965600031,
      "loss": 3.7329,
      "step": 19
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 6.449216842651367,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.0476,
      "step": 20
    },
    {
      "epoch": 0.6866952789699571,
      "eval_loss": 0.4746493995189667,
      "eval_runtime": 8.0715,
      "eval_samples_per_second": 6.071,
      "eval_steps_per_second": 1.611,
      "step": 20
    },
    {
      "epoch": 0.721030042918455,
      "grad_norm": 10.40072250366211,
      "learning_rate": 0.00016494480483301836,
      "loss": 3.6035,
      "step": 21
    },
    {
      "epoch": 0.7553648068669528,
      "grad_norm": 9.310944557189941,
      "learning_rate": 0.00015877852522924732,
      "loss": 3.1352,
      "step": 22
    },
    {
      "epoch": 0.7896995708154506,
      "grad_norm": 9.59798526763916,
      "learning_rate": 0.0001522498564715949,
      "loss": 3.9863,
      "step": 23
    },
    {
      "epoch": 0.8240343347639485,
      "grad_norm": 7.370415210723877,
      "learning_rate": 0.00014539904997395468,
      "loss": 3.0432,
      "step": 24
    },
    {
      "epoch": 0.8240343347639485,
      "eval_loss": 0.4330078065395355,
      "eval_runtime": 8.0682,
      "eval_samples_per_second": 6.073,
      "eval_steps_per_second": 1.611,
      "step": 24
    },
    {
      "epoch": 0.8583690987124464,
      "grad_norm": 9.128814697265625,
      "learning_rate": 0.000138268343236509,
      "loss": 3.4839,
      "step": 25
    },
    {
      "epoch": 0.8927038626609443,
      "grad_norm": 5.970047473907471,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.2252,
      "step": 26
    },
    {
      "epoch": 0.927038626609442,
      "grad_norm": 6.384853839874268,
      "learning_rate": 0.00012334453638559057,
      "loss": 3.4018,
      "step": 27
    },
    {
      "epoch": 0.9613733905579399,
      "grad_norm": 6.741840839385986,
      "learning_rate": 0.0001156434465040231,
      "loss": 3.4371,
      "step": 28
    },
    {
      "epoch": 0.9613733905579399,
      "eval_loss": 0.4020407199859619,
      "eval_runtime": 8.0743,
      "eval_samples_per_second": 6.069,
      "eval_steps_per_second": 1.61,
      "step": 28
    },
    {
      "epoch": 0.9957081545064378,
      "grad_norm": 5.92246675491333,
      "learning_rate": 0.0001078459095727845,
      "loss": 2.4705,
      "step": 29
    },
    {
      "epoch": 1.0300429184549356,
      "grad_norm": 6.4705681800842285,
      "learning_rate": 0.0001,
      "loss": 2.5391,
      "step": 30
    },
    {
      "epoch": 1.0643776824034334,
      "grad_norm": 7.236270427703857,
      "learning_rate": 9.215409042721552e-05,
      "loss": 3.4479,
      "step": 31
    },
    {
      "epoch": 1.0987124463519313,
      "grad_norm": 5.484566688537598,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.1396,
      "step": 32
    },
    {
      "epoch": 1.0987124463519313,
      "eval_loss": 0.3587982654571533,
      "eval_runtime": 8.0769,
      "eval_samples_per_second": 6.067,
      "eval_steps_per_second": 1.61,
      "step": 32
    },
    {
      "epoch": 1.1330472103004292,
      "grad_norm": 6.789762020111084,
      "learning_rate": 7.66554636144095e-05,
      "loss": 2.4319,
      "step": 33
    },
    {
      "epoch": 1.167381974248927,
      "grad_norm": 5.139922142028809,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.5539,
      "step": 34
    },
    {
      "epoch": 1.201716738197425,
      "grad_norm": 5.432690143585205,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.9336,
      "step": 35
    },
    {
      "epoch": 1.2360515021459229,
      "grad_norm": 4.705223560333252,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 1.6073,
      "step": 36
    },
    {
      "epoch": 1.2360515021459229,
      "eval_loss": 0.3393373191356659,
      "eval_runtime": 8.0747,
      "eval_samples_per_second": 6.068,
      "eval_steps_per_second": 1.61,
      "step": 36
    },
    {
      "epoch": 1.2703862660944205,
      "grad_norm": 8.144052505493164,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 2.4886,
      "step": 37
    },
    {
      "epoch": 1.3047210300429184,
      "grad_norm": 5.885042667388916,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.1173,
      "step": 38
    },
    {
      "epoch": 1.3390557939914163,
      "grad_norm": 5.44212532043457,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 1.5208,
      "step": 39
    },
    {
      "epoch": 1.3733905579399142,
      "grad_norm": 8.440479278564453,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 3.2822,
      "step": 40
    },
    {
      "epoch": 1.3733905579399142,
      "eval_loss": 0.3231399357318878,
      "eval_runtime": 8.0758,
      "eval_samples_per_second": 6.068,
      "eval_steps_per_second": 1.61,
      "step": 40
    },
    {
      "epoch": 1.407725321888412,
      "grad_norm": 6.7061991691589355,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 2.4418,
      "step": 41
    },
    {
      "epoch": 1.44206008583691,
      "grad_norm": 5.881109714508057,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.252,
      "step": 42
    },
    {
      "epoch": 1.4763948497854078,
      "grad_norm": 5.9437479972839355,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 1.8867,
      "step": 43
    },
    {
      "epoch": 1.5107296137339055,
      "grad_norm": 5.992803573608398,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.7314,
      "step": 44
    },
    {
      "epoch": 1.5107296137339055,
      "eval_loss": 0.31934094429016113,
      "eval_runtime": 8.0874,
      "eval_samples_per_second": 6.059,
      "eval_steps_per_second": 1.607,
      "step": 44
    },
    {
      "epoch": 1.5450643776824036,
      "grad_norm": 6.900696754455566,
      "learning_rate": 7.612046748871327e-06,
      "loss": 2.8172,
      "step": 45
    },
    {
      "epoch": 1.5793991416309012,
      "grad_norm": 4.783636569976807,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.6444,
      "step": 46
    },
    {
      "epoch": 1.613733905579399,
      "grad_norm": 7.204476356506348,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 2.3282,
      "step": 47
    },
    {
      "epoch": 1.648068669527897,
      "grad_norm": 5.65119743347168,
      "learning_rate": 1.231165940486234e-06,
      "loss": 1.7266,
      "step": 48
    },
    {
      "epoch": 1.648068669527897,
      "eval_loss": 0.3161769509315491,
      "eval_runtime": 8.1044,
      "eval_samples_per_second": 6.046,
      "eval_steps_per_second": 1.604,
      "step": 48
    },
    {
      "epoch": 1.6824034334763949,
      "grad_norm": 5.6475605964660645,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 1.6549,
      "step": 49
    },
    {
      "epoch": 1.7167381974248928,
      "grad_norm": 9.571765899658203,
      "learning_rate": 0.0,
      "loss": 3.696,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6089318710981427e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}