{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 18,
  "global_step": 213,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014084507042253521,
      "eval_loss": 11.91716480255127,
      "eval_runtime": 0.6125,
      "eval_samples_per_second": 195.905,
      "eval_steps_per_second": 24.488,
      "step": 1
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 0.2159075140953064,
      "learning_rate": 3e-05,
      "loss": 11.9107,
      "step": 3
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.2119741290807724,
      "learning_rate": 6e-05,
      "loss": 11.9164,
      "step": 6
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 0.21554657816886902,
      "learning_rate": 9e-05,
      "loss": 11.9129,
      "step": 9
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.19983112812042236,
      "learning_rate": 9.997605179330019e-05,
      "loss": 11.9137,
      "step": 12
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 0.23735706508159637,
      "learning_rate": 9.98503864319978e-05,
      "loss": 11.9074,
      "step": 15
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 0.28685566782951355,
      "learning_rate": 9.961728733030318e-05,
      "loss": 11.9116,
      "step": 18
    },
    {
      "epoch": 0.2535211267605634,
      "eval_loss": 11.904885292053223,
      "eval_runtime": 0.6128,
      "eval_samples_per_second": 195.813,
      "eval_steps_per_second": 24.477,
      "step": 18
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 0.32204487919807434,
      "learning_rate": 9.927725684557338e-05,
      "loss": 11.9111,
      "step": 21
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.36651644110679626,
      "learning_rate": 9.883102778550434e-05,
      "loss": 11.8957,
      "step": 24
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 0.5040445923805237,
      "learning_rate": 9.82795618288397e-05,
      "loss": 11.888,
      "step": 27
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 0.5162233114242554,
      "learning_rate": 9.762404745283439e-05,
      "loss": 11.8833,
      "step": 30
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 0.5750740170478821,
      "learning_rate": 9.686589737193929e-05,
      "loss": 11.879,
      "step": 33
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.5393357276916504,
      "learning_rate": 9.600674549322717e-05,
      "loss": 11.8624,
      "step": 36
    },
    {
      "epoch": 0.5070422535211268,
      "eval_loss": 11.857889175415039,
      "eval_runtime": 0.612,
      "eval_samples_per_second": 196.066,
      "eval_steps_per_second": 24.508,
      "step": 36
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 0.5249887108802795,
      "learning_rate": 9.504844339512095e-05,
      "loss": 11.8531,
      "step": 39
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 0.33441707491874695,
      "learning_rate": 9.399305633701373e-05,
      "loss": 11.8462,
      "step": 42
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 0.2839614152908325,
      "learning_rate": 9.284285880837946e-05,
      "loss": 11.8347,
      "step": 45
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.2555694878101349,
      "learning_rate": 9.160032962696734e-05,
      "loss": 11.834,
      "step": 48
    },
    {
      "epoch": 0.7183098591549296,
      "grad_norm": 0.23353426158428192,
      "learning_rate": 9.026814659664331e-05,
      "loss": 11.8343,
      "step": 51
    },
    {
      "epoch": 0.7605633802816901,
      "grad_norm": 0.23047791421413422,
      "learning_rate": 8.88491807363919e-05,
      "loss": 11.8276,
      "step": 54
    },
    {
      "epoch": 0.7605633802816901,
      "eval_loss": 11.828319549560547,
      "eval_runtime": 0.6154,
