{
  "best_metric": 0.9958813786506653,
  "best_model_checkpoint": "data/Llama-31-8B_task-2_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": 0.46718546748161316,
      "learning_rate": 1.818181818181818e-06,
      "loss": 1.4447,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.5743524432182312,
      "learning_rate": 3.636363636363636e-06,
      "loss": 1.6181,
      "step": 2
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.4949629604816437,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.483,
      "step": 4
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.467034250497818,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.5101,
      "step": 6
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4608269929885864,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 1.5531,
      "step": 8
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.4457903802394867,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.4871,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4805207252502441,
      "eval_runtime": 25.0007,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 11
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.4714236557483673,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 1.512,
      "step": 12
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.32585760951042175,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 1.4387,
      "step": 14
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.44309839606285095,
      "learning_rate": 2.909090909090909e-05,
      "loss": 1.4254,
      "step": 16
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.344897598028183,
      "learning_rate": 3.272727272727273e-05,
      "loss": 1.4579,
      "step": 18
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.35833805799484253,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.3853,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.24547061324119568,
      "learning_rate": 4e-05,
      "loss": 1.2753,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.342230200767517,
      "eval_runtime": 24.9976,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 22
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.21824195981025696,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 1.3244,
      "step": 24
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.25711968541145325,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 1.301,
      "step": 26
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.22954638302326202,
      "learning_rate": 5.090909090909091e-05,
      "loss": 1.2454,
      "step": 28
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.24975018203258514,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.2588,
      "step": 30
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.24941213428974152,
      "learning_rate": 5.818181818181818e-05,
      "loss": 1.1856,
      "step": 32
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.1891138553619385,
      "eval_runtime": 25.0023,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 33
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.22893352806568146,
      "learning_rate": 6.181818181818182e-05,
      "loss": 1.1741,
      "step": 34
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.2360878586769104,
      "learning_rate": 6.545454545454546e-05,
      "loss": 1.1069,
      "step": 36
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.3948248028755188,
      "learning_rate": 6.90909090909091e-05,
      "loss": 1.1066,
      "step": 38
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.24378176033496857,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.0245,
      "step": 40
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.37180250883102417,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.9665,
      "step": 42
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.17623767256736755,
      "learning_rate": 8e-05,
      "loss": 1.0973,
      "step": 44
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0591130256652832,
      "eval_runtime": 24.9994,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 44
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.17406652867794037,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.9692,
      "step": 46
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.1780126988887787,
      "learning_rate": 8.727272727272727e-05,
      "loss": 1.0189,
      "step": 48
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.1742819994688034,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9762,
      "step": 50
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.20706258714199066,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.9755,
      "step": 52
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.17788530886173248,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.0204,
      "step": 54
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0276859998703003,
      "eval_runtime": 25.0033,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 55
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.17162466049194336,
      "learning_rate": 9.999899300364532e-05,
      "loss": 0.9571,
      "step": 56
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.20154060423374176,
      "learning_rate": 9.99909372761763e-05,
