{
  "best_metric": 1.130280613899231,
  "best_model_checkpoint": "data/Llama-31-8B_task-3_120-samples_config-1_full/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": 0.5073621273040771,
      "learning_rate": 1.818181818181818e-06,
      "loss": 1.6175,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.6746556758880615,
      "learning_rate": 3.636363636363636e-06,
      "loss": 1.8463,
      "step": 2
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.47976866364479065,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.6704,
      "step": 4
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.5460829734802246,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.6998,
      "step": 6
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4562014639377594,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 1.7365,
      "step": 8
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.4486631751060486,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.6541,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6579986810684204,
      "eval_runtime": 20.9813,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 11
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.5103980898857117,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 1.7198,
      "step": 12
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.3330501914024353,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 1.6155,
      "step": 14
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.47797951102256775,
      "learning_rate": 2.909090909090909e-05,
      "loss": 1.6108,
      "step": 16
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.44466927647590637,
      "learning_rate": 3.272727272727273e-05,
      "loss": 1.6337,
      "step": 18
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.3738180696964264,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.559,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2718285918235779,
      "learning_rate": 4e-05,
      "loss": 1.4606,
      "step": 22
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5146384239196777,
      "eval_runtime": 20.9818,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 22
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.2300523966550827,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 1.5005,
      "step": 24
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.2499627023935318,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 1.4615,
      "step": 26
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.238471120595932,
      "learning_rate": 5.090909090909091e-05,
      "loss": 1.3991,
      "step": 28
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.2379378080368042,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.4259,
      "step": 30
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.31978145241737366,
      "learning_rate": 5.818181818181818e-05,
      "loss": 1.3657,
      "step": 32
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3458143472671509,
      "eval_runtime": 20.9773,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 33
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 0.27134522795677185,
      "learning_rate": 6.181818181818182e-05,
      "loss": 1.338,
      "step": 34
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.30198484659194946,
      "learning_rate": 6.545454545454546e-05,
      "loss": 1.2755,
      "step": 36
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.4572388827800751,
      "learning_rate": 6.90909090909091e-05,
      "loss": 1.2527,
      "step": 38
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.253333181142807,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.163,
      "step": 40
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.366847962141037,
      "learning_rate": 7.636363636363637e-05,
      "loss": 1.104,
      "step": 42
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2040766328573227,
      "learning_rate": 8e-05,
      "loss": 1.244,
      "step": 44
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2033618688583374,
      "eval_runtime": 20.982,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 44
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.2064678817987442,
      "learning_rate": 8.363636363636364e-05,
      "loss": 1.1091,
      "step": 46
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.2296631783246994,
      "learning_rate": 8.727272727272727e-05,
      "loss": 1.1591,
      "step": 48
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.19111566245555878,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.1098,
      "step": 50
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.2274666428565979,
      "learning_rate": 9.454545454545455e-05,
      "loss": 1.1056,
      "step": 52
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.17944614589214325,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.1606,
      "step": 54
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1656662225723267,
      "eval_runtime": 20.9817,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 55
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 0.20874111354351044,
      "learning_rate": 9.999899300364532e-05,
      "loss": 1.0895,
      "step": 56
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.19761574268341064,
      "learning_rate": 9.99909372761763e-05,
      "loss": 1.1108,
