{
  "best_metric": 1.1182136535644531,
  "best_model_checkpoint": "data/Llama-31-8B_task-3_120-samples_config-1_full_auto/checkpoint-88",
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.6140740513801575,
      "learning_rate": 1.818181818181818e-06,
      "loss": 1.6157,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.633514940738678,
      "learning_rate": 3.636363636363636e-06,
      "loss": 1.7906,
      "step": 2
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.4436061978340149,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.6545,
      "step": 4
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.5624129772186279,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.6752,
      "step": 6
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4438210129737854,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 1.6992,
      "step": 8
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.4410490393638611,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.6493,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6401925086975098,
      "eval_runtime": 21.0974,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 11
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.5115651488304138,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 1.6988,
      "step": 12
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.32359737157821655,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 1.5963,
      "step": 14
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.4572658836841583,
      "learning_rate": 2.909090909090909e-05,
      "loss": 1.5802,
      "step": 16
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.4237446188926697,
      "learning_rate": 3.272727272727273e-05,
      "loss": 1.6072,
      "step": 18
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.3928747773170471,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.543,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.27307966351509094,
      "learning_rate": 4e-05,
      "loss": 1.4499,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.49874746799469,
      "eval_runtime": 21.0991,
      "eval_samples_per_second": 1.137,
      "eval_steps_per_second": 1.137,
      "step": 22
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.23345141112804413,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 1.4916,
      "step": 24
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.2543642222881317,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 1.4322,
      "step": 26
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.23768730461597443,
      "learning_rate": 5.090909090909091e-05,
      "loss": 1.3876,
      "step": 28
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.23884046077728271,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.42,
      "step": 30
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.3190615177154541,
      "learning_rate": 5.818181818181818e-05,
      "loss": 1.3516,
      "step": 32
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3294841051101685,
      "eval_runtime": 21.0922,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 33
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.2684502899646759,
      "learning_rate": 6.181818181818182e-05,
      "loss": 1.3057,
      "step": 34
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.30202409625053406,
      "learning_rate": 6.545454545454546e-05,
      "loss": 1.2694,
      "step": 36
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.4531688094139099,
      "learning_rate": 6.90909090909091e-05,
      "loss": 1.235,
      "step": 38
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.2743944823741913,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.1495,
      "step": 40
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.35163456201553345,
      "learning_rate": 7.636363636363637e-05,
      "loss": 1.0883,
      "step": 42
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.20615524053573608,
      "learning_rate": 8e-05,
      "loss": 1.2309,
      "step": 44
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.1897262334823608,
      "eval_runtime": 21.0993,
      "eval_samples_per_second": 1.137,
      "eval_steps_per_second": 1.137,
      "step": 44
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.20419842004776,
      "learning_rate": 8.363636363636364e-05,
      "loss": 1.1011,
      "step": 46
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.21742255985736847,
      "learning_rate": 8.727272727272727e-05,
      "loss": 1.148,
      "step": 48
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.19342638552188873,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.1004,
      "step": 50
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.22799430787563324,
      "learning_rate": 9.454545454545455e-05,
      "loss": 1.0834,
      "step": 52
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.17923079431056976,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.151,
      "step": 54
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.151379108428955,
      "eval_runtime": 21.0959,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 55
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.19790033996105194,
      "learning_rate": 9.999899300364532e-05,
      "loss": 1.0753,
      "step": 56
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.19572222232818604,