      "eval_samples_per_second": 194.994,
      "eval_steps_per_second": 24.374,
      "step": 54
    },
    {
      "epoch": 0.8028169014084507,
      "grad_norm": 0.333280086517334,
      "learning_rate": 8.734649009291585e-05,
      "loss": 11.8283,
      "step": 57
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 0.29108697175979614,
      "learning_rate": 8.576331315016753e-05,
      "loss": 11.8236,
      "step": 60
    },
    {
      "epoch": 0.8873239436619719,
      "grad_norm": 0.2189083993434906,
      "learning_rate": 8.410306185001611e-05,
      "loss": 11.8169,
      "step": 63
    },
    {
      "epoch": 0.9295774647887324,
      "grad_norm": 0.2126510888338089,
      "learning_rate": 8.236931423909138e-05,
      "loss": 11.819,
      "step": 66
    },
    {
      "epoch": 0.971830985915493,
      "grad_norm": 0.22723552584648132,
      "learning_rate": 8.05658067576513e-05,
      "loss": 11.8203,
      "step": 69
    },
    {
      "epoch": 1.0140845070422535,
      "grad_norm": 0.20461063086986542,
      "learning_rate": 7.86964261870916e-05,
      "loss": 11.8133,
      "step": 72
    },
    {
      "epoch": 1.0140845070422535,
      "eval_loss": 11.81312370300293,
      "eval_runtime": 0.6161,
      "eval_samples_per_second": 194.759,
      "eval_steps_per_second": 24.345,
      "step": 72
    },
    {
      "epoch": 1.056338028169014,
      "grad_norm": 0.24878963828086853,
      "learning_rate": 7.676520127345197e-05,
      "loss": 11.8165,
      "step": 75
    },
    {
      "epoch": 1.0985915492957747,
      "grad_norm": 0.2186020314693451,
      "learning_rate": 7.477629404497048e-05,
      "loss": 11.8114,
      "step": 78
    },
    {
      "epoch": 1.1408450704225352,
      "grad_norm": 0.28986242413520813,
      "learning_rate": 7.273399084239878e-05,
      "loss": 11.8118,
      "step": 81
    },
    {
      "epoch": 1.1830985915492958,
      "grad_norm": 0.1976727992296219,
      "learning_rate": 7.06426930814083e-05,
      "loss": 11.8103,
      "step": 84
    },
    {
      "epoch": 1.2253521126760563,
      "grad_norm": 0.17177629470825195,
      "learning_rate": 6.850690776699573e-05,
      "loss": 11.8052,
      "step": 87
    },
    {
      "epoch": 1.267605633802817,
      "grad_norm": 0.2314409464597702,
      "learning_rate": 6.633123778033061e-05,
      "loss": 11.8072,
      "step": 90
    },
    {
      "epoch": 1.267605633802817,
      "eval_loss": 11.802838325500488,
      "eval_runtime": 0.615,
      "eval_samples_per_second": 195.129,
      "eval_steps_per_second": 24.391,
      "step": 90
    },
    {
      "epoch": 1.3098591549295775,
      "grad_norm": 0.17084774374961853,
      "learning_rate": 6.412037195897785e-05,
      "loss": 11.807,
      "step": 93
    },
    {
      "epoch": 1.352112676056338,
      "grad_norm": 0.1774490773677826,
      "learning_rate": 6.187907499187356e-05,
      "loss": 11.8047,
      "step": 96
    },
    {
      "epoch": 1.3943661971830985,
      "grad_norm": 0.1694556325674057,
      "learning_rate": 5.961217715083185e-05,
      "loss": 11.8025,
      "step": 99
    },
    {
      "epoch": 1.436619718309859,
      "grad_norm": 0.32927870750427246,
      "learning_rate": 5.732456388071247e-05,
      "loss": 11.8011,
      "step": 102
    },
    {
      "epoch": 1.4788732394366197,
      "grad_norm": 0.22614863514900208,
      "learning_rate": 5.502116527068363e-05,
      "loss": 11.8016,
      "step": 105
    },
    {
      "epoch": 1.5211267605633803,
      "grad_norm": 0.4875750243663788,
      "learning_rate": 5.270694542927088e-05,
      "loss": 11.8004,
      "step": 108
    },
    {
      "epoch": 1.5211267605633803,
      "eval_loss": 11.798242568969727,
      "eval_runtime": 0.6119,