      "step": 58
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.21238858997821808,
      "learning_rate": 9.997482711915927e-05,
      "loss": 1.0455,
      "step": 60
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.24546955525875092,
      "learning_rate": 9.99506651282272e-05,
      "loss": 1.0781,
      "step": 62
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.2169496864080429,
      "learning_rate": 9.991845519630678e-05,
      "loss": 1.0501,
      "step": 64
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2121065855026245,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1108,
      "step": 66
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.1445685625076294,
      "eval_runtime": 20.9862,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 66
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.2501777410507202,
      "learning_rate": 9.982991356370404e-05,
      "loss": 1.0065,
      "step": 68
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.25454187393188477,
      "learning_rate": 9.977359612865423e-05,
      "loss": 1.0647,
      "step": 70
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.23557862639427185,
      "learning_rate": 9.970925928158274e-05,
      "loss": 0.9846,
      "step": 72
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.28469789028167725,
      "learning_rate": 9.963691338830044e-05,
      "loss": 1.0349,
      "step": 74
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.21774668991565704,
      "learning_rate": 9.955657010501806e-05,
      "loss": 1.062,
      "step": 76
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.1340781450271606,
      "eval_runtime": 20.9821,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 77
    },
    {
      "epoch": 7.090909090909091,
      "grad_norm": 0.22603094577789307,
      "learning_rate": 9.946824237646824e-05,
      "loss": 1.1133,
      "step": 78
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.31671807169914246,
      "learning_rate": 9.937194443381972e-05,
      "loss": 0.9403,
      "step": 80
    },
    {
      "epoch": 7.454545454545454,
      "grad_norm": 0.2942790985107422,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.9473,
      "step": 82
    },
    {
      "epoch": 7.636363636363637,
      "grad_norm": 0.29537585377693176,
      "learning_rate": 9.915550124911866e-05,
      "loss": 0.997,
      "step": 84
    },
    {
      "epoch": 7.818181818181818,
      "grad_norm": 0.3028506934642792,
      "learning_rate": 9.903539087991462e-05,
      "loss": 0.9769,
      "step": 86
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.29490503668785095,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0372,
      "step": 88
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.130280613899231,
      "eval_runtime": 20.9854,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 88
    },
    {
      "epoch": 8.181818181818182,
      "grad_norm": 0.29014894366264343,
      "learning_rate": 9.877148934427037e-05,
      "loss": 0.9843,
      "step": 90
    },
    {
      "epoch": 8.363636363636363,
      "grad_norm": 0.30928847193717957,
      "learning_rate": 9.862774069706346e-05,
      "loss": 0.9135,
      "step": 92
    },
    {
      "epoch": 8.545454545454545,
      "grad_norm": 0.38922497630119324,
      "learning_rate": 9.847615725553456e-05,
      "loss": 0.9659,
      "step": 94
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 0.48642444610595703,
      "learning_rate": 9.831676344247342e-05,
      "loss": 0.8584,
      "step": 96
    },
    {
      "epoch": 8.909090909090908,
      "grad_norm": 0.36263683438301086,
      "learning_rate": 9.814958493905963e-05,
      "loss": 0.9427,
      "step": 98
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.1412957906723022,
      "eval_runtime": 20.9857,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 99
    },
    {
      "epoch": 9.090909090909092,
      "grad_norm": 0.3450450897216797,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.9568,
      "step": 100
    },
    {
      "epoch": 9.272727272727273,
      "grad_norm": 0.42660877108573914,
      "learning_rate": 9.779198285281325e-05,
      "loss": 0.8457,
      "step": 102
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 0.6125783920288086,
      "learning_rate": 9.760161688604008e-05,
      "loss": 0.8319,
      "step": 104
    },
    {
      "epoch": 9.636363636363637,
      "grad_norm": 0.48880472779273987,
      "learning_rate": 9.740358145174998e-05,
      "loss": 0.938,
      "step": 106
    },
    {
      "epoch": 9.818181818181818,
      "grad_norm": 0.44643890857696533,
      "learning_rate": 9.719790845697533e-05,
      "loss": 0.8584,
      "step": 108
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.555194079875946,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.819,
      "step": 110
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1795061826705933,
      "eval_runtime": 20.9824,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 110
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 0.543806791305542,
      "learning_rate": 9.676378356149734e-05,
      "loss": 0.7579,
      "step": 112
    },
    {
      "epoch": 10.363636363636363,
      "grad_norm": 0.5537196397781372,
      "learning_rate": 9.653540160603956e-05,
      "loss": 0.76,
      "step": 114
    },
    {