      "learning_rate": 9.99909372761763e-05,
      "loss": 1.1013,
      "step": 58
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.20267722010612488,
      "learning_rate": 9.997482711915927e-05,
      "loss": 1.0324,
      "step": 60
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.22312578558921814,
      "learning_rate": 9.99506651282272e-05,
      "loss": 1.0568,
      "step": 62
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.2083328664302826,
      "learning_rate": 9.991845519630678e-05,
      "loss": 1.0513,
      "step": 64
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.20508889853954315,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1003,
      "step": 66
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.1307473182678223,
      "eval_runtime": 21.0928,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 66
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.2443745732307434,
      "learning_rate": 9.982991356370404e-05,
      "loss": 0.9953,
      "step": 68
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.2539820075035095,
      "learning_rate": 9.977359612865423e-05,
      "loss": 1.063,
      "step": 70
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.22875210642814636,
      "learning_rate": 9.970925928158274e-05,
      "loss": 0.9689,
      "step": 72
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.25840261578559875,
      "learning_rate": 9.963691338830044e-05,
      "loss": 1.0165,
      "step": 74
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.2147582322359085,
      "learning_rate": 9.955657010501806e-05,
      "loss": 1.0537,
      "step": 76
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.1199712753295898,
      "eval_runtime": 21.0948,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 77
    },
    {
      "epoch": 7.090909090909091,
      "grad_norm": 0.21880163252353668,
      "learning_rate": 9.946824237646824e-05,
      "loss": 1.107,
      "step": 78
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.2924984097480774,
      "learning_rate": 9.937194443381972e-05,
      "loss": 0.929,
      "step": 80
    },
    {
      "epoch": 7.454545454545454,
      "grad_norm": 0.29512104392051697,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.9434,
      "step": 82
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.296135276556015,
      "learning_rate": 9.915550124911866e-05,
      "loss": 0.9888,
      "step": 84
    },
    {
      "epoch": 7.818181818181818,
      "grad_norm": 0.2890602946281433,
      "learning_rate": 9.903539087991462e-05,
      "loss": 0.962,
      "step": 86
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2855319678783417,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0287,
      "step": 88
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.1182136535644531,
      "eval_runtime": 21.0906,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 88
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.2914893329143524,
      "learning_rate": 9.877148934427037e-05,
      "loss": 0.9739,
      "step": 90
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.3012477159500122,
      "learning_rate": 9.862774069706346e-05,
      "loss": 0.9007,
      "step": 92
    },
    {
      "epoch": 8.545454545454545,
      "grad_norm": 0.3721104860305786,
      "learning_rate": 9.847615725553456e-05,
      "loss": 0.9611,
      "step": 94
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.37073028087615967,
      "learning_rate": 9.831676344247342e-05,
      "loss": 0.8585,
      "step": 96
    },
    {
      "epoch": 8.909090909090908,
      "grad_norm": 0.3731912672519684,
      "learning_rate": 9.814958493905963e-05,
      "loss": 0.9295,
      "step": 98
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.129991888999939,
      "eval_runtime": 21.0972,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 99
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.3577060401439667,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.941,
      "step": 100
    },
    {
      "epoch": 9.272727272727273,
      "grad_norm": 0.42204001545906067,
      "learning_rate": 9.779198285281325e-05,
      "loss": 0.8387,
      "step": 102
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.6319920420646667,
      "learning_rate": 9.760161688604008e-05,
      "loss": 0.8189,
      "step": 104
    },
    {
      "epoch": 9.636363636363637,
      "grad_norm": 0.47785764932632446,
      "learning_rate": 9.740358145174998e-05,
      "loss": 0.9293,
      "step": 106
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 0.4531428813934326,
      "learning_rate": 9.719790845697533e-05,
      "loss": 0.8554,
      "step": 108
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.5752642154693604,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8133,
      "step": 110
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1687343120574951,
      "eval_runtime": 21.0952,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 110
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.5641032457351685,
      "learning_rate": 9.676378356149734e-05,
      "loss": 0.7554,
      "step": 112
    },
    {
      "epoch": 10.363636363636363,
      "grad_norm": 0.49765628576278687,
      "learning_rate": 9.653540160603956e-05,
      "loss": 0.7516,
      "step": 114
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.5461922287940979,