      "eval_samples_per_second": 196.101,
      "eval_steps_per_second": 24.513,
      "step": 108
    },
    {
      "epoch": 1.563380281690141,
      "grad_norm": 0.16188736259937286,
      "learning_rate": 5.0386891786090105e-05,
      "loss": 11.7992,
      "step": 111
    },
    {
      "epoch": 1.6056338028169015,
      "grad_norm": 0.2233981341123581,
      "learning_rate": 4.806600434332056e-05,
      "loss": 11.7992,
      "step": 114
    },
    {
      "epoch": 1.647887323943662,
      "grad_norm": 0.16819994151592255,
      "learning_rate": 4.574928490008264e-05,
      "loss": 11.798,
      "step": 117
    },
    {
      "epoch": 1.6901408450704225,
      "grad_norm": 0.12405195087194443,
      "learning_rate": 4.344172627294289e-05,
      "loss": 11.8012,
      "step": 120
    },
    {
      "epoch": 1.732394366197183,
      "grad_norm": 0.14492444694042206,
      "learning_rate": 4.114830153577759e-05,
      "loss": 11.7989,
      "step": 123
    },
    {
      "epoch": 1.7746478873239435,
      "grad_norm": 0.3022187054157257,
      "learning_rate": 3.887395330218429e-05,
      "loss": 11.7966,
      "step": 126
    },
    {
      "epoch": 1.7746478873239435,
      "eval_loss": 11.796996116638184,
      "eval_runtime": 0.6204,
      "eval_samples_per_second": 193.41,
      "eval_steps_per_second": 24.176,
      "step": 126
    },
    {
      "epoch": 1.8169014084507042,
      "grad_norm": 0.34615883231163025,
      "learning_rate": 3.6623583073538966e-05,
      "loss": 11.7966,
      "step": 129
    },
    {
      "epoch": 1.8591549295774648,
      "grad_norm": 0.1670173704624176,
      "learning_rate": 3.440204067565511e-05,
      "loss": 11.798,
      "step": 132
    },
    {
      "epoch": 1.9014084507042255,
      "grad_norm": 0.25132665038108826,
      "learning_rate": 3.221411380681007e-05,
      "loss": 11.7989,
      "step": 135
    },
    {
      "epoch": 1.943661971830986,
      "grad_norm": 0.3825485408306122,
      "learning_rate": 3.006451771966383e-05,
      "loss": 11.8008,
      "step": 138
    },
    {
      "epoch": 1.9859154929577465,
      "grad_norm": 0.14148132503032684,
      "learning_rate": 2.79578850593071e-05,
      "loss": 11.7995,
      "step": 141
    },
    {
      "epoch": 2.028169014084507,
      "grad_norm": 0.1258476823568344,
      "learning_rate": 2.589875587933892e-05,
      "loss": 11.7966,
      "step": 144
    },
    {
      "epoch": 2.028169014084507,
      "eval_loss": 11.796266555786133,
      "eval_runtime": 0.6121,
      "eval_samples_per_second": 196.045,
      "eval_steps_per_second": 24.506,
      "step": 144
    },
    {
      "epoch": 2.0704225352112675,
      "grad_norm": 0.29805803298950195,
      "learning_rate": 2.3891567857490372e-05,
      "loss": 11.7973,
      "step": 147
    },
    {
      "epoch": 2.112676056338028,
      "grad_norm": 0.13624520599842072,
      "learning_rate": 2.194064673188089e-05,
      "loss": 11.7978,
      "step": 150
    },
    {
      "epoch": 2.1549295774647885,
      "grad_norm": 0.10893828421831131,
      "learning_rate": 2.005019697851832e-05,
      "loss": 11.7972,
      "step": 153
    },
    {
      "epoch": 2.1971830985915495,
      "grad_norm": 0.13635849952697754,
      "learning_rate": 1.8224292750133743e-05,
      "loss": 11.7988,
      "step": 156
    },
    {
      "epoch": 2.23943661971831,
      "grad_norm": 0.13502788543701172,
      "learning_rate": 1.646686909587908e-05,
      "loss": 11.7981,
      "step": 159
    },
    {
      "epoch": 2.2816901408450705,
      "grad_norm": 0.1165008544921875,
      "learning_rate": 1.4781713480810184e-05,
      "loss": 11.7969,
      "step": 162
    },
    {
      "epoch": 2.2816901408450705,