      "epoch": 10.545454545454545,
      "grad_norm": 0.5554760694503784,
      "learning_rate": 9.629952196931901e-05,
      "loss": 0.7664,
      "step": 116
    },
    {
      "epoch": 10.727272727272727,
      "grad_norm": 0.747921347618103,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.7458,
      "step": 118
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 0.6102632880210876,
      "learning_rate": 9.580542287160348e-05,
      "loss": 0.8148,
      "step": 120
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.210098385810852,
      "eval_runtime": 20.9818,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 121
    },
    {
      "epoch": 11.090909090909092,
      "grad_norm": 0.7422995567321777,
      "learning_rate": 9.554728301876526e-05,
      "loss": 0.7413,
      "step": 122
    },
    {
      "epoch": 11.272727272727273,
      "grad_norm": 1.029877781867981,
      "learning_rate": 9.528180468815155e-05,
      "loss": 0.6752,
      "step": 124
    },
    {
      "epoch": 11.454545454545455,
      "grad_norm": 0.7541818618774414,
      "learning_rate": 9.50090306530454e-05,
      "loss": 0.6829,
      "step": 126
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 0.7304781079292297,
      "learning_rate": 9.472900486219769e-05,
      "loss": 0.7175,
      "step": 128
    },
    {
      "epoch": 11.818181818181818,
      "grad_norm": 0.8420543670654297,
      "learning_rate": 9.444177243274618e-05,
      "loss": 0.6748,
      "step": 130
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.7322824001312256,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6121,
      "step": 132
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.2798398733139038,
      "eval_runtime": 20.9856,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 132
    },
    {
      "epoch": 12.181818181818182,
      "grad_norm": 0.9401576519012451,
      "learning_rate": 9.384587392471515e-05,
      "loss": 0.5991,
      "step": 134
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 0.9382196068763733,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.5451,
      "step": 136
    },
    {
      "epoch": 12.545454545454545,
      "grad_norm": 0.8877333998680115,
      "learning_rate": 9.322171915289635e-05,
      "loss": 0.5727,
      "step": 138
    },
    {
      "epoch": 12.727272727272727,
      "grad_norm": 0.8599797487258911,
      "learning_rate": 9.289917066174886e-05,
      "loss": 0.5479,
      "step": 140
    },
    {
      "epoch": 12.909090909090908,
      "grad_norm": 0.8650861382484436,
      "learning_rate": 9.256971035084785e-05,
      "loss": 0.6309,
      "step": 142
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.3036460876464844,
      "eval_runtime": 20.9853,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 143
    },
    {
      "epoch": 13.090909090909092,
      "grad_norm": 1.0195311307907104,
      "learning_rate": 9.223339130211192e-05,
      "loss": 0.4563,
      "step": 144
    },
    {
      "epoch": 13.272727272727273,
      "grad_norm": 1.6160974502563477,
      "learning_rate": 9.189026770252436e-05,
      "loss": 0.5025,
      "step": 146
    },
    {
      "epoch": 13.454545454545455,
      "grad_norm": 0.8924494981765747,
      "learning_rate": 9.154039483540273e-05,
      "loss": 0.5538,
      "step": 148
    },
    {
      "epoch": 13.636363636363637,
      "grad_norm": 1.0530997514724731,
      "learning_rate": 9.118382907149165e-05,
      "loss": 0.4939,
      "step": 150
    },
    {
      "epoch": 13.818181818181818,
      "grad_norm": 1.138434886932373,
      "learning_rate": 9.082062785988049e-05,
      "loss": 0.4578,
      "step": 152
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.1421233415603638,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3915,
      "step": 154
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.402987003326416,
      "eval_runtime": 20.9829,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 154
    },
    {
      "epoch": 14.181818181818182,
      "grad_norm": 1.0002199411392212,
      "learning_rate": 9.007455422593077e-05,
      "loss": 0.4021,
      "step": 156
    },
    {
      "epoch": 14.363636363636363,
      "grad_norm": 1.8315327167510986,
      "learning_rate": 8.969180200933047e-05,
      "loss": 0.4067,
      "step": 158
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 0.9818419218063354,
      "learning_rate": 8.930265473713938e-05,
      "loss": 0.4734,
      "step": 160
    },
    {
      "epoch": 14.727272727272727,
      "grad_norm": 1.1827267408370972,
      "learning_rate": 8.890717510790763e-05,
      "loss": 0.3701,
      "step": 162
    },
    {
      "epoch": 14.909090909090908,
      "grad_norm": 1.2774779796600342,
      "learning_rate": 8.850542684044078e-05,
      "loss": 0.3014,
      "step": 164
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.4186311960220337,
      "eval_runtime": 20.9816,
      "eval_samples_per_second": 1.144,
      "eval_steps_per_second": 1.144,
      "step": 165
    },
    {
      "epoch": 15.0,
      "step": 165,
      "total_flos": 1.0303059281942938e+17,
      "train_loss": 0.990465174479918,
      "train_runtime": 3797.6332,
      "train_samples_per_second": 1.159,
      "train_steps_per_second": 0.145
    }
  ],
  "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": 1.0303059281942938e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}