      "loss": 0.9837,
      "step": 58
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.1810280680656433,
      "learning_rate": 9.997482711915927e-05,
      "loss": 0.9029,
      "step": 60
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.18309460580348969,
      "learning_rate": 9.99506651282272e-05,
      "loss": 0.9343,
      "step": 62
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.19293639063835144,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.9374,
      "step": 64
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.18194247782230377,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9819,
      "step": 66
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0086289644241333,
      "eval_runtime": 25.0053,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 66
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.20677907764911652,
      "learning_rate": 9.982991356370404e-05,
      "loss": 0.8761,
      "step": 68
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.209967240691185,
      "learning_rate": 9.977359612865423e-05,
      "loss": 0.9365,
      "step": 70
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.20778240263462067,
      "learning_rate": 9.970925928158274e-05,
      "loss": 0.8617,
      "step": 72
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.3242216408252716,
      "learning_rate": 9.963691338830044e-05,
      "loss": 0.9073,
      "step": 74
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.19102028012275696,
      "learning_rate": 9.955657010501806e-05,
      "loss": 0.948,
      "step": 76
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.9992754459381104,
      "eval_runtime": 25.0039,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 77
    },
    {
      "epoch": 7.090909090909091,
      "grad_norm": 0.19626860320568085,
      "learning_rate": 9.946824237646824e-05,
      "loss": 0.9756,
      "step": 78
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.24306823313236237,
      "learning_rate": 9.937194443381972e-05,
      "loss": 0.8299,
      "step": 80
    },
    {
      "epoch": 7.454545454545454,
      "grad_norm": 0.26410818099975586,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.8304,
      "step": 82
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.2524285614490509,
      "learning_rate": 9.915550124911866e-05,
      "loss": 0.8707,
      "step": 84
    },
    {
      "epoch": 7.818181818181818,
      "grad_norm": 0.25569218397140503,
      "learning_rate": 9.903539087991462e-05,
      "loss": 0.8534,
      "step": 86
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2707505226135254,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9103,
      "step": 88
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9958813786506653,
      "eval_runtime": 24.996,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 88
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.25199592113494873,
      "learning_rate": 9.877148934427037e-05,
      "loss": 0.8582,
      "step": 90
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.2703748643398285,
      "learning_rate": 9.862774069706346e-05,
      "loss": 0.7961,
      "step": 92
    },
    {
      "epoch": 8.545454545454545,
      "grad_norm": 0.3369429111480713,
      "learning_rate": 9.847615725553456e-05,
      "loss": 0.8511,
      "step": 94
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.2925892770290375,
      "learning_rate": 9.831676344247342e-05,
      "loss": 0.7558,
      "step": 96
    },
    {
      "epoch": 8.909090909090908,
      "grad_norm": 0.310421347618103,
      "learning_rate": 9.814958493905963e-05,
      "loss": 0.8302,
      "step": 98
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.0062583684921265,
      "eval_runtime": 24.9965,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 99
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.30456843972206116,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.8344,
      "step": 100
    },
    {
      "epoch": 9.272727272727273,
      "grad_norm": 0.3575204312801361,
      "learning_rate": 9.779198285281325e-05,
      "loss": 0.7336,
      "step": 102
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.4703364074230194,
      "learning_rate": 9.760161688604008e-05,
      "loss": 0.7284,
      "step": 104
    },
    {
      "epoch": 9.636363636363637,
      "grad_norm": 0.4257412552833557,
      "learning_rate": 9.740358145174998e-05,
      "loss": 0.8143,
      "step": 106
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 0.4207710325717926,
      "learning_rate": 9.719790845697533e-05,
      "loss": 0.7592,
      "step": 108
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.512427806854248,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7247,
      "step": 110
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0326719284057617,
      "eval_runtime": 24.9981,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 110
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.47976231575012207,
      "learning_rate": 9.676378356149734e-05,
      "loss": 0.6739,
      "step": 112
    },
    {
      "epoch": 10.363636363636363,
      "grad_norm": 0.47625064849853516,
      "learning_rate": 9.653540160603956e-05,
      "loss": 0.6675,
      "step": 114
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.46235671639442444,