      "learning_rate": 9.629952196931901e-05,
      "loss": 0.7608,
      "step": 116
    },
    {
      "epoch": 10.727272727272727,
      "grad_norm": 0.6831594109535217,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.7381,
      "step": 118
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.6643287539482117,
      "learning_rate": 9.580542287160348e-05,
      "loss": 0.8071,
      "step": 120
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.2087494134902954,
      "eval_runtime": 21.1037,
      "eval_samples_per_second": 1.137,
      "eval_steps_per_second": 1.137,
      "step": 121
    },
    {
      "epoch": 11.090909090909092,
      "grad_norm": 0.7433243989944458,
      "learning_rate": 9.554728301876526e-05,
      "loss": 0.7306,
      "step": 122
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 0.8613724708557129,
      "learning_rate": 9.528180468815155e-05,
      "loss": 0.6656,
      "step": 124
    },
    {
      "epoch": 11.454545454545455,
      "grad_norm": 0.7362491488456726,
      "learning_rate": 9.50090306530454e-05,
      "loss": 0.6721,
      "step": 126
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 0.7671507596969604,
      "learning_rate": 9.472900486219769e-05,
      "loss": 0.7087,
      "step": 128
    },
    {
      "epoch": 11.818181818181818,
      "grad_norm": 0.8188756108283997,
      "learning_rate": 9.444177243274618e-05,
      "loss": 0.6663,
      "step": 130
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.7221516370773315,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6155,
      "step": 132
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.2670179605484009,
      "eval_runtime": 21.0987,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 132
    },
    {
      "epoch": 12.181818181818182,
      "grad_norm": 0.9694033265113831,
      "learning_rate": 9.384587392471515e-05,
      "loss": 0.5934,
      "step": 134
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.9179559946060181,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.5329,
      "step": 136
    },
    {
      "epoch": 12.545454545454545,
      "grad_norm": 0.8279669880867004,
      "learning_rate": 9.322171915289635e-05,
      "loss": 0.5661,
      "step": 138
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.9683154225349426,
      "learning_rate": 9.289917066174886e-05,
      "loss": 0.5416,
      "step": 140
    },
    {
      "epoch": 12.909090909090908,
      "grad_norm": 0.9345831274986267,
      "learning_rate": 9.256971035084785e-05,
      "loss": 0.6191,
      "step": 142
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.289109706878662,
      "eval_runtime": 21.0945,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 143
    },
    {
      "epoch": 13.090909090909092,
      "grad_norm": 1.0367761850357056,
      "learning_rate": 9.223339130211192e-05,
      "loss": 0.4474,
      "step": 144
    },
    {
      "epoch": 13.272727272727273,
      "grad_norm": 1.4238847494125366,
      "learning_rate": 9.189026770252436e-05,
      "loss": 0.4937,
      "step": 146
    },
    {
      "epoch": 13.454545454545455,
      "grad_norm": 0.9347456693649292,
      "learning_rate": 9.154039483540273e-05,
      "loss": 0.5332,
      "step": 148
    },
    {
      "epoch": 13.636363636363637,
      "grad_norm": 0.992377519607544,
      "learning_rate": 9.118382907149165e-05,
      "loss": 0.479,
      "step": 150
    },
    {
      "epoch": 13.818181818181818,
      "grad_norm": 1.094530463218689,
      "learning_rate": 9.082062785988049e-05,
      "loss": 0.4527,
      "step": 152
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.1631982326507568,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3871,
      "step": 154
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.423146367073059,
      "eval_runtime": 21.0955,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 154
    },
    {
      "epoch": 14.181818181818182,
      "grad_norm": 1.0176337957382202,
      "learning_rate": 9.007455422593077e-05,
      "loss": 0.3967,
      "step": 156
    },
    {
      "epoch": 14.363636363636363,
      "grad_norm": 1.7038488388061523,
      "learning_rate": 8.969180200933047e-05,
      "loss": 0.3914,
      "step": 158
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 0.9885173439979553,
      "learning_rate": 8.930265473713938e-05,
      "loss": 0.4627,
      "step": 160
    },
    {
      "epoch": 14.727272727272727,
      "grad_norm": 1.0425654649734497,
      "learning_rate": 8.890717510790763e-05,
      "loss": 0.3632,
      "step": 162
    },
    {
      "epoch": 14.909090909090908,
      "grad_norm": 1.3556066751480103,
      "learning_rate": 8.850542684044078e-05,
      "loss": 0.2973,
      "step": 164
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.3964157104492188,
      "eval_runtime": 21.0942,
      "eval_samples_per_second": 1.138,
      "eval_steps_per_second": 1.138,
      "step": 165
    },
    {
      "epoch": 15.0,
      "step": 165,
      "total_flos": 1.040005159893074e+17,
      "train_loss": 0.9787666850017779,
      "train_runtime": 3826.1851,
      "train_samples_per_second": 1.15,
      "train_steps_per_second": 0.144
    }
  ],
  "logging_steps": 2,
  "max_steps": 550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "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": 1.040005159893074e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}