      "eval_loss": 11.796056747436523,
      "eval_runtime": 0.6117,
      "eval_samples_per_second": 196.169,
      "eval_steps_per_second": 24.521,
      "step": 162
    },
    {
      "epoch": 2.323943661971831,
      "grad_norm": 0.19734472036361694,
      "learning_rate": 1.3172457623431706e-05,
      "loss": 11.7956,
      "step": 165
    },
    {
      "epoch": 2.3661971830985915,
      "grad_norm": 0.3292880356311798,
      "learning_rate": 1.164256966889517e-05,
      "loss": 11.7975,
      "step": 168
    },
    {
      "epoch": 2.408450704225352,
      "grad_norm": 0.24362030625343323,
      "learning_rate": 1.0195346714717813e-05,
      "loss": 11.7978,
      "step": 171
    },
    {
      "epoch": 2.4507042253521125,
      "grad_norm": 0.3114156723022461,
      "learning_rate": 8.83390770513009e-06,
      "loss": 11.7975,
      "step": 174
    },
    {
      "epoch": 2.492957746478873,
      "grad_norm": 0.26279327273368835,
      "learning_rate": 7.561186709365653e-06,
      "loss": 11.8017,
      "step": 177
    },
    {
      "epoch": 2.535211267605634,
      "grad_norm": 0.1340506225824356,
      "learning_rate": 6.379926598379726e-06,
      "loss": 11.7968,
      "step": 180
    },
    {
      "epoch": 2.535211267605634,
      "eval_loss": 11.796035766601562,
      "eval_runtime": 0.6227,
      "eval_samples_per_second": 192.708,
      "eval_steps_per_second": 24.089,
      "step": 180
    },
    {
      "epoch": 2.5774647887323945,
      "grad_norm": 0.36095118522644043,
      "learning_rate": 5.292673133623371e-06,
      "loss": 11.7982,
      "step": 183
    },
    {
      "epoch": 2.619718309859155,
      "grad_norm": 0.33758965134620667,
      "learning_rate": 4.301769480613116e-06,
      "loss": 11.7951,
      "step": 186
    },
    {
      "epoch": 2.6619718309859155,
      "grad_norm": 0.1514846533536911,
      "learning_rate": 3.4093511591198445e-06,
      "loss": 11.7959,
      "step": 189
    },
    {
      "epoch": 2.704225352112676,
      "grad_norm": 0.15260806679725647,
      "learning_rate": 2.6173414408598827e-06,
      "loss": 11.7991,
      "step": 192
    },
    {
      "epoch": 2.7464788732394365,
      "grad_norm": 0.16173598170280457,
      "learning_rate": 1.92744720460688e-06,
      "loss": 11.7977,
      "step": 195
    },
    {
      "epoch": 2.788732394366197,
      "grad_norm": 0.21083351969718933,
      "learning_rate": 1.341155257657256e-06,
      "loss": 11.8001,
      "step": 198
    },
    {
      "epoch": 2.788732394366197,
      "eval_loss": 11.795927047729492,
      "eval_runtime": 0.6119,
      "eval_samples_per_second": 196.107,
      "eval_steps_per_second": 24.513,
      "step": 198
    },
    {
      "epoch": 2.830985915492958,
      "grad_norm": 0.1594826728105545,
      "learning_rate": 8.597291315767808e-07,
      "loss": 11.8005,
      "step": 201
    },
    {
      "epoch": 2.873239436619718,
      "grad_norm": 0.20315298438072205,
      "learning_rate": 4.842063591339763e-07,
      "loss": 11.7946,
      "step": 204
    },
    {
      "epoch": 2.915492957746479,
      "grad_norm": 0.15598557889461517,
      "learning_rate": 2.153962382888841e-07,
      "loss": 11.7981,
      "step": 207
    },
    {
      "epoch": 2.9577464788732395,
      "grad_norm": 0.38635027408599854,
      "learning_rate": 5.3878088055947515e-08,
      "loss": 11.7958,
      "step": 210
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2931283414363861,
      "learning_rate": 0.0,
      "loss": 11.7986,
      "step": 213
    }
  ],
  "logging_steps": 3,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 18,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1025932492800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}