      "learning_rate": 9.629952196931901e-05,
      "loss": 0.6716,
      "step": 116
    },
    {
      "epoch": 10.727272727272727,
      "grad_norm": 0.5467497706413269,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.6618,
      "step": 118
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.5443487167358398,
      "learning_rate": 9.580542287160348e-05,
      "loss": 0.7159,
      "step": 120
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.079423189163208,
      "eval_runtime": 25.001,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 121
    },
    {
      "epoch": 11.090909090909092,
      "grad_norm": 0.5879309177398682,
      "learning_rate": 9.554728301876526e-05,
      "loss": 0.6414,
      "step": 122
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 0.6094502806663513,
      "learning_rate": 9.528180468815155e-05,
      "loss": 0.5946,
      "step": 124
    },
    {
      "epoch": 11.454545454545455,
      "grad_norm": 0.5761741399765015,
      "learning_rate": 9.50090306530454e-05,
      "loss": 0.5967,
      "step": 126
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 0.6594637036323547,
      "learning_rate": 9.472900486219769e-05,
      "loss": 0.6289,
      "step": 128
    },
    {
      "epoch": 11.818181818181818,
      "grad_norm": 0.7374260425567627,
      "learning_rate": 9.444177243274618e-05,
      "loss": 0.6028,
      "step": 130
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.6803016066551208,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5506,
      "step": 132
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1348603963851929,
      "eval_runtime": 25.0067,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 132
    },
    {
      "epoch": 12.181818181818182,
      "grad_norm": 0.7518048286437988,
      "learning_rate": 9.384587392471515e-05,
      "loss": 0.5354,
      "step": 134
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.714648425579071,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.4885,
      "step": 136
    },
    {
      "epoch": 12.545454545454545,
      "grad_norm": 0.7217809557914734,
      "learning_rate": 9.322171915289635e-05,
      "loss": 0.5091,
      "step": 138
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.8329242467880249,
      "learning_rate": 9.289917066174886e-05,
      "loss": 0.4898,
      "step": 140
    },
    {
      "epoch": 12.909090909090908,
      "grad_norm": 0.8458116054534912,
      "learning_rate": 9.256971035084785e-05,
      "loss": 0.5606,
      "step": 142
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.196074366569519,
      "eval_runtime": 25.0033,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 143
    },
    {
      "epoch": 13.090909090909092,
      "grad_norm": 0.8682050704956055,
      "learning_rate": 9.223339130211192e-05,
      "loss": 0.4004,
      "step": 144
    },
    {
      "epoch": 13.272727272727273,
      "grad_norm": 1.1295245885849,
      "learning_rate": 9.189026770252436e-05,
      "loss": 0.4494,
      "step": 146
    },
    {
      "epoch": 13.454545454545455,
      "grad_norm": 0.8367961645126343,
      "learning_rate": 9.154039483540273e-05,
      "loss": 0.4898,
      "step": 148
    },
    {
      "epoch": 13.636363636363637,
      "grad_norm": 0.9551791548728943,
      "learning_rate": 9.118382907149165e-05,
      "loss": 0.4388,
      "step": 150
    },
    {
      "epoch": 13.818181818181818,
      "grad_norm": 0.8031957745552063,
      "learning_rate": 9.082062785988049e-05,
      "loss": 0.4058,
      "step": 152
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.855376124382019,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3523,
      "step": 154
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.2591336965560913,
      "eval_runtime": 24.9961,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 154
    },
    {
      "epoch": 14.181818181818182,
      "grad_norm": 0.8191350698471069,
      "learning_rate": 9.007455422593077e-05,
      "loss": 0.3556,
      "step": 156
    },
    {
      "epoch": 14.363636363636363,
      "grad_norm": 0.8832336664199829,
      "learning_rate": 8.969180200933047e-05,
      "loss": 0.3506,
      "step": 158
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 0.770671546459198,
      "learning_rate": 8.930265473713938e-05,
      "loss": 0.4188,
      "step": 160
    },
    {
      "epoch": 14.727272727272727,
      "grad_norm": 1.2660021781921387,
      "learning_rate": 8.890717510790763e-05,
      "loss": 0.331,
      "step": 162
    },
    {
      "epoch": 14.909090909090908,
      "grad_norm": 0.938758373260498,
      "learning_rate": 8.850542684044078e-05,
      "loss": 0.2739,
      "step": 164
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.313956379890442,
      "eval_runtime": 25.0009,
      "eval_samples_per_second": 0.96,
      "eval_steps_per_second": 0.96,
      "step": 165
    },
    {
      "epoch": 15.0,
      "step": 165,
      "total_flos": 1.3064895880757248e+17,
      "train_loss": 0.8733351096962437,
      "train_runtime": 4662.5101,
      "train_samples_per_second": 0.944,
      "train_steps_per_second": 0.118
    }
  ],
  "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": 1.3064895880757248e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}